Fix CI: cspell EOJSON delimiter and telemetry workflow conan setup

- Rename EOJSON heredoc delimiter to EOF_JSON to avoid cspell unknown word
- Add conan installation step (pip3 install conan) to telemetry-validation workflow
- Use shared setup-conan action for proper Conan profile/remote configuration
- Align build commands with reusable-build-test-config.yml conventions

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

.clang-tidy

@@ -24,18 +24,22 @@ Checks: "-*,
   bugprone-misplaced-operator-in-strlen-in-alloc,
   bugprone-misplaced-pointer-arithmetic-in-alloc,
   bugprone-misplaced-widening-cast,
+  bugprone-move-forwarding-reference,
   bugprone-multi-level-implicit-pointer-conversion,
   bugprone-multiple-new-in-one-expression,
   bugprone-multiple-statement-macro,
   bugprone-no-escape,
   bugprone-non-zero-enum-to-bool-conversion,
   bugprone-parent-virtual-call,
+  bugprone-pointer-arithmetic-on-polymorphic-object,
   bugprone-posix-return,
   bugprone-redundant-branch-condition,
+  bugprone-return-const-ref-from-parameter,
   bugprone-shared-ptr-array-mismatch,
   bugprone-signal-handler,
   bugprone-signed-char-misuse,
   bugprone-sizeof-container,
+  bugprone-sizeof-expression,
   bugprone-spuriously-wake-up-functions,
   bugprone-standalone-empty,
   bugprone-string-constructor,
@@ -46,6 +50,7 @@ Checks: "-*,
   bugprone-suspicious-include,
   bugprone-suspicious-memory-comparison,
   bugprone-suspicious-memset-usage,
+  bugprone-suspicious-missing-comma,
   bugprone-suspicious-realloc-usage,
   bugprone-suspicious-semicolon,
   bugprone-suspicious-string-compare,
@@ -57,6 +62,7 @@ Checks: "-*,
   bugprone-unhandled-exception-at-new,
   bugprone-unique-ptr-array-mismatch,
   bugprone-unsafe-functions,
+  bugprone-unused-local-non-trivial-variable,
   bugprone-virtual-near-miss,
   cppcoreguidelines-no-suspend-with-lock,
   cppcoreguidelines-virtual-class-destructor,
@@ -88,13 +94,8 @@ Checks: "-*,
 # bugprone-inc-dec-in-conditions,
 # bugprone-reserved-identifier,
 # bugprone-move-forwarding-reference,
-# bugprone-unused-local-non-trivial-variable,
-# bugprone-return-const-ref-from-parameter,
 # bugprone-switch-missing-default-case,
-# bugprone-sizeof-expression,
 # bugprone-suspicious-stringview-data-usage,
-# bugprone-suspicious-missing-comma,
-# bugprone-pointer-arithmetic-on-polymorphic-object,
 # bugprone-optional-value-conversion,
 # bugprone-too-small-loop-variable,
 # bugprone-unused-return-value,

.cmake-format.yaml

@@ -1,247 +0,0 @@
-_help_parse: Options affecting listfile parsing
-parse:
-  _help_additional_commands:
-    - Specify structure for custom cmake functions
-  additional_commands:
-    target_protobuf_sources:
-      pargs:
-        - target
-        - prefix
-      kwargs:
-        PROTOS: "*"
-        LANGUAGE: cpp
-        IMPORT_DIRS: "*"
-        GENERATE_EXTENSIONS: "*"
-        PLUGIN: "*"
-  _help_override_spec:
-    - Override configurations per-command where available
-  override_spec: {}
-  _help_vartags:
-    - Specify variable tags.
-  vartags: []
-  _help_proptags:
-    - Specify property tags.
-  proptags: []
-_help_format: Options affecting formatting.
-format:
-  _help_disable:
-    - Disable formatting entirely, making cmake-format a no-op
-  disable: false
-  _help_line_width:
-    - How wide to allow formatted cmake files
-  line_width: 100
-  _help_tab_size:
-    - How many spaces to tab for indent
-  tab_size: 4
-  _help_use_tabchars:
-    - If true, lines are indented using tab characters (utf-8
-    - 0x09) instead of <tab_size> space characters (utf-8 0x20).
-    - In cases where the layout would require a fractional tab
-    - character, the behavior of the  fractional indentation is
-    - governed by <fractional_tab_policy>
-  use_tabchars: false
-  _help_fractional_tab_policy:
-    - If <use_tabchars> is True, then the value of this variable
-    - indicates how fractional indentions are handled during
-    - whitespace replacement. If set to 'use-space', fractional
-    - indentation is left as spaces (utf-8 0x20). If set to
-    - "`round-up` fractional indentation is replaced with a single"
-    - tab character (utf-8 0x09) effectively shifting the column
-    - to the next tabstop
-  fractional_tab_policy: use-space
-  _help_max_subgroups_hwrap:
-    - If an argument group contains more than this many sub-groups
-    - (parg or kwarg groups) then force it to a vertical layout.
-  max_subgroups_hwrap: 4
-  _help_max_pargs_hwrap:
-    - If a positional argument group contains more than this many
-    - arguments, then force it to a vertical layout.
-  max_pargs_hwrap: 5
-  _help_max_rows_cmdline:
-    - If a cmdline positional group consumes more than this many
-    - lines without nesting, then invalidate the layout (and nest)
-  max_rows_cmdline: 2
-  _help_separate_ctrl_name_with_space:
-    - If true, separate flow control names from their parentheses
-    - with a space
-  separate_ctrl_name_with_space: true
-  _help_separate_fn_name_with_space:
-    - If true, separate function names from parentheses with a
-    - space
-  separate_fn_name_with_space: false
-  _help_dangle_parens:
-    - If a statement is wrapped to more than one line, than dangle
-    - the closing parenthesis on its own line.
-  dangle_parens: false
-  _help_dangle_align:
-    - If the trailing parenthesis must be 'dangled' on its on
-    - "line, then align it to this reference: `prefix`: the start"
-    - "of the statement, `prefix-indent`: the start of the"
-    - "statement, plus one indentation level, `child`: align to"
-    - the column of the arguments
-  dangle_align: prefix
-  _help_min_prefix_chars:
-    - If the statement spelling length (including space and
-    - parenthesis) is smaller than this amount, then force reject
-    - nested layouts.
-  min_prefix_chars: 18
-  _help_max_prefix_chars:
-    - If the statement spelling length (including space and
-    - parenthesis) is larger than the tab width by more than this
-    - amount, then force reject un-nested layouts.
-  max_prefix_chars: 10
-  _help_max_lines_hwrap:
-    - If a candidate layout is wrapped horizontally but it exceeds
-    - this many lines, then reject the layout.
-  max_lines_hwrap: 2
-  _help_line_ending:
-    - What style line endings to use in the output.
-  line_ending: unix
-  _help_command_case:
-    - Format command names consistently as 'lower' or 'upper' case
-  command_case: canonical
-  _help_keyword_case:
-    - Format keywords consistently as 'lower' or 'upper' case
-  keyword_case: unchanged
-  _help_always_wrap:
-    - A list of command names which should always be wrapped
-  always_wrap: []
-  _help_enable_sort:
-    - If true, the argument lists which are known to be sortable
-    - will be sorted lexicographicall
-  enable_sort: true
-  _help_autosort:
-    - If true, the parsers may infer whether or not an argument
-    - list is sortable (without annotation).
-  autosort: true
-  _help_require_valid_layout:
-    - By default, if cmake-format cannot successfully fit
-    - everything into the desired linewidth it will apply the
-    - last, most aggressive attempt that it made. If this flag is
-    - True, however, cmake-format will print error, exit with non-
-    - zero status code, and write-out nothing
-  require_valid_layout: false
-  _help_layout_passes:
-    - A dictionary mapping layout nodes to a list of wrap
-    - decisions. See the documentation for more information.
-  layout_passes: {}
-_help_markup: Options affecting comment reflow and formatting.
-markup:
-  _help_bullet_char:
-    - What character to use for bulleted lists
-  bullet_char: "-"
-  _help_enum_char:
-    - What character to use as punctuation after numerals in an
-    - enumerated list
-  enum_char: .
-  _help_first_comment_is_literal:
-    - If comment markup is enabled, don't reflow the first comment
-    - block in each listfile. Use this to preserve formatting of
-    - your copyright/license statements.
-  first_comment_is_literal: false
-  _help_literal_comment_pattern:
-    - If comment markup is enabled, don't reflow any comment block
-    - which matches this (regex) pattern. Default is `None`
-    - (disabled).
-  literal_comment_pattern: null
-  _help_fence_pattern:
-    - Regular expression to match preformat fences in comments
-    - default= ``r'^\s*([`~]{3}[`~]*)(.*)$'``
-  fence_pattern: ^\s*([`~]{3}[`~]*)(.*)$
-  _help_ruler_pattern:
-    - Regular expression to match rulers in comments default=
-    - '``r''^\s*[^\w\s]{3}.*[^\w\s]{3}$''``'
-  ruler_pattern: ^\s*[^\w\s]{3}.*[^\w\s]{3}$
-  _help_explicit_trailing_pattern:
-    - If a comment line matches starts with this pattern then it
-    - is explicitly a trailing comment for the preceding
-    - argument. Default is '#<'
-  explicit_trailing_pattern: "#<"
-  _help_hashruler_min_length:
-    - If a comment line starts with at least this many consecutive
-    - hash characters, then don't lstrip() them off. This allows
-    - for lazy hash rulers where the first hash char is not
-    - separated by space
-  hashruler_min_length: 10
-  _help_canonicalize_hashrulers:
-    - If true, then insert a space between the first hash char and
-    - remaining hash chars in a hash ruler, and normalize its
-    - length to fill the column
-  canonicalize_hashrulers: true
-  _help_enable_markup:
-    - enable comment markup parsing and reflow
-  enable_markup: false
-_help_lint: Options affecting the linter
-lint:
-  _help_disabled_codes:
-    - a list of lint codes to disable
-  disabled_codes: []
-  _help_function_pattern:
-    - regular expression pattern describing valid function names
-  function_pattern: "[0-9a-z_]+"
-  _help_macro_pattern:
-    - regular expression pattern describing valid macro names
-  macro_pattern: "[0-9A-Z_]+"
-  _help_global_var_pattern:
-    - regular expression pattern describing valid names for
-    - variables with global (cache) scope
-  global_var_pattern: "[A-Z][0-9A-Z_]+"
-  _help_internal_var_pattern:
-    - regular expression pattern describing valid names for
-    - variables with global scope (but internal semantic)
-  internal_var_pattern: _[A-Z][0-9A-Z_]+
-  _help_local_var_pattern:
-    - regular expression pattern describing valid names for
-    - variables with local scope
-  local_var_pattern: "[a-z][a-z0-9_]+"
-  _help_private_var_pattern:
-    - regular expression pattern describing valid names for
-    - privatedirectory variables
-  private_var_pattern: _[0-9a-z_]+
-  _help_public_var_pattern:
-    - regular expression pattern describing valid names for public
-    - directory variables
-  public_var_pattern: "[A-Z][0-9A-Z_]+"
-  _help_argument_var_pattern:
-    - regular expression pattern describing valid names for
-    - function/macro arguments and loop variables.
-  argument_var_pattern: "[a-z][a-z0-9_]+"
-  _help_keyword_pattern:
-    - regular expression pattern describing valid names for
-    - keywords used in functions or macros
-  keyword_pattern: "[A-Z][0-9A-Z_]+"
-  _help_max_conditionals_custom_parser:
-    - In the heuristic for C0201, how many conditionals to match
-    - within a loop in before considering the loop a parser.
-  max_conditionals_custom_parser: 2
-  _help_min_statement_spacing:
-    - Require at least this many newlines between statements
-  min_statement_spacing: 1
-  _help_max_statement_spacing:
-    - Require no more than this many newlines between statements
-  max_statement_spacing: 2
-  max_returns: 6
-  max_branches: 12
-  max_arguments: 5
-  max_localvars: 15
-  max_statements: 50
-_help_encode: Options affecting file encoding
-encode:
-  _help_emit_byteorder_mark:
-    - If true, emit the unicode byte-order mark (BOM) at the start
-    - of the file
-  emit_byteorder_mark: false
-  _help_input_encoding:
-    - Specify the encoding of the input file. Defaults to utf-8
-  input_encoding: utf-8
-  _help_output_encoding:
-    - Specify the encoding of the output file. Defaults to utf-8.
-    - Note that cmake only claims to support utf-8 so be careful
-    - when using anything else
-  output_encoding: utf-8
-_help_misc: Miscellaneous configurations options.
-misc:
-  _help_per_command:
-    - A dictionary containing any per-command configuration
-    - overrides. Currently only `command_case` is supported.
-  per_command: {}

.gersemi/definitions.cmake

@@ -0,0 +1,98 @@
+# Custom CMake command definitions for gersemi formatting.
+# These stubs teach gersemi the signatures of project-specific commands
+# so it can format their invocations correctly.
+
+function(git_branch branch_val)
+endfunction()
+
+function(isolate_headers target A B scope)
+endfunction()
+
+function(create_symbolic_link target link)
+endfunction()
+
+function(xrpl_add_test name)
+endfunction()
+
+macro(exclude_from_default target_)
+endmacro()
+
+macro(exclude_if_included target_)
+endmacro()
+
+function(target_protobuf_sources target prefix)
+    set(options APPEND_PATH DESCRIPTORS)
+    set(oneValueArgs
+        LANGUAGE
+        OUT_VAR
+        EXPORT_MACRO
+        TARGET
+        PROTOC_OUT_DIR
+        PLUGIN
+        PLUGIN_OPTIONS
+        PROTOC_EXE
+    )
+    set(multiValueArgs
+        PROTOS
+        IMPORT_DIRS
+        GENERATE_EXTENSIONS
+        PROTOC_OPTIONS
+        DEPENDENCIES
+    )
+    cmake_parse_arguments(
+        THIS_FUNCTION_PREFIX
+        "${options}"
+        "${oneValueArgs}"
+        "${multiValueArgs}"
+        ${ARGN}
+    )
+endfunction()
+
+function(add_module parent name)
+endfunction()
+
+function(target_link_modules parent scope)
+endfunction()
+
+function(setup_target_for_coverage_gcovr)
+    set(options NONE)
+    set(oneValueArgs BASE_DIRECTORY NAME FORMAT)
+    set(multiValueArgs EXCLUDE EXECUTABLE EXECUTABLE_ARGS DEPENDENCIES)
+    cmake_parse_arguments(
+        THIS_FUNCTION_PREFIX
+        "${options}"
+        "${oneValueArgs}"
+        "${multiValueArgs}"
+        ${ARGN}
+    )
+endfunction()
+
+function(add_code_coverage_to_target name scope)
+endfunction()
+
+function(verbose_find_path variable name)
+    set(options
+        NO_CACHE
+        REQUIRED
+        OPTIONAL
+        NO_DEFAULT_PATH
+        NO_PACKAGE_ROOT_PATH
+        NO_CMAKE_PATH
+        NO_CMAKE_ENVIRONMENT_PATH
+        NO_SYSTEM_ENVIRONMENT_PATH
+        NO_CMAKE_SYSTEM_PATH
+        NO_CMAKE_INSTALL_PREFIX
+        CMAKE_FIND_ROOT_PATH_BOTH
+        ONLY_CMAKE_FIND_ROOT_PATH
+        NO_CMAKE_FIND_ROOT_PATH
+    )
+    set(oneValueArgs REGISTRY_VIEW VALIDATOR DOC)
+    set(multiValueArgs NAMES HINTS PATHS PATH_SUFFIXES)
+    cmake_parse_arguments(
+        THIS_FUNCTION_PREFIX
+        "${options}"
+        "${oneValueArgs}"
+        "${multiValueArgs}"
+        ${ARGN}
+    )
+endfunction()

.gersemirc

@@ -0,0 +1 @@
+definitions: [.gersemi]

.github/scripts/levelization/results/loops.txt

@@ -16,6 +16,9 @@ Loop: xrpld.app xrpld.rpc
 Loop: xrpld.app xrpld.shamap
   xrpld.shamap ~= xrpld.app
 
+Loop: xrpld.app xrpld.telemetry
+  xrpld.telemetry ~= xrpld.app
+
 Loop: xrpld.overlay xrpld.rpc
   xrpld.rpc ~= xrpld.overlay
 

.github/scripts/levelization/results/ordering.txt

@@ -32,6 +32,8 @@ libxrpl.server > xrpl.server
 libxrpl.shamap > xrpl.basics
 libxrpl.shamap > xrpl.protocol
 libxrpl.shamap > xrpl.shamap
+libxrpl.telemetry > xrpl.basics
+libxrpl.telemetry > xrpl.telemetry
 libxrpl.tx > xrpl.basics
 libxrpl.tx > xrpl.conditions
 libxrpl.tx > xrpl.core
@@ -168,12 +170,16 @@ test.shamap > xrpl.basics
 test.shamap > xrpl.nodestore
 test.shamap > xrpl.protocol
 test.shamap > xrpl.shamap
+test.telemetry > xrpl.core
+test.telemetry > xrpld.telemetry
 test.toplevel > test.csf
 test.toplevel > xrpl.json
 test.unit_test > xrpl.basics
 tests.libxrpl > xrpl.basics
+tests.libxrpl > xrpld.telemetry
 tests.libxrpl > xrpl.json
 tests.libxrpl > xrpl.net
+tests.libxrpl > xrpl.telemetry
 xrpl.conditions > xrpl.basics
 xrpl.conditions > xrpl.protocol
 xrpl.core > xrpl.basics
@@ -206,6 +212,7 @@ xrpl.server > xrpl.shamap
 xrpl.shamap > xrpl.basics
 xrpl.shamap > xrpl.nodestore
 xrpl.shamap > xrpl.protocol
+xrpl.telemetry > xrpl.basics
 xrpl.tx > xrpl.basics
 xrpl.tx > xrpl.core
 xrpl.tx > xrpl.ledger
@@ -224,6 +231,7 @@ xrpld.app > xrpl.rdb
 xrpld.app > xrpl.resource
 xrpld.app > xrpl.server
 xrpld.app > xrpl.shamap
+xrpld.app > xrpl.telemetry
 xrpld.app > xrpl.tx
 xrpld.consensus > xrpl.basics
 xrpld.consensus > xrpl.json
@@ -238,6 +246,7 @@ xrpld.overlay > xrpl.basics
 xrpld.overlay > xrpl.core
 xrpld.overlay > xrpld.core
 xrpld.overlay > xrpld.peerfinder
+xrpld.overlay > xrpld.telemetry
 xrpld.overlay > xrpl.json
 xrpld.overlay > xrpl.protocol
 xrpld.overlay > xrpl.rdb
@@ -251,10 +260,12 @@ xrpld.peerfinder > xrpl.rdb
 xrpld.perflog > xrpl.basics
 xrpld.perflog > xrpl.core
 xrpld.perflog > xrpld.rpc
+xrpld.perflog > xrpld.telemetry
 xrpld.perflog > xrpl.json
 xrpld.rpc > xrpl.basics
 xrpld.rpc > xrpl.core
 xrpld.rpc > xrpld.core
+xrpld.rpc > xrpld.telemetry
 xrpld.rpc > xrpl.json
 xrpld.rpc > xrpl.ledger
 xrpld.rpc > xrpl.net
@@ -265,3 +276,8 @@ xrpld.rpc > xrpl.resource
 xrpld.rpc > xrpl.server
 xrpld.rpc > xrpl.tx
 xrpld.shamap > xrpl.shamap
+xrpld.telemetry > xrpl.basics
+xrpld.telemetry > xrpl.core
+xrpld.telemetry > xrpl.nodestore
+xrpld.telemetry > xrpl.server
+xrpld.telemetry > xrpl.telemetry

.github/workflows/check-pr-title.yml

@@ -0,0 +1,10 @@
+name: Check PR title
+
+on:
+  pull_request:
+    types: [opened, edited, reopened, synchronize]
+    branches: [develop]
+
+jobs:
+  check_title:
+    uses: XRPLF/actions/.github/workflows/check-pr-title.yml@943eb8277e8f4b010fde0c826ce4154c36c39509

.github/workflows/on-pr.yml

@@ -46,7 +46,7 @@ jobs:
         # that Github considers any skipped jobs to have passed, and in
         # turn the required checks as well.
         id: changes
-        uses: tj-actions/changed-files@7dee1b0c1557f278e5c7dc244927139d78c0e22a # v47.0.4
+        uses: tj-actions/changed-files@22103cc46bda19c2b464ffe86db46df6922fd323 # v47.0.5
         with:
           files: |
             # These paths are unique to `on-pr.yml`.

.github/workflows/publish-docs.yml

@@ -40,15 +40,18 @@ env:
   NPROC_SUBTRACT: ${{ github.event.repository.private && '1' || '2' }}
 
 jobs:
-  publish:
+  build:
     runs-on: ubuntu-latest
     container: ghcr.io/xrplf/ci/tools-rippled-documentation:sha-a8c7be1
-    permissions:
-      contents: write
     steps:
       - name: Checkout repository
         uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
 
+      - name: Prepare runner
+        uses: XRPLF/actions/prepare-runner@2cbf481018d930656e9276fcc20dc0e3a0be5b6d
+        with:
+          enable_ccache: false
+
       - name: Get number of processors
         uses: XRPLF/actions/get-nproc@cf0433aa74563aead044a1e395610c96d65a37cf
         id: nproc
@@ -78,9 +81,23 @@ jobs:
           cmake -Donly_docs=ON ..
           cmake --build . --target docs --parallel ${BUILD_NPROC}
 
-      - name: Publish documentation
+      - name: Create documentation artifact
         if: ${{ github.event_name == 'push' }}
-        uses: peaceiris/actions-gh-pages@4f9cc6602d3f66b9c108549d475ec49e8ef4d45e # v4.0.0
+        uses: actions/upload-pages-artifact@7b1f4a764d45c48632c6b24a0339c27f5614fb0b # v4.0.0
         with:
-          github_token: ${{ secrets.GITHUB_TOKEN }}
-          publish_dir: ${{ env.BUILD_DIR }}/docs/html
+          path: ${{ env.BUILD_DIR }}/docs/html
+
+  deploy:
+    if: ${{ github.event_name == 'push' }}
+    needs: build
+    runs-on: ubuntu-latest
+    permissions:
+      pages: write
+      id-token: write
+    environment:
+      name: github-pages
+      url: ${{ steps.deploy.outputs.page_url }}
+    steps:
+      - name: Deploy to GitHub Pages
+        id: deploy
+        uses: actions/deploy-pages@d6db90164ac5ed86f2b6aed7e0febac5b3c0c03e # v4.0.5

.github/workflows/reusable-build-test-config.yml

@@ -101,7 +101,7 @@ jobs:
     steps:
       - name: Cleanup workspace (macOS and Windows)
         if: ${{ runner.os == 'macOS' || runner.os == 'Windows' }}
-        uses: XRPLF/actions/cleanup-workspace@c7d9ce5ebb03c752a354889ecd870cadfc2b1cd4
+        uses: XRPLF/actions/cleanup-workspace@cf0433aa74563aead044a1e395610c96d65a37cf
 
       - name: Checkout repository
         uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
@@ -177,7 +177,7 @@ jobs:
 
       - name: Upload the binary (Linux)
         if: ${{ github.repository_owner == 'XRPLF' && runner.os == 'Linux' }}
-        uses: actions/upload-artifact@b7c566a772e6b6bfb58ed0dc250532a479d7789f # v6.0.0
+        uses: actions/upload-artifact@bbbca2ddaa5d8feaa63e36b76fdaad77386f024f # v7.0.0
         with:
           name: xrpld-${{ inputs.config_name }}
           path: ${{ env.BUILD_DIR }}/xrpld
@@ -229,21 +229,8 @@ jobs:
         env:
           BUILD_NPROC: ${{ steps.nproc.outputs.nproc }}
         run: |
-          set -o pipefail
-          ./xrpld --unittest --unittest-jobs "${BUILD_NPROC}" 2>&1 | tee unittest.log
+          ./xrpld --unittest --unittest-jobs "${BUILD_NPROC}"
 
-      - name: Show test failure summary
-        if: ${{ failure() && !inputs.build_only }}
-        working-directory: ${{ runner.os == 'Windows' && format('{0}/{1}', env.BUILD_DIR, inputs.build_type) || env.BUILD_DIR }}
-        run: |
-          if [ ! -f unittest.log ]; then
-            echo "unittest.log not found; embedded tests may not have run."
-            exit 0
-          fi
-
-          if ! grep -E "failed" unittest.log; then
-            echo "Log present but no failure lines found in unittest.log."
-          fi
       - name: Debug failure (Linux)
         if: ${{ failure() && runner.os == 'Linux' && !inputs.build_only }}
         run: |

.github/workflows/reusable-clang-tidy-files.yml

@@ -78,13 +78,13 @@ jobs:
         id: run_clang_tidy
         continue-on-error: true
         env:
-          TARGETS: ${{ inputs.files != '' && inputs.files || 'src tests' }}
+          FILES: ${{ inputs.files }}
         run: |
-          run-clang-tidy -j ${{ steps.nproc.outputs.nproc }} -p "${BUILD_DIR}" ${TARGETS} 2>&1 | tee clang-tidy-output.txt
+          run-clang-tidy -j ${{ steps.nproc.outputs.nproc }} -p "$BUILD_DIR" $FILES 2>&1 | tee clang-tidy-output.txt
 
       - name: Upload clang-tidy output
         if: steps.run_clang_tidy.outcome != 'success'
-        uses: actions/upload-artifact@b7c566a772e6b6bfb58ed0dc250532a479d7789f # v6.0.0
+        uses: actions/upload-artifact@bbbca2ddaa5d8feaa63e36b76fdaad77386f024f # v7.0.0
         with:
           name: clang-tidy-results
           path: clang-tidy-output.txt

.github/workflows/reusable-clang-tidy.yml

@@ -31,7 +31,7 @@ jobs:
 
       - name: Get changed C++ files
         id: changed_files
-        uses: tj-actions/changed-files@7dee1b0c1557f278e5c7dc244927139d78c0e22a # v47.0.4
+        uses: tj-actions/changed-files@22103cc46bda19c2b464ffe86db46df6922fd323 # v47.0.5
         with:
           files: |
             **/*.cpp
@@ -41,7 +41,7 @@ jobs:
 
       - name: Get changed clang-tidy configuration
         id: changed_clang_tidy
-        uses: tj-actions/changed-files@7dee1b0c1557f278e5c7dc244927139d78c0e22a # v47.0.4
+        uses: tj-actions/changed-files@22103cc46bda19c2b464ffe86db46df6922fd323 # v47.0.5
         with:
           files: |
             .clang-tidy

.github/workflows/telemetry-validation.yml

@@ -0,0 +1,170 @@
+# Telemetry Validation CI Workflow
+#
+# Builds rippled with telemetry enabled, runs the multi-node workload
+# harness, validates all telemetry data, and runs performance benchmarks.
+#
+# This is a separate workflow from the main CI. It runs:
+#   - On manual dispatch (workflow_dispatch)
+#   - On pushes to telemetry-related branches
+#
+# The workflow is intentionally heavyweight (builds rippled, starts Docker
+# services, runs a multi-node cluster) — it validates the full telemetry
+# stack end-to-end rather than individual unit tests.
+
+name: Telemetry Validation
+
+on:
+  workflow_dispatch:
+    inputs:
+      rpc_rate:
+        description: "RPC load rate (requests per second)"
+        required: false
+        default: "50"
+      rpc_duration:
+        description: "RPC load duration (seconds)"
+        required: false
+        default: "120"
+      tx_tps:
+        description: "Transaction submit rate (TPS)"
+        required: false
+        default: "5"
+      tx_duration:
+        description: "Transaction submit duration (seconds)"
+        required: false
+        default: "120"
+      run_benchmark:
+        description: "Run performance benchmarks"
+        required: false
+        type: boolean
+        default: false
+
+  push:
+    branches:
+      - "pratik/otel-phase*"
+      - "feature/otel-*"
+      - "feature/telemetry-*"
+    paths:
+      - "docker/telemetry/**"
+      - "include/xrpl/basics/Telemetry*.h"
+      - "src/xrpld/app/misc/Telemetry*"
+
+concurrency:
+  group: telemetry-validation-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  validate-telemetry:
+    name: Telemetry Stack Validation
+    runs-on: ubuntu-latest
+    timeout-minutes: 60
+
+    services:
+      # Docker-in-Docker not needed — we use docker compose directly.
+      # The runner has Docker pre-installed.
+      docker:
+        image: docker:dind
+        options: --privileged
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Install system dependencies
+        run: |
+          sudo apt-get update
+          sudo apt-get install -y curl jq bc python3 python3-pip
+
+      - name: Install Python dependencies
+        run: pip3 install -r docker/telemetry/workload/requirements.txt
+
+      - name: Install Conan
+        run: pip3 install conan
+
+      - name: Set up Conan
+        uses: ./.github/actions/setup-conan
+
+      - name: Cache Conan packages and build directory
+        uses: actions/cache@v4
+        with:
+          path: |
+            ~/.conan2/p
+            .build
+          key: telemetry-build-${{ runner.os }}-${{ hashFiles('conanfile.py', 'CMakeLists.txt') }}
+          restore-keys: |
+            telemetry-build-${{ runner.os }}-
+
+      - name: Build rippled with telemetry
+        run: |
+          conan install . --build=missing --profile ci --output-folder=build
+          cmake -B build -DCMAKE_TOOLCHAIN_FILE:FILEPATH=build/generators/conan_toolchain.cmake -DCMAKE_BUILD_TYPE=Release -Dtelemetry=ON
+          cmake --build build --parallel $(nproc)
+
+      - name: Make scripts executable
+        run: |
+          chmod +x docker/telemetry/workload/*.sh
+
+      - name: Run full telemetry validation
+        id: validation
+        env:
+          XRPLD: build/xrpld
+        run: |
+          ARGS="--xrpld build/xrpld --skip-loki"
+          ARGS="$ARGS --rpc-rate ${{ github.event.inputs.rpc_rate || '50' }}"
+          ARGS="$ARGS --rpc-duration ${{ github.event.inputs.rpc_duration || '120' }}"
+          ARGS="$ARGS --tx-tps ${{ github.event.inputs.tx_tps || '5' }}"
+          ARGS="$ARGS --tx-duration ${{ github.event.inputs.tx_duration || '120' }}"
+          if [ "${{ github.event.inputs.run_benchmark }}" = "true" ]; then
+            ARGS="$ARGS --with-benchmark"
+          fi
+          docker/telemetry/workload/run-full-validation.sh $ARGS
+        continue-on-error: true
+
+      - name: Upload validation reports
+        if: always()
+        uses: actions/upload-artifact@v4
+        with:
+          name: telemetry-validation-reports
+          path: /tmp/xrpld-validation/reports/
+          retention-days: 30
+
+      - name: Upload node logs
+        if: failure()
+        uses: actions/upload-artifact@v4
+        with:
+          name: xrpld-node-logs
+          path: /tmp/xrpld-validation/node*/debug.log
+          retention-days: 7
+
+      - name: Print validation summary
+        if: always()
+        run: |
+          REPORT="/tmp/xrpld-validation/reports/validation-report.json"
+          if [ -f "$REPORT" ]; then
+            echo "## Telemetry Validation Results" >> "$GITHUB_STEP_SUMMARY"
+            echo "" >> "$GITHUB_STEP_SUMMARY"
+            TOTAL=$(jq '.summary.total' "$REPORT")
+            PASSED=$(jq '.summary.passed' "$REPORT")
+            FAILED=$(jq '.summary.failed' "$REPORT")
+            echo "| Metric | Value |" >> "$GITHUB_STEP_SUMMARY"
+            echo "|--------|-------|" >> "$GITHUB_STEP_SUMMARY"
+            echo "| Total Checks | $TOTAL |" >> "$GITHUB_STEP_SUMMARY"
+            echo "| Passed | $PASSED |" >> "$GITHUB_STEP_SUMMARY"
+            echo "| Failed | $FAILED |" >> "$GITHUB_STEP_SUMMARY"
+            echo "" >> "$GITHUB_STEP_SUMMARY"
+            if [ "$FAILED" -gt 0 ]; then
+              echo "### Failed Checks" >> "$GITHUB_STEP_SUMMARY"
+              echo "" >> "$GITHUB_STEP_SUMMARY"
+              jq -r '.checks[] | select(.passed == false) | "- **\(.name)**: \(.message)"' "$REPORT" >> "$GITHUB_STEP_SUMMARY"
+            fi
+          fi
+
+      - name: Cleanup
+        if: always()
+        run: |
+          docker/telemetry/workload/run-full-validation.sh --cleanup 2>/dev/null || true
+
+      - name: Check validation result
+        if: steps.validation.outcome == 'failure'
+        run: |
+          echo "Telemetry validation failed. Check the uploaded reports for details."
+          exit 1

.github/workflows/upload-conan-deps.yml

@@ -64,7 +64,7 @@ jobs:
     steps:
       - name: Cleanup workspace (macOS and Windows)
         if: ${{ runner.os == 'macOS' || runner.os == 'Windows' }}
-        uses: XRPLF/actions/cleanup-workspace@c7d9ce5ebb03c752a354889ecd870cadfc2b1cd4
+        uses: XRPLF/actions/cleanup-workspace@cf0433aa74563aead044a1e395610c96d65a37cf
 
       - name: Checkout repository
         uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2

.pre-commit-config.yaml

@@ -20,30 +20,29 @@ repos:
         args: [--assume-in-merge]
 
   - repo: https://github.com/pre-commit/mirrors-clang-format
-    rev: 75ca4ad908dc4a99f57921f29b7e6c1521e10b26 # frozen: v21.1.8
+    rev: cd481d7b0bfb5c7b3090c21846317f9a8262e891 # frozen: v22.1.0
     hooks:
       - id: clang-format
         args: [--style=file]
         "types_or": [c++, c, proto]
 
-  - repo: https://github.com/cheshirekow/cmake-format-precommit
-    rev: e2c2116d86a80e72e7146a06e68b7c228afc6319 # frozen: v0.6.13
+  - repo: https://github.com/BlankSpruce/gersemi
+    rev: 0.26.0
     hooks:
-      - id: cmake-format
-        additional_dependencies: [PyYAML]
+      - id: gersemi
 
   - repo: https://github.com/rbubley/mirrors-prettier
-    rev: 5ba47274f9b181bce26a5150a725577f3c336011 # frozen: v3.6.2
+    rev: c2bc67fe8f8f549cc489e00ba8b45aa18ee713b1 # frozen: v3.8.1
     hooks:
       - id: prettier
 
   - repo: https://github.com/psf/black-pre-commit-mirror
-    rev: 831207fd435b47aeffdf6af853097e64322b4d44 # frozen: v25.12.0
+    rev: ea488cebbfd88a5f50b8bd95d5c829d0bb76feb8 # frozen: 26.1.0
     hooks:
       - id: black
 
   - repo: https://github.com/streetsidesoftware/cspell-cli
-    rev: 1cfa010f078c354f3ffb8413616280cc28f5ba21 # frozen: v9.4.0
+    rev: a42085ade523f591dca134379a595e7859986445 # frozen: v9.7.0
     hooks:
       - id: cspell # Spell check changed files
         exclude: .config/cspell.config.yaml

API-CHANGELOG.md

@@ -22,6 +22,19 @@ API version 2 is available in `rippled` version 2.0.0 and later. See [API-VERSIO
 
 This version is supported by all `rippled` versions. For WebSocket and HTTP JSON-RPC requests, it is currently the default API version used when no `api_version` is specified.
 
+## Unreleased
+
+This section contains changes targeting a future version.
+
+### Additions
+
+- `server_definitions`: Added the following new sections to the response ([#6321](https://github.com/XRPLF/rippled/pull/6321)):
+  - `TRANSACTION_FORMATS`: Describes the fields and their optionality for each transaction type, including common fields shared across all transactions.
+  - `LEDGER_ENTRY_FORMATS`: Describes the fields and their optionality for each ledger entry type, including common fields shared across all ledger entries.
+  - `TRANSACTION_FLAGS`: Maps transaction type names to their supported flags and flag values.
+  - `LEDGER_ENTRY_FLAGS`: Maps ledger entry type names to their flags and flag values.
+  - `ACCOUNT_SET_FLAGS`: Maps AccountSet flag names (asf flags) to their numeric values.
+
 ## XRP Ledger server version 3.1.0
 
 [Version 3.1.0](https://github.com/XRPLF/rippled/releases/tag/3.1.0) was released on Jan 27, 2026.

CMakeLists.txt

@@ -1,16 +1,16 @@
 cmake_minimum_required(VERSION 3.16)
 
-if (POLICY CMP0074)
+if(POLICY CMP0074)
     cmake_policy(SET CMP0074 NEW)
-endif ()
-if (POLICY CMP0077)
+endif()
+if(POLICY CMP0077)
     cmake_policy(SET CMP0077 NEW)
-endif ()
+endif()
 
 # Fix "unrecognized escape" issues when passing CMAKE_MODULE_PATH on Windows.
-if (DEFINED CMAKE_MODULE_PATH)
+if(DEFINED CMAKE_MODULE_PATH)
     file(TO_CMAKE_PATH "${CMAKE_MODULE_PATH}" CMAKE_MODULE_PATH)
-endif ()
+endif()
 list(APPEND CMAKE_MODULE_PATH "${CMAKE_CURRENT_SOURCE_DIR}/cmake")
 
 project(xrpl)
@@ -21,77 +21,64 @@ set(CMAKE_EXPORT_COMPILE_COMMANDS ON)
 
 include(CompilationEnv)
 
-if (is_gcc)
+if(is_gcc)
     # GCC-specific fixes
     add_compile_options(-Wno-unknown-pragmas -Wno-subobject-linkage)
     # -Wno-subobject-linkage can be removed when we upgrade GCC version to at least 13.3
-elseif (is_clang)
+elseif(is_clang)
     # Clang-specific fixes
     add_compile_options(-Wno-unknown-warning-option) # Ignore unknown warning options
-elseif (is_msvc)
+elseif(is_msvc)
     # MSVC-specific fixes
     add_compile_options(/wd4068) # Ignore unknown pragmas
-endif ()
+endif()
 
 # Enable ccache to speed up builds.
 include(Ccache)
 
-# make GIT_COMMIT_HASH define available to all sources
-find_package(Git)
-if (Git_FOUND)
-    execute_process(COMMAND ${GIT_EXECUTABLE} --git-dir=${CMAKE_CURRENT_SOURCE_DIR}/.git rev-parse
-                            HEAD OUTPUT_STRIP_TRAILING_WHITESPACE OUTPUT_VARIABLE gch)
-    if (gch)
-        set(GIT_COMMIT_HASH "${gch}")
-        message(STATUS gch: ${GIT_COMMIT_HASH})
-        add_definitions(-DGIT_COMMIT_HASH="${GIT_COMMIT_HASH}")
-    endif ()
-
-    execute_process(COMMAND ${GIT_EXECUTABLE} --git-dir=${CMAKE_CURRENT_SOURCE_DIR}/.git rev-parse
-                            --abbrev-ref HEAD OUTPUT_STRIP_TRAILING_WHITESPACE OUTPUT_VARIABLE gb)
-    if (gb)
-        set(GIT_BRANCH "${gb}")
-        message(STATUS gb: ${GIT_BRANCH})
-        add_definitions(-DGIT_BRANCH="${GIT_BRANCH}")
-    endif ()
-endif () # git
-
-if (thread_safety_analysis)
-    add_compile_options(-Wthread-safety -D_LIBCPP_ENABLE_THREAD_SAFETY_ANNOTATIONS
-                        -DXRPL_ENABLE_THREAD_SAFETY_ANNOTATIONS)
+if(thread_safety_analysis)
+    add_compile_options(
+        -Wthread-safety
+        -D_LIBCPP_ENABLE_THREAD_SAFETY_ANNOTATIONS
+        -DXRPL_ENABLE_THREAD_SAFETY_ANNOTATIONS
+    )
     add_compile_options("-stdlib=libc++")
     add_link_options("-stdlib=libc++")
-endif ()
+endif()
 
 include(CheckCXXCompilerFlag)
 include(FetchContent)
 include(ExternalProject)
 include(CMakeFuncs) # must come *after* ExternalProject b/c it overrides one function in EP
-if (target)
-    message(FATAL_ERROR "The target option has been removed - use native cmake options to control build"
+if(target)
+    message(
+        FATAL_ERROR
+        "The target option has been removed - use native cmake options to control build"
     )
-endif ()
+endif()
 
 include(XrplSanity)
 include(XrplVersion)
 include(XrplSettings)
 # this check has to remain in the top-level cmake because of the early return statement
-if (packages_only)
-    if (NOT TARGET rpm)
-        message(FATAL_ERROR "packages_only requested, but targets were not created - is docker installed?"
+if(packages_only)
+    if(NOT TARGET rpm)
+        message(
+            FATAL_ERROR
+            "packages_only requested, but targets were not created - is docker installed?"
         )
-    endif ()
+    endif()
     return()
-endif ()
+endif()
 include(XrplCompiler)
 include(XrplSanitizers)
 include(XrplInterface)
 
 option(only_docs "Include only the docs target?" FALSE)
 include(XrplDocs)
-if (only_docs)
+if(only_docs)
     return()
-endif ()
+endif()
 
 include(deps/Boost)
 
@@ -110,42 +97,58 @@ find_package(xxHash REQUIRED)
 
 target_link_libraries(
     xrpl_libs
-    INTERFACE ed25519::ed25519
-              lz4::lz4
-              OpenSSL::Crypto
-              OpenSSL::SSL
-              secp256k1::secp256k1
-              soci::soci
-              SQLite::SQLite3)
+    INTERFACE
+        ed25519::ed25519
+        lz4::lz4
+        OpenSSL::Crypto
+        OpenSSL::SSL
+        secp256k1::secp256k1
+        soci::soci
+        SQLite::SQLite3
+)
 
 option(rocksdb "Enable RocksDB" ON)
-if (rocksdb)
+if(rocksdb)
     find_package(RocksDB REQUIRED)
-    set_target_properties(RocksDB::rocksdb PROPERTIES INTERFACE_COMPILE_DEFINITIONS
-                                                      XRPL_ROCKSDB_AVAILABLE=1)
+    set_target_properties(
+        RocksDB::rocksdb
+        PROPERTIES INTERFACE_COMPILE_DEFINITIONS XRPL_ROCKSDB_AVAILABLE=1
+    )
     target_link_libraries(xrpl_libs INTERFACE RocksDB::rocksdb)
-endif ()
+endif()
+
+# OpenTelemetry distributed tracing (optional).
+# When ON, links against opentelemetry-cpp and defines XRPL_ENABLE_TELEMETRY
+# so that tracing macros in TracingInstrumentation.h are compiled in.
+# When OFF (default), all tracing code compiles to no-ops with zero overhead.
+# Enable via: conan install -o telemetry=True, or cmake -Dtelemetry=ON.
+option(telemetry "Enable OpenTelemetry tracing" OFF)
+if(telemetry)
+    find_package(opentelemetry-cpp CONFIG REQUIRED)
+    add_compile_definitions(XRPL_ENABLE_TELEMETRY)
+    message(STATUS "OpenTelemetry tracing enabled")
+endif()
 
 # Work around changes to Conan recipe for now.
-if (TARGET nudb::core)
+if(TARGET nudb::core)
     set(nudb nudb::core)
-elseif (TARGET NuDB::nudb)
+elseif(TARGET NuDB::nudb)
     set(nudb NuDB::nudb)
-else ()
+else()
     message(FATAL_ERROR "unknown nudb target")
-endif ()
+endif()
 target_link_libraries(xrpl_libs INTERFACE ${nudb})
 
-if (coverage)
+if(coverage)
     include(XrplCov)
-endif ()
+endif()
 
 set(PROJECT_EXPORT_SET XrplExports)
 include(XrplCore)
 include(XrplInstall)
 include(XrplValidatorKeys)
 
-if (tests)
+if(tests)
     include(CTest)
     add_subdirectory(src/tests/libxrpl)
-endif ()
+endif()

CONTRIBUTING.md

@@ -251,29 +251,6 @@ pip3 install pre-commit
 pre-commit install
 ```
 
-## Clang-tidy
-
-All code must pass `clang-tidy` checks according to the settings in [`.clang-tidy`](./.clang-tidy).
-
-There is a Continuous Integration job that runs clang-tidy on pull requests. The CI will check:
-
-- All changed C++ files (`.cpp`, `.h`, `.ipp`) when only code files are modified
-- **All files in the repository** when the `.clang-tidy` configuration file is changed
-
-This ensures that configuration changes don't introduce new warnings across the codebase.
-
-### Running clang-tidy locally
-
-Before running clang-tidy, you must build the project to generate required files (particularly protobuf headers). Refer to [`BUILD.md`](./BUILD.md) for build instructions.
-
-Then run clang-tidy on your local changes:
-
-```
-run-clang-tidy -p build src tests
-```
-
-This will check all source files in the `src` and `tests` directories using the compile commands from your `build` directory.
-
 ## Contracts and instrumentation
 
 We are using [Antithesis](https://antithesis.com/) for continuous fuzzing,

OpenTelemetryPlan/00-tracing-fundamentals.md

@@ -0,0 +1,244 @@
+# Distributed Tracing Fundamentals
+
+> **Parent Document**: [OpenTelemetryPlan.md](./OpenTelemetryPlan.md)
+> **Next**: [Architecture Analysis](./01-architecture-analysis.md)
+
+---
+
+## What is Distributed Tracing?
+
+Distributed tracing is a method for tracking data objects as they flow through distributed systems. In a network like XRP Ledger, a single transaction touches multiple independent nodes—each with no shared memory or logging. Distributed tracing connects these dots.
+
+**Without tracing:** You see isolated logs on each node with no way to correlate them.
+
+**With tracing:** You see the complete journey of a transaction or an event across all nodes it touched.
+
+---
+
+## Core Concepts
+
+### 1. Trace
+
+A **trace** represents the entire journey of a request through the system. It has a unique `trace_id` that stays constant across all nodes.
+
+```
+Trace ID: abc123
+├── Node A: received transaction
+├── Node B: relayed transaction
+├── Node C: included in consensus
+└── Node D: applied to ledger
+```
+
+### 2. Span
+
+A **span** represents a single unit of work within a trace. Each span has:
+
+| Attribute        | Description           | Example                    |
+| ---------------- | --------------------- | -------------------------- |
+| `trace_id`       | Links to parent trace | `abc123`                   |
+| `span_id`        | Unique identifier     | `span456`                  |
+| `parent_span_id` | Parent span (if any)  | `p_span123`                |
+| `name`           | Operation name        | `rpc.submit`               |
+| `start_time`     | When work began       | `2024-01-15T10:30:00Z`     |
+| `end_time`       | When work completed   | `2024-01-15T10:30:00.050Z` |
+| `attributes`     | Key-value metadata    | `tx.hash=ABC...`           |
+| `status`         | OK, ERROR MSG         | `OK`                       |
+
+### 3. Trace Context
+
+**Trace context** is the data that propagates between services to link spans together. It contains:
+
+- `trace_id` - The trace this span belongs to
+- `span_id` - The current span (becomes parent for child spans)
+- `trace_flags` - Sampling decisions
+
+---
+
+## How Spans Form a Trace
+
+Spans have parent-child relationships forming a tree structure:
+
+```mermaid
+flowchart TB
+    subgraph trace["Trace: abc123"]
+        A["tx.submit<br/>span_id: 001<br/>50ms"] --> B["tx.validate<br/>span_id: 002<br/>5ms"]
+        A --> C["tx.relay<br/>span_id: 003<br/>10ms"]
+        A --> D["tx.apply<br/>span_id: 004<br/>30ms"]
+        D --> E["ledger.update<br/>span_id: 005<br/>20ms"]
+    end
+
+    style A fill:#0d47a1,stroke:#082f6a,color:#ffffff
+    style B fill:#1b5e20,stroke:#0d3d14,color:#ffffff
+    style C fill:#1b5e20,stroke:#0d3d14,color:#ffffff
+    style D fill:#1b5e20,stroke:#0d3d14,color:#ffffff
+    style E fill:#bf360c,stroke:#8c2809,color:#ffffff
+```
+
+The same trace visualized as a **timeline (Gantt chart)**:
+
+```
+Time →   0ms    10ms    20ms    30ms    40ms    50ms
+         ├───────────────────────────────────────────┤
+tx.submit│▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓│
+         ├─────┤
+tx.valid │▓▓▓▓▓│
+         │     ├──────────┤
+tx.relay │     │▓▓▓▓▓▓▓▓▓▓│
+         │               ├────────────────────────────┤
+tx.apply │               │▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓│
+         │                         ├──────────────────┤
+ledger   │                         │▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓│
+```
+
+---
+
+## Distributed Traces Across Nodes
+
+In distributed systems like rippled, traces span **multiple independent nodes**. The trace context must be propagated in network messages:
+
+```mermaid
+sequenceDiagram
+    participant Client
+    participant NodeA as Node A
+    participant NodeB as Node B
+    participant NodeC as Node C
+
+    Client->>NodeA: Submit TX<br/>(no trace context)
+
+    Note over NodeA: Creates new trace<br/>trace_id: abc123<br/>span: tx.receive
+
+    NodeA->>NodeB: Relay TX<br/>(trace_id: abc123, parent: 001)
+
+    Note over NodeB: Creates child span<br/>span: tx.relay<br/>parent_span_id: 001
+
+    NodeA->>NodeC: Relay TX<br/>(trace_id: abc123, parent: 001)
+
+    Note over NodeC: Creates child span<br/>span: tx.relay<br/>parent_span_id: 001
+
+    Note over NodeA,NodeC: All spans share trace_id: abc123<br/>enabling correlation across nodes
+```
+
+---
+
+## Context Propagation
+
+For traces to work across nodes, **trace context must be propagated** in messages.
+
+### What's in the Context (32 bytes)
+
+| Field         | Size       | Description                                             |
+| ------------- | ---------- | ------------------------------------------------------- |
+| `trace_id`    | 16 bytes   | Identifies the entire trace (constant across all nodes) |
+| `span_id`     | 8 bytes    | The sender's current span (becomes parent on receiver)  |
+| `trace_flags` | 4 bytes    | Sampling decision flags                                 |
+| `trace_state` | ~0-4 bytes | Optional vendor-specific data                           |
+
+### How span_id Changes at Each Hop
+
+Only **one** `span_id` travels in the context - the sender's current span. Each node:
+
+1. Extracts the received `span_id` and uses it as the `parent_span_id`
+2. Creates a **new** `span_id` for its own span
+3. Sends its own `span_id` as the parent when forwarding
+
+```
+Node A                      Node B                      Node C
+──────                      ──────                      ──────
+
+Span AAA                    Span BBB                    Span CCC
+   │                           │                           │
+   ▼                           ▼                           ▼
+Context out:                Context out:                Context out:
+├─ trace_id: abc123         ├─ trace_id: abc123         ├─ trace_id: abc123
+├─ span_id: AAA ──────────► ├─ span_id: BBB ──────────► ├─ span_id: CCC ──────►
+└─ flags: 01                └─ flags: 01                └─ flags: 01
+                               │                           │
+                          parent = AAA               parent = BBB
+```
+
+The `trace_id` stays constant, but `span_id` **changes at every hop** to maintain the parent-child chain.
+
+### Propagation Formats
+
+There are two patterns:
+
+### HTTP/RPC Headers (W3C Trace Context)
+
+```
+traceparent: 00-abc123def456-span789-01
+             │  │             │      │
+             │  │             │      └── Flags (sampled)
+             │  │             └── Parent span ID
+             │  └── Trace ID
+             └── Version
+```
+
+### Protocol Buffers (rippled P2P messages)
+
+```protobuf
+message TMTransaction {
+    bytes rawTransaction = 1;
+    // ... existing fields ...
+
+    // Trace context extension
+    bytes trace_parent = 100;  // W3C traceparent
+    bytes trace_state = 101;   // W3C tracestate
+}
+```
+
+---
+
+## Sampling
+
+Not every trace needs to be recorded. **Sampling** reduces overhead:
+
+### Head Sampling (at trace start)
+
+```
+Request arrives → Random 10% chance → Record or skip entire trace
+```
+
+- ✅ Low overhead
+- ❌ May miss interesting traces
+
+### Tail Sampling (after trace completes)
+
+```
+Trace completes → Collector evaluates:
+                  - Error? → KEEP
+                  - Slow? → KEEP
+                  - Normal? → Sample 10%
+```
+
+- ✅ Never loses important traces
+- ❌ Higher memory usage at collector
+
+---
+
+## Key Benefits for rippled
+
+| Challenge                          | How Tracing Helps                        |
+| ---------------------------------- | ---------------------------------------- |
+| "Where is my transaction?"         | Follow trace across all nodes it touched |
+| "Why was consensus slow?"          | See timing breakdown of each phase       |
+| "Which node is the bottleneck?"    | Compare span durations across nodes      |
+| "What happened during the outage?" | Correlate errors across the network      |
+
+---
+
+## Glossary
+
+| Term                | Definition                                                      |
+| ------------------- | --------------------------------------------------------------- |
+| **Trace**           | Complete journey of a request, identified by `trace_id`         |
+| **Span**            | Single operation within a trace                                 |
+| **Context**         | Data propagated between services (`trace_id`, `span_id`, flags) |
+| **Instrumentation** | Code that creates spans and propagates context                  |
+| **Collector**       | Service that receives, processes, and exports traces            |
+| **Backend**         | Storage/visualization system (Jaeger, Tempo, etc.)              |
+| **Head Sampling**   | Sampling decision at trace start                                |
+| **Tail Sampling**   | Sampling decision after trace completes                         |
+
+---
+
+_Next: [Architecture Analysis](./01-architecture-analysis.md)_ | _Back to: [Overview](./OpenTelemetryPlan.md)_

OpenTelemetryPlan/01-architecture-analysis.md

@@ -0,0 +1,330 @@
+# Architecture Analysis
+
+> **Parent Document**: [OpenTelemetryPlan.md](./OpenTelemetryPlan.md)
+> **Related**: [Design Decisions](./02-design-decisions.md) | [Implementation Strategy](./03-implementation-strategy.md)
+
+---
+
+## 1.1 Current rippled Architecture Overview
+
+The rippled node software consists of several interconnected components that need instrumentation for distributed tracing:
+
+```mermaid
+flowchart TB
+    subgraph rippled["rippled Node"]
+        subgraph services["Core Services"]
+            RPC["RPC Server<br/>(HTTP/WS/gRPC)"]
+            Overlay["Overlay<br/>(P2P Network)"]
+            Consensus["Consensus<br/>(RCLConsensus)"]
+        end
+
+        JobQueue["JobQueue<br/>(Thread Pool)"]
+
+        subgraph processing["Processing Layer"]
+            NetworkOPs["NetworkOPs<br/>(Tx Processing)"]
+            LedgerMaster["LedgerMaster<br/>(Ledger Mgmt)"]
+            NodeStore["NodeStore<br/>(Database)"]
+        end
+
+        subgraph observability["Existing Observability"]
+            PerfLog["PerfLog<br/>(JSON)"]
+            Insight["Insight<br/>(StatsD)"]
+            Logging["Logging<br/>(Journal)"]
+        end
+
+        services --> JobQueue
+        JobQueue --> processing
+    end
+
+    style rippled fill:#424242,stroke:#212121,color:#ffffff
+    style services fill:#1565c0,stroke:#0d47a1,color:#ffffff
+    style processing fill:#2e7d32,stroke:#1b5e20,color:#ffffff
+    style observability fill:#e65100,stroke:#bf360c,color:#ffffff
+```
+
+---
+
+## 1.2 Key Components for Instrumentation
+
+| Component         | Location                                   | Purpose                  | Trace Value                  |
+| ----------------- | ------------------------------------------ | ------------------------ | ---------------------------- |
+| **Overlay**       | `src/xrpld/overlay/`                       | P2P communication        | Message propagation timing   |
+| **PeerImp**       | `src/xrpld/overlay/detail/PeerImp.cpp`     | Individual peer handling | Per-peer latency             |
+| **RCLConsensus**  | `src/xrpld/app/consensus/RCLConsensus.cpp` | Consensus algorithm      | Round timing, phase analysis |
+| **NetworkOPs**    | `src/xrpld/app/misc/NetworkOPs.cpp`        | Transaction processing   | Tx lifecycle tracking        |
+| **ServerHandler** | `src/xrpld/rpc/detail/ServerHandler.cpp`   | RPC entry point          | Request latency              |
+| **RPCHandler**    | `src/xrpld/rpc/detail/RPCHandler.cpp`      | Command execution        | Per-command timing           |
+| **JobQueue**      | `src/xrpl/core/JobQueue.h`                 | Async task execution     | Queue wait times             |
+
+---
+
+## 1.3 Transaction Flow Diagram
+
+Transaction flow spans multiple nodes in the network. Each node creates linked spans to form a distributed trace:
+
+```mermaid
+sequenceDiagram
+    participant Client
+    participant PeerA as Peer A (Receive)
+    participant PeerB as Peer B (Relay)
+    participant PeerC as Peer C (Validate)
+
+    Client->>PeerA: 1. Submit TX
+
+    rect rgb(230, 245, 255)
+        Note over PeerA: tx.receive SPAN START
+        PeerA->>PeerA: HashRouter Deduplication
+        PeerA->>PeerA: tx.validate (child span)
+    end
+
+    PeerA->>PeerB: 2. Relay TX (with trace ctx)
+
+    rect rgb(230, 245, 255)
+        Note over PeerB: tx.receive (linked span)
+    end
+
+    PeerB->>PeerC: 3. Relay TX
+
+    rect rgb(230, 245, 255)
+        Note over PeerC: tx.receive (linked span)
+        PeerC->>PeerC: tx.process
+    end
+
+    Note over Client,PeerC: DISTRIBUTED TRACE (same trace_id: abc123)
+```
+
+### Trace Structure
+
+```
+trace_id: abc123
+├── span: tx.receive (Peer A)
+│   ├── span: tx.validate
+│   └── span: tx.relay
+├── span: tx.receive (Peer B) [parent: Peer A]
+│   └── span: tx.relay
+└── span: tx.receive (Peer C) [parent: Peer B]
+    └── span: tx.process
+```
+
+---
+
+## 1.4 Consensus Round Flow
+
+Consensus rounds are multi-phase operations that benefit significantly from tracing:
+
+```mermaid
+flowchart TB
+    subgraph round["consensus.round (root span)"]
+        attrs["Attributes:<br/>xrpl.consensus.ledger.seq = 12345678<br/>xrpl.consensus.mode = proposing<br/>xrpl.consensus.proposers = 35"]
+
+        subgraph open["consensus.phase.open"]
+            open_desc["Duration: ~3s<br/>Waiting for transactions"]
+        end
+
+        subgraph establish["consensus.phase.establish"]
+            est_attrs["proposals_received = 28<br/>disputes_resolved = 3"]
+            est_children["├── consensus.proposal.receive (×28)<br/>├── consensus.proposal.send (×1)<br/>└── consensus.dispute.resolve (×3)"]
+        end
+
+        subgraph accept["consensus.phase.accept"]
+            acc_attrs["transactions_applied = 150<br/>ledger.hash = DEF456..."]
+            acc_children["├── ledger.build<br/>└── ledger.validate"]
+        end
+
+        attrs --> open
+        open --> establish
+        establish --> accept
+    end
+
+    style round fill:#f57f17,stroke:#e65100,color:#ffffff
+    style open fill:#1565c0,stroke:#0d47a1,color:#ffffff
+    style establish fill:#2e7d32,stroke:#1b5e20,color:#ffffff
+    style accept fill:#c2185b,stroke:#880e4f,color:#ffffff
+```
+
+---
+
+## 1.5 RPC Request Flow
+
+RPC requests support W3C Trace Context headers for distributed tracing across services:
+
+```mermaid
+flowchart TB
+    subgraph request["rpc.request (root span)"]
+        http["HTTP Request<br/>POST /<br/>traceparent: 00-abc123...-def456...-01"]
+
+        attrs["Attributes:<br/>http.method = POST<br/>net.peer.ip = 192.168.1.100<br/>xrpl.rpc.command = submit"]
+
+        subgraph enqueue["jobqueue.enqueue"]
+            job_attr["xrpl.job.type = jtCLIENT_RPC"]
+        end
+
+        subgraph command["rpc.command.submit"]
+            cmd_attrs["xrpl.rpc.version = 2<br/>xrpl.rpc.role = user"]
+            cmd_children["├── tx.deserialize<br/>├── tx.validate_local<br/>└── tx.submit_to_network"]
+        end
+
+        response["Response: 200 OK<br/>Duration: 45ms"]
+
+        http --> attrs
+        attrs --> enqueue
+        enqueue --> command
+        command --> response
+    end
+
+    style request fill:#2e7d32,stroke:#1b5e20,color:#ffffff
+    style enqueue fill:#1565c0,stroke:#0d47a1,color:#ffffff
+    style command fill:#e65100,stroke:#bf360c,color:#ffffff
+```
+
+---
+
+## 1.6 Key Trace Points
+
+The following table identifies priority instrumentation points across the codebase:
+
+| Category        | Span Name              | File                 | Method                 | Priority |
+| --------------- | ---------------------- | -------------------- | ---------------------- | -------- |
+| **Transaction** | `tx.receive`           | `PeerImp.cpp`        | `handleTransaction()`  | High     |
+| **Transaction** | `tx.validate`          | `NetworkOPs.cpp`     | `processTransaction()` | High     |
+| **Transaction** | `tx.process`           | `NetworkOPs.cpp`     | `doTransactionSync()`  | High     |
+| **Transaction** | `tx.relay`             | `OverlayImpl.cpp`    | `relay()`              | Medium   |
+| **Consensus**   | `consensus.round`      | `RCLConsensus.cpp`   | `startRound()`         | High     |
+| **Consensus**   | `consensus.phase.*`    | `Consensus.h`        | `timerEntry()`         | High     |
+| **Consensus**   | `consensus.proposal.*` | `RCLConsensus.cpp`   | `peerProposal()`       | Medium   |
+| **RPC**         | `rpc.request`          | `ServerHandler.cpp`  | `onRequest()`          | High     |
+| **RPC**         | `rpc.command.*`        | `RPCHandler.cpp`     | `doCommand()`          | High     |
+| **Peer**        | `peer.connect`         | `OverlayImpl.cpp`    | `onHandoff()`          | Low      |
+| **Peer**        | `peer.message.*`       | `PeerImp.cpp`        | `onMessage()`          | Low      |
+| **Ledger**      | `ledger.acquire`       | `InboundLedgers.cpp` | `acquire()`            | Medium   |
+| **Ledger**      | `ledger.build`         | `RCLConsensus.cpp`   | `buildLCL()`           | High     |
+
+---
+
+## 1.7 Instrumentation Priority
+
+```mermaid
+quadrantChart
+    title Instrumentation Priority Matrix
+    x-axis Low Complexity --> High Complexity
+    y-axis Low Value --> High Value
+    quadrant-1 Implement First
+    quadrant-2 Plan Carefully
+    quadrant-3 Quick Wins
+    quadrant-4 Consider Later
+
+    RPC Tracing: [0.3, 0.85]
+    Transaction Tracing: [0.65, 0.92]
+    Consensus Tracing: [0.75, 0.87]
+    Peer Message Tracing: [0.4, 0.3]
+    Ledger Acquisition: [0.5, 0.6]
+    JobQueue Tracing: [0.35, 0.5]
+```
+
+---
+
+## 1.8 Observable Outcomes
+
+After implementing OpenTelemetry, operators and developers will gain visibility into the following:
+
+### 1.8.1 What You Will See: Traces
+
+| Trace Type                 | Description                                                                                 | Example Query in Grafana/Tempo                         |
+| -------------------------- | ------------------------------------------------------------------------------------------- | ------------------------------------------------------ |
+| **Transaction Lifecycle**  | Full journey from RPC submission through validation, relay, consensus, and ledger inclusion | `{service.name="rippled" && xrpl.tx.hash="ABC123..."}` |
+| **Cross-Node Propagation** | Transaction path across multiple rippled nodes with timing                                  | `{xrpl.tx.relay_count > 0}`                            |
+| **Consensus Rounds**       | Complete round with all phases (open, establish, accept)                                    | `{span.name=~"consensus.round.*"}`                     |
+| **RPC Request Processing** | Individual command execution with timing breakdown                                          | `{xrpl.rpc.command="account_info"}`                    |
+| **Ledger Acquisition**     | Peer-to-peer ledger data requests and responses                                             | `{span.name="ledger.acquire"}`                         |
+
+### 1.8.2 What You Will See: Metrics (Derived from Traces)
+
+| Metric                        | Description                            | Dashboard Panel             |
+| ----------------------------- | -------------------------------------- | --------------------------- |
+| **RPC Latency (p50/p95/p99)** | Response time distribution per command | Heatmap by command          |
+| **Transaction Throughput**    | Transactions processed per second      | Time series graph           |
+| **Consensus Round Duration**  | Time to complete consensus phases      | Histogram                   |
+| **Cross-Node Latency**        | Time for transaction to reach N nodes  | Line chart with percentiles |
+| **Error Rate**                | Failed transactions/RPC calls by type  | Stacked bar chart           |
+
+### 1.8.3 Concrete Dashboard Examples
+
+**Transaction Trace View (Jaeger/Tempo):**
+
+```
+┌────────────────────────────────────────────────────────────────────────────────┐
+│ Trace: abc123... (Transaction Submission)                    Duration: 847ms   │
+├────────────────────────────────────────────────────────────────────────────────┤
+│ ├── rpc.request [ServerHandler]                              ████░░░░░░  45ms  │
+│ │   └── rpc.command.submit [RPCHandler]                      ████░░░░░░  42ms  │
+│ │       └── tx.receive [NetworkOPs]                          ███░░░░░░░  35ms  │
+│ │           ├── tx.validate [TxQ]                            █░░░░░░░░░   8ms  │
+│ │           └── tx.relay [Overlay]                           ██░░░░░░░░  15ms  │
+│ │               ├── tx.receive [Node-B]                      █████░░░░░  52ms  │
+│ │               │   └── tx.relay [Node-B]                    ██░░░░░░░░  18ms  │
+│ │               └── tx.receive [Node-C]                      ██████░░░░  65ms  │
+│ └── consensus.round [RCLConsensus]                           ████████░░ 720ms  │
+│     ├── consensus.phase.open                                 ██░░░░░░░░ 180ms  │
+│     ├── consensus.phase.establish                            █████░░░░░ 480ms  │
+│     └── consensus.phase.accept                               █░░░░░░░░░  60ms  │
+└────────────────────────────────────────────────────────────────────────────────┘
+```
+
+**RPC Performance Dashboard Panel:**
+
+```
+┌─────────────────────────────────────────────────────────────┐
+│ RPC Command Latency (Last 1 Hour)                           │
+├─────────────────────────────────────────────────────────────┤
+│ Command          │ p50    │ p95    │ p99    │ Errors │ Rate │
+│──────────────────┼────────┼────────┼────────┼────────┼──────│
+│ account_info     │  12ms  │  45ms  │  89ms  │  0.1%  │ 150/s│
+│ submit           │  35ms  │ 120ms  │ 250ms  │  2.3%  │  45/s│
+│ ledger           │   8ms  │  25ms  │  55ms  │  0.0%  │  80/s│
+│ tx               │  15ms  │  50ms  │ 100ms  │  0.5%  │  60/s│
+│ server_info      │   5ms  │  12ms  │  20ms  │  0.0%  │ 200/s│
+└─────────────────────────────────────────────────────────────┘
+```
+
+**Consensus Health Dashboard Panel:**
+
+```mermaid
+---
+config:
+    xyChart:
+        width: 1200
+        height: 400
+        plotReservedSpacePercent: 50
+        chartOrientation: vertical
+    themeVariables:
+        xyChart:
+            plotColorPalette: "#3498db"
+---
+xychart-beta
+    title "Consensus Round Duration (Last 24 Hours)"
+    x-axis "Time of Day (Hours)" [0, 2, 4, 6, 8, 10, 12, 14, 16, 18, 20, 22, 24]
+    y-axis "Duration (seconds)" 1 --> 5
+    line [2.1, 2.3, 2.5, 2.4, 2.8, 1.6, 3.2, 3.0, 3.5, 1.3, 3.8, 3.6, 4.0, 3.2, 4.3, 4.1, 4.5, 4.3, 4.2, 2.4, 4.8, 4.6, 4.9, 4.7, 5.0, 4.9, 4.8, 2.6, 4.7, 4.5, 4.2, 4.0, 2.5, 3.7, 3.2, 3.4, 2.9, 3.1, 2.6, 2.8, 2.3, 1.5, 2.7, 2.4, 2.5, 2.3, 2.2, 2.1, 2.0]
+```
+
+### 1.8.4 Operator Actionable Insights
+
+| Scenario              | What You'll See                                                              | Action                           |
+| --------------------- | ---------------------------------------------------------------------------- | -------------------------------- |
+| **Slow RPC**          | Span showing which phase is slow (parsing, execution, serialization)         | Optimize specific code path      |
+| **Transaction Stuck** | Trace stops at validation; error attribute shows reason                      | Fix transaction parameters       |
+| **Consensus Delay**   | Phase.establish taking too long; proposer attribute shows missing validators | Investigate network connectivity |
+| **Memory Spike**      | Large batch of spans correlating with memory increase                        | Tune batch_size or sampling      |
+| **Network Partition** | Traces missing cross-node links for specific peer                            | Check peer connectivity          |
+
+### 1.8.5 Developer Debugging Workflow
+
+1. **Find Transaction**: Query by `xrpl.tx.hash` to get full trace
+2. **Identify Bottleneck**: Look at span durations to find slowest component
+3. **Check Attributes**: Review `xrpl.tx.validity`, `xrpl.rpc.status` for errors
+4. **Correlate Logs**: Use `trace_id` to find related PerfLog entries
+5. **Compare Nodes**: Filter by `service.instance.id` to compare behavior across nodes
+
+---
+
+_Next: [Design Decisions](./02-design-decisions.md)_ | _Back to: [Overview](./OpenTelemetryPlan.md)_

OpenTelemetryPlan/02-design-decisions.md

@@ -0,0 +1,498 @@
+# Design Decisions
+
+> **Parent Document**: [OpenTelemetryPlan.md](./OpenTelemetryPlan.md)
+> **Related**: [Architecture Analysis](./01-architecture-analysis.md) | [Code Samples](./04-code-samples.md)
+
+---
+
+## 2.1 OpenTelemetry Components
+
+### 2.1.1 SDK Selection
+
+**Primary Choice**: OpenTelemetry C++ SDK (`opentelemetry-cpp`)
+
+| Component                               | Purpose                | Required    |
+| --------------------------------------- | ---------------------- | ----------- |
+| `opentelemetry-cpp::api`                | Tracing API headers    | Yes         |
+| `opentelemetry-cpp::sdk`                | SDK implementation     | Yes         |
+| `opentelemetry-cpp::ext`                | Extensions (exporters) | Yes         |
+| `opentelemetry-cpp::otlp_grpc_exporter` | OTLP/gRPC export       | Recommended |
+| `opentelemetry-cpp::otlp_http_exporter` | OTLP/HTTP export       | Alternative |
+
+### 2.1.2 Instrumentation Strategy
+
+**Manual Instrumentation** (recommended):
+
+| Approach   | Pros                                                              | Cons                                                    |
+| ---------- | ----------------------------------------------------------------- | ------------------------------------------------------- |
+| **Manual** | Precise control, optimized placement, rippled-specific attributes | More development effort                                 |
+| **Auto**   | Less code, automatic coverage                                     | Less control, potential overhead, limited customization |
+
+---
+
+## 2.2 Exporter Configuration
+
+```mermaid
+flowchart TB
+    subgraph nodes["rippled Nodes"]
+        node1["rippled<br/>Node 1"]
+        node2["rippled<br/>Node 2"]
+        node3["rippled<br/>Node 3"]
+    end
+
+    collector["OpenTelemetry<br/>Collector<br/>(sidecar or standalone)"]
+
+    subgraph backends["Observability Backends"]
+        jaeger["Jaeger<br/>(Dev)"]
+        tempo["Tempo<br/>(Prod)"]
+        elastic["Elastic<br/>APM"]
+    end
+
+    node1 -->|"OTLP/gRPC<br/>:4317"| collector
+    node2 -->|"OTLP/gRPC<br/>:4317"| collector
+    node3 -->|"OTLP/gRPC<br/>:4317"| collector
+
+    collector --> jaeger
+    collector --> tempo
+    collector --> elastic
+
+    style nodes fill:#0d47a1,stroke:#082f6a,color:#ffffff
+    style backends fill:#1b5e20,stroke:#0d3d14,color:#ffffff
+    style collector fill:#bf360c,stroke:#8c2809,color:#ffffff
+```
+
+### 2.2.1 OTLP/gRPC (Recommended)
+
+```cpp
+// Configuration for OTLP over gRPC
+namespace otlp = opentelemetry::exporter::otlp;
+
+otlp::OtlpGrpcExporterOptions opts;
+opts.endpoint = "localhost:4317";
+opts.use_ssl_credentials = true;
+opts.ssl_credentials_cacert_path = "/path/to/ca.crt";
+```
+
+### 2.2.2 OTLP/HTTP (Alternative)
+
+```cpp
+// Configuration for OTLP over HTTP
+namespace otlp = opentelemetry::exporter::otlp;
+
+otlp::OtlpHttpExporterOptions opts;
+opts.url = "http://localhost:4318/v1/traces";
+opts.content_type = otlp::HttpRequestContentType::kJson;  // or kBinary
+```
+
+---
+
+## 2.3 Span Naming Conventions
+
+### 2.3.1 Naming Schema
+
+```
+<component>.<operation>[.<sub-operation>]
+```
+
+**Examples**:
+
+- `tx.receive` - Transaction received from peer
+- `consensus.phase.establish` - Consensus establish phase
+- `rpc.command.server_info` - server_info RPC command
+
+### 2.3.2 Complete Span Catalog
+
+```yaml
+# Transaction Spans
+tx:
+  receive: "Transaction received from network"
+  validate: "Transaction signature/format validation"
+  process: "Full transaction processing"
+  relay: "Transaction relay to peers"
+  apply: "Apply transaction to ledger"
+
+# Consensus Spans
+consensus:
+  round: "Complete consensus round"
+  phase:
+    open: "Open phase - collecting transactions"
+    establish: "Establish phase - reaching agreement"
+    accept: "Accept phase - applying consensus"
+  proposal:
+    receive: "Receive peer proposal"
+    send: "Send our proposal"
+  validation:
+    receive: "Receive peer validation"
+    send: "Send our validation"
+
+# RPC Spans
+rpc:
+  request: "HTTP/WebSocket request handling"
+  command:
+    "*": "Specific RPC command (dynamic)"
+
+# Peer Spans
+peer:
+  connect: "Peer connection establishment"
+  disconnect: "Peer disconnection"
+  message:
+    send: "Send protocol message"
+    receive: "Receive protocol message"
+
+# Ledger Spans
+ledger:
+  acquire: "Ledger acquisition from network"
+  build: "Build new ledger"
+  validate: "Ledger validation"
+  close: "Close ledger"
+
+# Job Spans
+job:
+  enqueue: "Job added to queue"
+  execute: "Job execution"
+```
+
+---
+
+## 2.4 Attribute Schema
+
+### 2.4.1 Resource Attributes (Set Once at Startup)
+
+```cpp
+// Standard OpenTelemetry semantic conventions
+resource::SemanticConventions::SERVICE_NAME        = "rippled"
+resource::SemanticConventions::SERVICE_VERSION     = BuildInfo::getVersionString()
+resource::SemanticConventions::SERVICE_INSTANCE_ID = <node_public_key_base58>
+
+// Custom rippled attributes
+"xrpl.network.id"      = <network_id>           // e.g., 0 for mainnet
+"xrpl.network.type"    = "mainnet" | "testnet" | "devnet" | "standalone"
+"xrpl.node.type"       = "validator" | "stock" | "reporting"
+"xrpl.node.cluster"    = <cluster_name>         // If clustered
+```
+
+### 2.4.2 Span Attributes by Category
+
+#### Transaction Attributes
+
+```cpp
+"xrpl.tx.hash"         = string   // Transaction hash (hex)
+"xrpl.tx.type"         = string   // "Payment", "OfferCreate", etc.
+"xrpl.tx.account"      = string   // Source account (redacted in prod)
+"xrpl.tx.sequence"     = int64    // Account sequence number
+"xrpl.tx.fee"          = int64    // Fee in drops
+"xrpl.tx.result"       = string   // "tesSUCCESS", "tecPATH_DRY", etc.
+"xrpl.tx.ledger_index" = int64    // Ledger containing transaction
+```
+
+#### Consensus Attributes
+
+```cpp
+"xrpl.consensus.round"          = int64    // Round number
+"xrpl.consensus.phase"          = string   // "open", "establish", "accept"
+"xrpl.consensus.mode"           = string   // "proposing", "observing", etc.
+"xrpl.consensus.proposers"      = int64    // Number of proposers
+"xrpl.consensus.ledger.prev"    = string   // Previous ledger hash
+"xrpl.consensus.ledger.seq"     = int64    // Ledger sequence
+"xrpl.consensus.tx_count"       = int64    // Transactions in consensus set
+"xrpl.consensus.duration_ms"    = float64  // Round duration
+```
+
+#### RPC Attributes
+
+```cpp
+"xrpl.rpc.command"     = string   // Command name
+"xrpl.rpc.version"     = int64    // API version
+"xrpl.rpc.role"        = string   // "admin" or "user"
+"xrpl.rpc.params"      = string   // Sanitized parameters (optional)
+```
+
+#### Peer & Message Attributes
+
+```cpp
+"xrpl.peer.id"            = string   // Peer public key (base58)
+"xrpl.peer.address"       = string   // IP:port
+"xrpl.peer.latency_ms"    = float64  // Measured latency
+"xrpl.peer.cluster"       = string   // Cluster name if clustered
+"xrpl.message.type"       = string   // Protocol message type name
+"xrpl.message.size_bytes" = int64    // Message size
+"xrpl.message.compressed" = bool     // Whether compressed
+```
+
+#### Ledger & Job Attributes
+
+```cpp
+"xrpl.ledger.hash"       = string   // Ledger hash
+"xrpl.ledger.index"      = int64    // Ledger sequence/index
+"xrpl.ledger.close_time" = int64    // Close time (epoch)
+"xrpl.ledger.tx_count"   = int64    // Transaction count
+"xrpl.job.type"          = string   // Job type name
+"xrpl.job.queue_ms"      = float64  // Time spent in queue
+"xrpl.job.worker"        = int64    // Worker thread ID
+```
+
+### 2.4.3 Data Collection Summary
+
+The following table summarizes what data is collected by category:
+
+| Category        | Attributes Collected                                                 | Purpose                     |
+| --------------- | -------------------------------------------------------------------- | --------------------------- |
+| **Transaction** | `tx.hash`, `tx.type`, `tx.result`, `tx.fee`, `ledger_index`          | Trace transaction lifecycle |
+| **Consensus**   | `round`, `phase`, `mode`, `proposers` (public keys), `duration_ms`   | Analyze consensus timing    |
+| **RPC**         | `command`, `version`, `status`, `duration_ms`                        | Monitor RPC performance     |
+| **Peer**        | `peer.id` (public key), `latency_ms`, `message.type`, `message.size` | Network topology analysis   |
+| **Ledger**      | `ledger.hash`, `ledger.index`, `close_time`, `tx_count`              | Ledger progression tracking |
+| **Job**         | `job.type`, `queue_ms`, `worker`                                     | JobQueue performance        |
+
+### 2.4.4 Privacy & Sensitive Data Policy
+
+OpenTelemetry instrumentation is designed to collect **operational metadata only**, never sensitive content.
+
+#### Data NOT Collected
+
+The following data is explicitly **excluded** from telemetry collection:
+
+| Excluded Data           | Reason                                    |
+| ----------------------- | ----------------------------------------- |
+| **Private Keys**        | Never exposed; not relevant to tracing    |
+| **Account Balances**    | Financial data; privacy sensitive         |
+| **Transaction Amounts** | Financial data; privacy sensitive         |
+| **Raw TX Payloads**     | May contain sensitive memo/data fields    |
+| **Personal Data**       | No PII collected                          |
+| **IP Addresses**        | Configurable; excluded by default in prod |
+
+#### Privacy Protection Mechanisms
+
+| Mechanism                     | Description                                                               |
+| ----------------------------- | ------------------------------------------------------------------------- |
+| **Account Hashing**           | `xrpl.tx.account` is hashed at collector level before storage             |
+| **Configurable Redaction**    | Sensitive fields can be excluded via `[telemetry]` config section         |
+| **Sampling**                  | Only 10% of traces recorded by default, reducing data exposure            |
+| **Local Control**             | Node operators have full control over what gets exported                  |
+| **No Raw Payloads**           | Transaction content is never recorded, only metadata (hash, type, result) |
+| **Collector-Level Filtering** | Additional redaction/hashing can be configured at OTel Collector          |
+
+#### Collector-Level Data Protection
+
+The OpenTelemetry Collector can be configured to hash or redact sensitive attributes before export:
+
+```yaml
+processors:
+  attributes:
+    actions:
+      # Hash account addresses before storage
+      - key: xrpl.tx.account
+        action: hash
+      # Remove IP addresses entirely
+      - key: xrpl.peer.address
+        action: delete
+      # Redact specific fields
+      - key: xrpl.rpc.params
+        action: delete
+```
+
+#### Configuration Options for Privacy
+
+In `rippled.cfg`, operators can control data collection granularity:
+
+```ini
+[telemetry]
+enabled=1
+
+# Disable collection of specific components
+trace_transactions=1
+trace_consensus=1
+trace_rpc=1
+trace_peer=0          # Disable peer tracing (high volume, includes addresses)
+
+# Redact specific attributes
+redact_account=1      # Hash account addresses before export
+redact_peer_address=1 # Remove peer IP addresses
+```
+
+> **Key Principle**: Telemetry collects **operational metadata** (timing, counts, hashes) — never **sensitive content** (keys, balances, amounts, raw payloads).
+
+---
+
+## 2.5 Context Propagation Design
+
+### 2.5.1 Propagation Boundaries
+
+```mermaid
+flowchart TB
+    subgraph http["HTTP/WebSocket (RPC)"]
+        w3c["W3C Trace Context Headers:<br/>traceparent: 00-{trace_id}-{span_id}-{flags}<br/>tracestate: rippled=<state>"]
+    end
+
+    subgraph protobuf["Protocol Buffers (P2P)"]
+        proto["message TraceContext {<br/>  bytes trace_id = 1;  // 16 bytes<br/>  bytes span_id = 2;   // 8 bytes<br/>  uint32 trace_flags = 3;<br/>  string trace_state = 4;<br/>}"]
+    end
+
+    subgraph jobqueue["JobQueue (Internal Async)"]
+        job["Context captured at job creation,<br/>restored at execution<br/><br/>class Job {<br/>  opentelemetry::context::Context traceContext_;<br/>};"]
+    end
+
+    style http fill:#0d47a1,stroke:#082f6a,color:#ffffff
+    style protobuf fill:#1b5e20,stroke:#0d3d14,color:#ffffff
+    style jobqueue fill:#bf360c,stroke:#8c2809,color:#ffffff
+```
+
+---
+
+## 2.6 Integration with Existing Observability
+
+### 2.6.1 Existing Frameworks Comparison
+
+rippled already has two observability mechanisms. OpenTelemetry complements (not replaces) them:
+
+| Aspect                | PerfLog                       | Beast Insight (StatsD)       | OpenTelemetry             |
+| --------------------- | ----------------------------- | ---------------------------- | ------------------------- |
+| **Type**              | Logging                       | Metrics                      | Distributed Tracing       |
+| **Data**              | JSON log entries              | Counters, gauges, histograms | Spans with context        |
+| **Scope**             | Single node                   | Single node                  | **Cross-node**            |
+| **Output**            | `perf.log` file               | StatsD server                | OTLP Collector            |
+| **Question answered** | "What happened on this node?" | "How many? How fast?"        | "What was the journey?"   |
+| **Correlation**       | By timestamp                  | By metric name               | By `trace_id`             |
+| **Overhead**          | Low (file I/O)                | Low (UDP packets)            | Low-Medium (configurable) |
+
+### 2.6.2 What Each Framework Does Best
+
+#### PerfLog
+
+- **Purpose**: Detailed local event logging for RPC and job execution
+- **Strengths**:
+  - Rich JSON output with timing data
+  - Already integrated in RPC handlers
+  - File-based, no external dependencies
+- **Limitations**:
+  - Single-node only (no cross-node correlation)
+  - No parent-child relationships between events
+  - Manual log parsing required
+
+```json
+// Example PerfLog entry
+{
+  "time": "2024-01-15T10:30:00.123Z",
+  "method": "submit",
+  "duration_us": 1523,
+  "result": "tesSUCCESS"
+}
+```
+
+#### Beast Insight (StatsD)
+
+- **Purpose**: Real-time metrics for monitoring dashboards
+- **Strengths**:
+  - Aggregated metrics (counters, gauges, histograms)
+  - Low overhead (UDP, fire-and-forget)
+  - Good for alerting thresholds
+- **Limitations**:
+  - No request-level detail
+  - No causal relationships
+  - Single-node perspective
+
+```cpp
+// Example StatsD usage in rippled
+insight.increment("rpc.submit.count");
+insight.gauge("ledger.age", age);
+insight.timing("consensus.round", duration);
+```
+
+#### OpenTelemetry (NEW)
+
+- **Purpose**: Distributed request tracing across nodes
+- **Strengths**:
+  - **Cross-node correlation** via `trace_id`
+  - Parent-child span relationships
+  - Rich attributes per span
+  - Industry standard (CNCF)
+- **Limitations**:
+  - Requires collector infrastructure
+  - Higher complexity than logging
+
+```cpp
+// Example OpenTelemetry span
+auto span = telemetry.startSpan("tx.relay");
+span->SetAttribute("tx.hash", hash);
+span->SetAttribute("peer.id", peerId);
+// Span automatically linked to parent via context
+```
+
+### 2.6.3 When to Use Each
+
+| Scenario                                | PerfLog    | StatsD | OpenTelemetry |
+| --------------------------------------- | ---------- | ------ | ------------- |
+| "How many TXs per second?"              | ❌         | ✅     | ❌            |
+| "What's the p99 RPC latency?"           | ❌         | ✅     | ✅            |
+| "Why was this specific TX slow?"        | ⚠️ partial | ❌     | ✅            |
+| "Which node delayed consensus?"         | ❌         | ❌     | ✅            |
+| "What happened on node X at time T?"    | ✅         | ❌     | ✅            |
+| "Show me the TX journey across 5 nodes" | ❌         | ❌     | ✅            |
+
+### 2.6.4 Coexistence Strategy
+
+> **Note**: Phase 7 replaces the StatsD bridge with native OTel Metrics SDK export. The diagram below shows the Phase 6 intermediate state. See [Phase7_taskList.md](./Phase7_taskList.md) for the migration design where Beast Insight emits via OTLP instead of StatsD.
+
+```mermaid
+flowchart TB
+    subgraph rippled["rippled Process"]
+        perflog["PerfLog<br/>(JSON to file)"]
+        insight["Beast Insight<br/>(StatsD)"]
+        otel["OpenTelemetry<br/>(Tracing)"]
+    end
+
+    perflog --> perffile["perf.log"]
+    insight --> statsd["StatsD Server"]
+    otel --> collector["OTLP Collector"]
+
+    perffile --> grafana["Grafana<br/>(Unified UI)"]
+    statsd --> grafana
+    collector --> grafana
+
+    style rippled fill:#212121,stroke:#0a0a0a,color:#ffffff
+    style grafana fill:#bf360c,stroke:#8c2809,color:#ffffff
+```
+
+**Phase 7 target state**: Beast Insight routes to `OTelCollector` (new `Collector` implementation) which exports via OTLP/HTTP to the same collector endpoint as traces. StatsD UDP path becomes a deprecated fallback (`[insight] server=statsd`). See [06-implementation-phases.md §6.8](./06-implementation-phases.md) and [Phase7_taskList.md](./Phase7_taskList.md) for details.
+
+### 2.6.5 Correlation with PerfLog
+
+Trace IDs can be correlated with existing PerfLog entries for comprehensive debugging:
+
+```cpp
+// In RPCHandler.cpp - correlate trace with PerfLog
+Status doCommand(RPC::JsonContext& context, Json::Value& result)
+{
+    // Start OpenTelemetry span
+    auto span = context.app.getTelemetry().startSpan(
+        "rpc.command." + context.method);
+
+    // Get trace ID for correlation
+    auto traceId = span->GetContext().trace_id().IsValid()
+        ? toHex(span->GetContext().trace_id())
+        : "";
+
+    // Use existing PerfLog with trace correlation
+    auto const curId = context.app.getPerfLog().currentId();
+    context.app.getPerfLog().rpcStart(context.method, curId);
+
+    // Future: Add trace ID to PerfLog entry
+    // context.app.getPerfLog().setTraceId(curId, traceId);
+
+    try {
+        auto ret = handler(context, result);
+        context.app.getPerfLog().rpcFinish(context.method, curId);
+        span->SetStatus(opentelemetry::trace::StatusCode::kOk);
+        return ret;
+    } catch (std::exception const& e) {
+        context.app.getPerfLog().rpcError(context.method, curId);
+        span->RecordException(e);
+        span->SetStatus(opentelemetry::trace::StatusCode::kError, e.what());
+        throw;
+    }
+}
+```
+
+---
+
+_Previous: [Architecture Analysis](./01-architecture-analysis.md)_ | _Next: [Implementation Strategy](./03-implementation-strategy.md)_ | _Back to: [Overview](./OpenTelemetryPlan.md)_

OpenTelemetryPlan/03-implementation-strategy.md

@@ -0,0 +1,451 @@
+# Implementation Strategy
+
+> **Parent Document**: [OpenTelemetryPlan.md](./OpenTelemetryPlan.md)
+> **Related**: [Code Samples](./04-code-samples.md) | [Configuration Reference](./05-configuration-reference.md)
+
+---
+
+## 3.1 Directory Structure
+
+The telemetry implementation follows rippled's existing code organization pattern:
+
+```
+include/xrpl/
+├── telemetry/
+│   ├── Telemetry.h              # Main telemetry interface
+│   ├── TelemetryConfig.h        # Configuration structures
+│   ├── TraceContext.h           # Context propagation utilities
+│   ├── SpanGuard.h              # RAII span management
+│   └── SpanAttributes.h         # Attribute helper functions
+
+src/libxrpl/
+├── telemetry/
+│   ├── Telemetry.cpp            # Implementation
+│   ├── TelemetryConfig.cpp      # Config parsing
+│   ├── TraceContext.cpp         # Context serialization
+│   └── NullTelemetry.cpp        # No-op implementation
+
+src/xrpld/
+├── telemetry/
+│   ├── TracingInstrumentation.h # Instrumentation macros
+│   └── TracingInstrumentation.cpp
+```
+
+---
+
+## 3.2 Implementation Approach
+
+<div align="center">
+
+```mermaid
+%%{init: {'flowchart': {'nodeSpacing': 20, 'rankSpacing': 30}}}%%
+flowchart TB
+    subgraph phase1["Phase 1: Core"]
+        direction LR
+        sdk["SDK Integration"] ~~~ interface["Telemetry Interface"] ~~~ config["Configuration"]
+    end
+
+    subgraph phase2["Phase 2: RPC"]
+        direction LR
+        http["HTTP Context"] ~~~ rpc["RPC Handlers"]
+    end
+
+    subgraph phase3["Phase 3: P2P"]
+        direction LR
+        proto["Protobuf Context"] ~~~ tx["Transaction Relay"]
+    end
+
+    subgraph phase4["Phase 4: Consensus"]
+        direction LR
+        consensus["Consensus Rounds"] ~~~ proposals["Proposals"]
+    end
+
+    phase1 --> phase2 --> phase3 --> phase4
+
+    style phase1 fill:#1565c0,stroke:#0d47a1,color:#ffffff
+    style phase2 fill:#2e7d32,stroke:#1b5e20,color:#ffffff
+    style phase3 fill:#e65100,stroke:#bf360c,color:#ffffff
+    style phase4 fill:#c2185b,stroke:#880e4f,color:#ffffff
+```
+
+</div>
+
+### Key Principles
+
+1. **Minimal Intrusion**: Instrumentation should not alter existing control flow
+2. **Zero-Cost When Disabled**: Use compile-time flags and no-op implementations
+3. **Backward Compatibility**: Protocol Buffer extensions use high field numbers
+4. **Graceful Degradation**: Tracing failures must not affect node operation
+
+---
+
+## 3.3 Performance Overhead Summary
+
+| Metric        | Overhead   | Notes                               |
+| ------------- | ---------- | ----------------------------------- |
+| CPU           | 1-3%       | Span creation and attribute setting |
+| Memory        | 2-5 MB     | Batch buffer for pending spans      |
+| Network       | 10-50 KB/s | Compressed OTLP export to collector |
+| Latency (p99) | <2%        | With proper sampling configuration  |
+
+---
+
+## 3.4 Detailed CPU Overhead Analysis
+
+### 3.4.1 Per-Operation Costs
+
+| Operation             | Time (ns) | Frequency              | Impact     |
+| --------------------- | --------- | ---------------------- | ---------- |
+| Span creation         | 200-500   | Every traced operation | Low        |
+| Span end              | 100-200   | Every traced operation | Low        |
+| SetAttribute (string) | 80-120    | 3-5 per span           | Low        |
+| SetAttribute (int)    | 40-60     | 2-3 per span           | Negligible |
+| AddEvent              | 50-80     | 0-2 per span           | Negligible |
+| Context injection     | 150-250   | Per outgoing message   | Low        |
+| Context extraction    | 100-180   | Per incoming message   | Low        |
+| GetCurrent context    | 10-20     | Thread-local access    | Negligible |
+
+### 3.4.2 Transaction Processing Overhead
+
+<div align="center">
+
+```mermaid
+%%{init: {'pie': {'textPosition': 0.75}}}%%
+pie showData
+    "tx.receive (800ns)" : 800
+    "tx.validate (500ns)" : 500
+    "tx.relay (500ns)" : 500
+    "Context inject (600ns)" : 600
+```
+
+**Transaction Tracing Overhead (~2.4μs total)**
+
+</div>
+
+**Overhead percentage**: 2.4 μs / 200 μs (avg tx processing) = **~1.2%**
+
+### 3.4.3 Consensus Round Overhead
+
+| Operation              | Count | Cost (ns) | Total      |
+| ---------------------- | ----- | --------- | ---------- |
+| consensus.round span   | 1     | ~1000     | ~1 μs      |
+| consensus.phase spans  | 3     | ~700      | ~2.1 μs    |
+| proposal.receive spans | ~20   | ~600      | ~12 μs     |
+| proposal.send spans    | ~3    | ~600      | ~1.8 μs    |
+| Context operations     | ~30   | ~200      | ~6 μs      |
+| **TOTAL**              |       |           | **~23 μs** |
+
+**Overhead percentage**: 23 μs / 3s (typical round) = **~0.0008%** (negligible)
+
+### 3.4.4 RPC Request Overhead
+
+| Operation        | Cost (ns)    |
+| ---------------- | ------------ |
+| rpc.request span | ~700         |
+| rpc.command span | ~600         |
+| Context extract  | ~250         |
+| Context inject   | ~200         |
+| **TOTAL**        | **~1.75 μs** |
+
+- Fast RPC (1ms): 1.75 μs / 1ms = **~0.175%**
+- Slow RPC (100ms): 1.75 μs / 100ms = **~0.002%**
+
+---
+
+## 3.5 Memory Overhead Analysis
+
+### 3.5.1 Static Memory
+
+| Component                | Size        | Allocated  |
+| ------------------------ | ----------- | ---------- |
+| TracerProvider singleton | ~64 KB      | At startup |
+| BatchSpanProcessor       | ~128 KB     | At startup |
+| OTLP exporter            | ~256 KB     | At startup |
+| Propagator registry      | ~8 KB       | At startup |
+| **Total static**         | **~456 KB** |            |
+
+### 3.5.2 Dynamic Memory
+
+| Component            | Size per unit | Max units  | Peak        |
+| -------------------- | ------------- | ---------- | ----------- |
+| Active span          | ~200 bytes    | 1000       | ~200 KB     |
+| Queued span (export) | ~500 bytes    | 2048       | ~1 MB       |
+| Attribute storage    | ~50 bytes     | 5 per span | Included    |
+| Context storage      | ~64 bytes     | Per thread | ~6.4 KB     |
+| **Total dynamic**    |               |            | **~1.2 MB** |
+
+### 3.5.3 Memory Growth Characteristics
+
+```mermaid
+---
+config:
+    xyChart:
+        width: 700
+        height: 400
+---
+xychart-beta
+    title "Memory Usage vs Span Rate"
+    x-axis "Spans/second" [0, 200, 400, 600, 800, 1000]
+    y-axis "Memory (MB)" 0 --> 6
+    line [1, 1.8, 2.6, 3.4, 4.2, 5]
+```
+
+**Notes**:
+
+- Memory increases linearly with span rate
+- Batch export prevents unbounded growth
+- Queue size is configurable (default 2048 spans)
+- At queue limit, oldest spans are dropped (not blocked)
+
+---
+
+## 3.6 Network Overhead Analysis
+
+### 3.6.1 Export Bandwidth
+
+| Sampling Rate | Spans/sec | Bandwidth | Notes            |
+| ------------- | --------- | --------- | ---------------- |
+| 100%          | ~500      | ~250 KB/s | Development only |
+| 10%           | ~50       | ~25 KB/s  | Staging          |
+| 1%            | ~5        | ~2.5 KB/s | Production       |
+| Error-only    | ~1        | ~0.5 KB/s | Minimal overhead |
+
+### 3.6.2 Trace Context Propagation
+
+| Message Type           | Context Size | Messages/sec | Overhead    |
+| ---------------------- | ------------ | ------------ | ----------- |
+| TMTransaction          | 32 bytes     | ~100         | ~3.2 KB/s   |
+| TMProposeSet           | 32 bytes     | ~10          | ~320 B/s    |
+| TMValidation           | 32 bytes     | ~50          | ~1.6 KB/s   |
+| **Total P2P overhead** |              |              | **~5 KB/s** |
+
+---
+
+## 3.7 Optimization Strategies
+
+### 3.7.1 Sampling Strategies
+
+```mermaid
+flowchart TD
+    trace["New Trace"]
+
+    trace --> errors{"Is Error?"}
+    errors -->|Yes| sample["SAMPLE"]
+    errors -->|No| consensus{"Is Consensus?"}
+
+    consensus -->|Yes| sample
+    consensus -->|No| slow{"Is Slow?"}
+
+    slow -->|Yes| sample
+    slow -->|No| prob{"Random < 10%?"}
+
+    prob -->|Yes| sample
+    prob -->|No| drop["DROP"]
+
+    style sample fill:#4caf50,stroke:#388e3c,color:#fff
+    style drop fill:#f44336,stroke:#c62828,color:#fff
+```
+
+### 3.7.2 Batch Tuning Recommendations
+
+| Environment        | Batch Size | Batch Delay | Max Queue |
+| ------------------ | ---------- | ----------- | --------- |
+| Low-latency        | 128        | 1000ms      | 512       |
+| High-throughput    | 1024       | 10000ms     | 8192      |
+| Memory-constrained | 256        | 2000ms      | 512       |
+
+### 3.7.3 Conditional Instrumentation
+
+```cpp
+// Compile-time feature flag
+#ifndef XRPL_ENABLE_TELEMETRY
+// Zero-cost when disabled
+#define XRPL_TRACE_SPAN(t, n) ((void)0)
+#endif
+
+// Runtime component filtering
+if (telemetry.shouldTracePeer())
+{
+    XRPL_TRACE_SPAN(telemetry, "peer.message.receive");
+    // ... instrumentation
+}
+// No overhead when component tracing disabled
+```
+
+---
+
+## 3.8 Links to Detailed Documentation
+
+- **[Code Samples](./04-code-samples.md)**: Complete implementation code for all components
+- **[Configuration Reference](./05-configuration-reference.md)**: Configuration options and collector setup
+- **[Implementation Phases](./06-implementation-phases.md)**: Detailed timeline and milestones
+
+---
+
+## 3.9 Code Intrusiveness Assessment
+
+This section provides a detailed assessment of how intrusive the OpenTelemetry integration is to the existing rippled codebase.
+
+### 3.9.1 Files Modified Summary
+
+| Component             | Files Modified | Lines Added | Lines Changed | Architectural Impact |
+| --------------------- | -------------- | ----------- | ------------- | -------------------- |
+| **Core Telemetry**    | 5 new files    | ~800        | 0             | None (new module)    |
+| **Application Init**  | 2 files        | ~30         | ~5            | Minimal              |
+| **RPC Layer**         | 3 files        | ~80         | ~20           | Minimal              |
+| **Transaction Relay** | 4 files        | ~120        | ~40           | Low                  |
+| **Consensus**         | 3 files        | ~100        | ~30           | Low-Medium           |
+| **Protocol Buffers**  | 1 file         | ~25         | 0             | Low                  |
+| **CMake/Build**       | 3 files        | ~50         | ~10           | Minimal              |
+| **Total**             | **~21 files**  | **~1,205**  | **~105**      | **Low**              |
+
+### 3.9.2 Detailed File Impact
+
+```mermaid
+pie title Code Changes by Component
+    "New Telemetry Module" : 800
+    "Transaction Relay" : 160
+    "Consensus" : 130
+    "RPC Layer" : 100
+    "Application Init" : 35
+    "Protocol Buffers" : 25
+    "Build System" : 60
+```
+
+#### New Files (No Impact on Existing Code)
+
+| File                                           | Lines | Purpose              |
+| ---------------------------------------------- | ----- | -------------------- |
+| `include/xrpl/telemetry/Telemetry.h`           | ~160  | Main interface       |
+| `include/xrpl/telemetry/SpanGuard.h`           | ~120  | RAII wrapper         |
+| `include/xrpl/telemetry/TraceContext.h`        | ~80   | Context propagation  |
+| `src/xrpld/telemetry/TracingInstrumentation.h` | ~60   | Macros               |
+| `src/libxrpl/telemetry/Telemetry.cpp`          | ~200  | Implementation       |
+| `src/libxrpl/telemetry/TelemetryConfig.cpp`    | ~60   | Config parsing       |
+| `src/libxrpl/telemetry/NullTelemetry.cpp`      | ~40   | No-op implementation |
+
+#### Modified Files (Existing Rippled Code)
+
+| File                                              | Lines Added | Lines Changed | Risk Level |
+| ------------------------------------------------- | ----------- | ------------- | ---------- |
+| `src/xrpld/app/main/Application.cpp`              | ~15         | ~3            | Low        |
+| `include/xrpl/app/main/Application.h`             | ~5          | ~2            | Low        |
+| `src/xrpld/rpc/detail/ServerHandler.cpp`          | ~40         | ~10           | Low        |
+| `src/xrpld/rpc/handlers/*.cpp`                    | ~30         | ~8            | Low        |
+| `src/xrpld/overlay/detail/PeerImp.cpp`            | ~60         | ~15           | Medium     |
+| `src/xrpld/overlay/detail/OverlayImpl.cpp`        | ~30         | ~10           | Medium     |
+| `src/xrpld/app/consensus/RCLConsensus.cpp`        | ~50         | ~15           | Medium     |
+| `src/xrpld/app/consensus/RCLConsensusAdaptor.cpp` | ~40         | ~12           | Medium     |
+| `src/xrpld/core/JobQueue.cpp`                     | ~20         | ~5            | Low        |
+| `src/xrpld/overlay/detail/ripple.proto`           | ~25         | 0             | Low        |
+| `CMakeLists.txt`                                  | ~40         | ~8            | Low        |
+| `cmake/FindOpenTelemetry.cmake`                   | ~50         | 0             | None (new) |
+
+### 3.9.3 Risk Assessment by Component
+
+<div align="center">
+
+**Do First** ↖ ↗ **Plan Carefully**
+
+```mermaid
+quadrantChart
+    title Code Intrusiveness Risk Matrix
+    x-axis Low Risk --> High Risk
+    y-axis Low Value --> High Value
+
+    RPC Tracing: [0.2, 0.8]
+    Transaction Relay: [0.5, 0.9]
+    Consensus Tracing: [0.7, 0.95]
+    Peer Message Tracing: [0.8, 0.4]
+    JobQueue Context: [0.4, 0.5]
+    Ledger Acquisition: [0.5, 0.6]
+```
+
+**Optional** ↙ ↘ **Avoid**
+
+</div>
+
+#### Risk Level Definitions
+
+| Risk Level | Definition                                                       | Mitigation                         |
+| ---------- | ---------------------------------------------------------------- | ---------------------------------- |
+| **Low**    | Additive changes only; no modification to existing logic         | Standard code review               |
+| **Medium** | Minor modifications to existing functions; clear boundaries      | Comprehensive unit tests           |
+| **High**   | Changes to core logic or data structures; potential side effects | Integration tests + staged rollout |
+
+### 3.9.4 Architectural Impact Assessment
+
+| Aspect               | Impact  | Justification                                                         |
+| -------------------- | ------- | --------------------------------------------------------------------- |
+| **Data Flow**        | None    | Tracing is purely observational; no business logic changes            |
+| **Threading Model**  | Minimal | Context propagation uses thread-local storage (standard OTel pattern) |
+| **Memory Model**     | Low     | Bounded queues prevent unbounded growth; RAII ensures cleanup         |
+| **Network Protocol** | Low     | Optional fields in protobuf (high field numbers); backward compatible |
+| **Configuration**    | None    | New config section; existing configs unaffected                       |
+| **Build System**     | Low     | Optional CMake flag; builds work without OpenTelemetry                |
+| **Dependencies**     | Low     | OpenTelemetry SDK is optional; null implementation when disabled      |
+
+### 3.9.5 Backward Compatibility
+
+| Compatibility   | Status  | Notes                                                 |
+| --------------- | ------- | ----------------------------------------------------- |
+| **Config File** | ✅ Full | New `[telemetry]` section is optional                 |
+| **Protocol**    | ✅ Full | Optional protobuf fields with high field numbers      |
+| **Build**       | ✅ Full | `XRPL_ENABLE_TELEMETRY=OFF` produces identical binary |
+| **Runtime**     | ✅ Full | `enabled=0` produces zero overhead                    |
+| **API**         | ✅ Full | No changes to public RPC or P2P APIs                  |
+
+### 3.9.6 Rollback Strategy
+
+If issues are discovered after deployment:
+
+1. **Immediate**: Set `enabled=0` in config and restart (zero code change)
+2. **Quick**: Rebuild with `XRPL_ENABLE_TELEMETRY=OFF`
+3. **Complete**: Revert telemetry commits (clean separation makes this easy)
+
+### 3.9.7 Code Change Examples
+
+**Minimal RPC Instrumentation (Low Intrusiveness):**
+
+```cpp
+// Before
+void ServerHandler::onRequest(...) {
+    auto result = processRequest(req);
+    send(result);
+}
+
+// After (only ~10 lines added)
+void ServerHandler::onRequest(...) {
+    XRPL_TRACE_RPC(app_.getTelemetry(), "rpc.request");  // +1 line
+    XRPL_TRACE_SET_ATTR("xrpl.rpc.command", command);     // +1 line
+
+    auto result = processRequest(req);
+
+    XRPL_TRACE_SET_ATTR("xrpl.rpc.status", status);       // +1 line
+    send(result);
+}
+```
+
+**Consensus Instrumentation (Medium Intrusiveness):**
+
+```cpp
+// Before
+void RCLConsensusAdaptor::startRound(...) {
+    // ... existing logic
+}
+
+// After (context storage required)
+void RCLConsensusAdaptor::startRound(...) {
+    XRPL_TRACE_CONSENSUS(app_.getTelemetry(), "consensus.round");
+    XRPL_TRACE_SET_ATTR("xrpl.consensus.ledger.seq", seq);
+
+    // Store context for child spans in phase transitions
+    currentRoundContext_ = _xrpl_guard_->context();  // New member variable
+
+    // ... existing logic unchanged
+}
+```
+
+---
+
+_Previous: [Design Decisions](./02-design-decisions.md)_ | _Next: [Code Samples](./04-code-samples.md)_ | _Back to: [Overview](./OpenTelemetryPlan.md)_

OpenTelemetryPlan/04-code-samples.md

@@ -0,0 +1,982 @@
+# Code Samples
+
+> **Parent Document**: [OpenTelemetryPlan.md](./OpenTelemetryPlan.md)
+> **Related**: [Implementation Strategy](./03-implementation-strategy.md) | [Configuration Reference](./05-configuration-reference.md)
+
+---
+
+## 4.1 Core Interfaces
+
+### 4.1.1 Main Telemetry Interface
+
+```cpp
+// include/xrpl/telemetry/Telemetry.h
+#pragma once
+
+#include <xrpl/telemetry/TelemetryConfig.h>
+#include <opentelemetry/trace/tracer.h>
+#include <opentelemetry/trace/span.h>
+#include <opentelemetry/context/context.h>
+
+#include <memory>
+#include <string>
+#include <string_view>
+
+namespace xrpl {
+namespace telemetry {
+
+/**
+ * Main telemetry interface for OpenTelemetry integration.
+ *
+ * This class provides the primary API for distributed tracing in rippled.
+ * It manages the OpenTelemetry SDK lifecycle and provides convenience
+ * methods for creating spans and propagating context.
+ */
+class Telemetry
+{
+public:
+    /**
+     * Configuration for the telemetry system.
+     */
+    struct Setup
+    {
+        bool enabled = false;
+        std::string serviceName = "rippled";
+        std::string serviceVersion;
+        std::string serviceInstanceId;  // Node public key
+
+        // Exporter configuration
+        std::string exporterType = "otlp_grpc";  // "otlp_grpc", "otlp_http", "none"
+        std::string exporterEndpoint = "localhost:4317";
+        bool useTls = false;
+        std::string tlsCertPath;
+
+        // Sampling configuration
+        double samplingRatio = 1.0;  // 1.0 = 100% sampling
+
+        // Batch processor settings
+        std::uint32_t batchSize = 512;
+        std::chrono::milliseconds batchDelay{5000};
+        std::uint32_t maxQueueSize = 2048;
+
+        // Network attributes
+        std::uint32_t networkId = 0;
+        std::string networkType = "mainnet";
+
+        // Component filtering
+        bool traceTransactions = true;
+        bool traceConsensus = true;
+        bool traceRpc = true;
+        bool tracePeer = false;  // High volume, disabled by default
+        bool traceLedger = true;
+    };
+
+    virtual ~Telemetry() = default;
+
+    // ═══════════════════════════════════════════════════════════════════════
+    // LIFECYCLE
+    // ═══════════════════════════════════════════════════════════════════════
+
+    /** Start the telemetry system (call after configuration) */
+    virtual void start() = 0;
+
+    /** Stop the telemetry system (flushes pending spans) */
+    virtual void stop() = 0;
+
+    /** Check if telemetry is enabled */
+    virtual bool isEnabled() const = 0;
+
+    // ═══════════════════════════════════════════════════════════════════════
+    // TRACER ACCESS
+    // ═══════════════════════════════════════════════════════════════════════
+
+    /** Get the tracer for creating spans */
+    virtual opentelemetry::nostd::shared_ptr<opentelemetry::trace::Tracer>
+    getTracer(std::string_view name = "rippled") = 0;
+
+    // ═══════════════════════════════════════════════════════════════════════
+    // SPAN CREATION (Convenience Methods)
+    // ═══════════════════════════════════════════════════════════════════════
+
+    /** Start a new span with default options */
+    virtual opentelemetry::nostd::shared_ptr<opentelemetry::trace::Span>
+    startSpan(
+        std::string_view name,
+        opentelemetry::trace::SpanKind kind =
+            opentelemetry::trace::SpanKind::kInternal) = 0;
+
+    /** Start a span as child of given context */
+    virtual opentelemetry::nostd::shared_ptr<opentelemetry::trace::Span>
+    startSpan(
+        std::string_view name,
+        opentelemetry::context::Context const& parentContext,
+        opentelemetry::trace::SpanKind kind =
+            opentelemetry::trace::SpanKind::kInternal) = 0;
+
+    // ═══════════════════════════════════════════════════════════════════════
+    // CONTEXT PROPAGATION
+    // ═══════════════════════════════════════════════════════════════════════
+
+    /** Serialize context for network transmission */
+    virtual std::string serializeContext(
+        opentelemetry::context::Context const& ctx) = 0;
+
+    /** Deserialize context from network data */
+    virtual opentelemetry::context::Context deserializeContext(
+        std::string const& serialized) = 0;
+
+    // ═══════════════════════════════════════════════════════════════════════
+    // COMPONENT FILTERING
+    // ═══════════════════════════════════════════════════════════════════════
+
+    /** Check if transaction tracing is enabled */
+    virtual bool shouldTraceTransactions() const = 0;
+
+    /** Check if consensus tracing is enabled */
+    virtual bool shouldTraceConsensus() const = 0;
+
+    /** Check if RPC tracing is enabled */
+    virtual bool shouldTraceRpc() const = 0;
+
+    /** Check if peer message tracing is enabled */
+    virtual bool shouldTracePeer() const = 0;
+};
+
+// Factory functions
+std::unique_ptr<Telemetry>
+make_Telemetry(
+    Telemetry::Setup const& setup,
+    beast::Journal journal);
+
+Telemetry::Setup
+setup_Telemetry(
+    Section const& section,
+    std::string const& nodePublicKey,
+    std::string const& version);
+
+} // namespace telemetry
+} // namespace xrpl
+```
+
+---
+
+## 4.2 RAII Span Guard
+
+```cpp
+// include/xrpl/telemetry/SpanGuard.h
+#pragma once
+
+#include <opentelemetry/trace/span.h>
+#include <opentelemetry/trace/scope.h>
+#include <opentelemetry/trace/status.h>
+
+#include <string_view>
+#include <exception>
+
+namespace xrpl {
+namespace telemetry {
+
+/**
+ * RAII guard for OpenTelemetry spans.
+ *
+ * Automatically ends the span on destruction and makes it the current
+ * span in the thread-local context.
+ */
+class SpanGuard
+{
+    opentelemetry::nostd::shared_ptr<opentelemetry::trace::Span> span_;
+    opentelemetry::trace::Scope scope_;
+
+public:
+    /**
+     * Construct guard with span.
+     * The span becomes the current span in thread-local context.
+     */
+    explicit SpanGuard(
+        opentelemetry::nostd::shared_ptr<opentelemetry::trace::Span> span)
+        : span_(std::move(span))
+        , scope_(span_)
+    {
+    }
+
+    // Non-copyable, non-movable
+    SpanGuard(SpanGuard const&) = delete;
+    SpanGuard& operator=(SpanGuard const&) = delete;
+    SpanGuard(SpanGuard&&) = delete;
+    SpanGuard& operator=(SpanGuard&&) = delete;
+
+    ~SpanGuard()
+    {
+        if (span_)
+            span_->End();
+    }
+
+    /** Access the underlying span */
+    opentelemetry::trace::Span& span() { return *span_; }
+    opentelemetry::trace::Span const& span() const { return *span_; }
+
+    /** Set span status to OK */
+    void setOk()
+    {
+        span_->SetStatus(opentelemetry::trace::StatusCode::kOk);
+    }
+
+    /** Set span status with code and description */
+    void setStatus(
+        opentelemetry::trace::StatusCode code,
+        std::string_view description = "")
+    {
+        span_->SetStatus(code, std::string(description));
+    }
+
+    /** Set an attribute on the span */
+    template<typename T>
+    void setAttribute(std::string_view key, T&& value)
+    {
+        span_->SetAttribute(
+            opentelemetry::nostd::string_view(key.data(), key.size()),
+            std::forward<T>(value));
+    }
+
+    /** Add an event to the span */
+    void addEvent(std::string_view name)
+    {
+        span_->AddEvent(std::string(name));
+    }
+
+    /** Record an exception on the span */
+    void recordException(std::exception const& e)
+    {
+        span_->RecordException(e);
+        span_->SetStatus(
+            opentelemetry::trace::StatusCode::kError,
+            e.what());
+    }
+
+    /** Get the current trace context */
+    opentelemetry::context::Context context() const
+    {
+        return opentelemetry::context::RuntimeContext::GetCurrent();
+    }
+};
+
+/**
+ * No-op span guard for when tracing is disabled.
+ * Provides the same interface but does nothing.
+ */
+class NullSpanGuard
+{
+public:
+    NullSpanGuard() = default;
+
+    void setOk() {}
+    void setStatus(opentelemetry::trace::StatusCode, std::string_view = "") {}
+
+    template<typename T>
+    void setAttribute(std::string_view, T&&) {}
+
+    void addEvent(std::string_view) {}
+    void recordException(std::exception const&) {}
+};
+
+} // namespace telemetry
+} // namespace xrpl
+```
+
+---
+
+## 4.3 Instrumentation Macros
+
+```cpp
+// src/xrpld/telemetry/TracingInstrumentation.h
+#pragma once
+
+#include <xrpl/telemetry/Telemetry.h>
+#include <xrpl/telemetry/SpanGuard.h>
+
+namespace xrpl {
+namespace telemetry {
+
+// ═══════════════════════════════════════════════════════════════════════════
+// INSTRUMENTATION MACROS
+// ═══════════════════════════════════════════════════════════════════════════
+
+#ifdef XRPL_ENABLE_TELEMETRY
+
+// Start a span that is automatically ended when guard goes out of scope
+#define XRPL_TRACE_SPAN(telemetry, name) \
+    auto _xrpl_span_ = (telemetry).startSpan(name); \
+    ::xrpl::telemetry::SpanGuard _xrpl_guard_(_xrpl_span_)
+
+// Start a span with specific kind
+#define XRPL_TRACE_SPAN_KIND(telemetry, name, kind) \
+    auto _xrpl_span_ = (telemetry).startSpan(name, kind); \
+    ::xrpl::telemetry::SpanGuard _xrpl_guard_(_xrpl_span_)
+
+// Conditional span based on component
+#define XRPL_TRACE_TX(telemetry, name) \
+    std::optional<::xrpl::telemetry::SpanGuard> _xrpl_guard_; \
+    if ((telemetry).shouldTraceTransactions()) { \
+        _xrpl_guard_.emplace((telemetry).startSpan(name)); \
+    }
+
+#define XRPL_TRACE_CONSENSUS(telemetry, name) \
+    std::optional<::xrpl::telemetry::SpanGuard> _xrpl_guard_; \
+    if ((telemetry).shouldTraceConsensus()) { \
+        _xrpl_guard_.emplace((telemetry).startSpan(name)); \
+    }
+
+#define XRPL_TRACE_RPC(telemetry, name) \
+    std::optional<::xrpl::telemetry::SpanGuard> _xrpl_guard_; \
+    if ((telemetry).shouldTraceRpc()) { \
+        _xrpl_guard_.emplace((telemetry).startSpan(name)); \
+    }
+
+// Set attribute on current span (if exists)
+#define XRPL_TRACE_SET_ATTR(key, value) \
+    if (_xrpl_guard_.has_value()) { \
+        _xrpl_guard_->setAttribute(key, value); \
+    }
+
+// Record exception on current span
+#define XRPL_TRACE_EXCEPTION(e) \
+    if (_xrpl_guard_.has_value()) { \
+        _xrpl_guard_->recordException(e); \
+    }
+
+#else  // XRPL_ENABLE_TELEMETRY not defined
+
+#define XRPL_TRACE_SPAN(telemetry, name) ((void)0)
+#define XRPL_TRACE_SPAN_KIND(telemetry, name, kind) ((void)0)
+#define XRPL_TRACE_TX(telemetry, name) ((void)0)
+#define XRPL_TRACE_CONSENSUS(telemetry, name) ((void)0)
+#define XRPL_TRACE_RPC(telemetry, name) ((void)0)
+#define XRPL_TRACE_SET_ATTR(key, value) ((void)0)
+#define XRPL_TRACE_EXCEPTION(e) ((void)0)
+
+#endif  // XRPL_ENABLE_TELEMETRY
+
+} // namespace telemetry
+} // namespace xrpl
+```
+
+---
+
+## 4.4 Protocol Buffer Extensions
+
+### 4.4.1 TraceContext Message Definition
+
+Add to `src/xrpld/overlay/detail/ripple.proto`:
+
+```protobuf
+// Trace context for distributed tracing across nodes
+// Uses W3C Trace Context format internally
+message TraceContext {
+    // 16-byte trace identifier (required for valid context)
+    bytes trace_id = 1;
+
+    // 8-byte span identifier of parent span
+    bytes span_id = 2;
+
+    // Trace flags (bit 0 = sampled)
+    uint32 trace_flags = 3;
+
+    // W3C tracestate header value for vendor-specific data
+    string trace_state = 4;
+}
+
+// Extend existing messages with optional trace context
+// High field numbers (1000+) to avoid conflicts
+
+message TMTransaction {
+    // ... existing fields ...
+
+    // Optional trace context for distributed tracing
+    optional TraceContext trace_context = 1001;
+}
+
+message TMProposeSet {
+    // ... existing fields ...
+    optional TraceContext trace_context = 1001;
+}
+
+message TMValidation {
+    // ... existing fields ...
+    optional TraceContext trace_context = 1001;
+}
+
+message TMGetLedger {
+    // ... existing fields ...
+    optional TraceContext trace_context = 1001;
+}
+
+message TMLedgerData {
+    // ... existing fields ...
+    optional TraceContext trace_context = 1001;
+}
+```
+
+### 4.4.2 Context Serialization/Deserialization
+
+```cpp
+// include/xrpl/telemetry/TraceContext.h
+#pragma once
+
+#include <opentelemetry/context/context.h>
+#include <opentelemetry/trace/span_context.h>
+#include <protocol/messages.h>  // Generated protobuf
+
+#include <optional>
+#include <string>
+
+namespace xrpl {
+namespace telemetry {
+
+/**
+ * Utilities for trace context serialization and propagation.
+ */
+class TraceContextPropagator
+{
+public:
+    /**
+     * Extract trace context from Protocol Buffer message.
+     * Returns empty context if no trace info present.
+     */
+    static opentelemetry::context::Context
+    extract(protocol::TraceContext const& proto);
+
+    /**
+     * Inject current trace context into Protocol Buffer message.
+     */
+    static void
+    inject(
+        opentelemetry::context::Context const& ctx,
+        protocol::TraceContext& proto);
+
+    /**
+     * Extract trace context from HTTP headers (for RPC).
+     * Supports W3C Trace Context (traceparent, tracestate).
+     */
+    static opentelemetry::context::Context
+    extractFromHeaders(
+        std::function<std::optional<std::string>(std::string_view)> headerGetter);
+
+    /**
+     * Inject trace context into HTTP headers (for RPC responses).
+     */
+    static void
+    injectToHeaders(
+        opentelemetry::context::Context const& ctx,
+        std::function<void(std::string_view, std::string_view)> headerSetter);
+};
+
+// ═══════════════════════════════════════════════════════════════════════════
+// IMPLEMENTATION
+// ═══════════════════════════════════════════════════════════════════════════
+
+inline opentelemetry::context::Context
+TraceContextPropagator::extract(protocol::TraceContext const& proto)
+{
+    using namespace opentelemetry::trace;
+
+    if (proto.trace_id().size() != 16 || proto.span_id().size() != 8)
+        return opentelemetry::context::Context{};  // Invalid, return empty
+
+    // Construct TraceId and SpanId from bytes
+    TraceId traceId(reinterpret_cast<uint8_t const*>(proto.trace_id().data()));
+    SpanId spanId(reinterpret_cast<uint8_t const*>(proto.span_id().data()));
+    TraceFlags flags(static_cast<uint8_t>(proto.trace_flags()));
+
+    // Create SpanContext from extracted data
+    SpanContext spanContext(traceId, spanId, flags, /* remote = */ true);
+
+    // Create context with extracted span as parent
+    return opentelemetry::context::Context{}.SetValue(
+        opentelemetry::trace::kSpanKey,
+        opentelemetry::nostd::shared_ptr<Span>(
+            new DefaultSpan(spanContext)));
+}
+
+inline void
+TraceContextPropagator::inject(
+    opentelemetry::context::Context const& ctx,
+    protocol::TraceContext& proto)
+{
+    using namespace opentelemetry::trace;
+
+    // Get current span from context
+    auto span = GetSpan(ctx);
+    if (!span)
+        return;
+
+    auto const& spanCtx = span->GetContext();
+    if (!spanCtx.IsValid())
+        return;
+
+    // Serialize trace_id (16 bytes)
+    auto const& traceId = spanCtx.trace_id();
+    proto.set_trace_id(traceId.Id().data(), TraceId::kSize);
+
+    // Serialize span_id (8 bytes)
+    auto const& spanId = spanCtx.span_id();
+    proto.set_span_id(spanId.Id().data(), SpanId::kSize);
+
+    // Serialize flags
+    proto.set_trace_flags(spanCtx.trace_flags().flags());
+
+    // Note: tracestate not implemented yet
+}
+
+} // namespace telemetry
+} // namespace xrpl
+```
+
+---
+
+## 4.5 Module-Specific Instrumentation
+
+### 4.5.1 Transaction Relay Instrumentation
+
+```cpp
+// src/xrpld/overlay/detail/PeerImp.cpp (modified)
+
+#include <xrpl/telemetry/TracingInstrumentation.h>
+
+void
+PeerImp::handleTransaction(
+    std::shared_ptr<protocol::TMTransaction> const& m)
+{
+    // Extract trace context from incoming message
+    opentelemetry::context::Context parentCtx;
+    if (m->has_trace_context())
+    {
+        parentCtx = telemetry::TraceContextPropagator::extract(
+            m->trace_context());
+    }
+
+    // Start span as child of remote span (cross-node link)
+    auto span = app_.getTelemetry().startSpan(
+        "tx.receive",
+        parentCtx,
+        opentelemetry::trace::SpanKind::kServer);
+    telemetry::SpanGuard guard(span);
+
+    try
+    {
+        // Parse and validate transaction
+        SerialIter sit(makeSlice(m->rawtransaction()));
+        auto stx = std::make_shared<STTx const>(sit);
+
+        // Add transaction attributes
+        guard.setAttribute("xrpl.tx.hash", to_string(stx->getTransactionID()));
+        guard.setAttribute("xrpl.tx.type", stx->getTxnType());
+        guard.setAttribute("xrpl.peer.id", remote_address_.to_string());
+
+        // Check if we've seen this transaction (HashRouter)
+        auto const [flags, suppressed] =
+            app_.getHashRouter().addSuppressionPeer(
+                stx->getTransactionID(),
+                id_);
+
+        if (suppressed)
+        {
+            guard.setAttribute("xrpl.tx.suppressed", true);
+            guard.addEvent("tx.duplicate");
+            return;  // Already processing this transaction
+        }
+
+        // Create child span for validation
+        {
+            auto validateSpan = app_.getTelemetry().startSpan("tx.validate");
+            telemetry::SpanGuard validateGuard(validateSpan);
+
+            auto [validity, reason] = checkTransaction(stx);
+            validateGuard.setAttribute("xrpl.tx.validity",
+                validity == Validity::Valid ? "valid" : "invalid");
+
+            if (validity != Validity::Valid)
+            {
+                validateGuard.setStatus(
+                    opentelemetry::trace::StatusCode::kError,
+                    reason);
+                return;
+            }
+        }
+
+        // Relay to other peers (capture context for propagation)
+        auto ctx = guard.context();
+
+        // Create child span for relay
+        auto relaySpan = app_.getTelemetry().startSpan(
+            "tx.relay",
+            ctx,
+            opentelemetry::trace::SpanKind::kClient);
+        {
+            telemetry::SpanGuard relayGuard(relaySpan);
+
+            // Inject context into outgoing message
+            protocol::TraceContext protoCtx;
+            telemetry::TraceContextPropagator::inject(
+                relayGuard.context(), protoCtx);
+
+            // Relay to other peers
+            app_.overlay().relay(
+                stx->getTransactionID(),
+                *m,
+                protoCtx,  // Pass trace context
+                exclusions);
+
+            relayGuard.setAttribute("xrpl.tx.relay_count",
+                static_cast<int64_t>(relayCount));
+        }
+
+        guard.setOk();
+    }
+    catch (std::exception const& e)
+    {
+        guard.recordException(e);
+        JLOG(journal_.warn()) << "Transaction handling failed: " << e.what();
+    }
+}
+```
+
+### 4.5.2 Consensus Instrumentation
+
+```cpp
+// src/xrpld/app/consensus/RCLConsensus.cpp (modified)
+
+#include <xrpl/telemetry/TracingInstrumentation.h>
+
+void
+RCLConsensusAdaptor::startRound(
+    NetClock::time_point const& now,
+    RCLCxLedger::ID const& prevLedgerHash,
+    RCLCxLedger const& prevLedger,
+    hash_set<NodeID> const& peers,
+    bool proposing)
+{
+    XRPL_TRACE_CONSENSUS(app_.getTelemetry(), "consensus.round");
+
+    XRPL_TRACE_SET_ATTR("xrpl.consensus.ledger.prev", to_string(prevLedgerHash));
+    XRPL_TRACE_SET_ATTR("xrpl.consensus.ledger.seq",
+        static_cast<int64_t>(prevLedger.seq() + 1));
+    XRPL_TRACE_SET_ATTR("xrpl.consensus.proposers",
+        static_cast<int64_t>(peers.size()));
+    XRPL_TRACE_SET_ATTR("xrpl.consensus.mode",
+        proposing ? "proposing" : "observing");
+
+    // Store trace context for use in phase transitions
+    currentRoundContext_ = _xrpl_guard_.has_value()
+        ? _xrpl_guard_->context()
+        : opentelemetry::context::Context{};
+
+    // ... existing implementation ...
+}
+
+ConsensusPhase
+RCLConsensusAdaptor::phaseTransition(ConsensusPhase newPhase)
+{
+    // Create span for phase transition
+    auto span = app_.getTelemetry().startSpan(
+        "consensus.phase." + to_string(newPhase),
+        currentRoundContext_);
+    telemetry::SpanGuard guard(span);
+
+    guard.setAttribute("xrpl.consensus.phase", to_string(newPhase));
+    guard.addEvent("phase.enter");
+
+    auto const startTime = std::chrono::steady_clock::now();
+
+    try
+    {
+        auto result = doPhaseTransition(newPhase);
+
+        auto const duration = std::chrono::steady_clock::now() - startTime;
+        guard.setAttribute("xrpl.consensus.phase_duration_ms",
+            std::chrono::duration<double, std::milli>(duration).count());
+
+        guard.setOk();
+        return result;
+    }
+    catch (std::exception const& e)
+    {
+        guard.recordException(e);
+        throw;
+    }
+}
+
+void
+RCLConsensusAdaptor::peerProposal(
+    NetClock::time_point const& now,
+    RCLCxPeerPos const& proposal)
+{
+    // Extract trace context from proposal message
+    opentelemetry::context::Context parentCtx;
+    if (proposal.hasTraceContext())
+    {
+        parentCtx = telemetry::TraceContextPropagator::extract(
+            proposal.traceContext());
+    }
+
+    auto span = app_.getTelemetry().startSpan(
+        "consensus.proposal.receive",
+        parentCtx,
+        opentelemetry::trace::SpanKind::kServer);
+    telemetry::SpanGuard guard(span);
+
+    guard.setAttribute("xrpl.consensus.proposer",
+        toBase58(TokenType::NodePublic, proposal.nodeId()));
+    guard.setAttribute("xrpl.consensus.round",
+        static_cast<int64_t>(proposal.proposal().proposeSeq()));
+
+    // ... existing implementation ...
+
+    guard.setOk();
+}
+```
+
+### 4.5.3 RPC Handler Instrumentation
+
+```cpp
+// src/xrpld/rpc/detail/ServerHandler.cpp (modified)
+
+#include <xrpl/telemetry/TracingInstrumentation.h>
+
+void
+ServerHandler::onRequest(
+    http_request_type&& req,
+    std::function<void(http_response_type&&)>&& send)
+{
+    // Extract trace context from HTTP headers (W3C Trace Context)
+    auto parentCtx = telemetry::TraceContextPropagator::extractFromHeaders(
+        [&req](std::string_view name) -> std::optional<std::string> {
+            auto it = req.find(boost::beast::http::field{
+                std::string(name)});
+            if (it != req.end())
+                return std::string(it->value());
+            return std::nullopt;
+        });
+
+    // Start request span
+    auto span = app_.getTelemetry().startSpan(
+        "rpc.request",
+        parentCtx,
+        opentelemetry::trace::SpanKind::kServer);
+    telemetry::SpanGuard guard(span);
+
+    // Add HTTP attributes
+    guard.setAttribute("http.method", std::string(req.method_string()));
+    guard.setAttribute("http.target", std::string(req.target()));
+    guard.setAttribute("http.user_agent",
+        std::string(req[boost::beast::http::field::user_agent]));
+
+    auto const startTime = std::chrono::steady_clock::now();
+
+    try
+    {
+        // Parse and process request
+        auto const& body = req.body();
+        Json::Value jv;
+        Json::Reader reader;
+
+        if (!reader.parse(body, jv))
+        {
+            guard.setStatus(
+                opentelemetry::trace::StatusCode::kError,
+                "Invalid JSON");
+            sendError(send, "Invalid JSON");
+            return;
+        }
+
+        // Extract command name
+        std::string command = jv.isMember("command")
+            ? jv["command"].asString()
+            : jv.isMember("method")
+                ? jv["method"].asString()
+                : "unknown";
+
+        guard.setAttribute("xrpl.rpc.command", command);
+
+        // Create child span for command execution
+        auto cmdSpan = app_.getTelemetry().startSpan(
+            "rpc.command." + command);
+        {
+            telemetry::SpanGuard cmdGuard(cmdSpan);
+
+            // Execute RPC command
+            auto result = processRequest(jv);
+
+            // Record result attributes
+            if (result.isMember("status"))
+            {
+                cmdGuard.setAttribute("xrpl.rpc.status",
+                    result["status"].asString());
+            }
+
+            if (result["status"].asString() == "error")
+            {
+                cmdGuard.setStatus(
+                    opentelemetry::trace::StatusCode::kError,
+                    result.isMember("error_message")
+                        ? result["error_message"].asString()
+                        : "RPC error");
+            }
+            else
+            {
+                cmdGuard.setOk();
+            }
+        }
+
+        auto const duration = std::chrono::steady_clock::now() - startTime;
+        guard.setAttribute("http.duration_ms",
+            std::chrono::duration<double, std::milli>(duration).count());
+
+        // Inject trace context into response headers
+        http_response_type resp;
+        telemetry::TraceContextPropagator::injectToHeaders(
+            guard.context(),
+            [&resp](std::string_view name, std::string_view value) {
+                resp.set(std::string(name), std::string(value));
+            });
+
+        guard.setOk();
+        send(std::move(resp));
+    }
+    catch (std::exception const& e)
+    {
+        guard.recordException(e);
+        JLOG(journal_.error()) << "RPC request failed: " << e.what();
+        sendError(send, e.what());
+    }
+}
+```
+
+### 4.5.4 JobQueue Context Propagation
+
+```cpp
+// src/xrpld/core/JobQueue.h (modified)
+
+#include <opentelemetry/context/context.h>
+
+class Job
+{
+    // ... existing members ...
+
+    // Captured trace context at job creation
+    opentelemetry::context::Context traceContext_;
+
+public:
+    // Constructor captures current trace context
+    Job(JobType type, std::function<void()> func, ...)
+        : type_(type)
+        , func_(std::move(func))
+        , traceContext_(opentelemetry::context::RuntimeContext::GetCurrent())
+        // ... other initializations ...
+    {
+    }
+
+    // Get trace context for restoration during execution
+    opentelemetry::context::Context const&
+    traceContext() const { return traceContext_; }
+};
+
+// src/xrpld/core/JobQueue.cpp (modified)
+
+void
+Worker::run()
+{
+    while (auto job = getJob())
+    {
+        // Restore trace context from job creation
+        auto token = opentelemetry::context::RuntimeContext::Attach(
+            job->traceContext());
+
+        // Start execution span
+        auto span = app_.getTelemetry().startSpan("job.execute");
+        telemetry::SpanGuard guard(span);
+
+        guard.setAttribute("xrpl.job.type", to_string(job->type()));
+        guard.setAttribute("xrpl.job.queue_ms", job->queueTimeMs());
+        guard.setAttribute("xrpl.job.worker", workerId_);
+
+        try
+        {
+            job->execute();
+            guard.setOk();
+        }
+        catch (std::exception const& e)
+        {
+            guard.recordException(e);
+            JLOG(journal_.error()) << "Job execution failed: " << e.what();
+        }
+    }
+}
+```
+
+---
+
+## 4.6 Span Flow Visualization
+
+<div align="center">
+
+```mermaid
+flowchart TB
+    subgraph Client["External Client"]
+        submit["Submit TX"]
+    end
+
+    subgraph NodeA["rippled Node A"]
+        rpcA["rpc.request"]
+        cmdA["rpc.command.submit"]
+        txRecvA["tx.receive"]
+        txValA["tx.validate"]
+        txRelayA["tx.relay"]
+    end
+
+    subgraph NodeB["rippled Node B"]
+        txRecvB["tx.receive"]
+        txValB["tx.validate"]
+        txRelayB["tx.relay"]
+    end
+
+    subgraph NodeC["rippled Node C"]
+        txRecvC["tx.receive"]
+        consensusC["consensus.round"]
+        phaseC["consensus.phase.establish"]
+    end
+
+    submit --> rpcA
+    rpcA --> cmdA
+    cmdA --> txRecvA
+    txRecvA --> txValA
+    txValA --> txRelayA
+    txRelayA -.->|"TraceContext"| txRecvB
+    txRecvB --> txValB
+    txValB --> txRelayB
+    txRelayB -.->|"TraceContext"| txRecvC
+    txRecvC --> consensusC
+    consensusC --> phaseC
+
+    style Client fill:#334155,stroke:#1e293b,color:#fff
+    style NodeA fill:#1e3a8a,stroke:#172554,color:#fff
+    style NodeB fill:#064e3b,stroke:#022c22,color:#fff
+    style NodeC fill:#78350f,stroke:#451a03,color:#fff
+    style submit fill:#e2e8f0,stroke:#cbd5e1,color:#1e293b
+    style rpcA fill:#1d4ed8,stroke:#1e40af,color:#fff
+    style cmdA fill:#1d4ed8,stroke:#1e40af,color:#fff
+    style txRecvA fill:#047857,stroke:#064e3b,color:#fff
+    style txValA fill:#047857,stroke:#064e3b,color:#fff
+    style txRelayA fill:#047857,stroke:#064e3b,color:#fff
+    style txRecvB fill:#047857,stroke:#064e3b,color:#fff
+    style txValB fill:#047857,stroke:#064e3b,color:#fff
+    style txRelayB fill:#047857,stroke:#064e3b,color:#fff
+    style txRecvC fill:#047857,stroke:#064e3b,color:#fff
+    style consensusC fill:#fef3c7,stroke:#fde68a,color:#1e293b
+    style phaseC fill:#fef3c7,stroke:#fde68a,color:#1e293b
+```
+
+</div>
+
+---
+
+_Previous: [Implementation Strategy](./03-implementation-strategy.md)_ | _Next: [Configuration Reference](./05-configuration-reference.md)_ | _Back to: [Overview](./OpenTelemetryPlan.md)_

OpenTelemetryPlan/05-configuration-reference.md

@@ -0,0 +1,958 @@
+# Configuration Reference
+
+> **Parent Document**: [OpenTelemetryPlan.md](./OpenTelemetryPlan.md)
+> **Related**: [Code Samples](./04-code-samples.md) | [Implementation Phases](./06-implementation-phases.md)
+
+---
+
+## 5.1 rippled Configuration
+
+### 5.1.1 Configuration File Section
+
+Add to `cfg/xrpld-example.cfg`:
+
+```ini
+# ═══════════════════════════════════════════════════════════════════════════════
+# TELEMETRY (OpenTelemetry Distributed Tracing)
+# ═══════════════════════════════════════════════════════════════════════════════
+#
+# Enables distributed tracing for transaction flow, consensus, and RPC calls.
+# Traces are exported to an OpenTelemetry Collector using OTLP protocol.
+#
+# [telemetry]
+#
+# # Enable/disable telemetry (default: 0 = disabled)
+# enabled=1
+#
+# # Exporter type: "otlp_grpc" (default), "otlp_http", or "none"
+# exporter=otlp_grpc
+#
+# # OTLP endpoint (default: localhost:4317 for gRPC, localhost:4318 for HTTP)
+# endpoint=localhost:4317
+#
+# # Use TLS for exporter connection (default: 0)
+# use_tls=0
+#
+# # Path to CA certificate for TLS (optional)
+# # tls_ca_cert=/path/to/ca.crt
+#
+# # Sampling ratio: 0.0-1.0 (default: 1.0 = 100% sampling)
+# # Use lower values in production to reduce overhead
+# sampling_ratio=0.1
+#
+# # Batch processor settings
+# batch_size=512           # Spans per batch (default: 512)
+# batch_delay_ms=5000      # Max delay before sending batch (default: 5000)
+# max_queue_size=2048      # Max queued spans (default: 2048)
+#
+# # Component-specific tracing (default: all enabled except peer)
+# trace_transactions=1     # Transaction relay and processing
+# trace_consensus=1        # Consensus rounds and proposals
+# trace_rpc=1              # RPC request handling
+# trace_peer=0             # Peer messages (high volume, disabled by default)
+# trace_ledger=1           # Ledger acquisition and building
+#
+# # Service identification (automatically detected if not specified)
+# # service_name=rippled
+# # service_instance_id=<node_public_key>
+
+[telemetry]
+enabled=0
+```
+
+### 5.1.2 Configuration Options Summary
+
+| Option                | Type   | Default          | Description                               |
+| --------------------- | ------ | ---------------- | ----------------------------------------- |
+| `enabled`             | bool   | `false`          | Enable/disable telemetry                  |
+| `exporter`            | string | `"otlp_grpc"`    | Exporter type: otlp_grpc, otlp_http, none |
+| `endpoint`            | string | `localhost:4317` | OTLP collector endpoint                   |
+| `use_tls`             | bool   | `false`          | Enable TLS for exporter connection        |
+| `tls_ca_cert`         | string | `""`             | Path to CA certificate file               |
+| `sampling_ratio`      | float  | `1.0`            | Sampling ratio (0.0-1.0)                  |
+| `batch_size`          | uint   | `512`            | Spans per export batch                    |
+| `batch_delay_ms`      | uint   | `5000`           | Max delay before sending batch (ms)       |
+| `max_queue_size`      | uint   | `2048`           | Maximum queued spans                      |
+| `trace_transactions`  | bool   | `true`           | Enable transaction tracing                |
+| `trace_consensus`     | bool   | `true`           | Enable consensus tracing                  |
+| `trace_rpc`           | bool   | `true`           | Enable RPC tracing                        |
+| `trace_peer`          | bool   | `false`          | Enable peer message tracing (high volume) |
+| `trace_ledger`        | bool   | `true`           | Enable ledger tracing                     |
+| `service_name`        | string | `"rippled"`      | Service name for traces                   |
+| `service_instance_id` | string | `<node_pubkey>`  | Instance identifier                       |
+
+---
+
+## 5.2 Configuration Parser
+
+```cpp
+// src/libxrpl/telemetry/TelemetryConfig.cpp
+
+#include <xrpl/telemetry/Telemetry.h>
+#include <xrpl/basics/Log.h>
+
+namespace xrpl {
+namespace telemetry {
+
+Telemetry::Setup
+setup_Telemetry(
+    Section const& section,
+    std::string const& nodePublicKey,
+    std::string const& version)
+{
+    Telemetry::Setup setup;
+
+    // Basic settings
+    setup.enabled = section.value_or("enabled", false);
+    setup.serviceName = section.value_or("service_name", "rippled");
+    setup.serviceVersion = version;
+    setup.serviceInstanceId = section.value_or(
+        "service_instance_id", nodePublicKey);
+
+    // Exporter settings
+    setup.exporterType = section.value_or("exporter", "otlp_grpc");
+
+    if (setup.exporterType == "otlp_grpc")
+        setup.exporterEndpoint = section.value_or("endpoint", "localhost:4317");
+    else if (setup.exporterType == "otlp_http")
+        setup.exporterEndpoint = section.value_or("endpoint", "localhost:4318");
+
+    setup.useTls = section.value_or("use_tls", false);
+    setup.tlsCertPath = section.value_or("tls_ca_cert", "");
+
+    // Sampling
+    setup.samplingRatio = section.value_or("sampling_ratio", 1.0);
+    if (setup.samplingRatio < 0.0 || setup.samplingRatio > 1.0)
+    {
+        Throw<std::runtime_error>(
+            "telemetry.sampling_ratio must be between 0.0 and 1.0");
+    }
+
+    // Batch processor
+    setup.batchSize = section.value_or("batch_size", 512u);
+    setup.batchDelay = std::chrono::milliseconds{
+        section.value_or("batch_delay_ms", 5000u)};
+    setup.maxQueueSize = section.value_or("max_queue_size", 2048u);
+
+    // Component filtering
+    setup.traceTransactions = section.value_or("trace_transactions", true);
+    setup.traceConsensus = section.value_or("trace_consensus", true);
+    setup.traceRpc = section.value_or("trace_rpc", true);
+    setup.tracePeer = section.value_or("trace_peer", false);
+    setup.traceLedger = section.value_or("trace_ledger", true);
+
+    return setup;
+}
+
+} // namespace telemetry
+} // namespace xrpl
+```
+
+---
+
+## 5.3 Application Integration
+
+### 5.3.1 ApplicationImp Changes
+
+```cpp
+// src/xrpld/app/main/Application.cpp (modified)
+
+#include <xrpl/telemetry/Telemetry.h>
+
+class ApplicationImp : public Application
+{
+    // ... existing members ...
+
+    // Telemetry (must be constructed early, destroyed late)
+    std::unique_ptr<telemetry::Telemetry> telemetry_;
+
+public:
+    ApplicationImp(...)
+    {
+        // Initialize telemetry early (before other components)
+        auto telemetrySection = config_->section("telemetry");
+        auto telemetrySetup = telemetry::setup_Telemetry(
+            telemetrySection,
+            toBase58(TokenType::NodePublic, nodeIdentity_.publicKey()),
+            BuildInfo::getVersionString());
+
+        // Set network attributes
+        telemetrySetup.networkId = config_->NETWORK_ID;
+        telemetrySetup.networkType = [&]() {
+            if (config_->NETWORK_ID == 0) return "mainnet";
+            if (config_->NETWORK_ID == 1) return "testnet";
+            if (config_->NETWORK_ID == 2) return "devnet";
+            return "custom";
+        }();
+
+        telemetry_ = telemetry::make_Telemetry(
+            telemetrySetup,
+            logs_->journal("Telemetry"));
+
+        // ... rest of initialization ...
+    }
+
+    void start() override
+    {
+        // Start telemetry first
+        if (telemetry_)
+            telemetry_->start();
+
+        // ... existing start code ...
+    }
+
+    void stop() override
+    {
+        // ... existing stop code ...
+
+        // Stop telemetry last (to capture shutdown spans)
+        if (telemetry_)
+            telemetry_->stop();
+    }
+
+    telemetry::Telemetry& getTelemetry() override
+    {
+        assert(telemetry_);
+        return *telemetry_;
+    }
+};
+```
+
+### 5.3.2 Application Interface Addition
+
+```cpp
+// include/xrpl/app/main/Application.h (modified)
+
+namespace telemetry { class Telemetry; }
+
+class Application
+{
+public:
+    // ... existing virtual methods ...
+
+    /** Get the telemetry system for distributed tracing */
+    virtual telemetry::Telemetry& getTelemetry() = 0;
+};
+```
+
+---
+
+## 5.4 CMake Integration
+
+### 5.4.1 Find OpenTelemetry Module
+
+```cmake
+# cmake/FindOpenTelemetry.cmake
+
+# Find OpenTelemetry C++ SDK
+#
+# This module defines:
+#   OpenTelemetry_FOUND - System has OpenTelemetry
+#   OpenTelemetry::api - API library target
+#   OpenTelemetry::sdk - SDK library target
+#   OpenTelemetry::otlp_grpc_exporter - OTLP gRPC exporter target
+#   OpenTelemetry::otlp_http_exporter - OTLP HTTP exporter target
+
+find_package(opentelemetry-cpp CONFIG QUIET)
+
+if(opentelemetry-cpp_FOUND)
+    set(OpenTelemetry_FOUND TRUE)
+
+    # Create imported targets if not already created by config
+    if(NOT TARGET OpenTelemetry::api)
+        add_library(OpenTelemetry::api ALIAS opentelemetry-cpp::api)
+    endif()
+    if(NOT TARGET OpenTelemetry::sdk)
+        add_library(OpenTelemetry::sdk ALIAS opentelemetry-cpp::sdk)
+    endif()
+    if(NOT TARGET OpenTelemetry::otlp_grpc_exporter)
+        add_library(OpenTelemetry::otlp_grpc_exporter ALIAS
+            opentelemetry-cpp::otlp_grpc_exporter)
+    endif()
+else()
+    # Try pkg-config fallback
+    find_package(PkgConfig QUIET)
+    if(PKG_CONFIG_FOUND)
+        pkg_check_modules(OTEL opentelemetry-cpp QUIET)
+        if(OTEL_FOUND)
+            set(OpenTelemetry_FOUND TRUE)
+            # Create imported targets from pkg-config
+            add_library(OpenTelemetry::api INTERFACE IMPORTED)
+            target_include_directories(OpenTelemetry::api INTERFACE
+                ${OTEL_INCLUDE_DIRS})
+        endif()
+    endif()
+endif()
+
+include(FindPackageHandleStandardArgs)
+find_package_handle_standard_args(OpenTelemetry
+    REQUIRED_VARS OpenTelemetry_FOUND)
+```
+
+### 5.4.2 CMakeLists.txt Changes
+
+```cmake
+# CMakeLists.txt (additions)
+
+# ═══════════════════════════════════════════════════════════════════════════════
+# TELEMETRY OPTIONS
+# ═══════════════════════════════════════════════════════════════════════════════
+
+option(XRPL_ENABLE_TELEMETRY
+    "Enable OpenTelemetry distributed tracing support" OFF)
+
+if(XRPL_ENABLE_TELEMETRY)
+    find_package(OpenTelemetry REQUIRED)
+
+    # Define compile-time flag
+    add_compile_definitions(XRPL_ENABLE_TELEMETRY)
+
+    message(STATUS "OpenTelemetry tracing: ENABLED")
+else()
+    message(STATUS "OpenTelemetry tracing: DISABLED")
+endif()
+
+# ═══════════════════════════════════════════════════════════════════════════════
+# TELEMETRY LIBRARY
+# ═══════════════════════════════════════════════════════════════════════════════
+
+if(XRPL_ENABLE_TELEMETRY)
+    add_library(xrpl_telemetry
+        src/libxrpl/telemetry/Telemetry.cpp
+        src/libxrpl/telemetry/TelemetryConfig.cpp
+        src/libxrpl/telemetry/TraceContext.cpp
+    )
+
+    target_include_directories(xrpl_telemetry
+        PUBLIC
+            ${CMAKE_CURRENT_SOURCE_DIR}/include
+    )
+
+    target_link_libraries(xrpl_telemetry
+        PUBLIC
+            OpenTelemetry::api
+            OpenTelemetry::sdk
+            OpenTelemetry::otlp_grpc_exporter
+        PRIVATE
+            xrpl_basics
+    )
+
+    # Add to main library dependencies
+    target_link_libraries(xrpld PRIVATE xrpl_telemetry)
+else()
+    # Create null implementation library
+    add_library(xrpl_telemetry
+        src/libxrpl/telemetry/NullTelemetry.cpp
+    )
+    target_include_directories(xrpl_telemetry
+        PUBLIC ${CMAKE_CURRENT_SOURCE_DIR}/include
+    )
+endif()
+```
+
+---
+
+## 5.5 OpenTelemetry Collector Configuration
+
+### 5.5.1 Development Configuration
+
+```yaml
+# otel-collector-dev.yaml
+# Minimal configuration for local development
+
+receivers:
+  otlp:
+    protocols:
+      grpc:
+        endpoint: 0.0.0.0:4317
+      http:
+        endpoint: 0.0.0.0:4318
+
+processors:
+  batch:
+    timeout: 1s
+    send_batch_size: 100
+
+exporters:
+  # Console output for debugging
+  logging:
+    verbosity: detailed
+    sampling_initial: 5
+    sampling_thereafter: 200
+
+  # Jaeger for trace visualization
+  jaeger:
+    endpoint: jaeger:14250
+    tls:
+      insecure: true
+
+  # Grafana Tempo for trace storage
+  otlp/tempo:
+    endpoint: tempo:4317
+    tls:
+      insecure: true
+
+service:
+  pipelines:
+    traces:
+      receivers: [otlp]
+      processors: [batch]
+      exporters: [logging, jaeger, otlp/tempo]
+```
+
+### 5.5.2 Production Configuration
+
+```yaml
+# otel-collector-prod.yaml
+# Production configuration with filtering, sampling, and multiple backends
+
+receivers:
+  otlp:
+    protocols:
+      grpc:
+        endpoint: 0.0.0.0:4317
+        tls:
+          cert_file: /etc/otel/server.crt
+          key_file: /etc/otel/server.key
+          ca_file: /etc/otel/ca.crt
+
+processors:
+  # Memory limiter to prevent OOM
+  memory_limiter:
+    check_interval: 1s
+    limit_mib: 1000
+    spike_limit_mib: 200
+
+  # Batch processing for efficiency
+  batch:
+    timeout: 5s
+    send_batch_size: 512
+    send_batch_max_size: 1024
+
+  # Tail-based sampling (keep errors and slow traces)
+  tail_sampling:
+    decision_wait: 10s
+    num_traces: 100000
+    expected_new_traces_per_sec: 1000
+    policies:
+      # Always keep error traces
+      - name: errors
+        type: status_code
+        status_code:
+          status_codes: [ERROR]
+      # Keep slow consensus rounds (>5s)
+      - name: slow-consensus
+        type: latency
+        latency:
+          threshold_ms: 5000
+      # Keep slow RPC requests (>1s)
+      - name: slow-rpc
+        type: and
+        and:
+          and_sub_policy:
+            - name: rpc-spans
+              type: string_attribute
+              string_attribute:
+                key: xrpl.rpc.command
+                values: [".*"]
+                enabled_regex_matching: true
+            - name: latency
+              type: latency
+              latency:
+                threshold_ms: 1000
+      # Probabilistic sampling for the rest
+      - name: probabilistic
+        type: probabilistic
+        probabilistic:
+          sampling_percentage: 10
+
+  # Attribute processing
+  attributes:
+    actions:
+      # Hash sensitive data
+      - key: xrpl.tx.account
+        action: hash
+      # Add deployment info
+      - key: deployment.environment
+        value: production
+        action: upsert
+
+exporters:
+  # Grafana Tempo for long-term storage
+  otlp/tempo:
+    endpoint: tempo.monitoring:4317
+    tls:
+      insecure: false
+      ca_file: /etc/otel/tempo-ca.crt
+
+  # Elastic APM for correlation with logs
+  otlp/elastic:
+    endpoint: apm.elastic:8200
+    headers:
+      Authorization: "Bearer ${ELASTIC_APM_TOKEN}"
+
+extensions:
+  health_check:
+    endpoint: 0.0.0.0:13133
+  zpages:
+    endpoint: 0.0.0.0:55679
+
+service:
+  extensions: [health_check, zpages]
+  pipelines:
+    traces:
+      receivers: [otlp]
+      processors: [memory_limiter, tail_sampling, attributes, batch]
+      exporters: [otlp/tempo, otlp/elastic]
+```
+
+---
+
+## 5.6 Docker Compose Development Environment
+
+```yaml
+# docker-compose-telemetry.yaml
+version: "3.8"
+
+services:
+  # OpenTelemetry Collector
+  otel-collector:
+    image: otel/opentelemetry-collector-contrib:0.92.0
+    container_name: otel-collector
+    command: ["--config=/etc/otel-collector-config.yaml"]
+    volumes:
+      - ./otel-collector-dev.yaml:/etc/otel-collector-config.yaml:ro
+    ports:
+      - "4317:4317" # OTLP gRPC
+      - "4318:4318" # OTLP HTTP
+      - "13133:13133" # Health check
+    depends_on:
+      - jaeger
+
+  # Jaeger for trace visualization
+  jaeger:
+    image: jaegertracing/all-in-one:1.53
+    container_name: jaeger
+    environment:
+      - COLLECTOR_OTLP_ENABLED=true
+    ports:
+      - "16686:16686" # UI
+      - "14250:14250" # gRPC
+
+  # Grafana Tempo for trace storage (recommended for production)
+  tempo:
+    image: grafana/tempo:2.7.2
+    container_name: tempo
+    command: ["-config.file=/etc/tempo.yaml"]
+    volumes:
+      - ./tempo.yaml:/etc/tempo.yaml:ro
+      - tempo-data:/var/tempo
+    ports:
+      - "3200:3200" # HTTP API
+
+  # Grafana for dashboards
+  grafana:
+    image: grafana/grafana:10.2.3
+    container_name: grafana
+    environment:
+      - GF_AUTH_ANONYMOUS_ENABLED=true
+      - GF_AUTH_ANONYMOUS_ORG_ROLE=Admin
+    volumes:
+      - ./grafana/provisioning:/etc/grafana/provisioning:ro
+      - ./grafana/dashboards:/var/lib/grafana/dashboards:ro
+    ports:
+      - "3000:3000"
+    depends_on:
+      - jaeger
+      - tempo
+
+  # Prometheus for metrics (optional, for correlation)
+  prometheus:
+    image: prom/prometheus:v2.48.1
+    container_name: prometheus
+    volumes:
+      - ./prometheus.yaml:/etc/prometheus/prometheus.yml:ro
+    ports:
+      - "9090:9090"
+
+networks:
+  default:
+    name: rippled-telemetry
+```
+
+---
+
+## 5.7 Configuration Architecture
+
+```mermaid
+flowchart TB
+    subgraph config["Configuration Sources"]
+        cfgFile["xrpld.cfg<br/>[telemetry] section"]
+        cmake["CMake<br/>XRPL_ENABLE_TELEMETRY"]
+    end
+
+    subgraph init["Initialization"]
+        parse["setup_Telemetry()"]
+        factory["make_Telemetry()"]
+    end
+
+    subgraph runtime["Runtime Components"]
+        tracer["TracerProvider"]
+        exporter["OTLP Exporter"]
+        processor["BatchProcessor"]
+    end
+
+    subgraph collector["Collector Pipeline"]
+        recv["Receivers"]
+        proc["Processors"]
+        exp["Exporters"]
+    end
+
+    cfgFile --> parse
+    cmake -->|"compile flag"| parse
+    parse --> factory
+    factory --> tracer
+    tracer --> processor
+    processor --> exporter
+    exporter -->|"OTLP"| recv
+    recv --> proc
+    proc --> exp
+
+    style config fill:#e3f2fd,stroke:#1976d2
+    style runtime fill:#e8f5e9,stroke:#388e3c
+    style collector fill:#fff3e0,stroke:#ff9800
+```
+
+---
+
+## 5.8 Grafana Integration
+
+Step-by-step instructions for integrating rippled traces with Grafana.
+
+### 5.8.1 Data Source Configuration
+
+#### Tempo (Recommended)
+
+```yaml
+# grafana/provisioning/datasources/tempo.yaml
+apiVersion: 1
+
+datasources:
+  - name: Tempo
+    type: tempo
+    access: proxy
+    url: http://tempo:3200
+    jsonData:
+      httpMethod: GET
+      tracesToLogs:
+        datasourceUid: loki
+        tags: ["service.name", "xrpl.tx.hash"]
+        mappedTags: [{ key: "trace_id", value: "traceID" }]
+        mapTagNamesEnabled: true
+        filterByTraceID: true
+      serviceMap:
+        datasourceUid: prometheus
+      nodeGraph:
+        enabled: true
+      search:
+        hide: false
+      lokiSearch:
+        datasourceUid: loki
+```
+
+#### Jaeger
+
+```yaml
+# grafana/provisioning/datasources/jaeger.yaml
+apiVersion: 1
+
+datasources:
+  - name: Jaeger
+    type: jaeger
+    access: proxy
+    url: http://jaeger:16686
+    jsonData:
+      tracesToLogs:
+        datasourceUid: loki
+        tags: ["service.name"]
+```
+
+#### Elastic APM
+
+```yaml
+# grafana/provisioning/datasources/elastic-apm.yaml
+apiVersion: 1
+
+datasources:
+  - name: Elasticsearch-APM
+    type: elasticsearch
+    access: proxy
+    url: http://elasticsearch:9200
+    database: "apm-*"
+    jsonData:
+      esVersion: "8.0.0"
+      timeField: "@timestamp"
+      logMessageField: message
+      logLevelField: log.level
+```
+
+### 5.8.2 Dashboard Provisioning
+
+```yaml
+# grafana/provisioning/dashboards/dashboards.yaml
+apiVersion: 1
+
+providers:
+  - name: "rippled-dashboards"
+    orgId: 1
+    folder: "rippled"
+    folderUid: "rippled"
+    type: file
+    disableDeletion: false
+    updateIntervalSeconds: 30
+    options:
+      path: /var/lib/grafana/dashboards/rippled
+```
+
+### 5.8.3 Example Dashboard: RPC Performance
+
+```json
+{
+  "title": "rippled RPC Performance",
+  "uid": "rippled-rpc-performance",
+  "panels": [
+    {
+      "title": "RPC Latency by Command",
+      "type": "heatmap",
+      "datasource": "Tempo",
+      "targets": [
+        {
+          "queryType": "traceql",
+          "query": "{resource.service.name=\"rippled\" && span.xrpl.rpc.command != \"\"} | histogram_over_time(duration) by (span.xrpl.rpc.command)"
+        }
+      ],
+      "gridPos": { "h": 8, "w": 12, "x": 0, "y": 0 }
+    },
+    {
+      "title": "RPC Error Rate",
+      "type": "timeseries",
+      "datasource": "Tempo",
+      "targets": [
+        {
+          "queryType": "traceql",
+          "query": "{resource.service.name=\"rippled\" && status.code=error} | rate() by (span.xrpl.rpc.command)"
+        }
+      ],
+      "gridPos": { "h": 8, "w": 12, "x": 12, "y": 0 }
+    },
+    {
+      "title": "Top 10 Slowest RPC Commands",
+      "type": "table",
+      "datasource": "Tempo",
+      "targets": [
+        {
+          "queryType": "traceql",
+          "query": "{resource.service.name=\"rippled\" && span.xrpl.rpc.command != \"\"} | avg(duration) by (span.xrpl.rpc.command) | topk(10)"
+        }
+      ],
+      "gridPos": { "h": 8, "w": 24, "x": 0, "y": 8 }
+    },
+    {
+      "title": "Recent Traces",
+      "type": "table",
+      "datasource": "Tempo",
+      "targets": [
+        {
+          "queryType": "traceql",
+          "query": "{resource.service.name=\"rippled\"}"
+        }
+      ],
+      "gridPos": { "h": 8, "w": 24, "x": 0, "y": 16 }
+    }
+  ]
+}
+```
+
+### 5.8.4 Example Dashboard: Transaction Tracing
+
+```json
+{
+  "title": "rippled Transaction Tracing",
+  "uid": "rippled-tx-tracing",
+  "panels": [
+    {
+      "title": "Transaction Throughput",
+      "type": "stat",
+      "datasource": "Tempo",
+      "targets": [
+        {
+          "queryType": "traceql",
+          "query": "{resource.service.name=\"rippled\" && name=\"tx.receive\"} | rate()"
+        }
+      ],
+      "gridPos": { "h": 4, "w": 6, "x": 0, "y": 0 }
+    },
+    {
+      "title": "Cross-Node Relay Count",
+      "type": "timeseries",
+      "datasource": "Tempo",
+      "targets": [
+        {
+          "queryType": "traceql",
+          "query": "{resource.service.name=\"rippled\" && name=\"tx.relay\"} | avg(span.xrpl.tx.relay_count)"
+        }
+      ],
+      "gridPos": { "h": 8, "w": 12, "x": 0, "y": 4 }
+    },
+    {
+      "title": "Transaction Validation Errors",
+      "type": "table",
+      "datasource": "Tempo",
+      "targets": [
+        {
+          "queryType": "traceql",
+          "query": "{resource.service.name=\"rippled\" && name=\"tx.validate\" && status.code=error}"
+        }
+      ],
+      "gridPos": { "h": 8, "w": 12, "x": 12, "y": 4 }
+    }
+  ]
+}
+```
+
+### 5.8.5 TraceQL Query Examples
+
+Common queries for rippled traces:
+
+```
+# Find all traces for a specific transaction hash
+{resource.service.name="rippled" && span.xrpl.tx.hash="ABC123..."}
+
+# Find slow RPC commands (>100ms)
+{resource.service.name="rippled" && name=~"rpc.command.*"} | duration > 100ms
+
+# Find consensus rounds taking >5 seconds
+{resource.service.name="rippled" && name="consensus.round"} | duration > 5s
+
+# Find failed transactions with error details
+{resource.service.name="rippled" && name="tx.validate" && status.code=error}
+
+# Find transactions relayed to many peers
+{resource.service.name="rippled" && name="tx.relay"} | span.xrpl.tx.relay_count > 10
+
+# Compare latency across nodes
+{resource.service.name="rippled" && name="rpc.command.account_info"} | avg(duration) by (resource.service.instance.id)
+```
+
+### 5.8.6 Correlation with PerfLog
+
+To correlate OpenTelemetry traces with existing PerfLog data:
+
+**Step 1: Configure Loki to ingest PerfLog**
+
+```yaml
+# promtail-config.yaml
+scrape_configs:
+  - job_name: rippled-perflog
+    static_configs:
+      - targets:
+          - localhost
+        labels:
+          job: rippled
+          __path__: /var/log/rippled/perf*.log
+    pipeline_stages:
+      - json:
+          expressions:
+            trace_id: trace_id
+            ledger_seq: ledger_seq
+            tx_hash: tx_hash
+      - labels:
+          trace_id:
+          ledger_seq:
+          tx_hash:
+```
+
+**Step 2: Add trace_id to PerfLog entries**
+
+Modify PerfLog to include trace_id when available:
+
+```cpp
+// In PerfLog output, add trace_id from current span context
+void logPerf(Json::Value& entry) {
+    auto span = opentelemetry::trace::GetSpan(
+        opentelemetry::context::RuntimeContext::GetCurrent());
+    if (span && span->GetContext().IsValid()) {
+        char traceIdHex[33];
+        span->GetContext().trace_id().ToLowerBase16(traceIdHex);
+        entry["trace_id"] = std::string(traceIdHex, 32);
+    }
+    // ... existing logging
+}
+```
+
+**Step 3: Configure Grafana trace-to-logs link**
+
+In Tempo data source configuration, set up the derived field:
+
+```yaml
+jsonData:
+  tracesToLogs:
+    datasourceUid: loki
+    tags: ["trace_id", "xrpl.tx.hash"]
+    filterByTraceID: true
+    filterBySpanID: false
+```
+
+### 5.8.7 Correlation with Insight/OTel System Metrics
+
+To correlate traces with Beast Insight system metrics:
+
+**Step 1: Export Insight metrics to Prometheus**
+
+Beast Insight metrics are exported natively via OTLP to the OTel Collector,
+which exposes them on the Prometheus endpoint alongside spanmetrics. No
+separate StatsD exporter is needed when using `server=otel`.
+
+```ini
+# xrpld.cfg — native OTel metrics (recommended)
+[insight]
+server=otel
+endpoint=http://localhost:4318/v1/metrics
+prefix=rippled
+```
+
+**Step 2: Add exemplars to metrics**
+
+OpenTelemetry SDK automatically adds exemplars (trace IDs) to metrics when using the Prometheus exporter. This links metrics spikes to specific traces.
+
+**Step 3: Configure Grafana metric-to-trace link**
+
+```yaml
+# In Prometheus data source
+jsonData:
+  exemplarTraceIdDestinations:
+    - name: trace_id
+      datasourceUid: tempo
+```
+
+**Step 4: Dashboard panel with exemplars**
+
+```json
+{
+  "title": "RPC Latency with Trace Links",
+  "type": "timeseries",
+  "datasource": "Prometheus",
+  "targets": [
+    {
+      "expr": "histogram_quantile(0.99, rate(rippled_rpc_duration_seconds_bucket[5m]))",
+      "exemplar": true
+    }
+  ]
+}
+```
+
+This allows clicking on metric data points to jump directly to the related trace.
+
+---
+
+_Previous: [Code Samples](./04-code-samples.md)_ | _Next: [Implementation Phases](./06-implementation-phases.md)_ | _Back to: [Overview](./OpenTelemetryPlan.md)_

OpenTelemetryPlan/07-observability-backends.md

@@ -0,0 +1,595 @@
+# Observability Backend Recommendations
+
+> **Parent Document**: [OpenTelemetryPlan.md](./OpenTelemetryPlan.md)
+> **Related**: [Implementation Phases](./06-implementation-phases.md) | [Appendix](./08-appendix.md)
+
+---
+
+## 7.1 Development/Testing Backends
+
+| Backend    | Pros                | Cons              | Use Case          |
+| ---------- | ------------------- | ----------------- | ----------------- |
+| **Jaeger** | Easy setup, good UI | Limited retention | Local dev, CI     |
+| **Zipkin** | Simple, lightweight | Basic features    | Quick prototyping |
+
+### Quick Start with Jaeger
+
+```bash
+# Start Jaeger with OTLP support
+docker run -d --name jaeger \
+  -e COLLECTOR_OTLP_ENABLED=true \
+  -p 16686:16686 \
+  -p 4317:4317 \
+  -p 4318:4318 \
+  jaegertracing/all-in-one:latest
+```
+
+---
+
+## 7.2 Production Backends
+
+| Backend           | Pros                                      | Cons               | Use Case                    |
+| ----------------- | ----------------------------------------- | ------------------ | --------------------------- |
+| **Grafana Tempo** | Cost-effective, Grafana integration       | Newer project      | Most production deployments |
+| **Elastic APM**   | Full observability stack, log correlation | Resource intensive | Existing Elastic users      |
+| **Honeycomb**     | Excellent query, high cardinality         | SaaS cost          | Deep debugging needs        |
+| **Datadog APM**   | Full platform, easy setup                 | SaaS cost          | Enterprise with budget      |
+
+### Backend Selection Flowchart
+
+```mermaid
+flowchart TD
+    start[Select Backend] --> budget{Budget<br/>Constraints?}
+
+    budget -->|Yes| oss[Open Source]
+    budget -->|No| saas{Prefer<br/>SaaS?}
+
+    oss --> existing{Existing<br/>Stack?}
+    existing -->|Grafana| tempo[Grafana Tempo]
+    existing -->|Elastic| elastic[Elastic APM]
+    existing -->|None| tempo
+
+    saas -->|Yes| enterprise{Enterprise<br/>Support?}
+    saas -->|No| oss
+
+    enterprise -->|Yes| datadog[Datadog APM]
+    enterprise -->|No| honeycomb[Honeycomb]
+
+    tempo --> final[Configure Collector]
+    elastic --> final
+    honeycomb --> final
+    datadog --> final
+
+    style start fill:#0f172a,stroke:#020617,color:#fff
+    style budget fill:#334155,stroke:#1e293b,color:#fff
+    style oss fill:#1e293b,stroke:#0f172a,color:#fff
+    style existing fill:#334155,stroke:#1e293b,color:#fff
+    style saas fill:#334155,stroke:#1e293b,color:#fff
+    style enterprise fill:#334155,stroke:#1e293b,color:#fff
+    style final fill:#0f172a,stroke:#020617,color:#fff
+    style tempo fill:#1b5e20,stroke:#0d3d14,color:#fff
+    style elastic fill:#bf360c,stroke:#8c2809,color:#fff
+    style honeycomb fill:#0d47a1,stroke:#082f6a,color:#fff
+    style datadog fill:#4a148c,stroke:#2e0d57,color:#fff
+```
+
+---
+
+## 7.3 Recommended Production Architecture
+
+```mermaid
+flowchart TB
+    subgraph validators["Validator Nodes"]
+        v1[rippled<br/>Validator 1]
+        v2[rippled<br/>Validator 2]
+    end
+
+    subgraph stock["Stock Nodes"]
+        s1[rippled<br/>Stock 1]
+        s2[rippled<br/>Stock 2]
+    end
+
+    subgraph collector["OTel Collector Cluster"]
+        c1[Collector<br/>DC1]
+        c2[Collector<br/>DC2]
+    end
+
+    subgraph backends["Storage Backends"]
+        tempo[(Grafana<br/>Tempo)]
+        elastic[(Elastic<br/>APM)]
+        archive[(S3/GCS<br/>Archive)]
+    end
+
+    subgraph ui["Visualization"]
+        grafana[Grafana<br/>Dashboards]
+    end
+
+    v1 -->|OTLP| c1
+    v2 -->|OTLP| c1
+    s1 -->|OTLP| c2
+    s2 -->|OTLP| c2
+
+    c1 --> tempo
+    c1 --> elastic
+    c2 --> tempo
+    c2 --> archive
+
+    tempo --> grafana
+    elastic --> grafana
+
+    style validators fill:#b71c1c,stroke:#7f1d1d,color:#ffffff
+    style stock fill:#0d47a1,stroke:#082f6a,color:#ffffff
+    style collector fill:#bf360c,stroke:#8c2809,color:#ffffff
+    style backends fill:#1b5e20,stroke:#0d3d14,color:#ffffff
+    style ui fill:#4a148c,stroke:#2e0d57,color:#ffffff
+```
+
+---
+
+## 7.4 Architecture Considerations
+
+### 7.4.1 Collector Placement
+
+| Strategy      | Description          | Pros                     | Cons                    |
+| ------------- | -------------------- | ------------------------ | ----------------------- |
+| **Sidecar**   | Collector per node   | Isolation, simple config | Resource overhead       |
+| **DaemonSet** | Collector per host   | Shared resources         | Complexity              |
+| **Gateway**   | Central collector(s) | Centralized processing   | Single point of failure |
+
+**Recommendation**: Use **Gateway** pattern with regional collectors for rippled networks:
+
+- One collector cluster per datacenter/region
+- Tail-based sampling at collector level
+- Multiple export destinations for redundancy
+
+### 7.4.2 Sampling Strategy
+
+```mermaid
+flowchart LR
+    subgraph head["Head Sampling (Node)"]
+        hs[10% probabilistic]
+    end
+
+    subgraph tail["Tail Sampling (Collector)"]
+        ts1[Keep all errors]
+        ts2[Keep slow >5s]
+        ts3[Keep 10% rest]
+    end
+
+    head --> tail
+
+    ts1 --> final[Final Traces]
+    ts2 --> final
+    ts3 --> final
+
+    style head fill:#0d47a1,stroke:#082f6a,color:#fff
+    style tail fill:#1b5e20,stroke:#0d3d14,color:#fff
+    style hs fill:#0d47a1,stroke:#082f6a,color:#fff
+    style ts1 fill:#1b5e20,stroke:#0d3d14,color:#fff
+    style ts2 fill:#1b5e20,stroke:#0d3d14,color:#fff
+    style ts3 fill:#1b5e20,stroke:#0d3d14,color:#fff
+    style final fill:#bf360c,stroke:#8c2809,color:#fff
+```
+
+### 7.4.3 Data Retention
+
+| Environment | Hot Storage | Warm Storage | Cold Archive |
+| ----------- | ----------- | ------------ | ------------ |
+| Development | 24 hours    | N/A          | N/A          |
+| Staging     | 7 days      | N/A          | N/A          |
+| Production  | 7 days      | 30 days      | many years   |
+
+---
+
+## 7.5 Integration Checklist
+
+- [ ] Choose primary backend (Tempo recommended for cost/features)
+- [ ] Deploy collector cluster with high availability
+- [ ] Configure tail-based sampling for error/latency traces
+- [ ] Set up Grafana dashboards for trace visualization
+- [ ] Configure alerts for trace anomalies
+- [ ] Establish data retention policies
+- [ ] Test trace correlation with logs and metrics
+
+---
+
+## 7.6 Grafana Dashboard Examples
+
+Pre-built dashboards for rippled observability.
+
+### 7.6.1 Consensus Health Dashboard
+
+```json
+{
+  "title": "rippled Consensus Health",
+  "uid": "rippled-consensus-health",
+  "tags": ["rippled", "consensus", "tracing"],
+  "panels": [
+    {
+      "title": "Consensus Round Duration",
+      "type": "timeseries",
+      "datasource": "Tempo",
+      "targets": [
+        {
+          "queryType": "traceql",
+          "query": "{resource.service.name=\"rippled\" && name=\"consensus.round\"} | avg(duration) by (resource.service.instance.id)"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "ms",
+          "thresholds": {
+            "steps": [
+              { "color": "green", "value": null },
+              { "color": "yellow", "value": 4000 },
+              { "color": "red", "value": 5000 }
+            ]
+          }
+        }
+      },
+      "gridPos": { "h": 8, "w": 12, "x": 0, "y": 0 }
+    },
+    {
+      "title": "Phase Duration Breakdown",
+      "type": "barchart",
+      "datasource": "Tempo",
+      "targets": [
+        {
+          "queryType": "traceql",
+          "query": "{resource.service.name=\"rippled\" && name=~\"consensus.phase.*\"} | avg(duration) by (name)"
+        }
+      ],
+      "gridPos": { "h": 8, "w": 12, "x": 12, "y": 0 }
+    },
+    {
+      "title": "Proposers per Round",
+      "type": "stat",
+      "datasource": "Tempo",
+      "targets": [
+        {
+          "queryType": "traceql",
+          "query": "{resource.service.name=\"rippled\" && name=\"consensus.round\"} | avg(span.xrpl.consensus.proposers)"
+        }
+      ],
+      "gridPos": { "h": 4, "w": 6, "x": 0, "y": 8 }
+    },
+    {
+      "title": "Recent Slow Rounds (>5s)",
+      "type": "table",
+      "datasource": "Tempo",
+      "targets": [
+        {
+          "queryType": "traceql",
+          "query": "{resource.service.name=\"rippled\" && name=\"consensus.round\"} | duration > 5s"
+        }
+      ],
+      "gridPos": { "h": 8, "w": 24, "x": 0, "y": 12 }
+    }
+  ]
+}
+```
+
+### 7.6.2 Node Overview Dashboard
+
+```json
+{
+  "title": "rippled Node Overview",
+  "uid": "rippled-node-overview",
+  "panels": [
+    {
+      "title": "Active Nodes",
+      "type": "stat",
+      "datasource": "Tempo",
+      "targets": [
+        {
+          "queryType": "traceql",
+          "query": "{resource.service.name=\"rippled\"} | count_over_time() by (resource.service.instance.id) | count()"
+        }
+      ],
+      "gridPos": { "h": 4, "w": 4, "x": 0, "y": 0 }
+    },
+    {
+      "title": "Total Transactions (1h)",
+      "type": "stat",
+      "datasource": "Tempo",
+      "targets": [
+        {
+          "queryType": "traceql",
+          "query": "{resource.service.name=\"rippled\" && name=\"tx.receive\"} | count()"
+        }
+      ],
+      "gridPos": { "h": 4, "w": 4, "x": 4, "y": 0 }
+    },
+    {
+      "title": "Error Rate",
+      "type": "gauge",
+      "datasource": "Tempo",
+      "targets": [
+        {
+          "queryType": "traceql",
+          "query": "{resource.service.name=\"rippled\" && status.code=error} | rate() / {resource.service.name=\"rippled\"} | rate() * 100"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "percent",
+          "max": 10,
+          "thresholds": {
+            "steps": [
+              { "color": "green", "value": null },
+              { "color": "yellow", "value": 1 },
+              { "color": "red", "value": 5 }
+            ]
+          }
+        }
+      },
+      "gridPos": { "h": 4, "w": 4, "x": 8, "y": 0 }
+    },
+    {
+      "title": "Service Map",
+      "type": "nodeGraph",
+      "datasource": "Tempo",
+      "gridPos": { "h": 12, "w": 12, "x": 12, "y": 0 }
+    }
+  ]
+}
+```
+
+### 7.6.3 Alert Rules
+
+```yaml
+# grafana/provisioning/alerting/rippled-alerts.yaml
+apiVersion: 1
+
+groups:
+  - name: rippled-tracing-alerts
+    folder: rippled
+    interval: 1m
+    rules:
+      - uid: consensus-slow
+        title: Consensus Round Slow
+        condition: A
+        data:
+          - refId: A
+            datasourceUid: tempo
+            model:
+              queryType: traceql
+              query: '{resource.service.name="rippled" && name="consensus.round"} | avg(duration) > 5s'
+        for: 5m
+        annotations:
+          summary: Consensus rounds taking >5 seconds
+          description: "Consensus duration: {{ $value }}ms"
+        labels:
+          severity: warning
+
+      - uid: rpc-error-spike
+        title: RPC Error Rate Spike
+        condition: B
+        data:
+          - refId: B
+            datasourceUid: tempo
+            model:
+              queryType: traceql
+              query: '{resource.service.name="rippled" && name=~"rpc.command.*" && status.code=error} | rate() > 0.05'
+        for: 2m
+        annotations:
+          summary: RPC error rate >5%
+        labels:
+          severity: critical
+
+      - uid: tx-throughput-drop
+        title: Transaction Throughput Drop
+        condition: C
+        data:
+          - refId: C
+            datasourceUid: tempo
+            model:
+              queryType: traceql
+              query: '{resource.service.name="rippled" && name="tx.receive"} | rate() < 10'
+        for: 10m
+        annotations:
+          summary: Transaction throughput below threshold
+        labels:
+          severity: warning
+```
+
+---
+
+## 7.7 PerfLog and Insight Correlation
+
+How to correlate OpenTelemetry traces with existing rippled observability.
+
+### 7.7.1 Correlation Architecture
+
+```mermaid
+flowchart TB
+    subgraph rippled["rippled Node"]
+        otel[OpenTelemetry<br/>Spans]
+        perflog[PerfLog<br/>JSON Logs]
+        insight[Beast Insight<br/>StatsD Metrics]
+    end
+
+    subgraph collectors["Data Collection"]
+        otelc[OTel Collector]
+        promtail[Promtail/Fluentd]
+        statsd[StatsD Exporter]
+    end
+
+    subgraph storage["Storage"]
+        tempo[(Tempo)]
+        loki[(Loki)]
+        prom[(Prometheus)]
+    end
+
+    subgraph grafana["Grafana"]
+        traces[Trace View]
+        logs[Log View]
+        metrics[Metrics View]
+        corr[Correlation<br/>Panel]
+    end
+
+    otel -->|OTLP| otelc --> tempo
+    perflog -->|JSON| promtail --> loki
+    insight -->|StatsD| statsd --> prom
+
+    tempo --> traces
+    loki --> logs
+    prom --> metrics
+
+    traces --> corr
+    logs --> corr
+    metrics --> corr
+
+    style rippled fill:#0d47a1,stroke:#082f6a,color:#fff
+    style collectors fill:#bf360c,stroke:#8c2809,color:#fff
+    style storage fill:#1b5e20,stroke:#0d3d14,color:#fff
+    style grafana fill:#4a148c,stroke:#2e0d57,color:#fff
+    style otel fill:#0d47a1,stroke:#082f6a,color:#fff
+    style perflog fill:#0d47a1,stroke:#082f6a,color:#fff
+    style insight fill:#0d47a1,stroke:#082f6a,color:#fff
+    style otelc fill:#bf360c,stroke:#8c2809,color:#fff
+    style promtail fill:#bf360c,stroke:#8c2809,color:#fff
+    style statsd fill:#bf360c,stroke:#8c2809,color:#fff
+    style tempo fill:#1b5e20,stroke:#0d3d14,color:#fff
+    style loki fill:#1b5e20,stroke:#0d3d14,color:#fff
+    style prom fill:#1b5e20,stroke:#0d3d14,color:#fff
+    style traces fill:#4a148c,stroke:#2e0d57,color:#fff
+    style logs fill:#4a148c,stroke:#2e0d57,color:#fff
+    style metrics fill:#4a148c,stroke:#2e0d57,color:#fff
+    style corr fill:#4a148c,stroke:#2e0d57,color:#fff
+```
+
+### 7.7.2 Correlation Fields
+
+| Source      | Field                       | Link To       | Purpose                    |
+| ----------- | --------------------------- | ------------- | -------------------------- |
+| **Trace**   | `trace_id`                  | Logs          | Find log entries for trace |
+| **Trace**   | `xrpl.tx.hash`              | Logs, Metrics | Find TX-related data       |
+| **Trace**   | `xrpl.consensus.ledger.seq` | Logs          | Find ledger-related logs   |
+| **PerfLog** | `trace_id` (new)            | Traces        | Jump to trace from log     |
+| **PerfLog** | `ledger_seq`                | Traces        | Find consensus trace       |
+| **Insight** | `exemplar.trace_id`         | Traces        | Jump from metric spike     |
+
+### 7.7.3 Example: Debugging a Slow Transaction
+
+**Step 1: Find the trace**
+
+```
+# In Grafana Explore with Tempo
+{resource.service.name="rippled" && span.xrpl.tx.hash="ABC123..."}
+```
+
+**Step 2: Get the trace_id from the trace view**
+
+```
+Trace ID: 4bf92f3577b34da6a3ce929d0e0e4736
+```
+
+**Step 3: Find related PerfLog entries**
+
+```
+# In Grafana Explore with Loki
+{job="rippled"} |= "4bf92f3577b34da6a3ce929d0e0e4736"
+```
+
+**Step 4: Check Insight metrics for the time window**
+
+```
+# In Grafana with Prometheus
+rate(rippled_tx_applied_total[1m])
+  @ timestamp_from_trace
+```
+
+### 7.7.4 Unified Dashboard Example
+
+```json
+{
+  "title": "rippled Unified Observability",
+  "uid": "rippled-unified",
+  "panels": [
+    {
+      "title": "Transaction Latency (Traces)",
+      "type": "timeseries",
+      "datasource": "Tempo",
+      "targets": [
+        {
+          "queryType": "traceql",
+          "query": "{resource.service.name=\"rippled\" && name=\"tx.receive\"} | histogram_over_time(duration)"
+        }
+      ],
+      "gridPos": { "h": 6, "w": 8, "x": 0, "y": 0 }
+    },
+    {
+      "title": "Transaction Rate (Metrics)",
+      "type": "timeseries",
+      "datasource": "Prometheus",
+      "targets": [
+        {
+          "expr": "rate(rippled_tx_received_total[5m])",
+          "legendFormat": "{{ instance }}"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "links": [
+            {
+              "title": "View traces",
+              "url": "/explore?left={\"datasource\":\"Tempo\",\"query\":\"{resource.service.name=\\\"rippled\\\" && name=\\\"tx.receive\\\"}\"}"
+            }
+          ]
+        }
+      },
+      "gridPos": { "h": 6, "w": 8, "x": 8, "y": 0 }
+    },
+    {
+      "title": "Recent Logs",
+      "type": "logs",
+      "datasource": "Loki",
+      "targets": [
+        {
+          "expr": "{job=\"rippled\"} | json"
+        }
+      ],
+      "gridPos": { "h": 6, "w": 8, "x": 16, "y": 0 }
+    },
+    {
+      "title": "Trace Search",
+      "type": "table",
+      "datasource": "Tempo",
+      "targets": [
+        {
+          "queryType": "traceql",
+          "query": "{resource.service.name=\"rippled\"}"
+        }
+      ],
+      "fieldConfig": {
+        "overrides": [
+          {
+            "matcher": { "id": "byName", "options": "traceID" },
+            "properties": [
+              {
+                "id": "links",
+                "value": [
+                  {
+                    "title": "View trace",
+                    "url": "/explore?left={\"datasource\":\"Tempo\",\"query\":\"${__value.raw}\"}"
+                  },
+                  {
+                    "title": "View logs",
+                    "url": "/explore?left={\"datasource\":\"Loki\",\"query\":\"{job=\\\"rippled\\\"} |= \\\"${__value.raw}\\\"\"}"
+                  }
+                ]
+              }
+            ]
+          }
+        ]
+      },
+      "gridPos": { "h": 12, "w": 24, "x": 0, "y": 6 }
+    }
+  ]
+}
+```
+
+---
+
+_Previous: [Implementation Phases](./06-implementation-phases.md)_ | _Next: [Appendix](./08-appendix.md)_ | _Back to: [Overview](./OpenTelemetryPlan.md)_

OpenTelemetryPlan/08-appendix.md

@@ -0,0 +1,231 @@
+# Appendix
+
+> **Parent Document**: [OpenTelemetryPlan.md](./OpenTelemetryPlan.md)
+> **Related**: [Observability Backends](./07-observability-backends.md)
+
+---
+
+## 8.1 Glossary
+
+| Term                  | Definition                                                 |
+| --------------------- | ---------------------------------------------------------- |
+| **Span**              | A unit of work with start/end time, name, and attributes   |
+| **Trace**             | A collection of spans representing a complete request flow |
+| **Trace ID**          | 128-bit unique identifier for a trace                      |
+| **Span ID**           | 64-bit unique identifier for a span within a trace         |
+| **Context**           | Carrier for trace/span IDs across boundaries               |
+| **Propagator**        | Component that injects/extracts context                    |
+| **Sampler**           | Decides which traces to record                             |
+| **Exporter**          | Sends spans to backend                                     |
+| **Collector**         | Receives, processes, and forwards telemetry                |
+| **OTLP**              | OpenTelemetry Protocol (wire format)                       |
+| **W3C Trace Context** | Standard HTTP headers for trace propagation                |
+| **Baggage**           | Key-value pairs propagated across service boundaries       |
+| **Resource**          | Entity producing telemetry (service, host, etc.)           |
+| **Instrumentation**   | Code that creates telemetry data                           |
+
+### rippled-Specific Terms
+
+| Term              | Definition                                         |
+| ----------------- | -------------------------------------------------- |
+| **Overlay**       | P2P network layer managing peer connections        |
+| **Consensus**     | XRP Ledger consensus algorithm (RCL)               |
+| **Proposal**      | Validator's suggested transaction set for a ledger |
+| **Validation**    | Validator's signature on a closed ledger           |
+| **HashRouter**    | Component for transaction deduplication            |
+| **JobQueue**      | Thread pool for asynchronous task execution        |
+| **PerfLog**       | Existing performance logging system in rippled     |
+| **Beast Insight** | Existing metrics framework in rippled              |
+
+### Phase 9–11 Terms
+
+| Term                        | Definition                                                                |
+| --------------------------- | ------------------------------------------------------------------------- |
+| **MetricsRegistry**         | Centralized class for OTel async gauge registrations (Phase 9)            |
+| **ObservableGauge**         | OTel Metrics SDK async instrument polled via callback at fixed intervals  |
+| **PeriodicMetricReader**    | OTel SDK component that invokes gauge callbacks at configurable intervals |
+| **CountedObject**           | rippled template that tracks live instance counts via atomic counters     |
+| **TxQ**                     | Transaction queue managing fee escalation and ordering                    |
+| **Load Factor**             | Combined multiplier affecting transaction cost (local, cluster, network)  |
+| **OTel Collector Receiver** | Custom Go plugin that polls rippled RPC and emits OTel metrics (Phase 11) |
+
+---
+
+## 8.2 Span Hierarchy Visualization
+
+```mermaid
+flowchart TB
+    subgraph trace["Trace: Transaction Lifecycle"]
+        rpc["rpc.submit<br/>(entry point)"]
+        validate["tx.validate"]
+        relay["tx.relay<br/>(parent span)"]
+
+        subgraph peers["Peer Spans"]
+            p1["peer.send<br/>Peer A"]
+            p2["peer.send<br/>Peer B"]
+            p3["peer.send<br/>Peer C"]
+        end
+
+        consensus["consensus.round"]
+        apply["tx.apply"]
+    end
+
+    rpc --> validate
+    validate --> relay
+    relay --> p1
+    relay --> p2
+    relay --> p3
+    p1 -.->|"context propagation"| consensus
+    consensus --> apply
+
+    style trace fill:#0f172a,stroke:#020617,color:#fff
+    style peers fill:#1e3a8a,stroke:#172554,color:#fff
+    style rpc fill:#1d4ed8,stroke:#1e40af,color:#fff
+    style validate fill:#047857,stroke:#064e3b,color:#fff
+    style relay fill:#047857,stroke:#064e3b,color:#fff
+    style p1 fill:#0e7490,stroke:#155e75,color:#fff
+    style p2 fill:#0e7490,stroke:#155e75,color:#fff
+    style p3 fill:#0e7490,stroke:#155e75,color:#fff
+    style consensus fill:#fef3c7,stroke:#fde68a,color:#1e293b
+    style apply fill:#047857,stroke:#064e3b,color:#fff
+```
+
+---
+
+## 8.3 References
+
+### OpenTelemetry Resources
+
+1. [OpenTelemetry C++ SDK](https://github.com/open-telemetry/opentelemetry-cpp)
+2. [OpenTelemetry Specification](https://opentelemetry.io/docs/specs/otel/)
+3. [OpenTelemetry Collector](https://opentelemetry.io/docs/collector/)
+4. [OTLP Protocol Specification](https://opentelemetry.io/docs/specs/otlp/)
+
+### Standards
+
+5. [W3C Trace Context](https://www.w3.org/TR/trace-context/)
+6. [W3C Baggage](https://www.w3.org/TR/baggage/)
+7. [Protocol Buffers](https://protobuf.dev/)
+
+### rippled Resources
+
+8. [rippled Source Code](https://github.com/XRPLF/rippled)
+9. [XRP Ledger Documentation](https://xrpl.org/docs/)
+10. [rippled Overlay README](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/README.md)
+11. [rippled RPC README](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/rpc/README.md)
+12. [rippled Consensus README](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/consensus/README.md)
+
+---
+
+## 8.4 Version History
+
+| Version | Date       | Author | Changes                                      |
+| ------- | ---------- | ------ | -------------------------------------------- |
+| 1.0     | 2026-02-12 | -      | Initial implementation plan                  |
+| 1.1     | 2026-02-13 | -      | Refactored into modular documents            |
+| 1.2     | 2026-03-09 | -      | Added Phases 9–11 (future enhancement plans) |
+
+---
+
+## 8.5 Document Index
+
+### Plan Documents
+
+| Document                                                             | Description                                  |
+| -------------------------------------------------------------------- | -------------------------------------------- |
+| [OpenTelemetryPlan.md](./OpenTelemetryPlan.md)                       | Master overview and executive summary        |
+| [00-tracing-fundamentals.md](./00-tracing-fundamentals.md)           | Distributed tracing concepts and OTel primer |
+| [01-architecture-analysis.md](./01-architecture-analysis.md)         | rippled architecture and trace points        |
+| [02-design-decisions.md](./02-design-decisions.md)                   | SDK selection, exporters, span conventions   |
+| [03-implementation-strategy.md](./03-implementation-strategy.md)     | Directory structure, performance analysis    |
+| [04-code-samples.md](./04-code-samples.md)                           | C++ code examples for all components         |
+| [05-configuration-reference.md](./05-configuration-reference.md)     | rippled config, CMake, Collector configs     |
+| [06-implementation-phases.md](./06-implementation-phases.md)         | Timeline, tasks, risks, success metrics      |
+| [07-observability-backends.md](./07-observability-backends.md)       | Backend selection and architecture           |
+| [08-appendix.md](./08-appendix.md)                                   | Glossary, references, version history        |
+| [09-data-collection-reference.md](./09-data-collection-reference.md) | Span/metric/dashboard inventory              |
+| [presentation.md](./presentation.md)                                 | Slide deck for OTel plan overview            |
+
+### Task Lists
+
+| Document                                                                   | Description                                         |
+| -------------------------------------------------------------------------- | --------------------------------------------------- |
+| [POC_taskList.md](./POC_taskList.md)                                       | Proof-of-concept telemetry integration              |
+| [Phase2_taskList.md](./Phase2_taskList.md)                                 | RPC layer trace instrumentation                     |
+| [Phase3_taskList.md](./Phase3_taskList.md)                                 | Peer overlay & consensus tracing                    |
+| [Phase4_taskList.md](./Phase4_taskList.md)                                 | Transaction lifecycle tracing                       |
+| [Phase5_taskList.md](./Phase5_taskList.md)                                 | Ledger processing & advanced tracing                |
+| [Phase5_IntegrationTest_taskList.md](./Phase5_IntegrationTest_taskList.md) | Observability stack integration tests               |
+| [Phase7_taskList.md](./Phase7_taskList.md)                                 | Native OTel metrics migration                       |
+| [Phase8_taskList.md](./Phase8_taskList.md)                                 | Log-trace correlation                               |
+| [Phase9_taskList.md](./Phase9_taskList.md)                                 | Internal metric instrumentation gap fill (future)   |
+| [Phase10_taskList.md](./Phase10_taskList.md)                               | Synthetic workload generation & validation (future) |
+| [Phase11_taskList.md](./Phase11_taskList.md)                               | Third-party data collection pipelines (future)      |
+
+> **Note**: Phases 1 and 6 do not have separate task list files. Phase 1 tasks are documented in [06-implementation-phases.md §6.2](./06-implementation-phases.md). Phase 6 tasks are documented in [06-implementation-phases.md §6.7](./06-implementation-phases.md).
+
+---
+
+## 8.6 Phase 9–11 Cross-Reference Guide
+
+This guide maps Phase 9–11 content to its location across the documentation.
+
+### Phase 9: Internal Metric Instrumentation Gap Fill
+
+| Content                         | Location                                                                 |
+| ------------------------------- | ------------------------------------------------------------------------ |
+| Plan & architecture             | [06-implementation-phases.md §6.8.2](./06-implementation-phases.md)      |
+| Task list (10 tasks, 12d)       | [Phase9_taskList.md](./Phase9_taskList.md)                               |
+| Future metric definitions (~50) | [09-data-collection-reference.md §5b](./09-data-collection-reference.md) |
+| New class: `MetricsRegistry`    | `src/xrpld/telemetry/MetricsRegistry.h/.cpp` (planned)                   |
+| New dashboards                  | `rippled-fee-market`, `rippled-job-queue` (planned)                      |
+
+**Metric categories**: NodeStore I/O, Cache Hit Rates, TxQ, PerfLog Per-RPC, PerfLog Per-Job, Counted Objects, Fee Escalation & Load Factors.
+
+### Phase 10: Synthetic Workload Generation & Telemetry Validation
+
+| Content                  | Location                                                                 |
+| ------------------------ | ------------------------------------------------------------------------ |
+| Plan & architecture      | [06-implementation-phases.md §6.8.3](./06-implementation-phases.md)      |
+| Task list (7 tasks, 10d) | [Phase10_taskList.md](./Phase10_taskList.md)                             |
+| Validation inventory     | [09-data-collection-reference.md §5c](./09-data-collection-reference.md) |
+| Test harness             | `docker/telemetry/docker-compose.workload.yaml` (planned)                |
+| CI workflow              | `.github/workflows/telemetry-validation.yml` (planned)                   |
+
+**Validates**: 16 spans, 22 attributes, 300+ metrics, 10 dashboards, log-trace correlation.
+
+### Phase 11: Third-Party Data Collection Pipelines
+
+| Content                           | Location                                                                 |
+| --------------------------------- | ------------------------------------------------------------------------ |
+| Plan & architecture               | [06-implementation-phases.md §6.8.4](./06-implementation-phases.md)      |
+| Task list (11 tasks, 15d)         | [Phase11_taskList.md](./Phase11_taskList.md)                             |
+| External metric definitions (~30) | [09-data-collection-reference.md §5d](./09-data-collection-reference.md) |
+| Custom OTel Collector receiver    | `docker/telemetry/otel-rippled-receiver/` (planned)                      |
+| Prometheus alerting rules (11)    | [09-data-collection-reference.md §5d](./09-data-collection-reference.md) |
+| New dashboards (4)                | Validator Health, Network Topology, Fee Market (External), DEX & AMM     |
+
+**Consumer categories**: Exchanges, Payment Processors, DeFi/AMM, NFT Marketplaces, Analytics Providers, Wallets, Compliance, Academic Researchers, Institutional Custody, CBDC Bridge Operators.
+
+---
+
+## 8.7 Effort Summary (All Phases)
+
+| Phase | Description                      | Effort     | Status             |
+| ----- | -------------------------------- | ---------- | ------------------ |
+| 1     | Core SDK integration             | 5d         | Active             |
+| 2     | RPC tracing                      | 5d         | Active             |
+| 3     | Peer & consensus tracing         | 8d         | Active             |
+| 4     | Transaction lifecycle            | 7d         | Active             |
+| 5     | Ledger & advanced                | 7.1d       | Active             |
+| 6     | StatsD → OTel bridge             | 8d         | Active             |
+| 7     | Native OTel metrics              | 15d        | Active             |
+| 8     | Log-trace correlation            | 10d        | Active             |
+| 9     | Internal metric gap fill         | 12d        | Future Enhancement |
+| 10    | Workload generation & validation | 10d        | Future Enhancement |
+| 11    | Third-party data pipelines       | 15d        | Future Enhancement |
+|       | **Total**                        | **102.1d** |                    |
+
+---
+
+_Previous: [Observability Backends](./07-observability-backends.md)_ | _Back to: [Overview](./OpenTelemetryPlan.md)_

OpenTelemetryPlan/09-data-collection-reference.md

@@ -0,0 +1,992 @@
+# Observability Data Collection Reference
+
+> **Audience**: Developers and operators. This is the single source of truth for all telemetry data collected by rippled's observability stack.
+>
+> **Related docs**: [docs/telemetry-runbook.md](../docs/telemetry-runbook.md) (operator runbook with alerting and troubleshooting) | [03-implementation-strategy.md](./03-implementation-strategy.md) (code structure and performance optimization) | [04-code-samples.md](./04-code-samples.md) (C++ instrumentation examples)
+
+## Data Flow Overview
+
+```mermaid
+graph LR
+    subgraph rippledNode["rippled Node"]
+        A["Trace Macros<br/>XRPL_TRACE_SPAN<br/>(OTLP/HTTP exporter)"]
+        B["beast::insight<br/>OTel native metrics<br/>(OTLP/HTTP exporter)"]
+        C["MetricsRegistry<br/>OTel SDK metrics<br/>(OTLP/HTTP exporter)"]
+    end
+
+    subgraph collector["OTel Collector  :4317 / :4318"]
+        direction TB
+        R1["OTLP Receiver<br/>:4317 gRPC  |  :4318 HTTP<br/>(traces + metrics)"]
+        BP["Batch Processor<br/>timeout 1s, batch 100"]
+        SM["SpanMetrics Connector<br/>derives RED metrics<br/>from trace spans"]
+
+        R1 --> BP
+        BP --> SM
+    end
+
+    subgraph backends["Trace Backends  (choose one or both)"]
+        D["Jaeger  :16686<br/>Trace search &<br/>visualization"]
+        T["Grafana Tempo<br/>(preferred for production)<br/>S3/GCS long-term storage"]
+    end
+
+    subgraph metrics["Metrics Stack"]
+        E["Prometheus  :9090<br/>scrapes :8889<br/>span-derived + system metrics"]
+    end
+
+    subgraph viz["Visualization"]
+        F["Grafana  :3000<br/>13 dashboards"]
+    end
+
+    A -->|"OTLP/HTTP :4318<br/>(traces + attributes)"| R1
+    B -->|"OTLP/HTTP :4318<br/>(gauges, counters, histograms)"| R1
+    C -->|"OTLP/HTTP :4318<br/>(counters, histograms,<br/>observable gauges)"| R1
+
+    BP -->|"OTLP/gRPC :4317"| D
+    BP -->|"OTLP/gRPC"| T
+
+    SM -->|"span_calls_total<br/>span_duration_ms<br/>(6 dimension labels)"| E
+    R1 -->|"rippled_* gauges<br/>rippled_* counters<br/>rippled_* histograms"| E
+
+    E -->|"Prometheus<br/>data source"| F
+    D -->|"Jaeger<br/>data source"| F
+    T -->|"Tempo<br/>data source"| F
+
+    style A fill:#4a90d9,color:#fff,stroke:#2a6db5
+    style B fill:#4a90d9,color:#fff,stroke:#2a6db5
+    style R1 fill:#5cb85c,color:#fff,stroke:#3d8b3d
+    style BP fill:#449d44,color:#fff,stroke:#2d6e2d
+    style SM fill:#449d44,color:#fff,stroke:#2d6e2d
+    style D fill:#f0ad4e,color:#000,stroke:#c78c2e
+    style T fill:#e8953a,color:#000,stroke:#b5732a
+    style E fill:#f0ad4e,color:#000,stroke:#c78c2e
+    style F fill:#5bc0de,color:#000,stroke:#3aa8c1
+    style rippledNode fill:#1a2633,color:#ccc,stroke:#4a90d9
+    style collector fill:#1a3320,color:#ccc,stroke:#5cb85c
+    style backends fill:#332a1a,color:#ccc,stroke:#f0ad4e
+    style metrics fill:#332a1a,color:#ccc,stroke:#f0ad4e
+    style viz fill:#1a2d33,color:#ccc,stroke:#5bc0de
+```
+
+There are two independent telemetry pipelines entering a single **OTel Collector** via the same OTLP receiver:
+
+1. **OpenTelemetry Traces** — Distributed spans with attributes, exported via OTLP/HTTP (:4318) to the collector's **OTLP Receiver**. The **Batch Processor** groups spans (1s timeout, batch size 100) before forwarding to trace backends. The **SpanMetrics Connector** derives RED metrics (rate, errors, duration) from every span and feeds them into the metrics pipeline.
+2. **beast::insight OTel Metrics** — System-level gauges, counters, and histograms exported natively via OTLP/HTTP (:4318) to the same **OTLP Receiver**. These are batched and exported to Prometheus alongside span-derived metrics. The StatsD UDP transport has been replaced by native OTLP; `server=statsd` remains available as a fallback.
+
+**Trace backends** — The collector exports traces via OTLP/gRPC to one or both:
+
+- **Jaeger** (development) — Provides trace search UI at `:16686`. Easy single-binary setup.
+- **Grafana Tempo** (production) — Preferred for production. Supports S3/GCS object storage for cost-effective long-term trace retention and integrates natively with Grafana.
+
+> **Further reading**: [00-tracing-fundamentals.md](./00-tracing-fundamentals.md) for core OpenTelemetry concepts (traces, spans, context propagation, sampling). [07-observability-backends.md](./07-observability-backends.md) for production backend selection, collector placement, and sampling strategies.
+
+---
+
+## 1. OpenTelemetry Spans
+
+### 1.1 Complete Span Inventory (16 spans)
+
+> **See also**: [02-design-decisions.md §2.3](./02-design-decisions.md#23-span-naming-conventions) for naming conventions and the full span catalog with rationale. [04-code-samples.md §4.6](./04-code-samples.md#46-span-flow-visualization) for span flow diagrams.
+
+#### RPC Spans
+
+Controlled by `trace_rpc=1` in `[telemetry]` config.
+
+| Span Name            | Parent        | Source File       | Description                                                              |
+| -------------------- | ------------- | ----------------- | ------------------------------------------------------------------------ |
+| `rpc.request`        | —             | ServerHandler.cpp | Top-level HTTP RPC request entry point                                   |
+| `rpc.process`        | `rpc.request` | ServerHandler.cpp | RPC processing pipeline                                                  |
+| `rpc.ws_message`     | —             | ServerHandler.cpp | WebSocket message handling                                               |
+| `rpc.command.<name>` | `rpc.process` | RPCHandler.cpp    | Per-command span (e.g., `rpc.command.server_info`, `rpc.command.ledger`) |
+
+**Where to find**: Jaeger → Service: `rippled` → Operation: `rpc.request` or `rpc.command.*`
+
+**Grafana dashboard**: _RPC Performance_ (`rippled-rpc-perf`)
+
+#### Transaction Spans
+
+Controlled by `trace_transactions=1` in `[telemetry]` config.
+
+| Span Name    | Parent         | Source File     | Description                                                       |
+| ------------ | -------------- | --------------- | ----------------------------------------------------------------- |
+| `tx.process` | —              | NetworkOPs.cpp  | Transaction submission entry point (local or peer-relayed)        |
+| `tx.receive` | —              | PeerImp.cpp     | Raw transaction received from peer overlay (before deduplication) |
+| `tx.apply`   | `ledger.build` | BuildLedger.cpp | Transaction set applied to new ledger during consensus            |
+
+**Where to find**: Jaeger → Operation: `tx.process` or `tx.receive`
+
+**Grafana dashboard**: _Transaction Overview_ (`rippled-transactions`)
+
+#### Consensus Spans
+
+Controlled by `trace_consensus=1` in `[telemetry]` config.
+
+| Span Name                   | Parent | Source File      | Description                                   |
+| --------------------------- | ------ | ---------------- | --------------------------------------------- |
+| `consensus.proposal.send`   | —      | RCLConsensus.cpp | Node broadcasts its transaction set proposal  |
+| `consensus.ledger_close`    | —      | RCLConsensus.cpp | Ledger close event triggered by consensus     |
+| `consensus.accept`          | —      | RCLConsensus.cpp | Consensus accepts a ledger (round complete)   |
+| `consensus.validation.send` | —      | RCLConsensus.cpp | Validation message sent after ledger accepted |
+| `consensus.accept.apply`    | —      | RCLConsensus.cpp | Ledger application with close time details    |
+
+**Where to find**: Jaeger → Operation: `consensus.*`
+
+**Grafana dashboard**: _Consensus Health_ (`rippled-consensus`)
+
+#### Ledger Spans
+
+Controlled by `trace_ledger=1` in `[telemetry]` config.
+
+| Span Name         | Parent | Source File      | Description                                    |
+| ----------------- | ------ | ---------------- | ---------------------------------------------- |
+| `ledger.build`    | —      | BuildLedger.cpp  | Build new ledger from accepted transaction set |
+| `ledger.validate` | —      | LedgerMaster.cpp | Ledger promoted to validated status            |
+| `ledger.store`    | —      | LedgerMaster.cpp | Ledger stored to database/history              |
+
+**Where to find**: Jaeger → Operation: `ledger.*`
+
+**Grafana dashboard**: _Ledger Operations_ (`rippled-ledger-ops`)
+
+#### Peer Spans
+
+Controlled by `trace_peer=1` in `[telemetry]` config. **Disabled by default** (high volume).
+
+| Span Name                 | Parent | Source File | Description                           |
+| ------------------------- | ------ | ----------- | ------------------------------------- |
+| `peer.proposal.receive`   | —      | PeerImp.cpp | Consensus proposal received from peer |
+| `peer.validation.receive` | —      | PeerImp.cpp | Validation message received from peer |
+
+**Where to find**: Jaeger → Operation: `peer.*`
+
+**Grafana dashboard**: _Peer Network_ (`rippled-peer-net`)
+
+---
+
+### 1.2 Complete Attribute Inventory (22 attributes)
+
+> **See also**: [02-design-decisions.md §2.4.2](./02-design-decisions.md#242-span-attributes-by-category) for attribute design rationale and privacy considerations.
+
+Every span can carry key-value attributes that provide context for filtering and aggregation.
+
+#### RPC Attributes
+
+| Attribute                | Type   | Set On          | Description                                      |
+| ------------------------ | ------ | --------------- | ------------------------------------------------ |
+| `xrpl.rpc.command`       | string | `rpc.command.*` | RPC command name (e.g., `server_info`, `ledger`) |
+| `xrpl.rpc.version`       | int64  | `rpc.command.*` | API version number                               |
+| `xrpl.rpc.role`          | string | `rpc.command.*` | Caller role: `"admin"` or `"user"`               |
+| `xrpl.rpc.status`        | string | `rpc.command.*` | Result: `"success"` or `"error"`                 |
+| `xrpl.rpc.duration_ms`   | int64  | `rpc.command.*` | Command execution time in milliseconds           |
+| `xrpl.rpc.error_message` | string | `rpc.command.*` | Error details (only set on failure)              |
+
+**Jaeger query**: Tag `xrpl.rpc.command=server_info` to find all `server_info` calls.
+
+**Prometheus label**: `xrpl_rpc_command` (dots converted to underscores by SpanMetrics).
+
+#### Transaction Attributes
+
+| Attribute            | Type    | Set On                     | Description                                          |
+| -------------------- | ------- | -------------------------- | ---------------------------------------------------- |
+| `xrpl.tx.hash`       | string  | `tx.process`, `tx.receive` | Transaction hash (hex-encoded)                       |
+| `xrpl.tx.local`      | boolean | `tx.process`               | `true` if locally submitted, `false` if peer-relayed |
+| `xrpl.tx.path`       | string  | `tx.process`               | Submission path: `"sync"` or `"async"`               |
+| `xrpl.tx.suppressed` | boolean | `tx.receive`               | `true` if transaction was suppressed (duplicate)     |
+| `xrpl.tx.status`     | string  | `tx.receive`               | Transaction status (e.g., `"known_bad"`)             |
+
+**Jaeger query**: Tag `xrpl.tx.hash=<hash>` to trace a specific transaction across nodes.
+
+**Prometheus label**: `xrpl_tx_local` (used as SpanMetrics dimension).
+
+#### Consensus Attributes
+
+| Attribute                            | Type    | Set On                                                                                              | Description                                                   |
+| ------------------------------------ | ------- | --------------------------------------------------------------------------------------------------- | ------------------------------------------------------------- |
+| `xrpl.consensus.round`               | int64   | `consensus.proposal.send`                                                                           | Consensus round number                                        |
+| `xrpl.consensus.mode`                | string  | `consensus.proposal.send`, `consensus.ledger_close`                                                 | Node mode: `"syncing"`, `"tracking"`, `"full"`, `"proposing"` |
+| `xrpl.consensus.proposers`           | int64   | `consensus.proposal.send`, `consensus.accept`                                                       | Number of proposers in the round                              |
+| `xrpl.consensus.proposing`           | boolean | `consensus.validation.send`                                                                         | Whether this node was a proposer                              |
+| `xrpl.consensus.ledger.seq`          | int64   | `consensus.ledger_close`, `consensus.accept`, `consensus.validation.send`, `consensus.accept.apply` | Ledger sequence number                                        |
+| `xrpl.consensus.close_time`          | int64   | `consensus.accept.apply`                                                                            | Agreed-upon ledger close time (epoch seconds)                 |
+| `xrpl.consensus.close_time_correct`  | boolean | `consensus.accept.apply`                                                                            | Whether validators reached agreement on close time            |
+| `xrpl.consensus.close_resolution_ms` | int64   | `consensus.accept.apply`                                                                            | Close time rounding granularity in milliseconds               |
+| `xrpl.consensus.state`               | string  | `consensus.accept.apply`                                                                            | Consensus outcome: `"finished"` or `"moved_on"`               |
+| `xrpl.consensus.round_time_ms`       | int64   | `consensus.accept.apply`                                                                            | Total consensus round duration in milliseconds                |
+
+**Jaeger query**: Tag `xrpl.consensus.mode=proposing` to find rounds where node was proposing.
+
+**Prometheus label**: `xrpl_consensus_mode` (used as SpanMetrics dimension).
+
+#### Ledger Attributes
+
+| Attribute                 | Type  | Set On                                                        | Description                                    |
+| ------------------------- | ----- | ------------------------------------------------------------- | ---------------------------------------------- |
+| `xrpl.ledger.seq`         | int64 | `ledger.build`, `ledger.validate`, `ledger.store`, `tx.apply` | Ledger sequence number                         |
+| `xrpl.ledger.validations` | int64 | `ledger.validate`                                             | Number of validations received for this ledger |
+| `xrpl.ledger.tx_count`    | int64 | `ledger.build`, `tx.apply`                                    | Transactions in the ledger                     |
+| `xrpl.ledger.tx_failed`   | int64 | `ledger.build`, `tx.apply`                                    | Failed transactions in the ledger              |
+
+**Jaeger query**: Tag `xrpl.ledger.seq=12345` to find all spans for a specific ledger.
+
+#### Peer Attributes
+
+| Attribute                      | Type    | Set On                                                           | Description                                          |
+| ------------------------------ | ------- | ---------------------------------------------------------------- | ---------------------------------------------------- |
+| `xrpl.peer.id`                 | int64   | `tx.receive`, `peer.proposal.receive`, `peer.validation.receive` | Peer identifier                                      |
+| `xrpl.peer.proposal.trusted`   | boolean | `peer.proposal.receive`                                          | Whether the proposal came from a trusted validator   |
+| `xrpl.peer.validation.trusted` | boolean | `peer.validation.receive`                                        | Whether the validation came from a trusted validator |
+
+**Prometheus labels**: `xrpl_peer_proposal_trusted`, `xrpl_peer_validation_trusted` (SpanMetrics dimensions).
+
+---
+
+### 1.3 SpanMetrics — Derived Prometheus Metrics
+
+> **See also**: [01-architecture-analysis.md](./01-architecture-analysis.md) §1.8.2 for how span-derived metrics map to operational insights.
+
+The OTel Collector's SpanMetrics connector automatically generates RED (Rate, Errors, Duration) metrics from every span. No custom metrics code in rippled is needed.
+
+| Prometheus Metric                                  | Type      | Description                                                                    |
+| -------------------------------------------------- | --------- | ------------------------------------------------------------------------------ |
+| `traces_span_metrics_calls_total`                  | Counter   | Total span invocations                                                         |
+| `traces_span_metrics_duration_milliseconds_bucket` | Histogram | Latency distribution (buckets: 1, 5, 10, 25, 50, 100, 250, 500, 1000, 5000 ms) |
+| `traces_span_metrics_duration_milliseconds_count`  | Histogram | Observation count                                                              |
+| `traces_span_metrics_duration_milliseconds_sum`    | Histogram | Cumulative latency                                                             |
+
+**Standard labels on every metric**: `span_name`, `status_code`, `service_name`, `span_kind`
+
+**Additional dimension labels** (configured in `otel-collector-config.yaml`):
+
+| Span Attribute                 | Prometheus Label               | Applies To                |
+| ------------------------------ | ------------------------------ | ------------------------- |
+| `xrpl.rpc.command`             | `xrpl_rpc_command`             | `rpc.command.*`           |
+| `xrpl.rpc.status`              | `xrpl_rpc_status`              | `rpc.command.*`           |
+| `xrpl.consensus.mode`          | `xrpl_consensus_mode`          | `consensus.ledger_close`  |
+| `xrpl.tx.local`                | `xrpl_tx_local`                | `tx.process`              |
+| `xrpl.peer.proposal.trusted`   | `xrpl_peer_proposal_trusted`   | `peer.proposal.receive`   |
+| `xrpl.peer.validation.trusted` | `xrpl_peer_validation_trusted` | `peer.validation.receive` |
+
+**Where to query**: Prometheus → `traces_span_metrics_calls_total{span_name="rpc.command.server_info"}`
+
+---
+
+## 2. System Metrics (beast::insight — OTel native)
+
+> **See also**: [02-design-decisions.md](./02-design-decisions.md) for the beast::insight coexistence design. [06-implementation-phases.md](./06-implementation-phases.md) for the Phase 6/7 metric inventory.
+>
+> **Migration complete**: Phase 7 replaced the StatsD UDP transport with native OTel Metrics SDK export via OTLP/HTTP. The `beast::insight::Collector` interface and all metric names are preserved — only the wire protocol changed. `[insight] server=statsd` remains as a fallback.
+
+These are system-level metrics emitted by rippled's `beast::insight` framework via OTel OTLP/HTTP. They cover operational data that doesn't map to individual trace spans.
+
+### Configuration
+
+```ini
+# Recommended: native OTel metrics via OTLP/HTTP
+[insight]
+server=otel
+endpoint=http://localhost:4318/v1/metrics
+prefix=rippled
+```
+
+Fallback (StatsD):
+
+```ini
+[insight]
+server=statsd
+address=127.0.0.1:8125
+prefix=rippled
+```
+
+### 2.1 Gauges
+
+| Prometheus Metric                                   | Source File           | Description                              | Typical Range                   |
+| --------------------------------------------------- | --------------------- | ---------------------------------------- | ------------------------------- |
+| `rippled_LedgerMaster_Validated_Ledger_Age`         | LedgerMaster.h        | Seconds since last validated ledger      | 0–10 (healthy), >30 (stale)     |
+| `rippled_LedgerMaster_Published_Ledger_Age`         | LedgerMaster.h        | Seconds since last published ledger      | 0–10 (healthy)                  |
+| `rippled_State_Accounting_Disconnected_duration`    | NetworkOPs.cpp        | Cumulative seconds in Disconnected state | Monotonic                       |
+| `rippled_State_Accounting_Connected_duration`       | NetworkOPs.cpp        | Cumulative seconds in Connected state    | Monotonic                       |
+| `rippled_State_Accounting_Syncing_duration`         | NetworkOPs.cpp        | Cumulative seconds in Syncing state      | Monotonic                       |
+| `rippled_State_Accounting_Tracking_duration`        | NetworkOPs.cpp        | Cumulative seconds in Tracking state     | Monotonic                       |
+| `rippled_State_Accounting_Full_duration`            | NetworkOPs.cpp        | Cumulative seconds in Full state         | Monotonic (should dominate)     |
+| `rippled_State_Accounting_Disconnected_transitions` | NetworkOPs.cpp        | Count of transitions to Disconnected     | Low                             |
+| `rippled_State_Accounting_Connected_transitions`    | NetworkOPs.cpp        | Count of transitions to Connected        | Low                             |
+| `rippled_State_Accounting_Syncing_transitions`      | NetworkOPs.cpp        | Count of transitions to Syncing          | Low                             |
+| `rippled_State_Accounting_Tracking_transitions`     | NetworkOPs.cpp        | Count of transitions to Tracking         | Low                             |
+| `rippled_State_Accounting_Full_transitions`         | NetworkOPs.cpp        | Count of transitions to Full             | Low (should be 1 after startup) |
+| `rippled_Peer_Finder_Active_Inbound_Peers`          | PeerfinderManager.cpp | Active inbound peer connections          | 0–85                            |
+| `rippled_Peer_Finder_Active_Outbound_Peers`         | PeerfinderManager.cpp | Active outbound peer connections         | 10–21                           |
+| `rippled_Overlay_Peer_Disconnects`                  | OverlayImpl.cpp       | Cumulative peer disconnection count      | Low growth                      |
+| `rippled_job_count`                                 | JobQueue.cpp          | Current job queue depth                  | 0–100 (healthy)                 |
+
+**Grafana dashboard**: _Node Health (System Metrics)_ (`rippled-system-node-health`)
+
+### 2.2 Counters
+
+| Prometheus Metric                 | Source File        | Description                                   |
+| --------------------------------- | ------------------ | --------------------------------------------- |
+| `rippled_rpc_requests`            | ServerHandler.cpp  | Total RPC requests received                   |
+| `rippled_ledger_fetches`          | InboundLedgers.cpp | Inbound ledger fetch attempts                 |
+| `rippled_ledger_history_mismatch` | LedgerHistory.cpp  | Ledger hash mismatches detected               |
+| `rippled_warn`                    | Logic.h            | Resource manager warnings issued              |
+| `rippled_drop`                    | Logic.h            | Resource manager drops (connections rejected) |
+
+**Note**: With `server=otel`, `rippled_warn` and `rippled_drop` are properly exported as OTel Counter instruments. The previous StatsD `|m` type limitation no longer applies.
+
+**Grafana dashboard**: _RPC & Pathfinding (System Metrics)_ (`rippled-system-rpc`)
+
+### 2.3 Histograms (Event timers)
+
+| Prometheus Metric       | Source File       | Unit  | Description                    |
+| ----------------------- | ----------------- | ----- | ------------------------------ |
+| `rippled_rpc_time`      | ServerHandler.cpp | ms    | RPC response time distribution |
+| `rippled_rpc_size`      | ServerHandler.cpp | bytes | RPC response size distribution |
+| `rippled_ios_latency`   | Application.cpp   | ms    | I/O service loop latency       |
+| `rippled_pathfind_fast` | PathRequests.h    | ms    | Fast pathfinding duration      |
+| `rippled_pathfind_full` | PathRequests.h    | ms    | Full pathfinding duration      |
+
+Quantiles collected: 0th, 50th, 90th, 95th, 99th, 100th percentile.
+
+**Grafana dashboards**: _Node Health_ (`ios_latency`), _RPC & Pathfinding_ (`rpc_time`, `rpc_size`, `pathfind_*`)
+
+### 2.4 Overlay Traffic Metrics
+
+For each of the 45+ overlay traffic categories (defined in `TrafficCount.h`), four gauges are emitted:
+
+- `rippled_{category}_Bytes_In`
+- `rippled_{category}_Bytes_Out`
+- `rippled_{category}_Messages_In`
+- `rippled_{category}_Messages_Out`
+
+**Key categories**:
+
+| Category                                                          | Description                |
+| ----------------------------------------------------------------- | -------------------------- |
+| `total`                                                           | All traffic aggregated     |
+| `overhead` / `overhead_overlay`                                   | Protocol overhead          |
+| `transactions` / `transactions_duplicate`                         | Transaction relay          |
+| `proposals` / `proposals_untrusted` / `proposals_duplicate`       | Consensus proposals        |
+| `validations` / `validations_untrusted` / `validations_duplicate` | Consensus validations      |
+| `ledger_data_get` / `ledger_data_share`                           | Ledger data exchange       |
+| `ledger_data_Transaction_Node_get/share`                          | Transaction node data      |
+| `ledger_data_Account_State_Node_get/share`                        | Account state node data    |
+| `ledger_data_Transaction_Set_candidate_get/share`                 | Transaction set candidates |
+| `getObject` / `haveTxSet` / `ledgerData`                          | Object requests            |
+| `ping` / `status`                                                 | Keepalive and status       |
+| `set_get`                                                         | Set requests               |
+
+**Grafana dashboards**: _Network Traffic_ (`rippled-system-network`), _Overlay Traffic Detail_ (`rippled-system-overlay-detail`), _Ledger Data & Sync_ (`rippled-system-ledger-sync`)
+
+---
+
+## 3. Grafana Dashboard Reference
+
+> **See also**: [05-configuration-reference.md](./05-configuration-reference.md) §5.8 for Grafana data source provisioning (Tempo, Jaeger, Prometheus) and TraceQL query examples.
+
+### 3.1 Span-Derived Dashboards (5)
+
+| Dashboard            | UID                    | Data Source              | Key Panels                                                                         |
+| -------------------- | ---------------------- | ------------------------ | ---------------------------------------------------------------------------------- |
+| RPC Performance      | `rippled-rpc-perf`     | Prometheus (SpanMetrics) | Request rate by command, p95 latency by command, error rate, heatmap, top commands |
+| Transaction Overview | `rippled-transactions` | Prometheus (SpanMetrics) | Processing rate, latency p95/p50, local vs relay split, apply duration, heatmap    |
+| Consensus Health     | `rippled-consensus`    | Prometheus (SpanMetrics) | Round duration p95/p50, proposals rate, close duration, mode timeline, heatmap     |
+| Ledger Operations    | `rippled-ledger-ops`   | Prometheus (SpanMetrics) | Build rate, build duration, validation rate, store rate, build vs close comparison |
+| Peer Network         | `rippled-peer-net`     | Prometheus (SpanMetrics) | Proposal receive rate, validation receive rate, trusted vs untrusted breakdown     |
+
+### 3.2 System Metrics Dashboards (5)
+
+| Dashboard              | UID                             | Data Source       | Key Panels                                                                        |
+| ---------------------- | ------------------------------- | ----------------- | --------------------------------------------------------------------------------- |
+| Node Health            | `rippled-system-node-health`    | Prometheus (OTLP) | Ledger age, operating mode, I/O latency, job queue, fetch rate                    |
+| Network Traffic        | `rippled-system-network`        | Prometheus (OTLP) | Active peers, disconnects, bytes in/out, messages in/out, traffic by category     |
+| RPC & Pathfinding      | `rippled-system-rpc`            | Prometheus (OTLP) | RPC rate, response time/size, pathfinding duration, resource warnings/drops       |
+| Overlay Traffic Detail | `rippled-system-overlay-detail` | Prometheus (OTLP) | Squelch, overhead, validator lists, set get/share, have/requested tx, proof paths |
+| Ledger Data & Sync     | `rippled-system-ledger-sync`    | Prometheus (OTLP) | Ledger data exchange, legacy ledger share/get, getobject by type, traffic heatmap |
+
+### 3.3 Accessing the Dashboards
+
+1. Open Grafana at **http://localhost:3000**
+2. Navigate to **Dashboards → rippled** folder
+3. All 10 dashboards are auto-provisioned from `docker/telemetry/grafana/dashboards/`
+
+---
+
+## 4. Jaeger Trace Search Guide
+
+> **See also**: [08-appendix.md](./08-appendix.md) §8.2 for span hierarchy visualizations. [05-configuration-reference.md](./05-configuration-reference.md) §5.8.5 for TraceQL examples when using Grafana Tempo instead of Jaeger.
+
+### Finding Traces by Type
+
+| What to Find             | Jaeger Search Parameters                                   |
+| ------------------------ | ---------------------------------------------------------- |
+| All RPC calls            | Service: `rippled`, Operation: `rpc.request`               |
+| Specific RPC command     | Operation: `rpc.command.server_info` (or any command name) |
+| Slow RPC calls           | Operation: `rpc.command.*`, Min Duration: `100ms`          |
+| Failed RPC calls         | Tag: `xrpl.rpc.status=error`                               |
+| Specific transaction     | Tag: `xrpl.tx.hash=<hex_hash>`                             |
+| Local transactions only  | Tag: `xrpl.tx.local=true`                                  |
+| Consensus rounds         | Operation: `consensus.accept`                              |
+| Rounds by mode           | Tag: `xrpl.consensus.mode=proposing`                       |
+| Specific ledger          | Tag: `xrpl.ledger.seq=12345`                               |
+| Peer proposals (trusted) | Tag: `xrpl.peer.proposal.trusted=true`                     |
+
+### Trace Structure
+
+A typical RPC trace shows the span hierarchy:
+
+```
+rpc.request (ServerHandler)
+  └── rpc.process (ServerHandler)
+       └── rpc.command.server_info (RPCHandler)
+```
+
+A consensus round produces independent spans (not parent-child):
+
+```
+consensus.ledger_close        (close event)
+consensus.proposal.send       (broadcast proposal)
+ledger.build                  (build new ledger)
+  └── tx.apply                (apply transaction set)
+consensus.accept              (accept result)
+consensus.validation.send     (send validation)
+ledger.validate               (promote to validated)
+ledger.store                  (persist to DB)
+```
+
+---
+
+## 5. Prometheus Query Examples
+
+> **See also**: [05-configuration-reference.md](./05-configuration-reference.md) §5.8.7 for correlating Prometheus system metrics with trace-derived metrics.
+
+### Span-Derived Metrics
+
+```promql
+# RPC request rate by command (last 5 minutes)
+sum by (xrpl_rpc_command) (rate(traces_span_metrics_calls_total{span_name=~"rpc.command.*"}[5m]))
+
+# RPC p95 latency by command
+histogram_quantile(0.95, sum by (le, xrpl_rpc_command) (rate(traces_span_metrics_duration_milliseconds_bucket{span_name=~"rpc.command.*"}[5m])))
+
+# Consensus round duration p95
+histogram_quantile(0.95, sum by (le) (rate(traces_span_metrics_duration_milliseconds_bucket{span_name="consensus.accept"}[5m])))
+
+# Transaction processing rate (local vs relay)
+sum by (xrpl_tx_local) (rate(traces_span_metrics_calls_total{span_name="tx.process"}[5m]))
+
+# Trusted vs untrusted proposal rate
+sum by (xrpl_peer_proposal_trusted) (rate(traces_span_metrics_calls_total{span_name="peer.proposal.receive"}[5m]))
+```
+
+### StatsD Metrics
+
+```promql
+# Validated ledger age (should be < 10s)
+rippled_LedgerMaster_Validated_Ledger_Age
+
+# Active peer count
+rippled_Peer_Finder_Active_Inbound_Peers + rippled_Peer_Finder_Active_Outbound_Peers
+
+# RPC response time p95
+histogram_quantile(0.95, rippled_rpc_time_bucket)
+
+# Total network bytes in (rate)
+rate(rippled_total_Bytes_In[5m])
+
+# Operating mode (should be "Full" after startup)
+rippled_State_Accounting_Full_duration
+```
+
+---
+
+## 5a. Log-Trace Correlation (Phase 8)
+
+> **Plan details**: [06-implementation-phases.md §6.8.1](./06-implementation-phases.md) — motivation, architecture, Mermaid diagrams
+> **Task breakdown**: [Phase8_taskList.md](./Phase8_taskList.md) — per-task implementation details
+
+Phase 8 injects OTel trace context into rippled's `Logs::format()` output, enabling log-trace correlation. When a log line is emitted within an active OTel span, the trace and span identifiers are automatically appended after the severity field:
+
+### Log Format
+
+```
+<timestamp> <partition>:<severity> trace_id=<32hex> span_id=<16hex> <message>
+```
+
+Example:
+
+```
+2024-01-15T10:30:45.123Z LedgerMaster:NFO trace_id=abc123def456789012345678abcdef01 span_id=0123456789abcdef Validated ledger 42
+```
+
+- **`trace_id=<hex32>`** — 32-character lowercase hex trace identifier. Links to the distributed trace in Tempo/Jaeger.
+- **`span_id=<hex16>`** — 16-character lowercase hex span identifier. Identifies the specific span within the trace.
+- **Only present** when the log is emitted within an active OTel span. Log lines outside of traced code paths have no trace context fields.
+
+### Implementation
+
+The trace context injection is implemented in `Logs::format()` (`src/libxrpl/basics/Log.cpp`), guarded by `#ifdef XRPL_ENABLE_TELEMETRY`. It reads the current span from OTel's thread-local runtime context via `opentelemetry::trace::GetSpan()` and `opentelemetry::context::RuntimeContext::GetCurrent()`. Both calls are lock-free thread-local reads measured at <10ns per call.
+
+### Log Ingestion Pipeline
+
+```
+rippled debug.log -> OTel Collector filelog receiver -> regex_parser -> Loki exporter -> Grafana Loki
+```
+
+The OTel Collector's `filelog` receiver tails `debug.log` files and uses a `regex_parser` operator to extract structured fields:
+
+| Field       | Type     | Description                                              |
+| ----------- | -------- | -------------------------------------------------------- |
+| `timestamp` | datetime | Log timestamp                                            |
+| `partition` | string   | Log partition (e.g., `LedgerMaster`, `PeerImp`)          |
+| `severity`  | string   | Severity code (`TRC`, `DBG`, `NFO`, `WRN`, `ERR`, `FTL`) |
+| `trace_id`  | string   | 32-hex trace identifier (optional)                       |
+| `span_id`   | string   | 16-hex span identifier (optional)                        |
+| `message`   | string   | Log message body                                         |
+
+### Grafana Correlation
+
+Bidirectional linking between logs and traces is configured via Grafana datasource provisioning:
+
+- **Tempo -> Loki** (`tracesToLogs`): Clicking "Logs for this trace" on a Tempo trace view filters Loki logs by `trace_id`, showing all log lines from that trace.
+- **Loki -> Tempo** (`derivedFields`): A regex-based derived field on the Loki datasource extracts `trace_id` from log lines and renders it as a clickable link to the corresponding trace in Tempo.
+
+### Loki Backend
+
+Grafana Loki (v2.9.0) serves as the log storage backend. It receives log entries from the OTel Collector's `loki` exporter via the push API at `http://loki:3100/loki/api/v1/push`.
+
+### LogQL Query Examples
+
+```logql
+# Find all logs for a specific trace
+{job="rippled"} |= "trace_id=abc123def456789012345678abcdef01"
+
+# Error logs with trace context
+{job="rippled"} |= "ERR" |= "trace_id="
+
+# Logs from a specific partition with trace context
+{job="rippled"} |= "LedgerMaster" | regexp `trace_id=(?P<trace_id>[a-f0-9]+)` | trace_id != ""
+
+# Count traced log lines over time
+count_over_time({job="rippled"} |= "trace_id=" [5m])
+```
+
+---
+
+## 5b. Future: Internal Metric Gap Fill (Phase 9)
+
+> **Status**: Planned, not yet implemented.
+> **Plan details**: [06-implementation-phases.md §6.8.2](./06-implementation-phases.md) — motivation, architecture, third-party context
+> **Task breakdown**: [Phase9_taskList.md](./Phase9_taskList.md) — per-task implementation details
+
+Phase 9 fills ~50+ metrics that exist inside rippled but currently lack time-series export. Uses a hybrid approach: `beast::insight` extensions for NodeStore I/O, OTel `ObservableGauge` async callbacks for new categories.
+
+### New Metric Categories
+
+#### NodeStore I/O (via beast::insight)
+
+| Prometheus Metric                    | Type  | Description                         |
+| ------------------------------------ | ----- | ----------------------------------- |
+| `rippled_nodestore_reads_total`      | Gauge | Cumulative read operations          |
+| `rippled_nodestore_reads_hit`        | Gauge | Cache-served reads                  |
+| `rippled_nodestore_writes`           | Gauge | Cumulative write operations         |
+| `rippled_nodestore_written_bytes`    | Gauge | Cumulative bytes written            |
+| `rippled_nodestore_read_bytes`       | Gauge | Cumulative bytes read               |
+| `rippled_nodestore_read_duration_us` | Gauge | Cumulative read time (microseconds) |
+| `rippled_nodestore_write_load`       | Gauge | Current write load score            |
+| `rippled_nodestore_read_queue`       | Gauge | Items in read queue                 |
+
+#### Cache Hit Rates (via OTel MetricsRegistry)
+
+| Prometheus Metric               | Type  | Description                          |
+| ------------------------------- | ----- | ------------------------------------ |
+| `rippled_cache_SLE_hit_rate`    | Gauge | SLE cache hit rate (0.0-1.0)         |
+| `rippled_cache_ledger_hit_rate` | Gauge | Ledger object cache hit rate         |
+| `rippled_cache_AL_hit_rate`     | Gauge | AcceptedLedger cache hit rate        |
+| `rippled_cache_treenode_size`   | Gauge | SHAMap TreeNode cache size (entries) |
+| `rippled_cache_fullbelow_size`  | Gauge | FullBelow cache size                 |
+
+#### Transaction Queue (via OTel MetricsRegistry)
+
+| Prometheus Metric                      | Type  | Description                      |
+| -------------------------------------- | ----- | -------------------------------- |
+| `rippled_txq_count`                    | Gauge | Current transactions in queue    |
+| `rippled_txq_max_size`                 | Gauge | Maximum queue capacity           |
+| `rippled_txq_in_ledger`                | Gauge | Transactions in open ledger      |
+| `rippled_txq_per_ledger`               | Gauge | Expected transactions per ledger |
+| `rippled_txq_open_ledger_fee_level`    | Gauge | Open ledger fee escalation level |
+| `rippled_txq_med_fee_level`            | Gauge | Median fee level in queue        |
+| `rippled_txq_reference_fee_level`      | Gauge | Reference fee level              |
+| `rippled_txq_min_processing_fee_level` | Gauge | Minimum fee to get processed     |
+
+#### PerfLog Per-RPC Method (via OTel Metrics SDK)
+
+| Prometheus Metric                       | Type      | Labels            | Description                 |
+| --------------------------------------- | --------- | ----------------- | --------------------------- |
+| `rippled_rpc_method_started_total`      | Counter   | `method="<name>"` | RPC calls started           |
+| `rippled_rpc_method_finished_total`     | Counter   | `method="<name>"` | RPC calls completed         |
+| `rippled_rpc_method_errored_total`      | Counter   | `method="<name>"` | RPC calls errored           |
+| `rippled_rpc_method_duration_us_bucket` | Histogram | `method="<name>"` | Execution time distribution |
+
+#### PerfLog Per-Job Type (via OTel Metrics SDK)
+
+| Prometheus Metric                        | Type      | Labels              | Description     |
+| ---------------------------------------- | --------- | ------------------- | --------------- |
+| `rippled_job_queued_total`               | Counter   | `job_type="<name>"` | Jobs queued     |
+| `rippled_job_started_total`              | Counter   | `job_type="<name>"` | Jobs started    |
+| `rippled_job_finished_total`             | Counter   | `job_type="<name>"` | Jobs completed  |
+| `rippled_job_queued_duration_us_bucket`  | Histogram | `job_type="<name>"` | Queue wait time |
+| `rippled_job_running_duration_us_bucket` | Histogram | `job_type="<name>"` | Execution time  |
+
+#### Counted Object Instances (via OTel MetricsRegistry)
+
+| Prometheus Metric      | Type  | Labels          | Description                     |
+| ---------------------- | ----- | --------------- | ------------------------------- |
+| `rippled_object_count` | Gauge | `type="<name>"` | Live instances of internal type |
+
+Tracked types: `Transaction`, `Ledger`, `NodeObject`, `STTx`, `STLedgerEntry`, `InboundLedger`, `Pathfinder`, `PathRequest`, `HashRouterEntry`
+
+#### Fee Escalation & Load Factors (via OTel MetricsRegistry)
+
+| Prometheus Metric                    | Type  | Description                          |
+| ------------------------------------ | ----- | ------------------------------------ |
+| `rippled_load_factor`                | Gauge | Combined transaction cost multiplier |
+| `rippled_load_factor_server`         | Gauge | Server + cluster + network load      |
+| `rippled_load_factor_local`          | Gauge | Local server load only               |
+| `rippled_load_factor_net`            | Gauge | Network-wide load estimate           |
+| `rippled_load_factor_cluster`        | Gauge | Cluster peer load                    |
+| `rippled_load_factor_fee_escalation` | Gauge | Open ledger fee escalation           |
+| `rippled_load_factor_fee_queue`      | Gauge | Queue entry fee level                |
+
+### New Grafana Dashboards (Phase 9)
+
+| Dashboard          | UID                  | Data Source | Key Panels                                                        |
+| ------------------ | -------------------- | ----------- | ----------------------------------------------------------------- |
+| Fee Market & TxQ   | `rippled-fee-market` | Prometheus  | TxQ depth/capacity, fee levels, load factor breakdown, escalation |
+| Job Queue Analysis | `rippled-job-queue`  | Prometheus  | Per-job rates, queue wait times, execution times, queue depth     |
+
+---
+
+## 5c. Future: Synthetic Workload Generation & Telemetry Validation (Phase 10)
+
+> **Plan details**: [06-implementation-phases.md §6.8.3](./06-implementation-phases.md) — motivation, architecture
+> **Task breakdown**: [Phase10_taskList.md](./Phase10_taskList.md) — per-task implementation details
+> **Tools**: [docker/telemetry/workload/](../docker/telemetry/workload/) — RPC load generator, transaction submitter, validation suite, benchmarks
+
+Phase 10 builds a 5-node validator docker-compose harness with RPC load generators, transaction submitters, and automated validation scripts that verify all spans, metrics, dashboards, and log-trace correlation work end-to-end. Includes a benchmark suite comparing telemetry-ON vs telemetry-OFF overhead.
+
+### Running the Validation Suite
+
+```bash
+# Full end-to-end validation (start cluster, generate load, validate):
+docker/telemetry/workload/run-full-validation.sh --xrpld .build/xrpld
+
+# Validation only (assumes stack and cluster are already running):
+python3 docker/telemetry/workload/validate_telemetry.py --report /tmp/report.json
+
+# Performance benchmark (baseline vs telemetry):
+docker/telemetry/workload/benchmark.sh --xrpld .build/xrpld --duration 300
+```
+
+### Validated Telemetry Inventory
+
+| Category           | Expected Count | Validation Method                | Config File             |
+| ------------------ | -------------- | -------------------------------- | ----------------------- |
+| Trace spans        | 17             | Jaeger/Tempo API query           | `expected_spans.json`   |
+| Span attributes    | 22             | Per-span attribute assertion     | `expected_spans.json`   |
+| StatsD metrics     | 255+           | Prometheus query                 | `expected_metrics.json` |
+| Phase 9 metrics    | 50+            | Prometheus query                 | `expected_metrics.json` |
+| SpanMetrics RED    | 4 per span     | Prometheus query                 | `expected_metrics.json` |
+| Grafana dashboards | 10             | Dashboard API "no data" check    | `expected_metrics.json` |
+| Log-trace links    | Present        | Loki query + Tempo reverse check | —                       |
+
+### Performance Overhead Targets
+
+| Metric            | Target       | Measurement Method                  |
+| ----------------- | ------------ | ----------------------------------- |
+| CPU overhead      | < 3%         | ps avg CPU% baseline vs telemetry   |
+| Memory overhead   | < 5MB        | ps peak RSS baseline vs telemetry   |
+| RPC p99 latency   | < 2ms impact | server_info round-trip timing       |
+| Throughput impact | < 5%         | Ledger close rate comparison        |
+| Consensus impact  | < 1%         | Consensus round time p95 comparison |
+
+---
+
+## 5d. Future: Third-Party Data Collection Pipelines (Phase 11)
+
+> **Status**: Planned, not yet implemented.
+> **Plan details**: [06-implementation-phases.md §6.8.4](./06-implementation-phases.md) — motivation, architecture, consumer gap analysis
+> **Task breakdown**: [Phase11_taskList.md](./Phase11_taskList.md) — per-task implementation details
+
+Phase 11 builds a custom OTel Collector receiver (Go) that polls rippled's admin RPCs and exports `xrpl_*` metrics for external consumers. No rippled code changes.
+
+### Exported Metrics (via Custom OTel Collector Receiver)
+
+#### Node Health (from server_info)
+
+| Prometheus Metric                       | Type  | Description                                     |
+| --------------------------------------- | ----- | ----------------------------------------------- |
+| `xrpl_server_state`                     | Gauge | Operating mode (0=disconnected ... 5=proposing) |
+| `xrpl_server_state_duration_seconds`    | Gauge | Seconds in current state                        |
+| `xrpl_uptime_seconds`                   | Gauge | Consecutive seconds running                     |
+| `xrpl_io_latency_ms`                    | Gauge | I/O subsystem latency                           |
+| `xrpl_amendment_blocked`                | Gauge | 1 if amendment-blocked, 0 otherwise             |
+| `xrpl_peers_count`                      | Gauge | Connected peers                                 |
+| `xrpl_validated_ledger_seq`             | Gauge | Latest validated ledger sequence                |
+| `xrpl_validated_ledger_age_seconds`     | Gauge | Seconds since last validated close              |
+| `xrpl_last_close_proposers`             | Gauge | Proposers in last consensus round               |
+| `xrpl_last_close_converge_time_seconds` | Gauge | Last consensus round duration                   |
+| `xrpl_load_factor`                      | Gauge | Transaction cost multiplier                     |
+| `xrpl_state_duration_seconds`           | Gauge | Per-state duration (`state` label)              |
+| `xrpl_state_transitions_total`          | Gauge | Per-state transition count (`state` label)      |
+
+#### Peer Topology (from peers)
+
+| Prometheus Metric           | Type  | Description                         |
+| --------------------------- | ----- | ----------------------------------- |
+| `xrpl_peers_inbound_count`  | Gauge | Inbound peer connections            |
+| `xrpl_peers_outbound_count` | Gauge | Outbound peer connections           |
+| `xrpl_peer_latency_p50_ms`  | Gauge | Median peer latency                 |
+| `xrpl_peer_latency_p95_ms`  | Gauge | p95 peer latency                    |
+| `xrpl_peer_version_count`   | Gauge | Peers per version (`version` label) |
+| `xrpl_peer_diverged_count`  | Gauge | Peers with diverged tracking status |
+
+#### Validator & Amendment (from validators, feature)
+
+| Prometheus Metric                     | Type  | Description                             |
+| ------------------------------------- | ----- | --------------------------------------- |
+| `xrpl_trusted_validators_count`       | Gauge | UNL validator count                     |
+| `xrpl_amendment_enabled_count`        | Gauge | Enabled amendments                      |
+| `xrpl_amendment_majority_count`       | Gauge | Amendments with majority                |
+| `xrpl_amendment_unsupported_majority` | Gauge | 1 if unsupported amendment has majority |
+| `xrpl_validator_list_active`          | Gauge | 1 if validator list is active           |
+
+#### Fee Market (from fee)
+
+| Prometheus Metric                | Type  | Description                           |
+| -------------------------------- | ----- | ------------------------------------- |
+| `xrpl_fee_open_ledger_fee_drops` | Gauge | Minimum fee for open ledger inclusion |
+| `xrpl_fee_median_fee_drops`      | Gauge | Median fee level                      |
+| `xrpl_fee_queue_size`            | Gauge | Current transaction queue depth       |
+| `xrpl_fee_current_ledger_size`   | Gauge | Transactions in current open ledger   |
+
+#### DEX & AMM (optional, from book_offers, amm_info)
+
+| Prometheus Metric          | Type  | Labels                | Description            |
+| -------------------------- | ----- | --------------------- | ---------------------- |
+| `xrpl_amm_tvl_drops`       | Gauge | `pool="<id>"`         | Total value locked     |
+| `xrpl_amm_trading_fee`     | Gauge | `pool="<id>"`         | Pool trading fee (bps) |
+| `xrpl_orderbook_bid_depth` | Gauge | `pair="<base/quote>"` | Total bid volume       |
+| `xrpl_orderbook_ask_depth` | Gauge | `pair="<base/quote>"` | Total ask volume       |
+| `xrpl_orderbook_spread`    | Gauge | `pair="<base/quote>"` | Best bid-ask spread    |
+
+### Phase 9: OTel SDK-Exported Metrics (MetricsRegistry)
+
+Phase 9 introduces the `MetricsRegistry` class (`src/xrpld/telemetry/MetricsRegistry.h/.cpp`)
+which registers metrics directly with the OpenTelemetry Metrics SDK. These are exported
+via OTLP/HTTP to the OTel Collector and scraped by Prometheus.
+
+#### NodeStore I/O (Observable Gauge — `nodestore_state`)
+
+| Prometheus Metric                                      | Type  | Labels   | Description                          |
+| ------------------------------------------------------ | ----- | -------- | ------------------------------------ |
+| `rippled_nodestore_state{metric="node_reads_total"}`   | Gauge | `metric` | Cumulative NodeStore read operations |
+| `rippled_nodestore_state{metric="node_reads_hit"}`     | Gauge | `metric` | Reads served from cache              |
+| `rippled_nodestore_state{metric="node_writes"}`        | Gauge | `metric` | Cumulative write operations          |
+| `rippled_nodestore_state{metric="node_written_bytes"}` | Gauge | `metric` | Cumulative bytes written             |
+| `rippled_nodestore_state{metric="node_read_bytes"}`    | Gauge | `metric` | Cumulative bytes read                |
+| `rippled_nodestore_state{metric="write_load"}`         | Gauge | `metric` | Current write load score             |
+| `rippled_nodestore_state{metric="read_queue"}`         | Gauge | `metric` | Items in read prefetch queue         |
+
+#### Cache Hit Rates & Sizes (Observable Gauge — `cache_metrics`)
+
+| Prometheus Metric                                     | Type  | Labels   | Description                   |
+| ----------------------------------------------------- | ----- | -------- | ----------------------------- |
+| `rippled_cache_metrics{metric="SLE_hit_rate"}`        | Gauge | `metric` | SLE cache hit rate (0.0-1.0)  |
+| `rippled_cache_metrics{metric="ledger_hit_rate"}`     | Gauge | `metric` | Ledger cache hit rate         |
+| `rippled_cache_metrics{metric="AL_hit_rate"}`         | Gauge | `metric` | AcceptedLedger cache hit rate |
+| `rippled_cache_metrics{metric="treenode_cache_size"}` | Gauge | `metric` | SHAMap TreeNode cache entries |
+| `rippled_cache_metrics{metric="treenode_track_size"}` | Gauge | `metric` | Tracked tree nodes            |
+| `rippled_cache_metrics{metric="fullbelow_size"}`      | Gauge | `metric` | FullBelow cache entries       |
+
+#### Transaction Queue (Observable Gauge — `txq_metrics`)
+
+| Prometheus Metric                                            | Type  | Labels   | Description                      |
+| ------------------------------------------------------------ | ----- | -------- | -------------------------------- |
+| `rippled_txq_metrics{metric="txq_count"}`                    | Gauge | `metric` | Transactions currently in queue  |
+| `rippled_txq_metrics{metric="txq_max_size"}`                 | Gauge | `metric` | Maximum queue capacity           |
+| `rippled_txq_metrics{metric="txq_in_ledger"}`                | Gauge | `metric` | Transactions in open ledger      |
+| `rippled_txq_metrics{metric="txq_per_ledger"}`               | Gauge | `metric` | Expected transactions per ledger |
+| `rippled_txq_metrics{metric="txq_reference_fee_level"}`      | Gauge | `metric` | Reference fee level              |
+| `rippled_txq_metrics{metric="txq_min_processing_fee_level"}` | Gauge | `metric` | Minimum fee to get processed     |
+| `rippled_txq_metrics{metric="txq_med_fee_level"}`            | Gauge | `metric` | Median fee level in queue        |
+| `rippled_txq_metrics{metric="txq_open_ledger_fee_level"}`    | Gauge | `metric` | Open ledger fee escalation level |
+
+#### Per-RPC Method Metrics (Synchronous Counters/Histogram)
+
+| Prometheus Metric                   | Type      | Labels            | Description                      |
+| ----------------------------------- | --------- | ----------------- | -------------------------------- |
+| `rippled_rpc_method_started_total`  | Counter   | `method="<name>"` | RPC calls started                |
+| `rippled_rpc_method_finished_total` | Counter   | `method="<name>"` | RPC calls completed successfully |
+| `rippled_rpc_method_errored_total`  | Counter   | `method="<name>"` | RPC calls that errored           |
+| `rippled_rpc_method_duration_us`    | Histogram | `method="<name>"` | Execution time distribution (us) |
+
+#### Per-Job-Type Metrics (Synchronous Counters/Histogram)
+
+| Prometheus Metric                 | Type      | Labels              | Description                       |
+| --------------------------------- | --------- | ------------------- | --------------------------------- |
+| `rippled_job_queued_total`        | Counter   | `job_type="<name>"` | Jobs enqueued                     |
+| `rippled_job_started_total`       | Counter   | `job_type="<name>"` | Jobs started                      |
+| `rippled_job_finished_total`      | Counter   | `job_type="<name>"` | Jobs completed                    |
+| `rippled_job_queued_duration_us`  | Histogram | `job_type="<name>"` | Queue wait time distribution (us) |
+| `rippled_job_running_duration_us` | Histogram | `job_type="<name>"` | Execution time distribution (us)  |
+
+#### Counted Object Instances (Observable Gauge — `object_count`)
+
+| Prometheus Metric                              | Type  | Labels          | Description                    |
+| ---------------------------------------------- | ----- | --------------- | ------------------------------ |
+| `rippled_object_count{type="Transaction"}`     | Gauge | `type="<name>"` | Live Transaction objects       |
+| `rippled_object_count{type="Ledger"}`          | Gauge | `type="<name>"` | Live Ledger objects            |
+| `rippled_object_count{type="NodeObject"}`      | Gauge | `type="<name>"` | Live NodeObject instances      |
+| `rippled_object_count{type="STTx"}`            | Gauge | `type="<name>"` | Serialized transaction objects |
+| `rippled_object_count{type="STLedgerEntry"}`   | Gauge | `type="<name>"` | Serialized ledger entries      |
+| `rippled_object_count{type="InboundLedger"}`   | Gauge | `type="<name>"` | Ledgers being fetched          |
+| `rippled_object_count{type="Pathfinder"}`      | Gauge | `type="<name>"` | Active pathfinding operations  |
+| `rippled_object_count{type="PathRequest"}`     | Gauge | `type="<name>"` | Active path requests           |
+| `rippled_object_count{type="HashRouterEntry"}` | Gauge | `type="<name>"` | Hash router entries            |
+
+#### Load Factor Breakdown (Observable Gauge — `load_factor_metrics`)
+
+| Prometheus Metric                                                  | Type  | Labels   | Description                             |
+| ------------------------------------------------------------------ | ----- | -------- | --------------------------------------- |
+| `rippled_load_factor_metrics{metric="load_factor"}`                | Gauge | `metric` | Combined transaction cost multiplier    |
+| `rippled_load_factor_metrics{metric="load_factor_server"}`         | Gauge | `metric` | Server + cluster + network contribution |
+| `rippled_load_factor_metrics{metric="load_factor_local"}`          | Gauge | `metric` | Local server load only                  |
+| `rippled_load_factor_metrics{metric="load_factor_net"}`            | Gauge | `metric` | Network-wide load estimate              |
+| `rippled_load_factor_metrics{metric="load_factor_cluster"}`        | Gauge | `metric` | Cluster peer load                       |
+| `rippled_load_factor_metrics{metric="load_factor_fee_escalation"}` | Gauge | `metric` | Open ledger fee escalation              |
+| `rippled_load_factor_metrics{metric="load_factor_fee_queue"}`      | Gauge | `metric` | Queue entry fee level                   |
+
+#### Prometheus Query Examples (Phase 9)
+
+```promql
+# NodeStore cache hit ratio
+rippled_nodestore_state{metric="node_reads_hit"} / rippled_nodestore_state{metric="node_reads_total"}
+
+# RPC error rate for server_info
+rate(rippled_rpc_method_errored_total{method="server_info"}[5m])
+
+# Job queue wait time p95
+histogram_quantile(0.95, sum by (le) (rate(rippled_job_queued_duration_us_bucket[5m])))
+
+# TxQ utilization percentage
+rippled_txq_metrics{metric="txq_count"} / rippled_txq_metrics{metric="txq_max_size"}
+
+# High load factor alert candidate
+rippled_load_factor_metrics{metric="load_factor"} > 5
+```
+
+### New Grafana Dashboards (Phase 9)
+
+| Dashboard              | UID                  | Data Source | Key Panels                                                |
+| ---------------------- | -------------------- | ----------- | --------------------------------------------------------- |
+| Fee Market & TxQ       | `rippled-fee-market` | Prometheus  | TxQ depth/capacity, fee levels, load factor breakdown     |
+| Job Queue Analysis     | `rippled-job-queue`  | Prometheus  | Per-job rates, queue wait times, execution times          |
+| RPC Performance (OTel) | `rippled-rpc-perf`   | Prometheus  | Per-method call rates, error rates, latency distributions |
+
+### Updated Grafana Dashboards (Phase 9)
+
+| Dashboard            | UID                          | New Panels Added                                       |
+| -------------------- | ---------------------------- | ------------------------------------------------------ |
+| Node Health (StatsD) | `rippled-statsd-node-health` | NodeStore I/O, cache hit rates, object instance counts |
+
+### New Grafana Dashboards (Phase 11)
+
+| Dashboard          | UID                           | Data Source | Key Panels                                                             |
+| ------------------ | ----------------------------- | ----------- | ---------------------------------------------------------------------- |
+| Validator Health   | `rippled-validator-health`    | Prometheus  | Server state timeline, proposer count, converge time, amendment voting |
+| Network Topology   | `rippled-network-topology`    | Prometheus  | Peer count, version distribution, latency distribution, diverged peers |
+| Fee Market (Ext)   | `rippled-fee-market-external` | Prometheus  | Fee levels, queue depth, load factor breakdown, escalation timeline    |
+| DEX & AMM Overview | `rippled-dex-amm`             | Prometheus  | AMM TVL, order book depth, spread trends, trading fee revenue          |
+
+### Prometheus Alerting Rules (Phase 11)
+
+| Alert Name                         | Severity | Condition                                                   | For |
+| ---------------------------------- | -------- | ----------------------------------------------------------- | --- |
+| `XRPLServerNotFull`                | Critical | `xrpl_server_state < 4` for 15m                             | 15m |
+| `XRPLAmendmentBlocked`             | Critical | `xrpl_amendment_blocked == 1`                               | 1m  |
+| `XRPLNoPeers`                      | Critical | `xrpl_peers_count == 0`                                     | 5m  |
+| `XRPLLedgerStale`                  | Critical | `xrpl_validated_ledger_age_seconds > 120`                   | 2m  |
+| `XRPLHighIOLatency`                | Critical | `xrpl_io_latency_ms > 100`                                  | 5m  |
+| `XRPLUnsupportedAmendmentMajority` | Critical | `xrpl_amendment_unsupported_majority == 1`                  | 1m  |
+| `XRPLLowPeerCount`                 | Warning  | `xrpl_peers_count < 10`                                     | 15m |
+| `XRPLHighLoadFactor`               | Warning  | `xrpl_load_factor > 10`                                     | 10m |
+| `XRPLSlowConsensus`                | Warning  | `xrpl_last_close_converge_time_seconds > 6`                 | 5m  |
+| `XRPLValidatorListExpiring`        | Warning  | `(xrpl_validator_list_expiration_seconds - time()) < 86400` | 1h  |
+| `XRPLStateFlapping`                | Warning  | `rate(xrpl_state_transitions_total{state="full"}[1h]) > 2`  | 30m |
+
+---
+
+## 6. Known Issues
+
+| Issue                                                              | Impact                                           | Status                                                               |
+| ------------------------------------------------------------------ | ------------------------------------------------ | -------------------------------------------------------------------- |
+| `warn` and `drop` metrics use non-standard StatsD `\|m` meter type | Metrics silently dropped by OTel StatsD receiver | Phase 6 Task 6.1 — needs `\|m` → `\|c` change in StatsDCollector.cpp |
+| `rippled_job_count` may not emit in standalone mode                | Missing from Prometheus in some test configs     | Requires active job queue activity                                   |
+| `rippled_rpc_requests` depends on `[insight]` config               | Zero series if StatsD not configured             | Requires `[insight] server=statsd` in xrpld.cfg                      |
+| Peer tracing disabled by default                                   | No `peer.*` spans unless `trace_peer=1`          | Intentional — high volume on mainnet                                 |
+
+---
+
+## 7. Privacy and Data Collection
+
+The telemetry system is designed with privacy in mind:
+
+- **No private keys** are ever included in spans or metrics
+- **No account balances** or financial data is traced
+- **Transaction hashes** are included (public on-ledger data) but not transaction contents
+- **Peer IDs** are internal identifiers, not IP addresses
+- **All telemetry is opt-in** — disabled by default at build time (`-Dtelemetry=OFF`)
+- **Sampling** reduces data volume — `sampling_ratio=0.01` recommended for production
+- **Data stays local** — the default stack sends data to `localhost` only
+
+---
+
+## 8. Configuration Quick Reference
+
+> **Full reference**: [05-configuration-reference.md](./05-configuration-reference.md) §5.1 for all `[telemetry]` options with defaults, the config parser implementation, and collector YAML configurations (dev and production).
+
+### Minimal Setup (development)
+
+```ini
+[telemetry]
+enabled=1
+
+[insight]
+server=statsd
+address=127.0.0.1:8125
+prefix=rippled
+```
+
+### Production Setup
+
+```ini
+[telemetry]
+enabled=1
+endpoint=http://otel-collector:4318/v1/traces
+sampling_ratio=0.01
+trace_peer=0
+batch_size=1024
+max_queue_size=4096
+
+[insight]
+server=statsd
+address=otel-collector:8125
+prefix=rippled
+```
+
+### Trace Category Toggle
+
+| Config Key           | Default | Controls                     |
+| -------------------- | ------- | ---------------------------- |
+| `trace_rpc`          | `1`     | `rpc.*` spans                |
+| `trace_transactions` | `1`     | `tx.*` spans                 |
+| `trace_consensus`    | `1`     | `consensus.*` spans          |
+| `trace_ledger`       | `1`     | `ledger.*` spans             |
+| `trace_peer`         | `0`     | `peer.*` spans (high volume) |

OpenTelemetryPlan/OpenTelemetryPlan.md

@@ -0,0 +1,205 @@
+# [OpenTelemetry](00-tracing-fundamentals.md) Distributed Tracing Implementation Plan for rippled (xrpld)
+
+## Executive Summary
+
+This document provides a comprehensive implementation plan for integrating OpenTelemetry distributed tracing into the rippled XRP Ledger node software. The plan addresses the unique challenges of a decentralized peer-to-peer system where trace context must propagate across network boundaries between independent nodes.
+
+### Key Benefits
+
+- **End-to-end transaction visibility**: Track transactions from submission through consensus to ledger inclusion
+- **Consensus round analysis**: Understand timing and behavior of consensus phases across validators
+- **RPC performance insights**: Identify slow handlers and optimize response times
+- **Network topology understanding**: Visualize message propagation patterns between peers
+- **Incident debugging**: Correlate events across distributed nodes during issues
+
+### Estimated Performance Overhead
+
+| Metric        | Overhead   | Notes                               |
+| ------------- | ---------- | ----------------------------------- |
+| CPU           | 1-3%       | Span creation and attribute setting |
+| Memory        | 2-5 MB     | Batch buffer for pending spans      |
+| Network       | 10-50 KB/s | Compressed OTLP export to collector |
+| Latency (p99) | <2%        | With proper sampling configuration  |
+
+---
+
+## Document Structure
+
+This implementation plan is organized into modular documents for easier navigation:
+
+<div align="center">
+
+```mermaid
+flowchart TB
+    overview["📋 OpenTelemetryPlan.md<br/>(This Document)"]
+
+    subgraph analysis["Analysis & Design"]
+        arch["01-architecture-analysis.md"]
+        design["02-design-decisions.md"]
+    end
+
+    subgraph impl["Implementation"]
+        strategy["03-implementation-strategy.md"]
+        code["04-code-samples.md"]
+        config["05-configuration-reference.md"]
+    end
+
+    subgraph deploy["Deployment & Planning"]
+        phases["06-implementation-phases.md"]
+        backends["07-observability-backends.md"]
+        appendix["08-appendix.md"]
+        dataref["09-data-collection-reference.md"]
+    end
+
+    overview --> analysis
+    overview --> impl
+    overview --> deploy
+
+    arch --> design
+    design --> strategy
+    strategy --> code
+    code --> config
+    config --> phases
+    phases --> backends
+    backends --> appendix
+    appendix --> dataref
+
+    style overview fill:#1b5e20,stroke:#0d3d14,color:#fff,stroke-width:2px
+    style analysis fill:#0d47a1,stroke:#082f6a,color:#fff
+    style impl fill:#bf360c,stroke:#8c2809,color:#fff
+    style deploy fill:#4a148c,stroke:#2e0d57,color:#fff
+    style arch fill:#0d47a1,stroke:#082f6a,color:#fff
+    style design fill:#0d47a1,stroke:#082f6a,color:#fff
+    style strategy fill:#bf360c,stroke:#8c2809,color:#fff
+    style code fill:#bf360c,stroke:#8c2809,color:#fff
+    style config fill:#bf360c,stroke:#8c2809,color:#fff
+    style phases fill:#4a148c,stroke:#2e0d57,color:#fff
+    style backends fill:#4a148c,stroke:#2e0d57,color:#fff
+    style appendix fill:#4a148c,stroke:#2e0d57,color:#fff
+    style dataref fill:#4a148c,stroke:#2e0d57,color:#fff
+```
+
+</div>
+
+---
+
+## Table of Contents
+
+| Section | Document                                                       | Description                                                            |
+| ------- | -------------------------------------------------------------- | ---------------------------------------------------------------------- |
+| **1**   | [Architecture Analysis](./01-architecture-analysis.md)         | rippled component analysis, trace points, instrumentation priorities   |
+| **2**   | [Design Decisions](./02-design-decisions.md)                   | SDK selection, exporters, span naming, attributes, context propagation |
+| **3**   | [Implementation Strategy](./03-implementation-strategy.md)     | Directory structure, key principles, performance optimization          |
+| **4**   | [Code Samples](./04-code-samples.md)                           | Complete C++ implementation examples for all components                |
+| **5**   | [Configuration Reference](./05-configuration-reference.md)     | rippled config, CMake integration, Collector configurations            |
+| **6**   | [Implementation Phases](./06-implementation-phases.md)         | 5-phase timeline, tasks, risks, success metrics                        |
+| **7**   | [Observability Backends](./07-observability-backends.md)       | Backend selection guide and production architecture                    |
+| **8**   | [Appendix](./08-appendix.md)                                   | Glossary, references, version history                                  |
+| **9**   | [Data Collection Reference](./09-data-collection-reference.md) | Complete inventory of spans, attributes, metrics, and dashboards       |
+
+---
+
+## 1. Architecture Analysis
+
+The rippled node consists of several key components that require instrumentation for comprehensive distributed tracing. The main areas include the RPC server (HTTP/WebSocket), Overlay P2P network, Consensus mechanism (RCLConsensus), JobQueue for async task execution, and existing observability infrastructure (PerfLog, Insight/StatsD, Journal logging).
+
+Key trace points span across transaction submission via RPC, peer-to-peer message propagation, consensus round execution, and ledger building. The implementation prioritizes high-value, low-risk components first: RPC handlers provide immediate value with minimal risk, while consensus tracing requires careful implementation to avoid timing impacts.
+
+➡️ **[Read full Architecture Analysis](./01-architecture-analysis.md)**
+
+---
+
+## 2. Design Decisions
+
+The OpenTelemetry C++ SDK is selected for its CNCF backing, active development, and native performance characteristics. Traces are exported via OTLP/gRPC (primary) or OTLP/HTTP (fallback) to an OpenTelemetry Collector, which provides flexible routing and sampling.
+
+Span naming follows a hierarchical `<component>.<operation>` convention (e.g., `rpc.submit`, `tx.relay`, `consensus.round`). Context propagation uses W3C Trace Context headers for HTTP and embedded Protocol Buffer fields for P2P messages. The implementation coexists with existing PerfLog and Insight observability systems through correlation IDs.
+
+**Data Collection & Privacy**: Telemetry collects only operational metadata (timing, counts, hashes) — never sensitive content (private keys, balances, amounts, raw payloads). Privacy protection includes account hashing, configurable redaction, sampling, and collector-level filtering. Node operators retain full control(not penned down in this document yet) over what data is exported.
+
+➡️ **[Read full Design Decisions](./02-design-decisions.md)**
+
+---
+
+## 3. Implementation Strategy
+
+The telemetry code is organized under `include/xrpl/telemetry/` for headers and `src/libxrpl/telemetry/` for implementation. Key principles include RAII-based span management via `SpanGuard`, conditional compilation with `XRPL_ENABLE_TELEMETRY`, and minimal runtime overhead through batch processing and efficient sampling.
+
+Performance optimization strategies include probabilistic head sampling (10% default), tail-based sampling at the collector for errors and slow traces, batch export to reduce network overhead, and conditional instrumentation that compiles to no-ops when disabled.
+
+➡️ **[Read full Implementation Strategy](./03-implementation-strategy.md)**
+
+---
+
+## 4. Code Samples
+
+Complete C++ implementation examples are provided for all telemetry components:
+
+- `Telemetry.h` - Core interface for tracer access and span creation
+- `SpanGuard.h` - RAII wrapper for automatic span lifecycle management
+- `TracingInstrumentation.h` - Macros for conditional instrumentation
+- Protocol Buffer extensions for trace context propagation
+- Module-specific instrumentation (RPC, Consensus, P2P, JobQueue)
+
+➡️ **[View all Code Samples](./04-code-samples.md)**
+
+---
+
+## 5. Configuration Reference
+
+Configuration is handled through the `[telemetry]` section in `xrpld.cfg` with options for enabling/disabling, exporter selection, endpoint configuration, sampling ratios, and component-level filtering. CMake integration includes a `XRPL_ENABLE_TELEMETRY` option for compile-time control.
+
+OpenTelemetry Collector configurations are provided for development (with Jaeger) and production (with tail-based sampling, Tempo, and Elastic APM). Docker Compose examples enable quick local development environment setup.
+
+➡️ **[View full Configuration Reference](./05-configuration-reference.md)**
+
+---
+
+## 6. Implementation Phases
+
+The implementation spans 13 weeks across 8 phases:
+
+| Phase | Duration    | Focus                 | Key Deliverables                                            |
+| ----- | ----------- | --------------------- | ----------------------------------------------------------- |
+| 1     | Weeks 1-2   | Core Infrastructure   | SDK integration, Telemetry interface, Configuration         |
+| 2     | Weeks 3-4   | RPC Tracing           | HTTP context extraction, Handler instrumentation            |
+| 3     | Weeks 5-6   | Transaction Tracing   | Protocol Buffer context, Relay propagation                  |
+| 4     | Weeks 7-8   | Consensus Tracing     | Round spans, Proposal/validation tracing                    |
+| 5     | Week 9      | Documentation         | Runbook, Dashboards, Training                               |
+| 6     | Week 10     | StatsD Metrics Bridge | OTel Collector StatsD receiver, 3 Grafana dashboards        |
+| 7     | Weeks 11-12 | Native OTel Metrics   | OTelCollector impl, OTLP metrics export, StatsD deprecation |
+| 8     | Week 13     | Log-Trace Correlation | trace_id in logs, Loki ingestion, Tempo↔Loki linking        |
+
+**Total Effort**: 65.1 developer-days with 2 developers
+
+➡️ **[View full Implementation Phases](./06-implementation-phases.md)**
+
+---
+
+## 7. Observability Backends
+
+For development and testing, Jaeger provides easy setup with a good UI. For production deployments, Grafana Tempo is recommended for its cost-effectiveness and Grafana integration, while Elastic APM is ideal for organizations with existing Elastic infrastructure.
+
+The recommended production architecture uses a gateway collector pattern with regional collectors performing tail-based sampling, routing traces to multiple backends (Tempo for primary storage, Elastic for log correlation, S3/GCS for long-term archive).
+
+➡️ **[View Observability Backend Recommendations](./07-observability-backends.md)**
+
+---
+
+## 8. Appendix
+
+The appendix contains a glossary of OpenTelemetry and rippled-specific terms, references to external documentation and specifications, version history for this implementation plan, and a complete document index.
+
+➡️ **[View Appendix](./08-appendix.md)**
+
+---
+
+## 9. Data Collection Reference
+
+A single-source-of-truth reference documenting every piece of telemetry data collected by rippled. Covers all 16 OpenTelemetry spans with their 22 attributes, all StatsD metrics (gauges, counters, histograms, overlay traffic), SpanMetrics-derived Prometheus metrics, and all 8 Grafana dashboards. Includes Jaeger search guides and Prometheus query examples.
+
+➡️ **[View Data Collection Reference](./09-data-collection-reference.md)**
+
+---
+
+_This document provides a comprehensive implementation plan for integrating OpenTelemetry distributed tracing into the rippled XRP Ledger node software. For detailed information on any section, follow the links to the corresponding sub-documents._

OpenTelemetryPlan/POC_taskList.md

@@ -0,0 +1,610 @@
+# OpenTelemetry POC Task List
+
+> **Goal**: Build a minimal end-to-end proof of concept that demonstrates distributed tracing in rippled. A successful POC will show RPC request traces flowing from rippled through an OTel Collector into Jaeger, viewable in a browser UI.
+>
+> **Scope**: RPC tracing only (highest value, lowest risk per the [CRAWL phase](./06-implementation-phases.md#6102-quick-wins-immediate-value) in the implementation phases). No cross-node P2P context propagation or consensus tracing in the POC.
+
+### Related Plan Documents
+
+| Document                                                         | Relevance to POC                                                                                                                                          |
+| ---------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| [00-tracing-fundamentals.md](./00-tracing-fundamentals.md)       | Core concepts: traces, spans, context propagation, sampling                                                                                               |
+| [01-architecture-analysis.md](./01-architecture-analysis.md)     | RPC request flow (§1.5), key trace points (§1.6), instrumentation priority (§1.7)                                                                         |
+| [02-design-decisions.md](./02-design-decisions.md)               | SDK selection (§2.1), exporter config (§2.2), span naming (§2.3), attribute schema (§2.4), coexistence with PerfLog/Insight (§2.6)                        |
+| [03-implementation-strategy.md](./03-implementation-strategy.md) | Directory structure (§3.1), key principles (§3.2), performance overhead (§3.3-3.6), conditional compilation (§3.7.3), code intrusiveness (§3.9)           |
+| [04-code-samples.md](./04-code-samples.md)                       | Telemetry interface (§4.1), SpanGuard (§4.2), macros (§4.3), RPC instrumentation (§4.5.3)                                                                 |
+| [05-configuration-reference.md](./05-configuration-reference.md) | rippled config (§5.1), config parser (§5.2), Application integration (§5.3), CMake (§5.4), Collector config (§5.5), Docker Compose (§5.6), Grafana (§5.8) |
+| [06-implementation-phases.md](./06-implementation-phases.md)     | Phase 1 core tasks (§6.2), Phase 2 RPC tasks (§6.3), quick wins (§6.10), definition of done (§6.11)                                                       |
+| [07-observability-backends.md](./07-observability-backends.md)   | Jaeger dev setup (§7.1), Grafana dashboards (§7.6), alert rules (§7.6.3)                                                                                  |
+
+---
+
+## Task 0: Docker Observability Stack Setup
+
+**Objective**: Stand up the backend infrastructure to receive, store, and display traces.
+
+**What to do**:
+
+- Create `docker/telemetry/docker-compose.yml` in the repo with three services:
+  1. **OpenTelemetry Collector** (`otel/opentelemetry-collector-contrib:latest`)
+     - Expose ports `4317` (OTLP gRPC) and `4318` (OTLP HTTP)
+     - Expose port `13133` (health check)
+     - Mount a config file `docker/telemetry/otel-collector-config.yaml`
+  2. **Jaeger** (`jaegertracing/all-in-one:latest`)
+     - Expose port `16686` (UI) and `14250` (gRPC collector)
+     - Set env `COLLECTOR_OTLP_ENABLED=true`
+  3. **Grafana** (`grafana/grafana:latest`) — optional but useful
+     - Expose port `3000`
+     - Enable anonymous admin access for local dev (`GF_AUTH_ANONYMOUS_ENABLED=true`, `GF_AUTH_ANONYMOUS_ORG_ROLE=Admin`)
+     - Provision Jaeger as a data source via `docker/telemetry/grafana/provisioning/datasources/jaeger.yaml`
+
+- Create `docker/telemetry/otel-collector-config.yaml`:
+
+  ```yaml
+  receivers:
+    otlp:
+      protocols:
+        grpc:
+          endpoint: 0.0.0.0:4317
+        http:
+          endpoint: 0.0.0.0:4318
+
+  processors:
+    batch:
+      timeout: 1s
+      send_batch_size: 100
+
+  exporters:
+    logging:
+      verbosity: detailed
+    otlp/jaeger:
+      endpoint: jaeger:4317
+      tls:
+        insecure: true
+
+  service:
+    pipelines:
+      traces:
+        receivers: [otlp]
+        processors: [batch]
+        exporters: [logging, otlp/jaeger]
+  ```
+
+- Create Grafana Jaeger datasource provisioning file at `docker/telemetry/grafana/provisioning/datasources/jaeger.yaml`:
+  ```yaml
+  apiVersion: 1
+  datasources:
+    - name: Jaeger
+      type: jaeger
+      access: proxy
+      url: http://jaeger:16686
+  ```
+
+**Verification**: Run `docker compose -f docker/telemetry/docker-compose.yml up -d`, then:
+
+- `curl http://localhost:13133` returns healthy (Collector)
+- `http://localhost:16686` opens Jaeger UI (no traces yet)
+- `http://localhost:3000` opens Grafana (optional)
+
+**Reference**:
+
+- [05-configuration-reference.md §5.5](./05-configuration-reference.md) — Collector config (dev YAML with Jaeger exporter)
+- [05-configuration-reference.md §5.6](./05-configuration-reference.md) — Docker Compose development environment
+- [07-observability-backends.md §7.1](./07-observability-backends.md) — Jaeger quick start and backend selection
+- [05-configuration-reference.md §5.8](./05-configuration-reference.md) — Grafana datasource provisioning and dashboards
+
+---
+
+## Task 1: Add OpenTelemetry C++ SDK Dependency
+
+**Objective**: Make `opentelemetry-cpp` available to the build system.
+
+**What to do**:
+
+- Edit `conanfile.py` to add `opentelemetry-cpp` as an **optional** dependency. The gRPC otel plugin flag (`"grpc/*:otel_plugin": False`) in the existing conanfile may need to remain false — we pull the OTel SDK separately.
+  - Add a Conan option: `with_telemetry = [True, False]` defaulting to `False`
+  - When `with_telemetry` is `True`, add `opentelemetry-cpp` to `self.requires()`
+  - Required OTel Conan components: `opentelemetry-cpp` (which bundles api, sdk, and exporters). If the package isn't in Conan Center, consider using `FetchContent` in CMake or building from source as a fallback.
+- Edit `CMakeLists.txt`:
+  - Add option: `option(XRPL_ENABLE_TELEMETRY "Enable OpenTelemetry tracing" OFF)`
+  - When ON, `find_package(opentelemetry-cpp CONFIG REQUIRED)` and add compile definition `XRPL_ENABLE_TELEMETRY`
+  - When OFF, do nothing (zero build impact)
+- Verify the build succeeds with `-DXRPL_ENABLE_TELEMETRY=OFF` (no regressions) and with `-DXRPL_ENABLE_TELEMETRY=ON` (SDK links successfully).
+
+**Key files**:
+
+- `conanfile.py`
+- `CMakeLists.txt`
+
+**Reference**:
+
+- [05-configuration-reference.md §5.4](./05-configuration-reference.md) — CMake integration, `FindOpenTelemetry.cmake`, `XRPL_ENABLE_TELEMETRY` option
+- [03-implementation-strategy.md §3.2](./03-implementation-strategy.md) — Key principle: zero-cost when disabled via compile-time flags
+- [02-design-decisions.md §2.1](./02-design-decisions.md) — SDK selection rationale and required OTel components
+
+---
+
+## Task 2: Create Core Telemetry Interface and NullTelemetry
+
+**Objective**: Define the `Telemetry` abstract interface and a no-op implementation so the rest of the codebase can reference telemetry without hard-depending on the OTel SDK.
+
+**What to do**:
+
+- Create `include/xrpl/telemetry/Telemetry.h`:
+  - Define `namespace xrpl::telemetry`
+  - Define `struct Telemetry::Setup` holding: `enabled`, `exporterEndpoint`, `samplingRatio`, `serviceName`, `serviceVersion`, `serviceInstanceId`, `traceRpc`, `traceTransactions`, `traceConsensus`, `tracePeer`
+  - Define abstract `class Telemetry` with:
+    - `virtual void start() = 0;`
+    - `virtual void stop() = 0;`
+    - `virtual bool isEnabled() const = 0;`
+    - `virtual nostd::shared_ptr<Tracer> getTracer(string_view name = "rippled") = 0;`
+    - `virtual nostd::shared_ptr<Span> startSpan(string_view name, SpanKind kind = kInternal) = 0;`
+    - `virtual nostd::shared_ptr<Span> startSpan(string_view name, Context const& parentContext, SpanKind kind = kInternal) = 0;`
+    - `virtual bool shouldTraceRpc() const = 0;`
+    - `virtual bool shouldTraceTransactions() const = 0;`
+    - `virtual bool shouldTraceConsensus() const = 0;`
+  - Factory: `std::unique_ptr<Telemetry> make_Telemetry(Setup const&, beast::Journal);`
+  - Config parser: `Telemetry::Setup setup_Telemetry(Section const&, std::string const& nodePublicKey, std::string const& version);`
+
+- Create `include/xrpl/telemetry/SpanGuard.h`:
+  - RAII guard that takes an `nostd::shared_ptr<Span>`, creates a `Scope`, and calls `span->End()` in destructor.
+  - Convenience: `setAttribute()`, `setOk()`, `setStatus()`, `addEvent()`, `recordException()`, `context()`
+  - See [04-code-samples.md](./04-code-samples.md) §4.2 for the full implementation.
+
+- Create `src/libxrpl/telemetry/NullTelemetry.cpp`:
+  - Implements `Telemetry` with all no-ops.
+  - `isEnabled()` returns `false`, `startSpan()` returns a noop span.
+  - This is used when `XRPL_ENABLE_TELEMETRY` is OFF or `enabled=0` in config.
+
+- Guard all OTel SDK headers behind `#ifdef XRPL_ENABLE_TELEMETRY`. The `NullTelemetry` implementation should compile without the OTel SDK present.
+
+**Key new files**:
+
+- `include/xrpl/telemetry/Telemetry.h`
+- `include/xrpl/telemetry/SpanGuard.h`
+- `src/libxrpl/telemetry/NullTelemetry.cpp`
+
+**Reference**:
+
+- [04-code-samples.md §4.1](./04-code-samples.md) — Full `Telemetry` interface with `Setup` struct, lifecycle, tracer access, span creation, and component filtering methods
+- [04-code-samples.md §4.2](./04-code-samples.md) — Full `SpanGuard` RAII implementation and `NullSpanGuard` no-op class
+- [03-implementation-strategy.md §3.1](./03-implementation-strategy.md) — Directory structure: `include/xrpl/telemetry/` for headers, `src/libxrpl/telemetry/` for implementation
+- [03-implementation-strategy.md §3.7.3](./03-implementation-strategy.md) — Conditional instrumentation and zero-cost compile-time disabled pattern
+
+---
+
+## Task 3: Implement OTel-Backed Telemetry
+
+**Objective**: Implement the real `Telemetry` class that initializes the OTel SDK, configures the OTLP exporter and batch processor, and creates tracers/spans.
+
+**What to do**:
+
+- Create `src/libxrpl/telemetry/Telemetry.cpp` (compiled only when `XRPL_ENABLE_TELEMETRY=ON`):
+  - `class TelemetryImpl : public Telemetry` that:
+    - In `start()`: creates a `TracerProvider` with:
+      - Resource attributes: `service.name`, `service.version`, `service.instance.id`
+      - An `OtlpGrpcExporter` pointed at `setup.exporterEndpoint` (default `localhost:4317`)
+      - A `BatchSpanProcessor` with configurable batch size and delay
+      - A `TraceIdRatioBasedSampler` using `setup.samplingRatio`
+    - Sets the global `TracerProvider`
+    - In `stop()`: calls `ForceFlush()` then shuts down the provider
+    - In `startSpan()`: delegates to `getTracer()->StartSpan(name, ...)`
+    - `shouldTraceRpc()` etc. read from `Setup` fields
+
+- Create `src/libxrpl/telemetry/TelemetryConfig.cpp`:
+  - `setup_Telemetry()` parses the `[telemetry]` config section from `xrpld.cfg`
+  - Maps config keys: `enabled`, `exporter`, `endpoint`, `sampling_ratio`, `trace_rpc`, `trace_transactions`, `trace_consensus`, `trace_peer`
+
+- Wire `make_Telemetry()` factory:
+  - If `setup.enabled` is true AND `XRPL_ENABLE_TELEMETRY` is defined: return `TelemetryImpl`
+  - Otherwise: return `NullTelemetry`
+
+- Add telemetry source files to CMake. When `XRPL_ENABLE_TELEMETRY=ON`, compile `Telemetry.cpp` and `TelemetryConfig.cpp` and link against `opentelemetry-cpp::api`, `opentelemetry-cpp::sdk`, `opentelemetry-cpp::otlp_grpc_exporter`. When OFF, compile only `NullTelemetry.cpp`.
+
+**Key new files**:
+
+- `src/libxrpl/telemetry/Telemetry.cpp`
+- `src/libxrpl/telemetry/TelemetryConfig.cpp`
+
+**Key modified files**:
+
+- `CMakeLists.txt` (add telemetry library target)
+
+**Reference**:
+
+- [04-code-samples.md §4.1](./04-code-samples.md) — `Telemetry` interface that `TelemetryImpl` must implement
+- [05-configuration-reference.md §5.2](./05-configuration-reference.md) — `setup_Telemetry()` config parser implementation
+- [02-design-decisions.md §2.2](./02-design-decisions.md) — OTLP/gRPC exporter config (endpoint, TLS options)
+- [02-design-decisions.md §2.4.1](./02-design-decisions.md) — Resource attributes: `service.name`, `service.version`, `service.instance.id`, `xrpl.network.id`
+- [03-implementation-strategy.md §3.4](./03-implementation-strategy.md) — Per-operation CPU costs and overhead budget for span creation
+- [03-implementation-strategy.md §3.5](./03-implementation-strategy.md) — Memory overhead: static (~456 KB) and dynamic (~1.2 MB) budgets
+
+---
+
+## Task 4: Integrate Telemetry into Application Lifecycle
+
+**Objective**: Wire the `Telemetry` object into `Application` so all components can access it.
+
+**What to do**:
+
+- Edit `src/xrpld/app/main/Application.h`:
+  - Forward-declare `namespace xrpl::telemetry { class Telemetry; }`
+  - Add pure virtual method: `virtual telemetry::Telemetry& getTelemetry() = 0;`
+
+- Edit `src/xrpld/app/main/Application.cpp` (the `ApplicationImp` class):
+  - Add member: `std::unique_ptr<telemetry::Telemetry> telemetry_;`
+  - In the constructor, after config is loaded and node identity is known:
+    ```cpp
+    auto const telemetrySection = config_->section("telemetry");
+    auto telemetrySetup = telemetry::setup_Telemetry(
+        telemetrySection,
+        toBase58(TokenType::NodePublic, nodeIdentity_.publicKey()),
+        BuildInfo::getVersionString());
+    telemetry_ = telemetry::make_Telemetry(telemetrySetup, logs_->journal("Telemetry"));
+    ```
+  - In `start()`: call `telemetry_->start()` early
+  - In `stop()` or destructor: call `telemetry_->stop()` late (to flush pending spans)
+  - Implement `getTelemetry()` override: return `*telemetry_`
+
+- Add `[telemetry]` section to the example config `cfg/rippled-example.cfg`:
+  ```ini
+  # [telemetry]
+  # enabled=1
+  # endpoint=localhost:4317
+  # sampling_ratio=1.0
+  # trace_rpc=1
+  ```
+
+**Key modified files**:
+
+- `src/xrpld/app/main/Application.h`
+- `src/xrpld/app/main/Application.cpp`
+- `cfg/rippled-example.cfg` (or equivalent example config)
+
+**Reference**:
+
+- [05-configuration-reference.md §5.3](./05-configuration-reference.md) — `ApplicationImp` changes: member declaration, constructor init, `start()`/`stop()` wiring, `getTelemetry()` override
+- [05-configuration-reference.md §5.1](./05-configuration-reference.md) — `[telemetry]` config section format and all option defaults
+- [03-implementation-strategy.md §3.9.2](./03-implementation-strategy.md) — File impact assessment: `Application.cpp` ~15 lines added, ~3 changed (Low risk)
+
+---
+
+## Task 5: Create Instrumentation Macros
+
+**Objective**: Define convenience macros that make instrumenting code one-liners, and that compile to zero-cost no-ops when telemetry is disabled.
+
+**What to do**:
+
+- Create `src/xrpld/telemetry/TracingInstrumentation.h`:
+  - When `XRPL_ENABLE_TELEMETRY` is defined:
+
+    ```cpp
+    #define XRPL_TRACE_SPAN(telemetry, name) \
+        auto _xrpl_span_ = (telemetry).startSpan(name); \
+        ::xrpl::telemetry::SpanGuard _xrpl_guard_(_xrpl_span_)
+
+    #define XRPL_TRACE_RPC(telemetry, name) \
+        std::optional<::xrpl::telemetry::SpanGuard> _xrpl_guard_; \
+        if ((telemetry).shouldTraceRpc()) { \
+            _xrpl_guard_.emplace((telemetry).startSpan(name)); \
+        }
+
+    #define XRPL_TRACE_SET_ATTR(key, value) \
+        if (_xrpl_guard_.has_value()) { \
+            _xrpl_guard_->setAttribute(key, value); \
+        }
+
+    #define XRPL_TRACE_EXCEPTION(e) \
+        if (_xrpl_guard_.has_value()) { \
+            _xrpl_guard_->recordException(e); \
+        }
+    ```
+
+  - When `XRPL_ENABLE_TELEMETRY` is NOT defined, all macros expand to `((void)0)`
+
+**Key new file**:
+
+- `src/xrpld/telemetry/TracingInstrumentation.h`
+
+**Reference**:
+
+- [04-code-samples.md §4.3](./04-code-samples.md) — Full macro definitions for `XRPL_TRACE_SPAN`, `XRPL_TRACE_RPC`, `XRPL_TRACE_CONSENSUS`, `XRPL_TRACE_SET_ATTR`, `XRPL_TRACE_EXCEPTION` with both enabled and disabled branches
+- [03-implementation-strategy.md §3.7.3](./03-implementation-strategy.md) — Conditional instrumentation pattern: compile-time `#ifndef` and runtime `shouldTrace*()` checks
+- [03-implementation-strategy.md §3.9.7](./03-implementation-strategy.md) — Before/after code examples showing minimal intrusiveness (~1-3 lines per instrumentation point)
+
+---
+
+## Task 6: Instrument RPC ServerHandler
+
+**Objective**: Add tracing to the HTTP RPC entry point so every incoming RPC request creates a span.
+
+**What to do**:
+
+- Edit `src/xrpld/rpc/detail/ServerHandler.cpp`:
+  - `#include` the `TracingInstrumentation.h` header
+  - In `ServerHandler::onRequest(Session& session)`:
+    - At the top of the method, add: `XRPL_TRACE_RPC(app_.getTelemetry(), "rpc.request");`
+    - After the RPC command name is extracted, set attribute: `XRPL_TRACE_SET_ATTR("xrpl.rpc.command", command);`
+    - After the response status is known, set: `XRPL_TRACE_SET_ATTR("http.status_code", static_cast<int64_t>(statusCode));`
+    - Wrap error paths with: `XRPL_TRACE_EXCEPTION(e);`
+  - In `ServerHandler::processRequest(...)`:
+    - Add a child span: `XRPL_TRACE_RPC(app_.getTelemetry(), "rpc.process");`
+    - Set method attribute: `XRPL_TRACE_SET_ATTR("xrpl.rpc.method", request_method);`
+  - In `ServerHandler::onWSMessage(...)` (WebSocket path):
+    - Add: `XRPL_TRACE_RPC(app_.getTelemetry(), "rpc.ws.message");`
+
+- The goal is to see spans like:
+  ```
+  rpc.request
+    └── rpc.process
+  ```
+  in Jaeger for every HTTP RPC call.
+
+**Key modified file**:
+
+- `src/xrpld/rpc/detail/ServerHandler.cpp` (~15-25 lines added)
+
+**Reference**:
+
+- [04-code-samples.md §4.5.3](./04-code-samples.md) — Complete `ServerHandler::onRequest()` instrumented code sample with W3C header extraction, span creation, attribute setting, and error handling
+- [01-architecture-analysis.md §1.5](./01-architecture-analysis.md) — RPC request flow diagram: HTTP request -> attributes -> jobqueue.enqueue -> rpc.command -> response
+- [01-architecture-analysis.md §1.6](./01-architecture-analysis.md) — Key trace points table: `rpc.request` in `ServerHandler.cpp::onRequest()` (Priority: High)
+- [02-design-decisions.md §2.3](./02-design-decisions.md) — Span naming convention: `rpc.request`, `rpc.command.*`
+- [02-design-decisions.md §2.4.2](./02-design-decisions.md) — RPC span attributes: `xrpl.rpc.command`, `xrpl.rpc.version`, `xrpl.rpc.role`, `xrpl.rpc.params`
+- [03-implementation-strategy.md §3.9.2](./03-implementation-strategy.md) — File impact: `ServerHandler.cpp` ~40 lines added, ~10 changed (Low risk)
+
+---
+
+## Task 7: Instrument RPC Command Execution
+
+**Objective**: Add per-command tracing inside the RPC handler so each command (e.g., `submit`, `account_info`, `server_info`) gets its own child span.
+
+**What to do**:
+
+- Edit `src/xrpld/rpc/detail/RPCHandler.cpp`:
+  - `#include` the `TracingInstrumentation.h` header
+  - In `doCommand(RPC::JsonContext& context, Json::Value& result)`:
+    - At the top: `XRPL_TRACE_RPC(context.app.getTelemetry(), "rpc.command." + context.method);`
+    - Set attributes:
+      - `XRPL_TRACE_SET_ATTR("xrpl.rpc.command", context.method);`
+      - `XRPL_TRACE_SET_ATTR("xrpl.rpc.version", static_cast<int64_t>(context.apiVersion));`
+      - `XRPL_TRACE_SET_ATTR("xrpl.rpc.role", (context.role == Role::ADMIN) ? "admin" : "user");`
+    - On success: `XRPL_TRACE_SET_ATTR("xrpl.rpc.status", "success");`
+    - On error: `XRPL_TRACE_SET_ATTR("xrpl.rpc.status", "error");` and set the error message
+
+- After this, traces in Jaeger should look like:
+  ```
+  rpc.request  (xrpl.rpc.command=account_info)
+    └── rpc.process
+          └── rpc.command.account_info  (xrpl.rpc.version=2, xrpl.rpc.role=user, xrpl.rpc.status=success)
+  ```
+
+**Key modified file**:
+
+- `src/xrpld/rpc/detail/RPCHandler.cpp` (~15-20 lines added)
+
+**Reference**:
+
+- [04-code-samples.md §4.5.3](./04-code-samples.md) — `ServerHandler::onRequest()` code sample (includes child span pattern for `rpc.command.*`)
+- [02-design-decisions.md §2.3](./02-design-decisions.md) — Span naming: `rpc.command.*` pattern with dynamic command name (e.g., `rpc.command.server_info`)
+- [02-design-decisions.md §2.4.2](./02-design-decisions.md) — RPC attribute schema: `xrpl.rpc.command`, `xrpl.rpc.version`, `xrpl.rpc.role`, `xrpl.rpc.status`
+- [01-architecture-analysis.md §1.6](./01-architecture-analysis.md) — Key trace points table: `rpc.command.*` in `RPCHandler.cpp::doCommand()` (Priority: High)
+- [02-design-decisions.md §2.6.5](./02-design-decisions.md) — Correlation with PerfLog: how `doCommand()` can link trace_id with existing PerfLog entries
+- [03-implementation-strategy.md §3.4.4](./03-implementation-strategy.md) — RPC request overhead budget: ~1.75 μs total per request
+
+---
+
+## Task 8: Build, Run, and Verify End-to-End
+
+**Objective**: Prove the full pipeline works: rippled emits traces -> OTel Collector receives them -> Jaeger displays them.
+
+**What to do**:
+
+1. **Start the Docker stack**:
+
+   ```bash
+   docker compose -f docker/telemetry/docker-compose.yml up -d
+   ```
+
+   Verify Collector health: `curl http://localhost:13133`
+
+2. **Build rippled with telemetry**:
+
+   ```bash
+   # Adjust for your actual build workflow
+   conan install . --build=missing -o with_telemetry=True
+   cmake --preset default -DXRPL_ENABLE_TELEMETRY=ON
+   cmake --build --preset default
+   ```
+
+3. **Configure rippled**:
+   Add to `rippled.cfg` (or your local test config):
+
+   ```ini
+   [telemetry]
+   enabled=1
+   endpoint=localhost:4317
+   sampling_ratio=1.0
+   trace_rpc=1
+   ```
+
+4. **Start rippled** in standalone mode:
+
+   ```bash
+   ./rippled --conf rippled.cfg -a --start
+   ```
+
+5. **Generate RPC traffic**:
+
+   ```bash
+   # server_info
+   curl -s -X POST http://localhost:5005 \
+     -H "Content-Type: application/json" \
+     -d '{"method":"server_info","params":[{}]}'
+
+   # ledger
+   curl -s -X POST http://localhost:5005 \
+     -H "Content-Type: application/json" \
+     -d '{"method":"ledger","params":[{"ledger_index":"current"}]}'
+
+   # account_info (will error in standalone, that's fine — we trace errors too)
+   curl -s -X POST http://localhost:5005 \
+     -H "Content-Type: application/json" \
+     -d '{"method":"account_info","params":[{"account":"rHb9CJAWyB4rj91VRWn96DkukG4bwdtyTh"}]}'
+   ```
+
+6. **Verify in Jaeger**:
+   - Open `http://localhost:16686`
+   - Select service `rippled` from the dropdown
+   - Click "Find Traces"
+   - Confirm you see traces with spans: `rpc.request` -> `rpc.process` -> `rpc.command.server_info`
+   - Click into a trace and verify attributes: `xrpl.rpc.command`, `xrpl.rpc.status`, `xrpl.rpc.version`
+
+7. **Verify zero-overhead when disabled**:
+   - Rebuild with `XRPL_ENABLE_TELEMETRY=OFF`, or set `enabled=0` in config
+   - Run the same RPC calls
+   - Confirm no new traces appear and no errors in rippled logs
+
+**Verification Checklist**:
+
+- [ ] Docker stack starts without errors
+- [ ] rippled builds with `-DXRPL_ENABLE_TELEMETRY=ON`
+- [ ] rippled starts and connects to OTel Collector (check rippled logs for telemetry messages)
+- [ ] Traces appear in Jaeger UI under service "rippled"
+- [ ] Span hierarchy is correct (parent-child relationships)
+- [ ] Span attributes are populated (`xrpl.rpc.command`, `xrpl.rpc.status`, etc.)
+- [ ] Error spans show error status and message
+- [ ] Building with `XRPL_ENABLE_TELEMETRY=OFF` produces no regressions
+- [ ] Setting `enabled=0` at runtime produces no traces and no errors
+
+**Reference**:
+
+- [06-implementation-phases.md §6.11.1](./06-implementation-phases.md) — Phase 1 definition of done: SDK compiles, runtime toggle works, span creation verified in Jaeger, config validation passes
+- [06-implementation-phases.md §6.11.2](./06-implementation-phases.md) — Phase 2 definition of done: 100% RPC coverage, traceparent propagation, <1ms p99 overhead, dashboard deployed
+- [06-implementation-phases.md §6.8](./06-implementation-phases.md) — Success metrics: trace coverage >95%, CPU overhead <3%, memory <5 MB, latency impact <2%
+- [03-implementation-strategy.md §3.9.5](./03-implementation-strategy.md) — Backward compatibility: config optional, protocol unchanged, `XRPL_ENABLE_TELEMETRY=OFF` produces identical binary
+- [01-architecture-analysis.md §1.8](./01-architecture-analysis.md) — Observable outcomes: what traces, metrics, and dashboards to expect
+
+---
+
+## Task 9: Document POC Results and Next Steps
+
+**Objective**: Capture findings, screenshots, and remaining work for the team.
+
+**What to do**:
+
+- Take screenshots of Jaeger showing:
+  - The service list with "rippled"
+  - A trace with the full span tree
+  - Span detail view showing attributes
+- Document any issues encountered (build issues, SDK quirks, missing attributes)
+- Note performance observations (build time impact, any noticeable runtime overhead)
+- Write a short summary of what the POC proves and what it doesn't cover yet:
+  - **Proves**: OTel SDK integrates with rippled, OTLP export works, RPC traces visible
+  - **Doesn't cover**: Cross-node P2P context propagation, consensus tracing, protobuf trace context, W3C traceparent header extraction, tail-based sampling, production deployment
+- Outline next steps (mapping to the full plan phases):
+  - [Phase 2](./06-implementation-phases.md) completion: [W3C header extraction](./02-design-decisions.md) (§2.5), WebSocket tracing, all [RPC handlers](./01-architecture-analysis.md) (§1.6)
+  - [Phase 3](./06-implementation-phases.md): [Protobuf `TraceContext` message](./04-code-samples.md) (§4.4), [transaction relay tracing](./04-code-samples.md) (§4.5.1) across nodes
+  - [Phase 4](./06-implementation-phases.md): [Consensus round and phase tracing](./04-code-samples.md) (§4.5.2)
+  - [Phase 5](./06-implementation-phases.md): [Production collector config](./05-configuration-reference.md) (§5.5.2), [Grafana dashboards](./07-observability-backends.md) (§7.6), [alerting](./07-observability-backends.md) (§7.6.3)
+
+**Reference**:
+
+- [06-implementation-phases.md §6.1](./06-implementation-phases.md) — Full 5-phase timeline overview and Gantt chart
+- [06-implementation-phases.md §6.10](./06-implementation-phases.md) — Crawl-Walk-Run strategy: POC is the CRAWL phase, next steps are WALK and RUN
+- [06-implementation-phases.md §6.12](./06-implementation-phases.md) — Recommended implementation order (14 steps across 9 weeks)
+- [03-implementation-strategy.md §3.9](./03-implementation-strategy.md) — Code intrusiveness assessment and risk matrix for each remaining component
+- [07-observability-backends.md §7.2](./07-observability-backends.md) — Production backend selection (Tempo, Elastic APM, Honeycomb, Datadog)
+- [02-design-decisions.md §2.5](./02-design-decisions.md) — Context propagation design: W3C HTTP headers, protobuf P2P, JobQueue internal
+- [00-tracing-fundamentals.md](./00-tracing-fundamentals.md) — Reference for team onboarding on distributed tracing concepts
+
+---
+
+## Summary
+
+| Task | Description                          | New Files | Modified Files | Depends On |
+| ---- | ------------------------------------ | --------- | -------------- | ---------- |
+| 0    | Docker observability stack           | 4         | 0              | —          |
+| 1    | OTel C++ SDK dependency              | 0         | 2              | —          |
+| 2    | Core Telemetry interface + NullImpl  | 3         | 0              | 1          |
+| 3    | OTel-backed Telemetry implementation | 2         | 1              | 1, 2       |
+| 4    | Application lifecycle integration    | 0         | 3              | 2, 3       |
+| 5    | Instrumentation macros               | 1         | 0              | 2          |
+| 6    | Instrument RPC ServerHandler         | 0         | 1              | 4, 5       |
+| 7    | Instrument RPC command execution     | 0         | 1              | 4, 5       |
+| 8    | End-to-end verification              | 0         | 0              | 0-7        |
+| 9    | Document results and next steps      | 1         | 0              | 8          |
+
+**Parallel work**: Tasks 0 and 1 can run in parallel. Tasks 2 and 5 have no dependency on each other. Tasks 6 and 7 can be done in parallel once Tasks 4 and 5 are complete.
+
+---
+
+## Next Steps (Post-POC)
+
+### Metrics Pipeline for Grafana Dashboards
+
+The current POC exports **traces only**. Grafana's Explore view can query Jaeger for individual traces, but time-series charts (latency histograms, request throughput, error rates) require a **metrics pipeline**. To enable this:
+
+1. **Add a `spanmetrics` connector** to the OTel Collector config that derives RED metrics (Rate, Errors, Duration) from trace spans automatically:
+
+   ```yaml
+   connectors:
+     spanmetrics:
+       histogram:
+         explicit:
+           buckets: [1ms, 5ms, 10ms, 25ms, 50ms, 100ms, 250ms, 500ms, 1s, 5s]
+       dimensions:
+         - name: xrpl.rpc.command
+         - name: xrpl.rpc.status
+
+   exporters:
+     prometheus:
+       endpoint: 0.0.0.0:8889
+
+   service:
+     pipelines:
+       traces:
+         receivers: [otlp]
+         processors: [batch]
+         exporters: [debug, otlp/jaeger, spanmetrics]
+       metrics:
+         receivers: [spanmetrics]
+         exporters: [prometheus]
+   ```
+
+2. **Add Prometheus** to the Docker Compose stack to scrape the collector's metrics endpoint.
+
+3. **Add Prometheus as a Grafana datasource** and build dashboards for:
+   - RPC request latency (p50/p95/p99) by command
+   - RPC throughput (requests/sec) by command
+   - Error rate by command
+   - Span duration distribution
+
+### Additional Instrumentation
+
+- **W3C `traceparent` header extraction** in `ServerHandler` to support cross-service context propagation from external callers
+- **WebSocket RPC tracing** in `ServerHandler::onWSMessage()`
+- **Transaction relay tracing** across nodes using protobuf `TraceContext` messages
+- **Consensus round and phase tracing** for validator coordination visibility
+- **Ledger close tracing** to measure close-to-validated latency
+
+### Production Hardening
+
+- **Tail-based sampling** in the OTel Collector to reduce volume while retaining error/slow traces
+- **TLS configuration** for the OTLP exporter in production deployments
+- **Resource limits** on the batch processor queue to prevent unbounded memory growth
+- **Health monitoring** for the telemetry pipeline itself (collector lag, export failures)
+
+### POC Lessons Learned
+
+Issues encountered during POC implementation that inform future work:
+
+| Issue                                                                                              | Resolution                                                                    | Impact on Future Work                                            |
+| -------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------- | ---------------------------------------------------------------- |
+| Conan lockfile rejected `opentelemetry-cpp/1.18.0`                                                 | Used `--lockfile=""` to bypass                                                | Lockfile must be regenerated when adding new dependencies        |
+| Conan package only builds OTLP HTTP exporter, not gRPC                                             | Switched from gRPC to HTTP exporter (`localhost:4318/v1/traces`)              | HTTP exporter is the default; gRPC requires custom Conan profile |
+| CMake target `opentelemetry-cpp::api` etc. don't exist in Conan package                            | Use umbrella target `opentelemetry-cpp::opentelemetry-cpp`                    | Conan targets differ from upstream CMake targets                 |
+| OTel Collector `logging` exporter deprecated                                                       | Renamed to `debug` exporter                                                   | Use `debug` in all collector configs going forward               |
+| Macro parameter `telemetry` collided with `::xrpl::telemetry::` namespace                          | Renamed macro params to `_tel_obj_`, `_span_name_`                            | Avoid common words as macro parameter names                      |
+| `opentelemetry::trace::Scope` creates new context on move                                          | Store scope as member, create once in constructor                             | SpanGuard move semantics need care with Scope lifecycle          |
+| `TracerProviderFactory::Create` returns `unique_ptr<sdk::TracerProvider>`, not `nostd::shared_ptr` | Use `std::shared_ptr` member, wrap in `nostd::shared_ptr` for global provider | OTel SDK factory return types don't match API provider types     |

OpenTelemetryPlan/Phase10_taskList.md

@@ -0,0 +1,256 @@
+# Phase 10: Synthetic Workload Generation & Telemetry Validation — Task List
+
+> **Status**: Future Enhancement
+>
+> **Goal**: Build tools that generate realistic XRPL traffic to validate the full Phases 1-9 telemetry stack end-to-end — all spans, attributes, metrics, dashboards, and log-trace correlation — under controlled load.
+>
+> **Scope**: Python/shell test harness + multi-node docker-compose environment + automated validation scripts + performance benchmarks.
+>
+> **Branch**: `pratik/otel-phase10-workload-validation` (from `pratik/otel-phase9-metric-gap-fill`)
+>
+> **Depends on**: Phase 9 (internal metric gap fill) — validates the full metric surface
+
+### Related Plan Documents
+
+| Document                                                             | Relevance                                                       |
+| -------------------------------------------------------------------- | --------------------------------------------------------------- |
+| [06-implementation-phases.md](./06-implementation-phases.md)         | Phase 10 plan: motivation, architecture, exit criteria (§6.8.3) |
+| [09-data-collection-reference.md](./09-data-collection-reference.md) | Defines the full inventory of spans/metrics to validate         |
+| [Phase9_taskList.md](./Phase9_taskList.md)                           | Prerequisite — all internal metrics must be emitting            |
+
+### Why This Phase Exists
+
+Before Phases 1-9 can be considered production-ready, we need proof that:
+
+1. All 16 spans fire with correct attributes under real transaction workloads
+2. All 255+ StatsD metrics + ~50 Phase 9 metrics appear in Prometheus with non-zero values
+3. Log-trace correlation (Phase 8) produces clickable trace_id links in Loki
+4. All 10 Grafana dashboards render meaningful data (no empty panels)
+5. Performance overhead stays within bounds (< 3% CPU, < 5MB memory)
+6. The telemetry stack survives sustained load without data loss or queue backpressure
+
+---
+
+## Task 10.1: Multi-Node Test Harness
+
+**Objective**: Create a docker-compose environment with 3-5 validator nodes that produces real consensus rounds.
+
+**What to do**:
+
+- Create `docker/telemetry/docker-compose.workload.yaml`:
+  - 5 rippled validator nodes with UNL configured for each other
+  - All telemetry enabled: `[telemetry] enabled=1`, `[insight] server=otel`
+  - Full OTel stack: Collector, Jaeger, Tempo, Prometheus, Loki, Grafana
+  - Shared network with service discovery
+
+- Each node should:
+  - Generate validator keys at startup
+  - Configure all 5 nodes in its UNL
+  - Enable all trace categories including `trace_peer=1`
+  - Write logs to a file tailed by the OTel Collector filelog receiver
+
+- Include a `Makefile` target: `make telemetry-workload-up` / `make telemetry-workload-down`
+
+**Key files**:
+
+- New: `docker/telemetry/docker-compose.workload.yaml`
+- New: `docker/telemetry/workload/generate-validator-keys.sh`
+- New: `docker/telemetry/workload/xrpld-validator.cfg.template`
+
+---
+
+## Task 10.2: RPC Load Generator
+
+**Objective**: Configurable tool that fires all traced RPC commands at controlled rates.
+
+**What to do**:
+
+- Create `docker/telemetry/workload/rpc_load_generator.py`:
+  - Connects to one or more rippled WebSocket endpoints
+  - Fires all RPC commands that have trace spans: `server_info`, `ledger`, `tx`, `account_info`, `account_lines`, `fee`, `submit`, etc.
+  - Configurable parameters: rate (RPS), duration, command distribution weights
+  - Injects `traceparent` HTTP headers to test W3C context propagation
+  - Logs progress and errors to stdout
+
+- Command distribution should match realistic production ratios:
+  - 40% `server_info` / `fee` (health checks)
+  - 30% `account_info` / `account_lines` / `account_objects` (wallet queries)
+  - 15% `ledger` / `ledger_data` (explorer queries)
+  - 10% `tx` / `account_tx` (transaction lookups)
+  - 5% `book_offers` / `amm_info` (DEX queries)
+
+**Key files**:
+
+- New: `docker/telemetry/workload/rpc_load_generator.py`
+- New: `docker/telemetry/workload/requirements.txt`
+
+---
+
+## Task 10.3: Transaction Submitter
+
+**Objective**: Generate diverse transaction types to exercise `tx.*` and `ledger.*` spans.
+
+**What to do**:
+
+- Create `docker/telemetry/workload/tx_submitter.py`:
+  - Pre-funds test accounts from genesis account
+  - Submits a mix of transaction types:
+    - `Payment` (XRP and issued currencies) — exercises `tx.process`, `tx.apply`
+    - `OfferCreate` / `OfferCancel` — DEX activity
+    - `TrustSet` — trust line creation for issued currencies
+    - `NFTokenMint` / `NFTokenCreateOffer` / `NFTokenAcceptOffer` — NFT activity
+    - `EscrowCreate` / `EscrowFinish` — escrow lifecycle
+    - `AMMCreate` / `AMMDeposit` / `AMMWithdraw` — AMM pool operations (if amendment enabled)
+  - Configurable: TPS target, transaction mix weights, duration
+  - Monitors submission results and tracks success/failure rates
+
+- The transaction mix ensures the telemetry captures the full range of ledger activity that third parties care about.
+
+**Key files**:
+
+- New: `docker/telemetry/workload/tx_submitter.py`
+- New: `docker/telemetry/workload/test_accounts.json` (pre-generated keypairs)
+
+---
+
+## Task 10.4: Telemetry Validation Suite
+
+**Objective**: Automated scripts that verify all expected telemetry data exists after a workload run.
+
+**What to do**:
+
+- Create `docker/telemetry/workload/validate_telemetry.py`:
+
+  **Span validation** (queries Jaeger/Tempo API):
+  - Assert all 16 span names appear in traces
+  - Assert each span has its required attributes (22 total attributes across spans)
+  - Assert parent-child relationships are correct (`rpc.request` → `rpc.process` → `rpc.command.*`)
+  - Assert span durations are reasonable (> 0, < 60s)
+
+  **Metric validation** (queries Prometheus API):
+  - Assert all SpanMetrics-derived metrics are non-zero: `traces_span_metrics_calls_total`, `traces_span_metrics_duration_milliseconds_bucket`
+  - Assert all StatsD metrics are non-zero: `rippled_LedgerMaster_Validated_Ledger_Age`, `rippled_Peer_Finder_Active_*`, etc.
+  - Assert all Phase 9 metrics are non-zero: `rippled_nodestore_*`, `rippled_cache_*`, `rippled_txq_*`, `rippled_rpc_method_*`, `rippled_object_count`, `rippled_load_factor*`
+  - Assert metric label cardinality is within bounds
+
+  **Log-trace correlation validation** (queries Loki API):
+  - Assert logs contain `trace_id=` and `span_id=` fields
+  - Pick a random trace_id from Jaeger → query Loki for matching logs → assert results exist
+  - Assert Grafana derived field links are functional
+
+  **Dashboard validation**:
+  - For each of the 10 Grafana dashboards, query the dashboard API and assert no panels show "No data"
+
+- Output: JSON report with pass/fail per check, suitable for CI.
+
+**Key files**:
+
+- New: `docker/telemetry/workload/validate_telemetry.py`
+- New: `docker/telemetry/workload/expected_spans.json` (span inventory for validation)
+- New: `docker/telemetry/workload/expected_metrics.json` (metric inventory for validation)
+
+---
+
+## Task 10.5: Performance Benchmark Suite
+
+**Objective**: Measure CPU/memory/latency overhead of the telemetry stack.
+
+**What to do**:
+
+- Create `docker/telemetry/workload/benchmark.sh`:
+  - **Baseline run**: Start cluster with `[telemetry] enabled=0`, run transaction workload for 5 minutes, record metrics
+  - **Telemetry run**: Start cluster with full telemetry enabled, run identical workload, record metrics
+  - **Comparison**: Calculate deltas for:
+    - CPU usage (per-node average)
+    - Memory RSS (per-node peak)
+    - RPC p99 latency
+    - Transaction throughput (TPS)
+    - Consensus round time p95
+    - Ledger close time p95
+
+- Output: Markdown table comparing baseline vs. telemetry, with pass/fail against targets:
+  - CPU overhead < 3%
+  - Memory overhead < 5MB
+  - RPC latency impact < 2ms p99
+  - Throughput impact < 5%
+  - Consensus impact < 1%
+
+- Store results in `docker/telemetry/workload/benchmark-results/` for historical tracking.
+
+**Key files**:
+
+- New: `docker/telemetry/workload/benchmark.sh`
+- New: `docker/telemetry/workload/collect_system_metrics.sh`
+
+---
+
+## Task 10.6: CI Integration
+
+**Objective**: Wire the validation suite into CI for regression detection.
+
+**What to do**:
+
+- Create a CI workflow (GitHub Actions or equivalent) that:
+  1. Builds rippled with `-DXRPL_ENABLE_TELEMETRY=ON`
+  2. Starts the multi-node workload harness
+  3. Runs the RPC load generator + transaction submitter for 2 minutes
+  4. Runs the validation suite
+  5. Runs the benchmark suite
+  6. Fails the build if any validation check fails or benchmark exceeds thresholds
+  7. Archives the validation report and benchmark results as artifacts
+
+- This should be a separate workflow (not part of the main CI), triggered manually or on telemetry-related branch changes.
+
+**Key files**:
+
+- New: `.github/workflows/telemetry-validation.yml`
+- New: `docker/telemetry/workload/run-full-validation.sh` (orchestrator script)
+
+---
+
+## Task 10.7: Documentation
+
+**Objective**: Document the workload tools and validation process.
+
+**What to do**:
+
+- Create `docker/telemetry/workload/README.md`:
+  - Quick start guide for running workload harness
+  - Configuration options for load generator and tx submitter
+  - How to read validation reports
+  - How to run benchmarks and interpret results
+
+- Update `docs/telemetry-runbook.md`:
+  - Add "Validating Telemetry Stack" section
+  - Add "Performance Benchmarking" section
+
+- Update `OpenTelemetryPlan/09-data-collection-reference.md`:
+  - Add "Validation" section with expected metric/span counts
+
+---
+
+## Effort Summary
+
+| Task | Description                 | Effort | Risk   |
+| ---- | --------------------------- | ------ | ------ |
+| 10.1 | Multi-node test harness     | 2d     | Medium |
+| 10.2 | RPC load generator          | 1d     | Low    |
+| 10.3 | Transaction submitter       | 2d     | Medium |
+| 10.4 | Telemetry validation suite  | 2d     | Medium |
+| 10.5 | Performance benchmark suite | 1.5d   | Low    |
+| 10.6 | CI integration              | 1d     | Medium |
+| 10.7 | Documentation               | 0.5d   | Low    |
+
+**Total Effort**: 10 days
+
+## Exit Criteria
+
+- [ ] 5-node validator cluster starts and reaches consensus in docker-compose
+- [ ] RPC load generator fires all traced RPC commands at configurable rates
+- [ ] Transaction submitter generates 6+ transaction types at configurable TPS
+- [ ] Validation suite confirms all 16 spans, 22 attributes, 300+ metrics are present
+- [ ] Log-trace correlation validated end-to-end (Loki ↔ Tempo)
+- [ ] All 10 Grafana dashboards render data (no empty panels)
+- [ ] Benchmark shows < 3% CPU overhead, < 5MB memory overhead
+- [ ] CI workflow runs validation on telemetry branch changes
+- [ ] Validation report output is CI-parseable (JSON with exit codes)

OpenTelemetryPlan/Phase11_taskList.md

@@ -0,0 +1,471 @@
+# Phase 11: Third-Party Data Collection Pipelines — Task List
+
+> **Status**: Future Enhancement
+>
+> **Goal**: Build a custom OTel Collector receiver that periodically polls rippled's admin RPCs and exports structured metrics for external consumers — making all XRPL health, validator, peer, fee, and DEX data available as Prometheus/OTLP metrics without rippled code changes.
+>
+> **Scope**: Go-based OTel Collector receiver plugin + Grafana dashboards + Prometheus alerting rules.
+>
+> **Branch**: `pratik/otel-phase11-third-party-collection` (from `pratik/otel-phase10-workload-validation`)
+>
+> **Depends on**: Phase 10 (validation harness for testing the new receiver)
+
+### Related Plan Documents
+
+| Document                                                             | Relevance                                                       |
+| -------------------------------------------------------------------- | --------------------------------------------------------------- |
+| [06-implementation-phases.md](./06-implementation-phases.md)         | Phase 11 plan: motivation, architecture, exit criteria (§6.8.4) |
+| [09-data-collection-reference.md](./09-data-collection-reference.md) | Defines full metric inventory including third-party metrics     |
+| [Phase10_taskList.md](./Phase10_taskList.md)                         | Prerequisite — validation harness for testing                   |
+
+### Third-Party Consumer Gap Analysis
+
+This phase addresses the cross-cutting gap identified during research: **rippled has no native Prometheus/OTLP metrics export for data accessible only via RPC**. Every consumer (exchanges, payment processors, analytics providers, validators, researchers, compliance firms, custodians) must build custom JSON-RPC polling and conversion. This receiver centralizes that work.
+
+| Consumer Category          | Data Unlocked by This Phase                                        |
+| -------------------------- | ------------------------------------------------------------------ |
+| **Exchanges**              | Real-time fee estimates, TxQ capacity, server health scores        |
+| **Payment Processors**     | Settlement latency percentiles, corridor health, path availability |
+| **Analytics Providers**    | Validator metrics, network topology, amendment voting status       |
+| **DeFi / AMM**             | AMM pool TVL, DEX order book depth, trade volumes                  |
+| **Validators / Operators** | Per-peer latency, version distribution, UNL health, alerting       |
+| **Compliance**             | Transaction volume trends, network growth metrics                  |
+| **Academic Researchers**   | Consensus performance time-series, decentralization metrics        |
+| **CBDC / Tokenization**    | Token supply tracking, trust line adoption, freeze status          |
+| **Institutional Custody**  | Multi-sig status, escrow tracking, reserve calculations            |
+| **Wallet Providers**       | Server health for node selection, fee prediction data              |
+
+---
+
+## Task 11.1: OTel Collector Receiver Scaffold
+
+**Objective**: Create the Go project structure for a custom OTel Collector receiver that polls rippled JSON-RPC.
+
+**What to do**:
+
+- Create `docker/telemetry/otel-rippled-receiver/`:
+  - `receiver.go` — implements `receiver.Metrics` interface
+  - `config.go` — configuration struct (endpoint, poll interval, enabled RPCs)
+  - `factory.go` — receiver factory registration
+  - `go.mod` / `go.sum` — Go module with OTel Collector SDK dependency
+
+- Configuration model:
+
+  ```yaml
+  rippled_receiver:
+    endpoint: "http://localhost:5005" # rippled admin RPC
+    poll_interval: 30s # how often to poll
+    enabled_collectors:
+      - server_info
+      - get_counts
+      - fee
+      - peers
+      - validators
+      - feature
+      - server_state
+    amm_pools: [] # optional: AMM pool IDs to track
+    book_offers_pairs: [] # optional: currency pairs for DEX depth
+  ```
+
+- Build a custom OTel Collector binary that includes this receiver alongside the standard receivers.
+
+**Key files**:
+
+- New: `docker/telemetry/otel-rippled-receiver/receiver.go`
+- New: `docker/telemetry/otel-rippled-receiver/config.go`
+- New: `docker/telemetry/otel-rippled-receiver/factory.go`
+- New: `docker/telemetry/otel-rippled-receiver/go.mod`
+- New: `docker/telemetry/otel-rippled-receiver/Dockerfile`
+
+---
+
+## Task 11.2: server_info / server_state Collector
+
+**Objective**: Poll `server_info` and `server_state` and export all fields as OTel metrics.
+
+**What to do**:
+
+- Implement `serverInfoCollector` that calls `server_info` (admin) and extracts:
+
+  **Node Health Gauges:**
+  - `xrpl_server_state` (enum → int: disconnected=0, connected=1, syncing=2, tracking=3, full=4, proposing=5)
+  - `xrpl_server_state_duration_seconds`
+  - `xrpl_uptime_seconds`
+  - `xrpl_io_latency_ms`
+  - `xrpl_amendment_blocked` (0 or 1)
+  - `xrpl_peers_count`
+  - `xrpl_peer_disconnects_total`
+  - `xrpl_peer_disconnects_resources_total`
+  - `xrpl_jq_trans_overflow_total`
+
+  **Consensus Gauges:**
+  - `xrpl_last_close_proposers`
+  - `xrpl_last_close_converge_time_seconds`
+  - `xrpl_validation_quorum`
+
+  **Ledger Gauges:**
+  - `xrpl_validated_ledger_seq`
+  - `xrpl_validated_ledger_age_seconds`
+  - `xrpl_validated_ledger_base_fee_drops`
+  - `xrpl_validated_ledger_reserve_base_drops`
+  - `xrpl_validated_ledger_reserve_inc_drops`
+  - `xrpl_close_time_offset_seconds` (0 when absent)
+
+  **Load Factor Gauges:**
+  - `xrpl_load_factor`
+  - `xrpl_load_factor_server`
+  - `xrpl_load_factor_fee_escalation`
+  - `xrpl_load_factor_fee_queue`
+  - `xrpl_load_factor_local`
+  - `xrpl_load_factor_net`
+  - `xrpl_load_factor_cluster`
+
+  **State Accounting Gauges** (per state: disconnected, connected, syncing, tracking, full):
+  - `xrpl_state_duration_seconds{state="<name>"}`
+  - `xrpl_state_transitions_total{state="<name>"}`
+
+  **Validator Info** (when node is a validator):
+  - `xrpl_validator_list_count`
+  - `xrpl_validator_list_expiration_seconds` (epoch)
+  - `xrpl_validator_list_active` (0 or 1)
+
+**Key files**:
+
+- New: `docker/telemetry/otel-rippled-receiver/collectors/server_info.go`
+
+---
+
+## Task 11.3: get_counts Collector
+
+**Objective**: Poll `get_counts` and export internal object counts and NodeStore stats.
+
+**What to do**:
+
+- Implement `getCountsCollector`:
+
+  **Database Gauges:**
+  - `xrpl_db_size_kb{db="total"}`, `xrpl_db_size_kb{db="ledger"}`, `xrpl_db_size_kb{db="transaction"}`
+
+  **NodeStore Gauges:**
+  - `xrpl_nodestore_reads_total`, `xrpl_nodestore_reads_hit`, `xrpl_nodestore_writes_total`
+  - `xrpl_nodestore_read_bytes`, `xrpl_nodestore_written_bytes`
+  - `xrpl_nodestore_read_duration_us`, `xrpl_nodestore_write_load`
+  - `xrpl_nodestore_read_queue`, `xrpl_nodestore_read_threads_running`
+
+  **Cache Gauges:**
+  - `xrpl_cache_hit_rate{cache="SLE"}`, `xrpl_cache_hit_rate{cache="ledger"}`, `xrpl_cache_hit_rate{cache="accepted_ledger"}`
+  - `xrpl_cache_size{cache="treenode"}`, `xrpl_cache_size{cache="fullbelow"}`, `xrpl_cache_size{cache="accepted_ledger"}`
+
+  **Object Count Gauges:**
+  - `xrpl_object_count{type="<name>"}` for each counted object type (Transaction, Ledger, NodeObject, STTx, STLedgerEntry, InboundLedger, Pathfinder, etc.)
+
+  **Rates:**
+  - `xrpl_historical_fetch_per_minute`
+  - `xrpl_local_txs`
+
+**Key files**:
+
+- New: `docker/telemetry/otel-rippled-receiver/collectors/get_counts.go`
+
+---
+
+## Task 11.4: Peer Topology Collector
+
+**Objective**: Poll `peers` and export per-peer and aggregate network metrics.
+
+**What to do**:
+
+- Implement `peersCollector`:
+
+  **Aggregate Gauges:**
+  - `xrpl_peers_inbound_count`
+  - `xrpl_peers_outbound_count`
+  - `xrpl_peers_cluster_count`
+
+  **Per-Peer Gauges** (with labels `peer_key` truncated to 8 chars for cardinality control):
+  - `xrpl_peer_latency_ms{peer="<key>", version="<ver>", inbound="<bool>"}`
+  - `xrpl_peer_uptime_seconds{peer="<key>"}`
+  - `xrpl_peer_load{peer="<key>"}`
+
+  **Distribution Gauges** (aggregated across all peers):
+  - `xrpl_peer_latency_p50_ms`, `xrpl_peer_latency_p95_ms`, `xrpl_peer_latency_p99_ms`
+  - `xrpl_peer_version_count{version="<semver>"}` — count of peers per software version
+
+  **Tracking Status:**
+  - `xrpl_peer_diverged_count` — peers with `track=diverged`
+  - `xrpl_peer_unknown_count` — peers with `track=unknown`
+
+**Key files**:
+
+- New: `docker/telemetry/otel-rippled-receiver/collectors/peers.go`
+
+**Cardinality note**: Per-peer metrics use truncated keys. For large peer sets (50+), the aggregate distribution gauges are preferred over per-peer labels.
+
+---
+
+## Task 11.5: Validator & Amendment Collector
+
+**Objective**: Poll `validators` and `feature` to export validator health and amendment voting status.
+
+**What to do**:
+
+- Implement `validatorCollector`:
+
+  **From `validators` RPC:**
+  - `xrpl_trusted_validators_count`
+  - `xrpl_validator_signing` (0 or 1 — whether local validator is signing)
+
+  **From `feature` RPC:**
+  - `xrpl_amendment_enabled_count` — total enabled amendments
+  - `xrpl_amendment_majority_count` — amendments with majority but not yet enabled
+  - `xrpl_amendment_vetoed_count` — locally vetoed amendments
+  - `xrpl_amendment_unsupported_majority` (0 or 1) — any unsupported amendment has majority (critical alert)
+
+  **Per-amendment with majority** (limited cardinality — only amendments with `majority` set):
+  - `xrpl_amendment_majority_time{name="<amendment>"}` — epoch time when majority was gained
+  - `xrpl_amendment_votes{name="<amendment>"}` — current vote count
+  - `xrpl_amendment_threshold{name="<amendment>"}` — votes needed
+
+**Key files**:
+
+- New: `docker/telemetry/otel-rippled-receiver/collectors/validators.go`
+
+---
+
+## Task 11.6: Fee & TxQ Collector
+
+**Objective**: Poll `fee` RPC and export real-time fee market data.
+
+**What to do**:
+
+- Implement `feeCollector` that calls the public `fee` RPC:
+
+  **Fee Level Gauges:**
+  - `xrpl_fee_current_ledger_size` — transactions in current open ledger
+  - `xrpl_fee_expected_ledger_size` — expected transactions at close
+  - `xrpl_fee_max_queue_size` — maximum transaction queue size
+  - `xrpl_fee_open_ledger_fee_drops` — minimum fee for open ledger inclusion
+  - `xrpl_fee_median_fee_drops` — median fee level
+  - `xrpl_fee_minimum_fee_drops` — base reference fee
+  - `xrpl_fee_queue_size` — current queue depth
+
+- This overlaps with Phase 9's internal TxQ metrics but provides an external-only collection path that doesn't require rippled code changes.
+
+**Key files**:
+
+- New: `docker/telemetry/otel-rippled-receiver/collectors/fee.go`
+
+---
+
+## Task 11.7: DEX & AMM Collector (Optional)
+
+**Objective**: Periodically poll configured AMM pools and order book pairs for DeFi metrics.
+
+**What to do**:
+
+- Implement `dexCollector` (enabled only when `amm_pools` or `book_offers_pairs` are configured):
+
+  **AMM Pool Gauges** (per configured pool):
+  - `xrpl_amm_reserve{pool="<id>", asset="<currency>"}` — pool reserve amount
+  - `xrpl_amm_lp_token_supply{pool="<id>"}` — outstanding LP tokens
+  - `xrpl_amm_trading_fee{pool="<id>"}` — pool trading fee (basis points)
+  - `xrpl_amm_tvl_drops{pool="<id>"}` — total value locked (XRP-denominated)
+
+  **Order Book Gauges** (per configured pair):
+  - `xrpl_orderbook_bid_depth{pair="<base>/<quote>"}` — total bid volume
+  - `xrpl_orderbook_ask_depth{pair="<base>/<quote>"}` — total ask volume
+  - `xrpl_orderbook_spread{pair="<base>/<quote>"}` — best bid-ask spread
+  - `xrpl_orderbook_offer_count{pair="<base>/<quote>", side="bid|ask"}` — number of offers
+
+**Key files**:
+
+- New: `docker/telemetry/otel-rippled-receiver/collectors/dex.go`
+
+**Note**: This is optional because it requires explicit configuration of which pools/pairs to track. Default configuration tracks no DEX data.
+
+---
+
+## Task 11.8: Prometheus Alerting Rules
+
+**Objective**: Create production-ready alerting rules for the metrics exported by this receiver.
+
+**What to do**:
+
+- Create `docker/telemetry/prometheus/rippled-alerts.yml`:
+
+  **Tier 1 — Critical (page immediately):**
+
+  ```yaml
+  - alert: XRPLServerNotFull
+    expr: xrpl_server_state < 4
+    for: 15m
+
+  - alert: XRPLAmendmentBlocked
+    expr: xrpl_amendment_blocked == 1
+    for: 1m
+
+  - alert: XRPLNoPeers
+    expr: xrpl_peers_count == 0
+    for: 5m
+
+  - alert: XRPLLedgerStale
+    expr: xrpl_validated_ledger_age_seconds > 120
+    for: 2m
+
+  - alert: XRPLHighIOLatency
+    expr: xrpl_io_latency_ms > 100
+    for: 5m
+
+  - alert: XRPLUnsupportedAmendmentMajority
+    expr: xrpl_amendment_unsupported_majority == 1
+    for: 1m
+  ```
+
+  **Tier 2 — Warning (investigate within hours):**
+
+  ```yaml
+  - alert: XRPLLowPeerCount
+    expr: xrpl_peers_count < 10
+    for: 15m
+
+  - alert: XRPLHighLoadFactor
+    expr: xrpl_load_factor > 10
+    for: 10m
+
+  - alert: XRPLSlowConsensus
+    expr: xrpl_last_close_converge_time_seconds > 6
+    for: 5m
+
+  - alert: XRPLValidatorListExpiring
+    expr: (xrpl_validator_list_expiration_seconds - time()) < 86400
+    for: 1h
+
+  - alert: XRPLClockDrift
+    expr: xrpl_close_time_offset_seconds > 0
+    for: 5m
+
+  - alert: XRPLStateFlapping
+    expr: rate(xrpl_state_transitions_total{state="full"}[1h]) > 2
+    for: 30m
+  ```
+
+**Key files**:
+
+- New: `docker/telemetry/prometheus/rippled-alerts.yml`
+- Update: `docker/telemetry/prometheus/prometheus.yml` (add rule_files reference)
+
+---
+
+## Task 11.9: New Grafana Dashboards
+
+**Objective**: Create 4 new dashboards for the data exported by the receiver.
+
+**What to do**:
+
+- **Validator Health** (`rippled-validator-health`):
+  - Server state timeline, state duration breakdown
+  - Proposer count trend, converge time trend, validation quorum
+  - Validator list expiration countdown
+  - Amendment voting status (majority/enabled/vetoed)
+
+- **Network Topology** (`rippled-network-topology`):
+  - Peer count (inbound/outbound/cluster), peer version distribution
+  - Peer latency distribution (p50/p95/p99), diverged peer count
+  - Geographic distribution (if enriched with GeoIP)
+  - Peer uptime distribution
+
+- **Fee Market** (`rippled-fee-market-external`):
+  - Current fee levels (open ledger, median, minimum), fee escalation timeline
+  - Queue depth vs. capacity, transactions per ledger
+  - Load factor breakdown (server/network/cluster/escalation)
+
+- **DEX & AMM Overview** (`rippled-dex-amm`) (only populated when DEX collectors are configured):
+  - AMM pool TVL, reserve ratios, LP token supply
+  - Order book depth per pair, spread trends
+  - Trading fee revenue estimates
+
+**Key files**:
+
+- New: `docker/telemetry/grafana/dashboards/rippled-validator-health.json`
+- New: `docker/telemetry/grafana/dashboards/rippled-network-topology.json`
+- New: `docker/telemetry/grafana/dashboards/rippled-fee-market-external.json`
+- New: `docker/telemetry/grafana/dashboards/rippled-dex-amm.json`
+
+---
+
+## Task 11.10: Integration with Phase 10 Validation
+
+**Objective**: Extend the Phase 10 validation suite to verify this receiver's metrics.
+
+**What to do**:
+
+- Update `docker/telemetry/workload/validate_telemetry.py`:
+  - Add assertions for all `xrpl_*` metrics produced by the receiver
+  - Verify metric labels have expected values
+  - Verify alerting rules fire correctly (inject a "bad" state and check alert)
+
+- Update `docker/telemetry/docker-compose.workload.yaml`:
+  - Add the custom OTel Collector build with the rippled receiver
+  - Configure the receiver to poll one of the test nodes
+
+**Key files**:
+
+- Update: `docker/telemetry/workload/validate_telemetry.py`
+- Update: `docker/telemetry/docker-compose.workload.yaml`
+- Update: `docker/telemetry/workload/expected_metrics.json`
+
+---
+
+## Task 11.11: Documentation
+
+**Objective**: Document the receiver, its metrics, deployment, and alerting.
+
+**What to do**:
+
+- Create `docker/telemetry/otel-rippled-receiver/README.md`:
+  - Architecture overview (how the receiver fits into the OTel Collector)
+  - Configuration reference (all config options with defaults)
+  - Metric reference table (all exported metrics with types and labels)
+  - Deployment guide (building custom collector binary, docker-compose integration)
+
+- Update `OpenTelemetryPlan/09-data-collection-reference.md`:
+  - Add "Third-Party Metrics (OTel Collector Receiver)" section
+  - Add new Grafana dashboard reference (4 dashboards)
+  - Add alerting rules reference
+
+- Update `docs/telemetry-runbook.md`:
+  - Add "Third-Party Metrics Receiver" troubleshooting section
+  - Add alerting playbook (what to do for each Tier 1/Tier 2 alert)
+
+---
+
+## Effort Summary
+
+| Task  | Description                          | Effort | Risk   |
+| ----- | ------------------------------------ | ------ | ------ |
+| 11.1  | OTel Collector receiver scaffold     | 1.5d   | Medium |
+| 11.2  | server_info / server_state collector | 2d     | Low    |
+| 11.3  | get_counts collector                 | 1.5d   | Low    |
+| 11.4  | Peer topology collector              | 1.5d   | Medium |
+| 11.5  | Validator & amendment collector      | 1d     | Low    |
+| 11.6  | Fee & TxQ collector                  | 0.5d   | Low    |
+| 11.7  | DEX & AMM collector (optional)       | 1.5d   | Medium |
+| 11.8  | Prometheus alerting rules            | 1d     | Low    |
+| 11.9  | New Grafana dashboards (4)           | 2d     | Low    |
+| 11.10 | Integration with Phase 10 validation | 1d     | Low    |
+| 11.11 | Documentation                        | 1d     | Low    |
+
+**Total Effort**: 15 days
+
+## Exit Criteria
+
+- [ ] Custom OTel Collector receiver builds and starts without errors
+- [ ] All `xrpl_*` metrics from server_info, get_counts, peers, validators, fee appear in Prometheus
+- [ ] Metrics update at configured poll interval (default 30s)
+- [ ] 4 new Grafana dashboards operational with data
+- [ ] Prometheus alerting rules fire correctly for simulated failure conditions
+- [ ] DEX/AMM collector works when configured (optional — not required for base exit criteria)
+- [ ] Phase 10 validation suite passes with receiver metrics included
+- [ ] Receiver handles rippled restart/unavailability gracefully (no crash, logs warning, retries)
+- [ ] Documentation complete: receiver README, metric reference, alerting playbook
+- [ ] Go receiver has unit tests with >80% coverage

OpenTelemetryPlan/Phase2_taskList.md

@@ -0,0 +1,220 @@
+# Phase 2: RPC Tracing Completion Task List
+
+> **Goal**: Complete full RPC tracing coverage with W3C Trace Context propagation, unit tests, and performance validation. Build on the POC foundation to achieve production-quality RPC observability.
+>
+> **Scope**: W3C header extraction, TraceContext propagation utilities, unit tests for core telemetry, integration tests for RPC tracing, and performance benchmarks.
+>
+> **Branch**: `pratik/otel-phase2-rpc-tracing` (from `pratik/OpenTelemetry_and_DistributedTracing_planning`)
+
+### Related Plan Documents
+
+| Document                                                     | Relevance                                                     |
+| ------------------------------------------------------------ | ------------------------------------------------------------- |
+| [04-code-samples.md](./04-code-samples.md)                   | TraceContextPropagator (§4.4.2), RPC instrumentation (§4.5.3) |
+| [02-design-decisions.md](./02-design-decisions.md)           | W3C Trace Context (§2.5), span attributes (§2.4.2)            |
+| [06-implementation-phases.md](./06-implementation-phases.md) | Phase 2 tasks (§6.3), definition of done (§6.11.2)            |
+
+---
+
+## Task 2.1: Implement W3C Trace Context HTTP Header Extraction
+
+**Objective**: Extract `traceparent` and `tracestate` headers from incoming HTTP RPC requests so external callers can propagate their trace context into rippled.
+
+**What to do**:
+
+- Create `include/xrpl/telemetry/TraceContextPropagator.h`:
+  - `extractFromHeaders(headerGetter)` - extract W3C traceparent/tracestate from HTTP headers
+  - `injectToHeaders(ctx, headerSetter)` - inject trace context into response headers
+  - Use OTel's `TextMapPropagator` with `W3CTraceContextPropagator` for standards compliance
+  - Only compiled when `XRPL_ENABLE_TELEMETRY` is defined
+
+- Create `src/libxrpl/telemetry/TraceContextPropagator.cpp`:
+  - Implement a simple `TextMapCarrier` adapter for HTTP headers
+  - Use `opentelemetry::context::propagation::GlobalTextMapPropagator` for extraction/injection
+  - Register the W3C propagator in `TelemetryImpl::start()`
+
+- Modify `src/xrpld/rpc/detail/ServerHandler.cpp`:
+  - In the HTTP request handler, extract parent context from headers before creating span
+  - Pass extracted context to `startSpan()` as parent
+  - Inject trace context into response headers
+
+**Key new files**:
+
+- `include/xrpl/telemetry/TraceContextPropagator.h`
+- `src/libxrpl/telemetry/TraceContextPropagator.cpp`
+
+**Key modified files**:
+
+- `src/xrpld/rpc/detail/ServerHandler.cpp`
+- `src/libxrpl/telemetry/Telemetry.cpp` (register W3C propagator)
+
+**Reference**:
+
+- [04-code-samples.md §4.4.2](./04-code-samples.md) — TraceContextPropagator with extractFromHeaders/injectToHeaders
+- [02-design-decisions.md §2.5](./02-design-decisions.md) — W3C Trace Context propagation design
+
+---
+
+## Task 2.2: Add XRPL_TRACE_PEER Macro
+
+**Objective**: Add the missing peer-tracing macro for future Phase 3 use and ensure macro completeness.
+
+**What to do**:
+
+- Edit `src/xrpld/telemetry/TracingInstrumentation.h`:
+  - Add `XRPL_TRACE_PEER(_tel_obj_, _span_name_)` macro that checks `shouldTracePeer()`
+  - Add `XRPL_TRACE_LEDGER(_tel_obj_, _span_name_)` macro (for future ledger tracing)
+  - Ensure disabled variants expand to `((void)0)`
+
+**Key modified file**:
+
+- `src/xrpld/telemetry/TracingInstrumentation.h`
+
+---
+
+## Task 2.3: Add shouldTraceLedger() to Telemetry Interface
+
+**Objective**: The `Setup` struct has a `traceLedger` field but there's no corresponding virtual method. Add it for interface completeness.
+
+**What to do**:
+
+- Edit `include/xrpl/telemetry/Telemetry.h`:
+  - Add `virtual bool shouldTraceLedger() const = 0;`
+
+- Update all implementations:
+  - `src/libxrpl/telemetry/Telemetry.cpp` (TelemetryImpl, NullTelemetryOtel)
+  - `src/libxrpl/telemetry/NullTelemetry.cpp` (NullTelemetry)
+
+**Key modified files**:
+
+- `include/xrpl/telemetry/Telemetry.h`
+- `src/libxrpl/telemetry/Telemetry.cpp`
+- `src/libxrpl/telemetry/NullTelemetry.cpp`
+
+---
+
+## Task 2.4: Unit Tests for Core Telemetry Infrastructure
+
+**Objective**: Add unit tests for the core telemetry abstractions to validate correctness and catch regressions.
+
+**What to do**:
+
+- Create `src/test/telemetry/Telemetry_test.cpp`:
+  - Test NullTelemetry: verify all methods return expected no-op values
+  - Test Setup defaults: verify all Setup fields have correct defaults
+  - Test setup_Telemetry config parser: verify parsing of [telemetry] section
+  - Test enabled/disabled factory paths
+  - Test shouldTrace\* methods respect config flags
+
+- Create `src/test/telemetry/SpanGuard_test.cpp`:
+  - Test SpanGuard RAII lifecycle (span ends on destruction)
+  - Test move constructor works correctly
+  - Test setAttribute, setOk, setStatus, addEvent, recordException
+  - Test context() returns valid context
+
+- Add test files to CMake build
+
+**Key new files**:
+
+- `src/test/telemetry/Telemetry_test.cpp`
+- `src/test/telemetry/SpanGuard_test.cpp`
+
+**Reference**:
+
+- [06-implementation-phases.md §6.11.1](./06-implementation-phases.md) — Phase 1 exit criteria (unit tests passing)
+
+---
+
+## Task 2.5: Enhance RPC Span Attributes
+
+**Objective**: Add additional attributes to RPC spans per the semantic conventions defined in the plan.
+
+**What to do**:
+
+- Edit `src/xrpld/rpc/detail/ServerHandler.cpp`:
+  - Add `http.method` attribute for HTTP requests
+  - Add `http.status_code` attribute for responses
+  - Add `net.peer.ip` attribute for client IP (if available)
+
+- Edit `src/xrpld/rpc/detail/RPCHandler.cpp`:
+  - Add `xrpl.rpc.duration_ms` attribute on completion
+  - Add error message attribute on failure: `xrpl.rpc.error_message`
+
+**Key modified files**:
+
+- `src/xrpld/rpc/detail/ServerHandler.cpp`
+- `src/xrpld/rpc/detail/RPCHandler.cpp`
+
+**Reference**:
+
+- [02-design-decisions.md §2.4.2](./02-design-decisions.md) — RPC attribute schema
+
+---
+
+## Task 2.6: Build Verification and Performance Baseline
+
+**Objective**: Verify the build succeeds with and without telemetry, and establish a performance baseline.
+
+**What to do**:
+
+1. Build with `telemetry=ON` and verify no compilation errors
+2. Build with `telemetry=OFF` and verify no regressions
+3. Run existing unit tests to verify no breakage
+4. Document any build issues in lessons.md
+
+**Verification Checklist**:
+
+- [ ] `conan install . --build=missing -o telemetry=True` succeeds
+- [ ] `cmake --preset default -Dtelemetry=ON` configures correctly
+- [ ] Build succeeds with telemetry ON
+- [ ] Build succeeds with telemetry OFF
+- [ ] Existing tests pass with telemetry ON
+- [ ] Existing tests pass with telemetry OFF
+
+---
+
+## Summary
+
+| Task | Description                                 | New Files | Modified Files | Depends On |
+| ---- | ------------------------------------------- | --------- | -------------- | ---------- |
+| 2.1  | W3C Trace Context header extraction         | 2         | 2              | POC        |
+| 2.2  | Add XRPL_TRACE_PEER/LEDGER macros           | 0         | 1              | POC        |
+| 2.3  | Add shouldTraceLedger() interface method    | 0         | 3              | POC        |
+| 2.4  | Unit tests for core telemetry               | 2         | 1              | POC        |
+| 2.5  | Enhanced RPC span attributes                | 0         | 2              | POC        |
+| 2.6  | Build verification and performance baseline | 0         | 0              | 2.1-2.5    |
+
+**Parallel work**: Tasks 2.1, 2.2, 2.3 can run in parallel. Task 2.4 depends on 2.3. Task 2.5 can run in parallel with 2.4. Task 2.6 depends on all others.
+
+---
+
+## Known Issues / Future Work
+
+### Thread safety of TelemetryImpl::stop() vs startSpan()
+
+`TelemetryImpl::stop()` resets `sdkProvider_` (a `std::shared_ptr`) without
+synchronization. `getTracer()` reads the same member from RPC handler threads.
+This is a data race if any thread calls `startSpan()` concurrently with `stop()`.
+
+**Current mitigation**: `Application::stop()` shuts down `serverHandler_`,
+`overlay_`, and `jobQueue_` before calling `telemetry_->stop()`, so no callers
+remain. See comments in `Telemetry.cpp:stop()` and `Application.cpp`.
+
+**TODO**: Add an `std::atomic<bool> stopped_` flag checked in `getTracer()` to
+make this robust against future shutdown order changes.
+
+### Macro incompatibility: XRPL_TRACE_SPAN vs XRPL_TRACE_SET_ATTR
+
+`XRPL_TRACE_SPAN` and `XRPL_TRACE_SPAN_KIND` declare `_xrpl_guard_` as a bare
+`SpanGuard`, but `XRPL_TRACE_SET_ATTR` and `XRPL_TRACE_EXCEPTION` call
+`_xrpl_guard_.has_value()` which requires `std::optional<SpanGuard>`. Using
+`XRPL_TRACE_SPAN` followed by `XRPL_TRACE_SET_ATTR` in the same scope would
+fail to compile.
+
+**Current mitigation**: No call site currently uses `XRPL_TRACE_SPAN` — all
+production code uses the conditional macros (`XRPL_TRACE_RPC`, `XRPL_TRACE_TX`,
+etc.) which correctly wrap the guard in `std::optional`.
+
+**TODO**: Either make `XRPL_TRACE_SPAN`/`XRPL_TRACE_SPAN_KIND` also wrap in
+`std::optional`, or document that `XRPL_TRACE_SET_ATTR` is only compatible with
+the conditional macros.

OpenTelemetryPlan/Phase3_taskList.md

@@ -0,0 +1,263 @@
+# Phase 3: Transaction Tracing Task List
+
+> **Goal**: Trace the full transaction lifecycle from RPC submission through peer relay, including cross-node context propagation via Protocol Buffer extensions. This is the WALK phase that demonstrates true distributed tracing.
+>
+> **Scope**: Protocol Buffer `TraceContext` message, context serialization, PeerImp transaction instrumentation, NetworkOPs processing instrumentation, HashRouter visibility, and multi-node relay context propagation.
+>
+> **Branch**: `pratik/otel-phase3-tx-tracing` (from `pratik/otel-phase2-rpc-tracing`)
+
+### Related Plan Documents
+
+| Document                                                     | Relevance                                                                                        |
+| ------------------------------------------------------------ | ------------------------------------------------------------------------------------------------ |
+| [04-code-samples.md](./04-code-samples.md)                   | TraceContext protobuf (§4.4.1), PeerImp instrumentation (§4.5.1), context serialization (§4.4.2) |
+| [01-architecture-analysis.md](./01-architecture-analysis.md) | Transaction flow (§1.3), key trace points (§1.6)                                                 |
+| [06-implementation-phases.md](./06-implementation-phases.md) | Phase 3 tasks (§6.4), definition of done (§6.11.3)                                               |
+| [02-design-decisions.md](./02-design-decisions.md)           | Context propagation design (§2.5), attribute schema (§2.4.3)                                     |
+
+---
+
+## Task 3.1: Define TraceContext Protocol Buffer Message
+
+**Objective**: Add trace context fields to the P2P protocol messages so trace IDs can propagate across nodes.
+
+**What to do**:
+
+- Edit `include/xrpl/proto/xrpl.proto` (or `src/ripple/proto/ripple.proto`, wherever the proto is):
+  - Add `TraceContext` message definition:
+    ```protobuf
+    message TraceContext {
+        bytes trace_id = 1;      // 16-byte trace identifier
+        bytes span_id = 2;       // 8-byte span identifier
+        uint32 trace_flags = 3;  // bit 0 = sampled
+        string trace_state = 4;  // W3C tracestate value
+    }
+    ```
+  - Add `optional TraceContext trace_context = 1001;` to:
+    - `TMTransaction`
+    - `TMProposeSet` (for Phase 4 use)
+    - `TMValidation` (for Phase 4 use)
+  - Use high field numbers (1001+) to avoid conflicts with existing fields
+
+- Regenerate protobuf C++ code
+
+**Key modified files**:
+
+- `include/xrpl/proto/xrpl.proto` (or equivalent)
+
+**Reference**:
+
+- [04-code-samples.md §4.4.1](./04-code-samples.md) — TraceContext message definition
+- [02-design-decisions.md §2.5.2](./02-design-decisions.md) — Protocol buffer context propagation design
+
+---
+
+## Task 3.2: Implement Protobuf Context Serialization
+
+**Objective**: Create utilities to serialize/deserialize OTel trace context to/from protobuf `TraceContext` messages.
+
+**What to do**:
+
+- Create `include/xrpl/telemetry/TraceContextPropagator.h` (extend from Phase 2 if exists, or add protobuf methods):
+  - Add protobuf-specific methods:
+    - `static Context extractFromProtobuf(protocol::TraceContext const& proto)` — reconstruct OTel context from protobuf fields
+    - `static void injectToProtobuf(Context const& ctx, protocol::TraceContext& proto)` — serialize current span context into protobuf fields
+  - Both methods guard behind `#ifdef XRPL_ENABLE_TELEMETRY`
+
+- Create/extend `src/libxrpl/telemetry/TraceContextPropagator.cpp`:
+  - Implement extraction: read trace_id (16 bytes), span_id (8 bytes), trace_flags from protobuf, construct `SpanContext`, wrap in `Context`
+  - Implement injection: get current span from context, serialize its TraceId, SpanId, and TraceFlags into protobuf fields
+
+**Key new/modified files**:
+
+- `include/xrpl/telemetry/TraceContextPropagator.h`
+- `src/libxrpl/telemetry/TraceContextPropagator.cpp`
+
+**Reference**:
+
+- [04-code-samples.md §4.4.2](./04-code-samples.md) — Full extract/inject implementation
+
+---
+
+## Task 3.3: Instrument PeerImp Transaction Handling
+
+**Objective**: Add trace spans to the peer-level transaction receive and relay path.
+
+**What to do**:
+
+- Edit `src/xrpld/overlay/detail/PeerImp.cpp`:
+  - In `onMessage(TMTransaction)` / `handleTransaction()`:
+    - Extract parent trace context from incoming `TMTransaction::trace_context` field (if present)
+    - Create `tx.receive` span as child of extracted context (or new root if none)
+    - Set attributes: `xrpl.tx.hash`, `xrpl.peer.id`, `xrpl.tx.status`
+    - On HashRouter suppression (duplicate): set `xrpl.tx.suppressed=true`, add `tx.duplicate` event
+    - Wrap validation call with child span `tx.validate`
+    - Wrap relay with `tx.relay` span
+  - When relaying to peers:
+    - Inject current trace context into outgoing `TMTransaction::trace_context`
+    - Set `xrpl.tx.relay_count` attribute
+
+- Include `TracingInstrumentation.h` and use `XRPL_TRACE_TX` macro
+
+**Key modified files**:
+
+- `src/xrpld/overlay/detail/PeerImp.cpp`
+
+**Reference**:
+
+- [04-code-samples.md §4.5.1](./04-code-samples.md) — Full PeerImp instrumentation example
+- [01-architecture-analysis.md §1.3](./01-architecture-analysis.md) — Transaction flow diagram
+- [01-architecture-analysis.md §1.6](./01-architecture-analysis.md) — tx.receive trace point
+
+---
+
+## Task 3.4: Instrument NetworkOPs Transaction Processing
+
+**Objective**: Trace the transaction processing pipeline in NetworkOPs, covering both sync and async paths.
+
+**What to do**:
+
+- Edit `src/xrpld/app/misc/NetworkOPs.cpp`:
+  - In `processTransaction()`:
+    - Create `tx.process` span
+    - Set attributes: `xrpl.tx.hash`, `xrpl.tx.type`, `xrpl.tx.local` (whether from RPC or peer)
+    - Record whether sync or async path is taken
+
+  - In `doTransactionAsync()`:
+    - Capture parent context before queuing
+    - Create `tx.queue` span with queue depth attribute
+    - Add event when transaction is dequeued for processing
+
+  - In `doTransactionSync()`:
+    - Create `tx.process_sync` span
+    - Record result (applied, queued, rejected)
+
+**Key modified files**:
+
+- `src/xrpld/app/misc/NetworkOPs.cpp`
+
+**Reference**:
+
+- [01-architecture-analysis.md §1.6](./01-architecture-analysis.md) — tx.validate and tx.process trace points
+- [02-design-decisions.md §2.4.3](./02-design-decisions.md) — Transaction attribute schema
+
+---
+
+## Task 3.5: Instrument HashRouter for Dedup Visibility
+
+**Objective**: Make transaction deduplication visible in traces by recording HashRouter decisions as span attributes/events.
+
+**What to do**:
+
+- Edit `src/xrpld/overlay/detail/PeerImp.cpp` (in handleTransaction):
+  - After calling `HashRouter::shouldProcess()` or `addSuppressionPeer()`:
+    - Record `xrpl.tx.suppressed` attribute (true/false)
+    - Record `xrpl.tx.flags` showing current HashRouter state (SAVED, TRUSTED, etc.)
+    - Add `tx.first_seen` or `tx.duplicate` event
+
+- This is NOT a modification to HashRouter itself — just recording its decisions as span attributes in the existing PeerImp instrumentation from Task 3.3.
+
+**Key modified files**:
+
+- `src/xrpld/overlay/detail/PeerImp.cpp` (same changes as 3.3, logically grouped)
+
+---
+
+## Task 3.6: Context Propagation in Transaction Relay
+
+**Objective**: Ensure trace context flows correctly when transactions are relayed between peers, creating linked spans across nodes.
+
+**What to do**:
+
+- Verify the relay path injects trace context:
+  - When `PeerImp` relays a transaction, the `TMTransaction` message should carry `trace_context`
+  - When a remote peer receives it, the context is extracted and used as parent
+
+- Test context propagation:
+  - Manually verify with 2+ node setup that trace IDs match across nodes
+  - Confirm parent-child span relationships are correct in Jaeger
+
+- Handle edge cases:
+  - Missing trace context (older peers): create new root span
+  - Corrupted trace context: log warning, create new root span
+  - Sampled-out traces: respect trace flags
+
+**Key modified files**:
+
+- `src/xrpld/overlay/detail/PeerImp.cpp`
+- `src/xrpld/overlay/detail/OverlayImpl.cpp` (if relay method needs context param)
+
+**Reference**:
+
+- [02-design-decisions.md §2.5](./02-design-decisions.md) — Context propagation design
+- [04-code-samples.md §4.5.1](./04-code-samples.md) — Relay context injection pattern
+
+---
+
+## Task 3.7: Build Verification and Testing
+
+**Objective**: Verify all Phase 3 changes compile and work correctly.
+
+**What to do**:
+
+1. Build with `telemetry=ON` — verify no compilation errors
+2. Build with `telemetry=OFF` — verify no regressions
+3. Run existing unit tests
+4. Verify protobuf regeneration produces correct C++ code
+5. Document any issues encountered
+
+**Verification Checklist**:
+
+- [ ] Protobuf changes generate valid C++
+- [ ] Build succeeds with telemetry ON
+- [ ] Build succeeds with telemetry OFF
+- [ ] Existing tests pass
+- [ ] No undefined symbols from new telemetry calls
+
+---
+
+## Summary
+
+| Task | Description                         | New Files | Modified Files | Depends On |
+| ---- | ----------------------------------- | --------- | -------------- | ---------- |
+| 3.1  | TraceContext protobuf message       | 0         | 1              | Phase 2    |
+| 3.2  | Protobuf context serialization      | 1-2       | 0              | 3.1        |
+| 3.3  | PeerImp transaction instrumentation | 0         | 1              | 3.2        |
+| 3.4  | NetworkOPs transaction processing   | 0         | 1              | Phase 2    |
+| 3.5  | HashRouter dedup visibility         | 0         | 1              | 3.3        |
+| 3.6  | Relay context propagation           | 0         | 1-2            | 3.3, 3.5   |
+| 3.7  | Build verification and testing      | 0         | 0              | 3.1-3.6    |
+
+**Parallel work**: Tasks 3.1 and 3.4 can start in parallel. Task 3.2 depends on 3.1. Tasks 3.3 and 3.5 depend on 3.2. Task 3.6 depends on 3.3 and 3.5.
+
+**Exit Criteria** (from [06-implementation-phases.md §6.11.3](./06-implementation-phases.md)):
+
+- [ ] Transaction traces span across nodes
+- [ ] Trace context in Protocol Buffer messages
+- [ ] HashRouter deduplication visible in traces
+- [ ] <5% overhead on transaction throughput
+
+---
+
+## Known Issues / Future Work
+
+### Propagation utilities not yet wired into P2P flow
+
+`extractFromProtobuf()` and `injectToProtobuf()` in `TraceContextPropagator.h`
+are implemented and tested but not called from production code. To enable
+cross-node distributed traces:
+
+- Call `injectToProtobuf()` in `PeerImp` when sending `TMTransaction` /
+  `TMProposeSet` messages
+- Call `extractFromProtobuf()` in the corresponding message handlers to
+  reconstruct the parent span context, then pass it to `startSpan()` as the
+  parent
+
+This was deferred to validate single-node tracing performance first.
+
+### Unused trace_state proto field
+
+The `TraceContext.trace_state` field (field 4) in `xrpl.proto` is reserved for
+W3C `tracestate` vendor-specific key-value pairs but is not read or written by
+`TraceContextPropagator`. Wire it when cross-vendor trace propagation is needed.
+No wire cost since proto `optional` fields are zero-cost when absent.

OpenTelemetryPlan/Phase4_taskList.md

@@ -0,0 +1,244 @@
+# Phase 4: Consensus Tracing Task List
+
+> **Goal**: Full observability into consensus rounds — track round lifecycle, phase transitions, proposal handling, and validation. This is the RUN phase that completes the distributed tracing story.
+>
+> **Scope**: RCLConsensus instrumentation for round starts, phase transitions (open/establish/accept), proposal send/receive, validation handling, and correlation with transaction traces from Phase 3.
+>
+> **Branch**: `pratik/otel-phase4-consensus-tracing` (from `pratik/otel-phase3-tx-tracing`)
+
+### Related Plan Documents
+
+| Document                                                     | Relevance                                                   |
+| ------------------------------------------------------------ | ----------------------------------------------------------- |
+| [04-code-samples.md](./04-code-samples.md)                   | Consensus instrumentation (§4.5.2), consensus span patterns |
+| [01-architecture-analysis.md](./01-architecture-analysis.md) | Consensus round flow (§1.4), key trace points (§1.6)        |
+| [06-implementation-phases.md](./06-implementation-phases.md) | Phase 4 tasks (§6.5), definition of done (§6.11.4)          |
+| [02-design-decisions.md](./02-design-decisions.md)           | Consensus attribute schema (§2.4.4)                         |
+
+---
+
+## Task 4.1: Instrument Consensus Round Start
+
+**Objective**: Create a root span for each consensus round that captures the round's key parameters.
+
+**What to do**:
+
+- Edit `src/xrpld/app/consensus/RCLConsensus.cpp`:
+  - In `RCLConsensus::startRound()` (or the Adaptor's startRound):
+    - Create `consensus.round` span using `XRPL_TRACE_CONSENSUS` macro
+    - Set attributes:
+      - `xrpl.consensus.ledger.prev` — previous ledger hash
+      - `xrpl.consensus.ledger.seq` — target ledger sequence
+      - `xrpl.consensus.proposers` — number of trusted proposers
+      - `xrpl.consensus.mode` — "proposing" or "observing"
+    - Store the span context for use by child spans in phase transitions
+
+- Add a member to hold current round trace context:
+  - `opentelemetry::context::Context currentRoundContext_` (guarded by `#ifdef`)
+  - Updated at round start, used by phase transition spans
+
+**Key modified files**:
+
+- `src/xrpld/app/consensus/RCLConsensus.cpp`
+- `src/xrpld/app/consensus/RCLConsensus.h` (add context member)
+
+**Reference**:
+
+- [04-code-samples.md §4.5.2](./04-code-samples.md) — startRound instrumentation example
+- [01-architecture-analysis.md §1.4](./01-architecture-analysis.md) — Consensus round flow
+
+---
+
+## Task 4.2: Instrument Phase Transitions
+
+**Objective**: Create child spans for each consensus phase (open, establish, accept) to show timing breakdown.
+
+**What to do**:
+
+- Edit `src/xrpld/app/consensus/RCLConsensus.cpp`:
+  - Identify where phase transitions occur (the `Consensus<Adaptor>` template drives this)
+  - For each phase entry:
+    - Create span as child of `currentRoundContext_`: `consensus.phase.open`, `consensus.phase.establish`, `consensus.phase.accept`
+    - Set `xrpl.consensus.phase` attribute
+    - Add `phase.enter` event at start, `phase.exit` event at end
+    - Record phase duration in milliseconds
+
+  - In the `onClose` adaptor method:
+    - Create `consensus.ledger_close` span
+    - Set attributes: close_time, mode, transaction count in initial position
+
+  - Note: The Consensus template class in `include/xrpl/consensus/Consensus.h` drives phase transitions — check if instrumentation goes there or in the Adaptor
+
+**Key modified files**:
+
+- `src/xrpld/app/consensus/RCLConsensus.cpp`
+- Possibly `include/xrpl/consensus/Consensus.h` (for template-level phase tracking)
+
+**Reference**:
+
+- [04-code-samples.md §4.5.2](./04-code-samples.md) — phaseTransition instrumentation
+
+---
+
+## Task 4.3: Instrument Proposal Handling
+
+**Objective**: Trace proposal send and receive to show validator coordination.
+
+**What to do**:
+
+- Edit `src/xrpld/app/consensus/RCLConsensus.cpp`:
+  - In `Adaptor::propose()`:
+    - Create `consensus.proposal.send` span
+    - Set attributes: `xrpl.consensus.round` (proposal sequence), proposal hash
+    - Inject trace context into outgoing `TMProposeSet::trace_context` (from Phase 3 protobuf)
+
+  - In `Adaptor::peerProposal()` (or wherever peer proposals are received):
+    - Extract trace context from incoming `TMProposeSet::trace_context`
+    - Create `consensus.proposal.receive` span as child of extracted context
+    - Set attributes: `xrpl.consensus.proposer` (node ID), `xrpl.consensus.round`
+
+  - In `Adaptor::share(RCLCxPeerPos)`:
+    - Create `consensus.proposal.relay` span for relaying peer proposals
+
+**Key modified files**:
+
+- `src/xrpld/app/consensus/RCLConsensus.cpp`
+
+**Reference**:
+
+- [04-code-samples.md §4.5.2](./04-code-samples.md) — peerProposal instrumentation
+- [02-design-decisions.md §2.4.4](./02-design-decisions.md) — Consensus attribute schema
+
+---
+
+## Task 4.4: Instrument Validation Handling
+
+**Objective**: Trace validation send and receive to show ledger validation flow.
+
+**What to do**:
+
+- Edit `src/xrpld/app/consensus/RCLConsensus.cpp` (or the validation handler):
+  - When sending our validation:
+    - Create `consensus.validation.send` span
+    - Set attributes: validated ledger hash, sequence, signing time
+
+  - When receiving a peer validation:
+    - Extract trace context from `TMValidation::trace_context` (if present)
+    - Create `consensus.validation.receive` span
+    - Set attributes: `xrpl.consensus.validator` (node ID), ledger hash
+
+**Key modified files**:
+
+- `src/xrpld/app/consensus/RCLConsensus.cpp`
+- `src/xrpld/app/misc/NetworkOPs.cpp` (if validation handling is here)
+
+---
+
+## Task 4.5: Add Consensus-Specific Attributes
+
+**Objective**: Enrich consensus spans with detailed attributes for debugging and analysis.
+
+**What to do**:
+
+- Review all consensus spans and ensure they include:
+  - `xrpl.consensus.ledger.seq` — target ledger sequence number
+  - `xrpl.consensus.round` — consensus round number
+  - `xrpl.consensus.mode` — proposing/observing/wrongLedger
+  - `xrpl.consensus.phase` — current phase name
+  - `xrpl.consensus.phase_duration_ms` — time spent in phase
+  - `xrpl.consensus.proposers` — number of trusted proposers
+  - `xrpl.consensus.tx_count` — transactions in proposed set
+  - `xrpl.consensus.disputes` — number of disputed transactions
+  - `xrpl.consensus.converge_percent` — convergence percentage
+
+**Key modified files**:
+
+- `src/xrpld/app/consensus/RCLConsensus.cpp`
+
+---
+
+## Task 4.6: Correlate Transaction and Consensus Traces
+
+**Objective**: Link transaction traces from Phase 3 with consensus traces so you can follow a transaction from submission through consensus into the ledger.
+
+**What to do**:
+
+- In `onClose()` or `onAccept()`:
+  - When building the consensus position, link the round span to individual transaction spans using span links (if OTel SDK supports it) or events
+  - At minimum, record the transaction hashes included in the consensus set as span events: `tx.included` with `xrpl.tx.hash` attribute
+
+- In `processTransactionSet()` (NetworkOPs):
+  - If the consensus round span context is available, create child spans for each transaction applied to the ledger
+
+**Key modified files**:
+
+- `src/xrpld/app/consensus/RCLConsensus.cpp`
+- `src/xrpld/app/misc/NetworkOPs.cpp`
+
+---
+
+## Task 4.7: Build Verification and Testing
+
+**Objective**: Verify all Phase 4 changes compile and don't affect consensus timing.
+
+**What to do**:
+
+1. Build with `telemetry=ON` — verify no compilation errors
+2. Build with `telemetry=OFF` — verify no regressions (critical for consensus code)
+3. Run existing consensus-related unit tests
+4. Verify that all macros expand to no-ops when disabled
+5. Check that no consensus-critical code paths are affected by instrumentation overhead
+
+**Verification Checklist**:
+
+- [ ] Build succeeds with telemetry ON
+- [ ] Build succeeds with telemetry OFF
+- [ ] Existing consensus tests pass
+- [ ] No new includes in consensus headers when telemetry is OFF
+- [ ] Phase timing instrumentation doesn't use blocking operations
+
+---
+
+## Summary
+
+| Task | Description                           | New Files | Modified Files | Depends On    |
+| ---- | ------------------------------------- | --------- | -------------- | ------------- |
+| 4.1  | Consensus round start instrumentation | 0         | 2              | Phase 3       |
+| 4.2  | Phase transition instrumentation      | 0         | 1-2            | 4.1           |
+| 4.3  | Proposal handling instrumentation     | 0         | 1              | 4.1           |
+| 4.4  | Validation handling instrumentation   | 0         | 1-2            | 4.1           |
+| 4.5  | Consensus-specific attributes         | 0         | 1              | 4.2, 4.3, 4.4 |
+| 4.6  | Transaction-consensus correlation     | 0         | 2              | 4.2, Phase 3  |
+| 4.7  | Build verification and testing        | 0         | 0              | 4.1-4.6       |
+
+**Parallel work**: Tasks 4.2, 4.3, and 4.4 can run in parallel after 4.1 is complete. Task 4.5 depends on all three. Task 4.6 depends on 4.2 and Phase 3.
+
+### Implemented Spans
+
+| Span Name                   | Method                             | Key Attributes                                                                                                                |
+| --------------------------- | ---------------------------------- | ----------------------------------------------------------------------------------------------------------------------------- |
+| `consensus.proposal.send`   | `Adaptor::propose`                 | `xrpl.consensus.round`                                                                                                        |
+| `consensus.ledger_close`    | `Adaptor::onClose`                 | `xrpl.consensus.ledger.seq`, `xrpl.consensus.mode`                                                                            |
+| `consensus.accept`          | `Adaptor::onAccept`                | `xrpl.consensus.proposers`, `xrpl.consensus.round_time_ms`                                                                    |
+| `consensus.accept.apply`    | `Adaptor::doAccept`                | `xrpl.consensus.close_time`, `close_time_correct`, `close_resolution_ms`, `state`, `proposing`, `round_time_ms`, `ledger.seq` |
+| `consensus.validation.send` | `Adaptor::onAccept` (via validate) | `xrpl.consensus.proposing`                                                                                                    |
+
+#### Close Time Attributes (consensus.accept.apply)
+
+The `consensus.accept.apply` span captures ledger close time agreement details
+driven by `avCT_CONSENSUS_PCT` (75% validator agreement threshold):
+
+- **`xrpl.consensus.close_time`** — Agreed-upon ledger close time (epoch seconds). When validators disagree (`consensusCloseTime == epoch`), this is synthetically set to `prevCloseTime + 1s`.
+- **`xrpl.consensus.close_time_correct`** — `true` if validators reached agreement, `false` if they "agreed to disagree" (close time forced to prev+1s).
+- **`xrpl.consensus.close_resolution_ms`** — Rounding granularity for close time (starts at 30s, decreases as ledger interval stabilizes).
+- **`xrpl.consensus.state`** — `"finished"` (normal) or `"moved_on"` (consensus failed, adopted best available).
+- **`xrpl.consensus.proposing`** — Whether this node was proposing.
+- **`xrpl.consensus.round_time_ms`** — Total consensus round duration.
+
+**Exit Criteria** (from [06-implementation-phases.md §6.11.4](./06-implementation-phases.md)):
+
+- [ ] Complete consensus round traces
+- [ ] Phase transitions visible
+- [ ] Proposals and validations traced
+- [ ] Close time agreement tracked (per `avCT_CONSENSUS_PCT`)
+- [ ] No impact on consensus timing

OpenTelemetryPlan/Phase5_IntegrationTest_taskList.md

@@ -0,0 +1,221 @@
+# Phase 5: Integration Test Task List
+
+> **Goal**: End-to-end verification of the complete telemetry pipeline using a
+> 6-node consensus network. Proves that RPC, transaction, and consensus spans
+> flow through the observability stack (otel-collector, Jaeger, Prometheus,
+> Grafana) under realistic conditions.
+>
+> **Scope**: Integration test script, manual testing plan, 6-node local network
+> setup, Jaeger/Prometheus/Grafana verification.
+>
+> **Branch**: `pratik/otel-phase5-docs-deployment`
+
+### Related Plan Documents
+
+| Document                                                         | Relevance                                  |
+| ---------------------------------------------------------------- | ------------------------------------------ |
+| [07-observability-backends.md](./07-observability-backends.md)   | Jaeger, Grafana, Prometheus setup          |
+| [05-configuration-reference.md](./05-configuration-reference.md) | Collector config, Docker Compose           |
+| [06-implementation-phases.md](./06-implementation-phases.md)     | Phase 5 tasks, definition of done          |
+| [Phase5_taskList.md](./Phase5_taskList.md)                       | Phase 5 main task list (5.6 = integration) |
+
+---
+
+## Task IT.1: Create Integration Test Script
+
+**Objective**: Automated bash script that stands up a 6-node xrpld network
+with telemetry, exercises all span categories, and verifies data in
+Jaeger/Prometheus.
+
+**What to do**:
+
+- Create `docker/telemetry/integration-test.sh`:
+  - Prerequisites check (docker, xrpld binary, curl, jq)
+  - Start observability stack via `docker compose`
+  - Generate 6 validator key pairs via temp standalone xrpld
+  - Generate 6 node configs + shared `validators.txt`
+  - Start 6 xrpld nodes in consensus mode (`--start`, no `-a`)
+  - Wait for all nodes to reach `"proposing"` state (120s timeout)
+
+**Key new file**: `docker/telemetry/integration-test.sh`
+
+**Verification**:
+
+- [ ] Script starts without errors
+- [ ] All 6 nodes reach "proposing" state
+- [ ] Observability stack is healthy (otel-collector, Jaeger, Prometheus, Grafana)
+
+---
+
+## Task IT.2: RPC Span Verification (Phase 2)
+
+**Objective**: Verify RPC spans flow through the telemetry pipeline.
+
+**What to do**:
+
+- Send `server_info`, `server_state`, `ledger` RPCs to node1 (port 5005)
+- Wait for batch export (5s)
+- Query Jaeger API for:
+  - `rpc.request` spans (ServerHandler::onRequest)
+  - `rpc.process` spans (ServerHandler::processRequest)
+  - `rpc.command.server_info` spans (callMethod)
+  - `rpc.command.server_state` spans (callMethod)
+  - `rpc.command.ledger` spans (callMethod)
+- Verify `xrpl.rpc.command` attribute present on `rpc.command.*` spans
+
+**Verification**:
+
+- [ ] Jaeger shows `rpc.request` traces
+- [ ] Jaeger shows `rpc.process` traces
+- [ ] Jaeger shows `rpc.command.*` traces with correct attributes
+
+---
+
+## Task IT.3: Transaction Span Verification (Phase 3)
+
+**Objective**: Verify transaction spans flow through the telemetry pipeline.
+
+**What to do**:
+
+- Get genesis account sequence via `account_info` RPC
+- Submit Payment transaction using genesis seed (`snoPBrXtMeMyMHUVTgbuqAfg1SUTb`)
+- Wait for consensus inclusion (10s)
+- Query Jaeger API for:
+  - `tx.process` spans (NetworkOPsImp::processTransaction) on submitting node
+  - `tx.receive` spans (PeerImp::handleTransaction) on peer nodes
+- Verify `xrpl.tx.hash` attribute on `tx.process` spans
+- Verify `xrpl.peer.id` attribute on `tx.receive` spans
+
+**Verification**:
+
+- [ ] Jaeger shows `tx.process` traces with `xrpl.tx.hash`
+- [ ] Jaeger shows `tx.receive` traces with `xrpl.peer.id`
+
+---
+
+## Task IT.4: Consensus Span Verification (Phase 4)
+
+**Objective**: Verify consensus spans flow through the telemetry pipeline.
+
+**What to do**:
+
+- Consensus runs automatically in 6-node network
+- Query Jaeger API for:
+  - `consensus.proposal.send` (Adaptor::propose)
+  - `consensus.ledger_close` (Adaptor::onClose)
+  - `consensus.accept` (Adaptor::onAccept)
+  - `consensus.validation.send` (Adaptor::validate)
+- Verify attributes:
+  - `xrpl.consensus.mode` on `consensus.ledger_close`
+  - `xrpl.consensus.proposers` on `consensus.accept`
+  - `xrpl.consensus.ledger.seq` on `consensus.validation.send`
+
+**Verification**:
+
+- [ ] Jaeger shows `consensus.ledger_close` traces with `xrpl.consensus.mode`
+- [ ] Jaeger shows `consensus.accept` traces with `xrpl.consensus.proposers`
+- [ ] Jaeger shows `consensus.proposal.send` traces
+- [ ] Jaeger shows `consensus.validation.send` traces
+
+---
+
+## Task IT.5: Spanmetrics Verification (Phase 5)
+
+**Objective**: Verify spanmetrics connector derives RED metrics from spans.
+
+**What to do**:
+
+- Query Prometheus for `traces_span_metrics_calls_total`
+- Query Prometheus for `traces_span_metrics_duration_milliseconds_count`
+- Verify Grafana loads at `http://localhost:3000`
+
+**Verification**:
+
+- [ ] Prometheus returns non-empty results for `traces_span_metrics_calls_total`
+- [ ] Prometheus returns non-empty results for duration histogram
+- [ ] Grafana UI accessible with dashboards visible
+
+---
+
+## Task IT.6: Manual Testing Plan
+
+**Objective**: Document how to run tests manually for future reference.
+
+**What to do**:
+
+- Create `docker/telemetry/TESTING.md` with:
+  - Prerequisites section
+  - Single-node standalone test (quick verification)
+  - 6-node consensus test (full verification)
+  - Expected span catalog (all 12 span names with attributes)
+  - Verification queries (Jaeger API, Prometheus API)
+  - Troubleshooting guide
+
+**Key new file**: `docker/telemetry/TESTING.md`
+
+**Verification**:
+
+- [ ] Document covers both single-node and multi-node testing
+- [ ] All 12 span names documented with source file and attributes
+- [ ] Troubleshooting section covers common failure modes
+
+---
+
+## Task IT.7: Run and Verify
+
+**Objective**: Execute the integration test and validate results.
+
+**What to do**:
+
+- Run `docker/telemetry/integration-test.sh` locally
+- Debug any failures
+- Leave stack running for manual verification
+- Share URLs:
+  - Jaeger: `http://localhost:16686`
+  - Grafana: `http://localhost:3000`
+  - Prometheus: `http://localhost:9090`
+
+**Verification**:
+
+- [ ] Script completes with all checks passing
+- [ ] Jaeger UI shows rippled service with all expected span names
+- [ ] Grafana dashboards load and show data
+
+---
+
+## Task IT.8: Commit
+
+**Objective**: Commit all new files to Phase 5 branch.
+
+**What to do**:
+
+- Run `pcc` (pre-commit checks)
+- Commit 3 new files to `pratik/otel-phase5-docs-deployment`
+
+**Verification**:
+
+- [ ] `pcc` passes
+- [ ] Commit created on Phase 5 branch
+
+---
+
+## Summary
+
+| Task | Description                   | New Files | Depends On |
+| ---- | ----------------------------- | --------- | ---------- |
+| IT.1 | Integration test script       | 1         | Phase 5    |
+| IT.2 | RPC span verification         | 0         | IT.1       |
+| IT.3 | Transaction span verification | 0         | IT.1       |
+| IT.4 | Consensus span verification   | 0         | IT.1       |
+| IT.5 | Spanmetrics verification      | 0         | IT.1       |
+| IT.6 | Manual testing plan           | 1         | --         |
+| IT.7 | Run and verify                | 0         | IT.1-IT.6  |
+| IT.8 | Commit                        | 0         | IT.7       |
+
+**Exit Criteria**:
+
+- [ ] All 6 xrpld nodes reach "proposing" state
+- [ ] All 11 expected span names visible in Jaeger
+- [ ] Spanmetrics available in Prometheus
+- [ ] Grafana dashboards show data
+- [ ] Manual testing plan document complete

OpenTelemetryPlan/Phase5_taskList.md

@@ -0,0 +1,241 @@
+# Phase 5: Documentation & Deployment Task List
+
+> **Goal**: Production readiness — Grafana dashboards, spanmetrics pipeline, operator runbook, alert definitions, and final integration testing. This phase ensures the telemetry system is useful and maintainable in production.
+>
+> **Scope**: Grafana dashboard definitions, OTel Collector spanmetrics connector, Prometheus integration, alert rules, operator documentation, and production-ready Docker Compose stack.
+>
+> **Branch**: `pratik/otel-phase5-docs-deployment` (from `pratik/otel-phase4-consensus-tracing`)
+
+### Related Plan Documents
+
+| Document                                                         | Relevance                                                                  |
+| ---------------------------------------------------------------- | -------------------------------------------------------------------------- |
+| [07-observability-backends.md](./07-observability-backends.md)   | Jaeger setup (§7.1), Grafana dashboards (§7.6), alerts (§7.6.3)            |
+| [05-configuration-reference.md](./05-configuration-reference.md) | Collector config (§5.5), production config (§5.5.2), Docker Compose (§5.6) |
+| [06-implementation-phases.md](./06-implementation-phases.md)     | Phase 5 tasks (§6.6), definition of done (§6.11.5)                         |
+
+---
+
+## Task 5.1: Add Spanmetrics Connector to OTel Collector
+
+**Objective**: Derive RED metrics (Rate, Errors, Duration) from trace spans automatically, enabling Grafana time-series dashboards.
+
+**What to do**:
+
+- Edit `docker/telemetry/otel-collector-config.yaml`:
+  - Add `spanmetrics` connector:
+    ```yaml
+    connectors:
+      spanmetrics:
+        histogram:
+          explicit:
+            buckets: [1ms, 5ms, 10ms, 25ms, 50ms, 100ms, 250ms, 500ms, 1s, 5s]
+        dimensions:
+          - name: xrpl.rpc.command
+          - name: xrpl.rpc.status
+          - name: xrpl.consensus.phase
+          - name: xrpl.tx.type
+    ```
+  - Add `prometheus` exporter:
+    ```yaml
+    exporters:
+      prometheus:
+        endpoint: 0.0.0.0:8889
+    ```
+  - Wire the pipeline:
+    ```yaml
+    service:
+      pipelines:
+        traces:
+          receivers: [otlp]
+          processors: [batch]
+          exporters: [debug, otlp/jaeger, spanmetrics]
+        metrics:
+          receivers: [spanmetrics]
+          exporters: [prometheus]
+    ```
+
+- Edit `docker/telemetry/docker-compose.yml`:
+  - Expose port `8889` on the collector for Prometheus scraping
+  - Add Prometheus service
+  - Add Prometheus as Grafana datasource
+
+**Key modified files**:
+
+- `docker/telemetry/otel-collector-config.yaml`
+- `docker/telemetry/docker-compose.yml`
+
+**Key new files**:
+
+- `docker/telemetry/prometheus.yml` (Prometheus scrape config)
+- `docker/telemetry/grafana/provisioning/datasources/prometheus.yaml`
+
+**Reference**:
+
+- [POC_taskList.md §Next Steps](./POC_taskList.md) — Metrics pipeline for Grafana dashboards
+
+---
+
+## Task 5.2: Create Grafana Dashboards
+
+**Objective**: Provide pre-built Grafana dashboards for RPC performance, transaction lifecycle, and consensus health.
+
+**What to do**:
+
+- Create `docker/telemetry/grafana/provisioning/dashboards/dashboards.yaml` (provisioning config)
+- Create dashboard JSON files:
+  1. **RPC Performance Dashboard** (`rpc-performance.json`):
+     - RPC request latency (p50/p95/p99) by command — histogram panel
+     - RPC throughput (requests/sec) by command — time series
+     - RPC error rate by command — bar gauge
+     - Top slowest RPC commands — table
+
+  2. **Transaction Overview Dashboard** (`transaction-overview.json`):
+     - Transaction processing rate — time series
+     - Transaction latency distribution — histogram
+     - Suppression rate (duplicates) — stat panel
+     - Transaction processing path (sync vs async) — pie chart
+
+  3. **Consensus Health Dashboard** (`consensus-health.json`):
+     - Consensus round duration — time series
+     - Phase duration breakdown (open/establish/accept) — stacked bar
+     - Proposals sent/received per round — stat panel
+     - Consensus mode distribution (proposing/observing) — pie chart
+
+- Store dashboards in `docker/telemetry/grafana/dashboards/`
+
+**Key new files**:
+
+- `docker/telemetry/grafana/provisioning/dashboards/dashboards.yaml`
+- `docker/telemetry/grafana/dashboards/rpc-performance.json`
+- `docker/telemetry/grafana/dashboards/transaction-overview.json`
+- `docker/telemetry/grafana/dashboards/consensus-health.json`
+
+**Reference**:
+
+- [07-observability-backends.md §7.6](./07-observability-backends.md) — Grafana dashboard specifications
+- [01-architecture-analysis.md §1.8.3](./01-architecture-analysis.md) — Dashboard panel examples
+
+---
+
+## Task 5.3: Define Alert Rules
+
+**Objective**: Create alert definitions for key telemetry anomalies.
+
+**What to do**:
+
+- Create `docker/telemetry/grafana/provisioning/alerting/alerts.yaml`:
+  - **RPC Latency Alert**: p99 latency > 1s for any command over 5 minutes
+  - **RPC Error Rate Alert**: Error rate > 5% for any command over 5 minutes
+  - **Consensus Duration Alert**: Round duration > 10s (warn), > 30s (critical)
+  - **Transaction Processing Alert**: Processing rate drops below threshold
+  - **Telemetry Pipeline Health**: No spans received for > 2 minutes
+
+**Key new files**:
+
+- `docker/telemetry/grafana/provisioning/alerting/alerts.yaml`
+
+**Reference**:
+
+- [07-observability-backends.md §7.6.3](./07-observability-backends.md) — Alert rule definitions
+
+---
+
+## Task 5.4: Production Collector Configuration
+
+**Objective**: Create a production-ready OTel Collector configuration with tail-based sampling and resource limits.
+
+**What to do**:
+
+- Create `docker/telemetry/otel-collector-config-production.yaml`:
+  - Tail-based sampling policy:
+    - Always sample errors and slow traces
+    - 10% base sampling rate for normal traces
+    - Always sample first trace for each unique RPC command
+  - Resource limits:
+    - Memory limiter processor (80% of available memory)
+    - Queued retry for export failures
+  - TLS configuration for production endpoints
+  - Health check endpoint
+
+**Key new files**:
+
+- `docker/telemetry/otel-collector-config-production.yaml`
+
+**Reference**:
+
+- [05-configuration-reference.md §5.5.2](./05-configuration-reference.md) — Production collector config
+
+---
+
+## Task 5.5: Operator Runbook
+
+**Objective**: Create operator documentation for managing the telemetry system in production.
+
+**What to do**:
+
+- Create `docs/telemetry-runbook.md`:
+  - **Setup**: How to enable telemetry in rippled
+  - **Configuration**: All config options with descriptions
+  - **Collector Deployment**: Docker Compose vs. Kubernetes vs. bare metal
+  - **Troubleshooting**: Common issues and resolutions
+    - No traces appearing
+    - High memory usage from telemetry
+    - Collector connection failures
+    - Sampling configuration tuning
+  - **Performance Tuning**: Batch size, queue size, sampling ratio guidelines
+  - **Upgrading**: How to upgrade OTel SDK and Collector versions
+
+**Key new files**:
+
+- `docs/telemetry-runbook.md`
+
+---
+
+## Task 5.6: Final Integration Testing
+
+**Objective**: Validate the complete telemetry stack end-to-end.
+
+**What to do**:
+
+1. Start full Docker stack (Collector, Jaeger, Grafana, Prometheus)
+2. Build rippled with `telemetry=ON`
+3. Run in standalone mode with telemetry enabled
+4. Generate RPC traffic and verify traces in Jaeger
+5. Verify dashboards populate in Grafana
+6. Verify alerts trigger correctly
+7. Test telemetry OFF path (no regressions)
+8. Run full test suite
+
+**Verification Checklist**:
+
+- [ ] Docker stack starts without errors
+- [ ] Traces appear in Jaeger with correct hierarchy
+- [ ] Grafana dashboards show metrics derived from spans
+- [ ] Prometheus scrapes spanmetrics successfully
+- [ ] Alerts can be triggered by simulated conditions
+- [ ] Build succeeds with telemetry ON and OFF
+- [ ] Full test suite passes
+
+---
+
+## Summary
+
+| Task | Description                        | New Files | Modified Files | Depends On |
+| ---- | ---------------------------------- | --------- | -------------- | ---------- |
+| 5.1  | Spanmetrics connector + Prometheus | 2         | 2              | Phase 4    |
+| 5.2  | Grafana dashboards                 | 4         | 0              | 5.1        |
+| 5.3  | Alert definitions                  | 1         | 0              | 5.1        |
+| 5.4  | Production collector config        | 1         | 0              | Phase 4    |
+| 5.5  | Operator runbook                   | 1         | 0              | Phase 4    |
+| 5.6  | Final integration testing          | 0         | 0              | 5.1-5.5    |
+
+**Parallel work**: Tasks 5.1, 5.4, and 5.5 can run in parallel. Tasks 5.2 and 5.3 depend on 5.1. Task 5.6 depends on all others.
+
+**Exit Criteria** (from [06-implementation-phases.md §6.11.5](./06-implementation-phases.md)):
+
+- [ ] Dashboards deployed and showing data
+- [ ] Alerts configured and tested
+- [ ] Operator documentation complete
+- [ ] Production collector config ready
+- [ ] Full test suite passes

OpenTelemetryPlan/Phase7_taskList.md

@@ -0,0 +1,256 @@
+# Phase 7: Native OTel Metrics Migration — Task List
+
+> **Goal**: Replace `StatsDCollector` with a native OpenTelemetry Metrics SDK implementation behind the existing `beast::insight::Collector` interface, eliminating the StatsD UDP dependency.
+>
+> **Scope**: New `OTelCollectorImpl` class, `CollectorManager` config change, OTel Collector pipeline update, Grafana dashboard metric name migration, integration tests.
+>
+> **Branch**: `pratik/otel-phase7-native-metrics` (from `pratik/otel-phase6-statsd`)
+
+### Related Plan Documents
+
+| Document                                                             | Relevance                                                       |
+| -------------------------------------------------------------------- | --------------------------------------------------------------- |
+| [06-implementation-phases.md](./06-implementation-phases.md)         | Phase 7 plan: motivation, architecture, exit criteria (§6.8)    |
+| [02-design-decisions.md](./02-design-decisions.md)                   | Collector interface design, beast::insight coexistence strategy |
+| [05-configuration-reference.md](./05-configuration-reference.md)     | `[insight]` and `[telemetry]` config sections                   |
+| [09-data-collection-reference.md](./09-data-collection-reference.md) | Complete metric inventory that must be preserved                |
+
+---
+
+## Task 7.1: Add OTel Metrics SDK to Build Dependencies
+
+**Objective**: Enable the OTel C++ Metrics SDK components in the build system.
+
+**What to do**:
+
+- Edit `conanfile.py`:
+  - Add OTel metrics SDK components to the dependency list when `telemetry=True`
+  - Components needed: `opentelemetry-cpp::metrics`, `opentelemetry-cpp::otlp_http_metric_exporter`
+
+- Edit `CMakeLists.txt` (telemetry section):
+  - Link `opentelemetry::metrics` and `opentelemetry::otlp_http_metric_exporter` targets
+
+**Key modified files**:
+
+- `conanfile.py`
+- `CMakeLists.txt` (or the relevant telemetry cmake target)
+
+**Reference**: [05-configuration-reference.md §5.3](./05-configuration-reference.md) — CMake integration
+
+---
+
+## Task 7.2: Implement OTelCollector Class
+
+**Objective**: Create the core `OTelCollector` implementation that maps beast::insight instruments to OTel Metrics SDK instruments.
+
+**What to do**:
+
+- Create `include/xrpl/beast/insight/OTelCollector.h`:
+  - Public factory: `static std::shared_ptr<OTelCollector> New(std::string const& endpoint, std::string const& prefix, beast::Journal journal)`
+  - Derives from `StatsDCollector` (or directly from `Collector` — TBD based on shared code)
+
+- Create `src/libxrpl/beast/insight/OTelCollector.cpp` (~400-500 lines):
+  - **OTelCounterImpl**: Wraps `opentelemetry::metrics::Counter<int64_t>`. `increment(amount)` calls `counter->Add(amount)`.
+  - **OTelGaugeImpl**: Uses `opentelemetry::metrics::ObservableGauge<uint64_t>` with an async callback. `set(value)` stores value atomically; callback reads it during collection.
+  - **OTelMeterImpl**: Wraps `opentelemetry::metrics::Counter<uint64_t>`. `increment(amount)` calls `counter->Add(amount)`. Semantically identical to Counter but unsigned.
+  - **OTelEventImpl**: Wraps `opentelemetry::metrics::Histogram<double>`. `notify(duration)` calls `histogram->Record(duration.count())`. Uses explicit bucket boundaries matching SpanMetrics: [1, 5, 10, 25, 50, 100, 250, 500, 1000, 5000] ms.
+  - **OTelHookImpl**: Stores handler function. Called during periodic metric collection (same 1s pattern via PeriodicMetricReader).
+  - **OTelCollectorImp**: Main class.
+    - Creates `MeterProvider` with `PeriodicMetricReader` (1s export interval)
+    - Creates `OtlpHttpMetricExporter` pointing to `[telemetry]` endpoint
+    - Sets resource attributes (service.name, service.instance.id) matching trace exporter
+    - Implements all `make_*()` factory methods
+    - Prefixes metric names with `[insight] prefix=` value
+
+- Guard all OTel SDK includes with `#ifdef XRPL_ENABLE_TELEMETRY` to compile to `NullCollector` equivalents when telemetry disabled.
+
+**Key new files**:
+
+- `include/xrpl/beast/insight/OTelCollector.h`
+- `src/libxrpl/beast/insight/OTelCollector.cpp`
+
+**Key patterns to follow**:
+
+- Match `StatsDCollector.cpp` structure: private impl classes, intrusive list for metrics, strand-based thread safety
+- Match existing telemetry code style from `src/libxrpl/telemetry/Telemetry.cpp`
+- Use RAII for MeterProvider lifecycle (shutdown on destructor)
+
+**Reference**: [04-code-samples.md](./04-code-samples.md) — code style and patterns
+
+---
+
+## Task 7.3: Update CollectorManager
+
+**Objective**: Add `server=otel` config option to route metric creation to the new OTel backend.
+
+**What to do**:
+
+- Edit `src/xrpld/app/main/CollectorManager.cpp`:
+  - In the constructor, add a third branch after `server == "statsd"`:
+    ```cpp
+    else if (server == "otel")
+    {
+        // Read endpoint from [telemetry] section
+        auto const endpoint = get(telemetryParams, "endpoint",
+            "http://localhost:4318/v1/metrics");
+        std::string const& prefix(get(params, "prefix"));
+        m_collector = beast::insight::OTelCollector::New(
+            endpoint, prefix, journal);
+    }
+    ```
+  - This requires access to the `[telemetry]` config section — may need to pass it as a parameter or read from Application config.
+
+- Edit `src/xrpld/app/main/CollectorManager.h`:
+  - Add `#include <xrpl/beast/insight/OTelCollector.h>`
+
+**Key modified files**:
+
+- `src/xrpld/app/main/CollectorManager.cpp`
+- `src/xrpld/app/main/CollectorManager.h`
+
+---
+
+## Task 7.4: Update OTel Collector Configuration
+
+**Objective**: Add a metrics pipeline to the OTLP receiver and remove the StatsD receiver dependency.
+
+**What to do**:
+
+- Edit `docker/telemetry/otel-collector-config.yaml`:
+  - Remove `statsd` receiver (no longer needed when `server=otel`)
+  - Add metrics pipeline under `service.pipelines`:
+    ```yaml
+    metrics:
+      receivers: [otlp, spanmetrics]
+      processors: [batch]
+      exporters: [prometheus]
+    ```
+  - The OTLP receiver already listens on :4318 — it just needs to be added to the metrics pipeline receivers.
+  - Keep `spanmetrics` connector in the metrics pipeline so span-derived RED metrics continue working.
+
+- Edit `docker/telemetry/docker-compose.yml`:
+  - Remove UDP :8125 port mapping from otel-collector service
+  - Update rippled service config: change `[insight] server=statsd` to `server=otel`
+
+**Key modified files**:
+
+- `docker/telemetry/otel-collector-config.yaml`
+- `docker/telemetry/docker-compose.yml`
+
+**Note**: Keep a commented-out `statsd` receiver block for operators who need backward compatibility.
+
+---
+
+## Task 7.5: Preserve Metric Names in Prometheus
+
+**Objective**: Ensure existing Grafana dashboards continue working with identical metric names.
+
+**What to do**:
+
+- In `OTelCollector.cpp`, construct OTel instrument names to match existing Prometheus metric names:
+  - beast::insight `make_gauge("LedgerMaster", "Validated_Ledger_Age")` → OTel instrument name: `rippled_LedgerMaster_Validated_Ledger_Age`
+  - The prefix + group + name concatenation must produce the same string as `StatsDCollector`'s format
+  - Use underscores as separators (matching StatsD convention)
+
+- Verify in integration test that key Prometheus queries still return data:
+  - `rippled_LedgerMaster_Validated_Ledger_Age`
+  - `rippled_Peer_Finder_Active_Inbound_Peers`
+  - `rippled_rpc_requests`
+
+**Key consideration**: OTel Prometheus exporter may normalize metric names differently than StatsD receiver. Test this early (Task 7.2) and adjust naming strategy if needed. The OTel SDK's Prometheus exporter adds `_total` suffix to counters and converts dots to underscores — match existing conventions.
+
+---
+
+## Task 7.6: Update Grafana Dashboards
+
+**Objective**: Update the 3 StatsD dashboards if any metric names change due to OTLP export format differences.
+
+**What to do**:
+
+- If Task 7.5 confirms metric names are preserved exactly, no dashboard changes needed.
+- If OTLP export produces different names (e.g., `_total` suffix on counters), update:
+  - `docker/telemetry/grafana/dashboards/statsd-node-health.json`
+  - `docker/telemetry/grafana/dashboards/statsd-network-traffic.json`
+  - `docker/telemetry/grafana/dashboards/statsd-rpc-pathfinding.json`
+- Rename dashboard titles from "StatsD" to "System Metrics" or similar (since they're no longer StatsD-sourced).
+
+**Key modified files**:
+
+- `docker/telemetry/grafana/dashboards/statsd-*.json` (3 files, conditionally)
+
+---
+
+## Task 7.7: Update Integration Tests
+
+**Objective**: Verify the full OTLP metrics pipeline end-to-end.
+
+**What to do**:
+
+- Edit `docker/telemetry/integration-test.sh`:
+  - Update test config to use `[insight] server=otel`
+  - Verify metrics arrive in Prometheus via OTLP (not StatsD)
+  - Add check that StatsD receiver is no longer required
+  - Preserve all existing metric presence checks
+
+**Key modified files**:
+
+- `docker/telemetry/integration-test.sh`
+
+---
+
+## Task 7.8: Update Documentation
+
+**Objective**: Update all plan docs, runbook, and reference docs to reflect the migration.
+
+**What to do**:
+
+- Edit `docs/telemetry-runbook.md`:
+  - Update `[insight]` config examples to show `server=otel`
+  - Update troubleshooting section (no more StatsD UDP debugging)
+
+- Edit `OpenTelemetryPlan/09-data-collection-reference.md`:
+  - Update Data Flow Overview diagram (remove StatsD receiver)
+  - Update Section 2 header from "StatsD Metrics" to "System Metrics (OTel native)"
+  - Update config examples
+
+- Edit `OpenTelemetryPlan/05-configuration-reference.md`:
+  - Add `server=otel` option to `[insight]` section docs
+
+- Edit `docker/telemetry/TESTING.md`:
+  - Update setup instructions to use `server=otel`
+
+**Key modified files**:
+
+- `docs/telemetry-runbook.md`
+- `OpenTelemetryPlan/09-data-collection-reference.md`
+- `OpenTelemetryPlan/05-configuration-reference.md`
+- `docker/telemetry/TESTING.md`
+
+---
+
+## Summary Table
+
+| Task | Description                            | New Files | Modified Files | Effort | Risk   | Depends On |
+| ---- | -------------------------------------- | --------- | -------------- | ------ | ------ | ---------- |
+| 7.1  | Add OTel Metrics SDK to build deps     | 0         | 2              | 0.5d   | Low    | —          |
+| 7.2  | Implement OTelCollector class          | 2         | 0              | 3d     | Medium | 7.1        |
+| 7.3  | Update CollectorManager config routing | 0         | 2              | 0.5d   | Low    | 7.2        |
+| 7.4  | Update OTel Collector YAML and Docker  | 0         | 2              | 0.5d   | Low    | 7.3        |
+| 7.5  | Preserve metric names in Prometheus    | 0         | 1              | 1d     | Medium | 7.2        |
+| 7.6  | Update Grafana dashboards (if needed)  | 0         | 3              | 1d     | Low    | 7.5        |
+| 7.7  | Update integration tests               | 0         | 1              | 0.5d   | Low    | 7.4        |
+| 7.8  | Update documentation                   | 0         | 4              | 1d     | Low    | 7.6        |
+
+**Total Effort**: 8 days
+
+**Parallel work**: Tasks 7.4 and 7.5 can run in parallel after 7.2/7.3 complete. Task 7.6 depends on 7.5's findings. Tasks 7.7 and 7.8 can run in parallel after 7.6.
+
+**Exit Criteria** (from [06-implementation-phases.md §6.8](./06-implementation-phases.md)):
+
+- [ ] All 255+ metrics visible in Prometheus via OTLP pipeline (no StatsD receiver)
+- [ ] `server=otel` is the default in development docker-compose
+- [ ] `server=statsd` still works as a fallback
+- [ ] Existing Grafana dashboards display data correctly
+- [ ] Integration test passes with OTLP-only metrics pipeline
+- [ ] No performance regression vs StatsD baseline (< 1% CPU overhead)
+- [ ] Deferred Task 6.1 (`|m` wire format) no longer relevant — Meter mapped to OTel Counter

OpenTelemetryPlan/Phase8_taskList.md

@@ -0,0 +1,234 @@
+# Phase 8: Log-Trace Correlation and Centralized Log Ingestion — Task List
+
+> **Goal**: Inject trace context (trace_id, span_id) into rippled's Journal log output for log-trace correlation, and add OTel Collector filelog receiver to ingest logs into Grafana Loki for unified observability.
+>
+> **Scope**: Two independent sub-phases — 8a (code change: trace_id in logs) and 8b (infra only: filelog receiver to Loki). No changes to the `beast::Journal` public API.
+>
+> **Branch**: `pratik/otel-phase8-log-correlation` (from `pratik/otel-phase7-native-metrics`)
+
+### Related Plan Documents
+
+| Document                                                         | Relevance                                                      |
+| ---------------------------------------------------------------- | -------------------------------------------------------------- |
+| [06-implementation-phases.md](./06-implementation-phases.md)     | Phase 8 plan: motivation, architecture, exit criteria (§6.8.1) |
+| [07-observability-backends.md](./07-observability-backends.md)   | Loki backend recommendation, Grafana data source provisioning  |
+| [Phase7_taskList.md](./Phase7_taskList.md)                       | Prerequisite — native OTel metrics pipeline must be working    |
+| [05-configuration-reference.md](./05-configuration-reference.md) | `[telemetry]` config (trace_id injection toggle)               |
+
+---
+
+## Task 8.1: Inject trace_id into Logs::format()
+
+**Objective**: Add OTel trace context to every log line that is emitted within an active span.
+
+**What to do**:
+
+- Edit `src/libxrpl/basics/Log.cpp`:
+  - In `Logs::format()` (around line 346), after severity is appended, check for active OTel span:
+    ```cpp
+    #ifdef XRPL_ENABLE_TELEMETRY
+    auto span = opentelemetry::trace::GetSpan(
+        opentelemetry::context::RuntimeContext::GetCurrent());
+    auto ctx = span->GetContext();
+    if (ctx.IsValid())
+    {
+        // Append trace context as structured fields
+        char traceId[33], spanId[17];
+        ctx.trace_id().ToLowerBase16(traceId);
+        ctx.span_id().ToLowerBase16(spanId);
+        output += "trace_id=";
+        output.append(traceId, 32);
+        output += " span_id=";
+        output.append(spanId, 16);
+        output += ' ';
+    }
+    #endif
+    ```
+  - Add `#include` for OTel context headers, guarded by `#ifdef XRPL_ENABLE_TELEMETRY`
+
+- Edit `include/xrpl/basics/Log.h`:
+  - No changes needed — format() signature unchanged
+
+**Key modified files**:
+
+- `src/libxrpl/basics/Log.cpp`
+
+**Performance note**: `GetSpan()` and `GetContext()` are thread-local reads with no locking — measured at <10ns per call. With ~1000 JLOG calls/min, this adds <10us/min of overhead.
+
+---
+
+## Task 8.2: Add Loki to Docker Compose Stack
+
+**Objective**: Add Grafana Loki as a log storage backend in the development observability stack.
+
+**What to do**:
+
+- Edit `docker/telemetry/docker-compose.yml`:
+  - Add Loki service:
+    ```yaml
+    loki:
+      image: grafana/loki:2.9.0
+      ports:
+        - "3100:3100"
+      command: -config.file=/etc/loki/local-config.yaml
+    ```
+  - Add Loki as a Grafana data source in provisioning
+
+- Create `docker/telemetry/grafana/provisioning/datasources/loki.yaml`:
+  - Configure Loki data source with derived fields linking `trace_id` to Tempo
+
+**Key new files**:
+
+- `docker/telemetry/grafana/provisioning/datasources/loki.yaml`
+
+**Key modified files**:
+
+- `docker/telemetry/docker-compose.yml`
+
+---
+
+## Task 8.3: Add Filelog Receiver to OTel Collector
+
+**Objective**: Configure the OTel Collector to tail rippled's log file and export to Loki.
+
+**What to do**:
+
+- Edit `docker/telemetry/otel-collector-config.yaml`:
+  - Add `filelog` receiver:
+    ```yaml
+    receivers:
+      filelog:
+        include: [/var/log/rippled/debug.log]
+        operators:
+          - type: regex_parser
+            regex: '^(?P<timestamp>\S+)\s+(?P<partition>\S+):(?P<severity>\S+)\s+(?:trace_id=(?P<trace_id>[a-f0-9]+)\s+span_id=(?P<span_id>[a-f0-9]+)\s+)?(?P<message>.*)$'
+            timestamp:
+              parse_from: attributes.timestamp
+              layout: "%Y-%m-%dT%H:%M:%S.%fZ"
+    ```
+  - Add logs pipeline:
+    ```yaml
+    service:
+      pipelines:
+        logs:
+          receivers: [filelog]
+          processors: [batch]
+          exporters: [otlp/loki]
+    ```
+  - Add Loki exporter:
+    ```yaml
+    exporters:
+      otlp/loki:
+        endpoint: loki:3100
+        tls:
+          insecure: true
+    ```
+
+- Mount rippled's log directory into the collector container via docker-compose volume
+
+**Key modified files**:
+
+- `docker/telemetry/otel-collector-config.yaml`
+- `docker/telemetry/docker-compose.yml`
+
+---
+
+## Task 8.4: Configure Grafana Trace-to-Log Correlation
+
+**Objective**: Enable one-click navigation from Tempo traces to Loki logs in Grafana.
+
+**What to do**:
+
+- Edit Grafana Tempo data source provisioning to add `tracesToLogs` configuration:
+
+  ```yaml
+  tracesToLogs:
+    datasourceUid: loki
+    filterByTraceID: true
+    filterBySpanID: false
+    tags: ["partition", "severity"]
+  ```
+
+- Edit Grafana Loki data source provisioning to add `derivedFields` linking trace_id back to Tempo:
+  ```yaml
+  derivedFields:
+    - datasourceUid: tempo
+      matcherRegex: "trace_id=(\\w+)"
+      name: TraceID
+      url: "$${__value.raw}"
+  ```
+
+**Key modified files**:
+
+- `docker/telemetry/grafana/provisioning/datasources/loki.yaml`
+- `docker/telemetry/grafana/provisioning/datasources/` (Tempo data source file)
+
+---
+
+## Task 8.5: Update Integration Tests
+
+**Objective**: Verify trace_id appears in logs and Loki correlation works.
+
+**What to do**:
+
+- Edit `docker/telemetry/integration-test.sh`:
+  - After sending RPC requests (which create spans), grep rippled's log output for `trace_id=`
+  - Verify trace_id matches a trace visible in Jaeger
+  - Optionally: query Loki via API to confirm log ingestion
+
+**Key modified files**:
+
+- `docker/telemetry/integration-test.sh`
+
+---
+
+## Task 8.6: Update Documentation
+
+**Objective**: Document the log correlation feature in runbook and reference docs.
+
+**What to do**:
+
+- Edit `docs/telemetry-runbook.md`:
+  - Add "Log-Trace Correlation" section explaining how to use Grafana Tempo -> Loki linking
+  - Add LogQL query examples for filtering by trace_id
+
+- Edit `OpenTelemetryPlan/09-data-collection-reference.md`:
+  - Add new section "3. Log Correlation" between SpanMetrics and StatsD sections
+  - Document the log format with trace_id injection
+  - Document Loki as a new backend
+
+- Edit `docker/telemetry/TESTING.md`:
+  - Add log correlation verification steps
+
+**Key modified files**:
+
+- `docs/telemetry-runbook.md`
+- `OpenTelemetryPlan/09-data-collection-reference.md`
+- `docker/telemetry/TESTING.md`
+
+---
+
+## Summary Table
+
+| Task | Description                                | Sub-Phase | New Files | Modified Files | Effort | Risk   | Depends On |
+| ---- | ------------------------------------------ | --------- | --------- | -------------- | ------ | ------ | ---------- |
+| 8.1  | Inject trace_id into Logs::format()        | 8a        | 0         | 1              | 1d     | Low    | Phase 7    |
+| 8.2  | Add Loki to Docker Compose stack           | 8b        | 1         | 1              | 0.5d   | Low    | --         |
+| 8.3  | Add filelog receiver to OTel Collector     | 8b        | 0         | 2              | 1d     | Medium | 8.1, 8.2   |
+| 8.4  | Configure Grafana trace-to-log correlation | 8b        | 0         | 2              | 0.5d   | Low    | 8.3        |
+| 8.5  | Update integration tests                   | 8a + 8b   | 0         | 1              | 0.5d   | Low    | 8.4        |
+| 8.6  | Update documentation                       | 8a + 8b   | 0         | 3              | 1d     | Low    | 8.5        |
+
+**Total Effort**: 4.5 days
+
+**Parallel work**: Task 8.2 (Loki infra) can run in parallel with Task 8.1 (code change). Tasks 8.3-8.6 are sequential.
+
+**Exit Criteria** (from [06-implementation-phases.md §6.8.1](./06-implementation-phases.md)):
+
+- [ ] Log lines within active spans contain `trace_id=<hex> span_id=<hex>`
+- [ ] Log lines outside spans have no trace context (no empty fields)
+- [ ] Loki ingests rippled logs via OTel Collector filelog receiver
+- [ ] Grafana Tempo -> Loki one-click correlation works
+- [ ] Grafana Loki -> Tempo reverse lookup works via derived field
+- [ ] Integration test verifies trace_id presence in logs
+- [ ] No performance regression from trace_id injection (< 0.1% overhead)

OpenTelemetryPlan/Phase9_taskList.md

@@ -0,0 +1,329 @@
+# Phase 9: Internal Metric Instrumentation Gap Fill — Task List
+
+> **Status**: Future Enhancement
+>
+> **Goal**: Instrument rippled to emit ~50+ metrics that exist in `get_counts`/`server_info`/TxQ/PerfLog but currently lack time-series export via the OTel or beast::insight pipelines.
+>
+> **Scope**: Hybrid approach — extend `beast::insight` for metrics near existing registrations, use OTel Metrics SDK `ObservableGauge` callbacks for new categories (TxQ, PerfLog, CountedObjects).
+>
+> **Branch**: `pratik/otel-phase9-metric-gap-fill` (from `pratik/otel-phase8-log-correlation`)
+>
+> **Depends on**: Phase 7 (native OTel metrics pipeline) and Phase 8 (log-trace correlation)
+
+### Related Plan Documents
+
+| Document                                                             | Relevance                                                      |
+| -------------------------------------------------------------------- | -------------------------------------------------------------- |
+| [06-implementation-phases.md](./06-implementation-phases.md)         | Phase 9 plan: motivation, architecture, exit criteria (§6.8.2) |
+| [09-data-collection-reference.md](./09-data-collection-reference.md) | Current metric inventory + future metrics section              |
+| [Phase7_taskList.md](./Phase7_taskList.md)                           | Prerequisite — OTel Metrics SDK and `OTelCollector` class      |
+| [Phase8_taskList.md](./Phase8_taskList.md)                           | Prerequisite — log-trace correlation                           |
+
+### Third-Party Consumer Context
+
+These metrics serve multiple external consumer categories identified during research:
+
+| Consumer Category         | Key Metrics They Need                                           |
+| ------------------------- | --------------------------------------------------------------- |
+| **Exchanges**             | Fee escalation levels, TxQ depth, settlement latency            |
+| **Payment Processors**    | Load factors, io_latency, transaction throughput                |
+| **Analytics Providers**   | NodeStore I/O, cache hit rates, counted objects                 |
+| **Validators/Operators**  | Per-job execution times, PerfLog RPC counters, consensus timing |
+| **Academic Researchers**  | Consensus performance time-series, fee market dynamics          |
+| **Institutional Custody** | Server health scores, reserve calculations, node availability   |
+
+---
+
+## Task 9.1: NodeStore I/O Metrics
+
+**Objective**: Export node store read/write performance as time-series metrics.
+
+**What to do**:
+
+- In `src/libxrpl/nodestore/Database.cpp`, extend existing `beast::insight` registrations to add:
+  - Gauge: `node_reads_total` (cumulative read operations)
+  - Gauge: `node_reads_hit` (cache-served reads)
+  - Gauge: `node_writes` (cumulative write operations)
+  - Gauge: `node_written_bytes` (cumulative bytes written)
+  - Gauge: `node_read_bytes` (cumulative bytes read)
+  - Gauge: `node_reads_duration_us` (cumulative read time in microseconds)
+  - Gauge: `write_load` (current write load score)
+  - Gauge: `read_queue` (items in read queue)
+
+- These values are already computed in `Database::getCountsJson()` (line ~236). Wire the same counters to `beast::insight` hooks.
+
+**Key modified files**:
+
+- `src/libxrpl/nodestore/Database.cpp`
+- `src/libxrpl/nodestore/Database.h` (add insight members)
+
+**Derived Prometheus metrics**: `rippled_nodestore_reads_total`, `rippled_nodestore_reads_hit`, `rippled_nodestore_write_load`, etc.
+
+**Grafana dashboard**: Add "NodeStore I/O" panel group to _Node Health_ dashboard.
+
+---
+
+## Task 9.2: Cache Hit Rate Metrics
+
+**Objective**: Export SHAMap and ledger cache performance as time-series gauges.
+
+**What to do**:
+
+- Register OTel `ObservableGauge` callbacks (via Phase 7's `OTelCollector`) for:
+  - `SLE_hit_rate` — SLE cache hit rate (0.0–1.0)
+  - `ledger_hit_rate` — Ledger object cache hit rate
+  - `AL_hit_rate` — AcceptedLedger cache hit rate
+  - `treenode_cache_size` — SHAMap TreeNode cache size (entries)
+  - `treenode_track_size` — Tracked tree nodes
+  - `fullbelow_size` — FullBelow cache size
+
+- The callback should read from the same sources as `GetCounts.cpp` handler (line ~43).
+
+- Create a centralized `MetricsRegistry` class that holds all OTel async gauge registrations, polled at 10-second intervals by the `PeriodicMetricReader`.
+
+**Key modified files**:
+
+- New: `src/xrpld/telemetry/MetricsRegistry.h` / `.cpp`
+- `src/xrpld/rpc/handlers/GetCounts.cpp` (extract shared access methods)
+- `src/xrpld/app/main/Application.cpp` (register MetricsRegistry at startup)
+
+**Derived Prometheus metrics**: `rippled_cache_SLE_hit_rate`, `rippled_cache_ledger_hit_rate`, `rippled_cache_treenode_size`, etc.
+
+---
+
+## Task 9.3: Transaction Queue (TxQ) Metrics
+
+**Objective**: Export TxQ depth, capacity, and fee escalation levels as time-series.
+
+**What to do**:
+
+- Register OTel `ObservableGauge` callbacks for TxQ state (from `TxQ.h` line ~143):
+  - `txq_count` — Current transactions in queue
+  - `txq_max_size` — Maximum queue capacity
+  - `txq_in_ledger` — Transactions in current open ledger
+  - `txq_per_ledger` — Expected transactions per ledger
+  - `txq_reference_fee_level` — Reference fee level
+  - `txq_min_processing_fee_level` — Minimum fee to get processed
+  - `txq_med_fee_level` — Median fee level in queue
+  - `txq_open_ledger_fee_level` — Open ledger fee escalation level
+
+- Add to the `MetricsRegistry` (Task 9.2).
+
+**Key modified files**:
+
+- `src/xrpld/telemetry/MetricsRegistry.cpp` (add TxQ callbacks)
+- `src/xrpld/app/tx/detail/TxQ.h` (expose metrics accessor if needed)
+
+**Derived Prometheus metrics**: `rippled_txq_count`, `rippled_txq_max_size`, `rippled_txq_open_ledger_fee_level`, etc.
+
+**Grafana dashboard**: New _Fee Market & TxQ_ dashboard (`rippled-fee-market`).
+
+---
+
+## Task 9.4: PerfLog Per-RPC Method Metrics
+
+**Objective**: Export per-RPC-method call counts and latency as OTel metrics.
+
+**What to do**:
+
+- Register OTel instruments for PerfLog RPC counters (from `PerfLogImp.cpp` line ~63):
+  - Counter: `rpc_method_started_total{method="<name>"}` — calls started
+  - Counter: `rpc_method_finished_total{method="<name>"}` — calls completed
+  - Counter: `rpc_method_errored_total{method="<name>"}` — calls errored
+  - Histogram: `rpc_method_duration_us{method="<name>"}` — execution time distribution
+
+- Use OTel `Counter<int64_t>` and `Histogram<double>` instruments with `method` attribute label.
+
+- Hook into the existing PerfLog callback mechanism rather than adding new instrumentation points.
+
+**Key modified files**:
+
+- `src/xrpld/perflog/detail/PerfLogImp.cpp` (add OTel instrument updates alongside existing JSON counters)
+- `src/xrpld/telemetry/MetricsRegistry.cpp` (register instruments)
+
+**Derived Prometheus metrics**: `rippled_rpc_method_started_total{method="server_info"}`, `rippled_rpc_method_duration_us_bucket{method="ledger"}`, etc.
+
+**Grafana dashboard**: Add "Per-Method RPC Breakdown" panel group to _RPC Performance_ dashboard.
+
+---
+
+## Task 9.5: PerfLog Per-Job-Type Metrics
+
+**Objective**: Export per-job-type queue and execution metrics.
+
+**What to do**:
+
+- Register OTel instruments for PerfLog job counters:
+  - Counter: `job_queued_total{job_type="<name>"}` — jobs queued
+  - Counter: `job_started_total{job_type="<name>"}` — jobs started
+  - Counter: `job_finished_total{job_type="<name>"}` — jobs completed
+  - Histogram: `job_queued_duration_us{job_type="<name>"}` — time spent waiting in queue
+  - Histogram: `job_running_duration_us{job_type="<name>"}` — execution time distribution
+
+- Hook into PerfLog's existing job tracking alongside Task 9.4.
+
+**Key modified files**:
+
+- `src/xrpld/perflog/detail/PerfLogImp.cpp`
+- `src/xrpld/telemetry/MetricsRegistry.cpp`
+
+**Derived Prometheus metrics**: `rippled_job_queued_total{job_type="ledgerData"}`, `rippled_job_running_duration_us_bucket{job_type="transaction"}`, etc.
+
+**Grafana dashboard**: New _Job Queue Analysis_ dashboard (`rippled-job-queue`).
+
+---
+
+## Task 9.6: Counted Object Instance Metrics
+
+**Objective**: Export live instance counts for key internal object types.
+
+**What to do**:
+
+- Register OTel `ObservableGauge` callbacks for `CountedObject<T>` instance counts:
+  - `object_count{type="Transaction"}` — live Transaction objects
+  - `object_count{type="Ledger"}` — live Ledger objects
+  - `object_count{type="NodeObject"}` — live NodeObject instances
+  - `object_count{type="STTx"}` — serialized transaction objects
+  - `object_count{type="STLedgerEntry"}` — serialized ledger entries
+  - `object_count{type="InboundLedger"}` — ledgers being fetched
+  - `object_count{type="Pathfinder"}` — active pathfinding computations
+  - `object_count{type="PathRequest"}` — active path requests
+  - `object_count{type="HashRouterEntry"}` — hash router entries
+
+- The `CountedObject` template already tracks these via atomic counters. The callback just reads the current counts.
+
+**Key modified files**:
+
+- `src/xrpld/telemetry/MetricsRegistry.cpp` (add counted object callbacks)
+- `include/xrpl/basics/CountedObject.h` (may need static accessor for iteration)
+
+**Derived Prometheus metrics**: `rippled_object_count{type="Transaction"}`, `rippled_object_count{type="NodeObject"}`, etc.
+
+**Grafana dashboard**: Add "Object Instance Counts" panel to _Node Health_ dashboard.
+
+---
+
+## Task 9.7: Fee Escalation & Load Factor Metrics
+
+**Objective**: Export the full load factor breakdown as time-series.
+
+**What to do**:
+
+- Register OTel `ObservableGauge` callbacks for load factors (from `NetworkOPs.cpp` line ~2694):
+  - `load_factor` — combined transaction cost multiplier
+  - `load_factor_server` — server + cluster + network contribution
+  - `load_factor_local` — local server load only
+  - `load_factor_net` — network-wide load estimate
+  - `load_factor_cluster` — cluster peer load
+  - `load_factor_fee_escalation` — open ledger fee escalation
+  - `load_factor_fee_queue` — queue entry fee level
+
+- These overlap with some existing StatsD metrics but provide finer granularity (individual factor breakdown vs. combined value).
+
+**Key modified files**:
+
+- `src/xrpld/telemetry/MetricsRegistry.cpp`
+- `src/xrpld/app/misc/NetworkOPs.cpp` (expose load factor accessors if needed)
+
+**Derived Prometheus metrics**: `rippled_load_factor`, `rippled_load_factor_fee_escalation`, etc.
+
+**Grafana dashboard**: Add "Load Factor Breakdown" panel to _Fee Market & TxQ_ dashboard.
+
+---
+
+## Task 9.8: New Grafana Dashboards
+
+**Objective**: Create Grafana dashboards for the new metric categories.
+
+**What to do**:
+
+- Create 2 new dashboards:
+  1. **Fee Market & TxQ** (`rippled-fee-market`) — TxQ depth/capacity, fee levels, load factor breakdown, fee escalation timeline
+  2. **Job Queue Analysis** (`rippled-job-queue`) — Per-job-type rates, queue wait times, execution times, job queue depth
+
+- Update 2 existing dashboards:
+  1. **Node Health** (`rippled-statsd-node-health`) — Add NodeStore I/O panels, cache hit rate panels, object instance counts
+  2. **RPC Performance** (`rippled-rpc-perf`) — Add per-method RPC breakdown panels
+
+**Key modified files**:
+
+- New: `docker/telemetry/grafana/dashboards/rippled-fee-market.json`
+- New: `docker/telemetry/grafana/dashboards/rippled-job-queue.json`
+- `docker/telemetry/grafana/dashboards/rippled-statsd-node-health.json`
+- `docker/telemetry/grafana/dashboards/rippled-rpc-perf.json`
+
+---
+
+## Task 9.9: Update Documentation
+
+**Objective**: Update telemetry reference docs with all new metrics.
+
+**What to do**:
+
+- Update `OpenTelemetryPlan/09-data-collection-reference.md`:
+  - Add new section for OTel SDK-exported metrics (NodeStore, cache, TxQ, PerfLog, CountedObjects, load factors)
+  - Update Grafana dashboard reference table (add 2 new dashboards)
+  - Add Prometheus query examples for new metrics
+
+- Update `docs/telemetry-runbook.md`:
+  - Add alerting rules for new metrics (NodeStore write_load, TxQ capacity, cache hit rate degradation)
+  - Add troubleshooting entries for new metric categories
+
+**Key modified files**:
+
+- `OpenTelemetryPlan/09-data-collection-reference.md`
+- `docs/telemetry-runbook.md`
+
+---
+
+## Task 9.10: Integration Tests
+
+**Objective**: Verify all new metrics appear in Prometheus after a test workload.
+
+**What to do**:
+
+- Extend the existing telemetry integration test:
+  - Start rippled with `[telemetry] enabled=1` and `[insight] server=otel`
+  - Submit a batch of RPC calls and transactions
+  - Query Prometheus for each new metric family
+  - Assert non-zero values for: NodeStore reads, cache hit rates, TxQ count, PerfLog RPC counters, object counts, load factors
+
+- Add unit tests for the `MetricsRegistry` class:
+  - Verify callback registration and deregistration
+  - Verify metric values match `get_counts` JSON output
+  - Verify graceful behavior when telemetry is disabled
+
+**Key modified files**:
+
+- `src/test/telemetry/MetricsRegistry_test.cpp` (new)
+- Existing integration test script (extend assertions)
+
+---
+
+## Effort Summary
+
+| Task | Description                              | Effort | Risk   |
+| ---- | ---------------------------------------- | ------ | ------ |
+| 9.1  | NodeStore I/O metrics                    | 1d     | Low    |
+| 9.2  | Cache hit rate metrics + MetricsRegistry | 2d     | Medium |
+| 9.3  | TxQ metrics                              | 1d     | Low    |
+| 9.4  | PerfLog per-RPC metrics                  | 1.5d   | Medium |
+| 9.5  | PerfLog per-job metrics                  | 1d     | Low    |
+| 9.6  | Counted object instance metrics          | 0.5d   | Low    |
+| 9.7  | Fee escalation & load factor metrics     | 0.5d   | Low    |
+| 9.8  | New Grafana dashboards                   | 2d     | Low    |
+| 9.9  | Update documentation                     | 1d     | Low    |
+| 9.10 | Integration tests                        | 1.5d   | Medium |
+
+**Total Effort**: 12 days
+
+## Exit Criteria
+
+- [ ] All ~50 new metrics visible in Prometheus via OTLP pipeline
+- [ ] `MetricsRegistry` class registers/deregisters cleanly with OTel SDK
+- [ ] Async gauge callbacks execute at 10s intervals without performance impact
+- [ ] 2 new Grafana dashboards operational (Fee Market, Job Queue)
+- [ ] 2 existing dashboards updated with new panel groups
+- [ ] Integration test validates all new metric families are non-zero
+- [ ] No performance regression (< 0.5% CPU overhead from new callbacks)
+- [ ] Documentation updated with full new metric inventory

OpenTelemetryPlan/presentation.md

@@ -0,0 +1,280 @@
+# OpenTelemetry Distributed Tracing for rippled
+
+---
+
+## Slide 1: Introduction
+
+### What is OpenTelemetry?
+
+OpenTelemetry is an open-source, CNCF-backed observability framework for distributed tracing, metrics, and logs.
+
+### Why OpenTelemetry for rippled?
+
+- **End-to-End Transaction Visibility**: Track transactions from submission → consensus → ledger inclusion
+- **Cross-Node Correlation**: Follow requests across multiple independent nodes using a unique `trace_id`
+- **Consensus Round Analysis**: Understand timing and behavior across validators
+- **Incident Debugging**: Correlate events across distributed nodes during issues
+
+```mermaid
+flowchart LR
+    A["Node A<br/>tx.receive<br/>trace_id: abc123"] --> B["Node B<br/>tx.relay<br/>trace_id: abc123"] --> C["Node C<br/>tx.validate<br/>trace_id: abc123"] --> D["Node D<br/>ledger.apply<br/>trace_id: abc123"]
+
+    style A fill:#1565c0,stroke:#0d47a1,color:#fff
+    style B fill:#2e7d32,stroke:#1b5e20,color:#fff
+    style C fill:#2e7d32,stroke:#1b5e20,color:#fff
+    style D fill:#e65100,stroke:#bf360c,color:#fff
+```
+
+> **Trace ID: abc123** — All nodes share the same trace, enabling cross-node correlation.
+
+---
+
+## Slide 2: OpenTelemetry vs Open Source Alternatives
+
+| Feature             | OpenTelemetry    | Jaeger           | Zipkin             | SkyWalking | Pinpoint   | Prometheus |
+| ------------------- | ---------------- | ---------------- | ------------------ | ---------- | ---------- | ---------- |
+| **Tracing**         | YES              | YES              | YES                | YES        | YES        | NO         |
+| **Metrics**         | YES              | NO               | NO                 | YES        | YES        | YES        |
+| **Logs**            | YES              | NO               | NO                 | YES        | NO         | NO         |
+| **C++ SDK**         | YES Official     | YES (Deprecated) | YES (Unmaintained) | NO         | NO         | YES        |
+| **Vendor Neutral**  | YES Primary goal | NO               | NO                 | NO         | NO         | NO         |
+| **Instrumentation** | Manual + Auto    | Manual           | Manual             | Auto-first | Auto-first | Manual     |
+| **Backend**         | Any (exporters)  | Self             | Self               | Self       | Self       | Self       |
+| **CNCF Status**     | Incubating       | Graduated        | NO                 | Incubating | NO         | Graduated  |
+
+> **Why OpenTelemetry?** It's the only actively maintained, full-featured C++ option with vendor neutrality — allowing export to Jaeger, Prometheus, Grafana, or any commercial backend without changing instrumentation.
+
+---
+
+## Slide 3: Comparison with rippled's Existing Solutions
+
+### Current Observability Stack
+
+| Aspect                | PerfLog (JSON)        | StatsD (Metrics)      | OpenTelemetry (NEW)         |
+| --------------------- | --------------------- | --------------------- | --------------------------- |
+| **Type**              | Logging               | Metrics               | Distributed Tracing         |
+| **Scope**             | Single node           | Single node           | **Cross-node**              |
+| **Data**              | JSON log entries      | Counters, gauges      | Spans with context          |
+| **Correlation**       | By timestamp          | By metric name        | By `trace_id`               |
+| **Overhead**          | Low (file I/O)        | Low (UDP)             | Low-Medium (configurable)   |
+| **Question Answered** | "What happened here?" | "How many? How fast?" | **"What was the journey?"** |
+
+### Use Case Matrix
+
+| Scenario                         | PerfLog | StatsD | OpenTelemetry |
+| -------------------------------- | ------- | ------ | ------------- |
+| "How many TXs per second?"       | ❌      | ✅     | ❌            |
+| "Why was this specific TX slow?" | ⚠️      | ❌     | ✅            |
+| "Which node delayed consensus?"  | ❌      | ❌     | ✅            |
+| "Show TX journey across 5 nodes" | ❌      | ❌     | ✅            |
+
+> **Key Insight**: OpenTelemetry **complements** (not replaces) existing systems.
+
+---
+
+## Slide 4: Architecture
+
+### High-Level Integration Architecture
+
+```mermaid
+flowchart TB
+    subgraph rippled["rippled Node"]
+        subgraph services["Core Services"]
+            direction LR
+            RPC["RPC Server<br/>(HTTP/WS)"] ~~~ Overlay["Overlay<br/>(P2P Network)"] ~~~ Consensus["Consensus<br/>(RCLConsensus)"]
+        end
+
+        Telemetry["Telemetry Module<br/>(OpenTelemetry SDK)"]
+
+        services --> Telemetry
+    end
+
+    Telemetry -->|OTLP/gRPC| Collector["OTel Collector"]
+
+    Collector --> Tempo["Grafana Tempo"]
+    Collector --> Jaeger["Jaeger"]
+    Collector --> Elastic["Elastic APM"]
+
+    style rippled fill:#424242,stroke:#212121,color:#fff
+    style services fill:#1565c0,stroke:#0d47a1,color:#fff
+    style Telemetry fill:#2e7d32,stroke:#1b5e20,color:#fff
+    style Collector fill:#e65100,stroke:#bf360c,color:#fff
+```
+
+### Context Propagation
+
+```mermaid
+sequenceDiagram
+    participant Client
+    participant NodeA as Node A
+    participant NodeB as Node B
+
+    Client->>NodeA: Submit TX (no context)
+    Note over NodeA: Creates trace_id: abc123<br/>span: tx.receive
+    NodeA->>NodeB: Relay TX<br/>(traceparent: abc123)
+    Note over NodeB: Links to trace_id: abc123<br/>span: tx.relay
+```
+
+- **HTTP/RPC**: W3C Trace Context headers (`traceparent`)
+- **P2P Messages**: Protocol Buffer extension fields
+
+---
+
+## Slide 5: Implementation Plan
+
+### 5-Phase Rollout (9 Weeks)
+
+```mermaid
+gantt
+    title Implementation Timeline
+    dateFormat  YYYY-MM-DD
+    axisFormat  Week %W
+
+    section Phase 1
+    Core Infrastructure    :p1, 2024-01-01, 2w
+
+    section Phase 2
+    RPC Tracing           :p2, after p1, 2w
+
+    section Phase 3
+    Transaction Tracing   :p3, after p2, 2w
+
+    section Phase 4
+    Consensus Tracing     :p4, after p3, 2w
+
+    section Phase 5
+    Documentation         :p5, after p4, 1w
+```
+
+### Phase Details
+
+| Phase | Focus               | Key Deliverables                             | Effort  |
+| ----- | ------------------- | -------------------------------------------- | ------- |
+| 1     | Core Infrastructure | SDK integration, Telemetry interface, Config | 10 days |
+| 2     | RPC Tracing         | HTTP context extraction, Handler spans       | 10 days |
+| 3     | Transaction Tracing | Protobuf context, P2P relay propagation      | 10 days |
+| 4     | Consensus Tracing   | Round spans, Proposal/validation tracing     | 10 days |
+| 5     | Documentation       | Runbook, Dashboards, Training                | 7 days  |
+
+**Total Effort**: ~47 developer-days (2 developers)
+
+---
+
+## Slide 6: Performance Overhead
+
+### Estimated System Impact
+
+| Metric            | Overhead   | Notes                               |
+| ----------------- | ---------- | ----------------------------------- |
+| **CPU**           | 1-3%       | Span creation and attribute setting |
+| **Memory**        | 2-5 MB     | Batch buffer for pending spans      |
+| **Network**       | 10-50 KB/s | Compressed OTLP export to collector |
+| **Latency (p99)** | <2%        | With proper sampling configuration  |
+
+### Per-Message Overhead (Context Propagation)
+
+Each P2P message carries trace context with the following overhead:
+
+| Field         | Size          | Description                               |
+| ------------- | ------------- | ----------------------------------------- |
+| `trace_id`    | 16 bytes      | Unique identifier for the entire trace    |
+| `span_id`     | 8 bytes       | Current span (becomes parent on receiver) |
+| `trace_flags` | 4 bytes       | Sampling decision flags                   |
+| `trace_state` | 0-4 bytes     | Optional vendor-specific data             |
+| **Total**     | **~32 bytes** | **Added per traced P2P message**          |
+
+```mermaid
+flowchart LR
+    subgraph msg["P2P Message with Trace Context"]
+        A["Original Message<br/>(variable size)"] --> B["+ TraceContext<br/>(~32 bytes)"]
+    end
+
+    subgraph breakdown["Context Breakdown"]
+        C["trace_id<br/>16 bytes"]
+        D["span_id<br/>8 bytes"]
+        E["flags<br/>4 bytes"]
+        F["state<br/>0-4 bytes"]
+    end
+
+    B --> breakdown
+
+    style A fill:#424242,stroke:#212121,color:#fff
+    style B fill:#2e7d32,stroke:#1b5e20,color:#fff
+    style C fill:#1565c0,stroke:#0d47a1,color:#fff
+    style D fill:#1565c0,stroke:#0d47a1,color:#fff
+    style E fill:#e65100,stroke:#bf360c,color:#fff
+    style F fill:#4a148c,stroke:#2e0d57,color:#fff
+```
+
+> **Note**: 32 bytes is negligible compared to typical transaction messages (hundreds to thousands of bytes)
+
+### Mitigation Strategies
+
+```mermaid
+flowchart LR
+    A["Head Sampling<br/>10% default"] --> B["Tail Sampling<br/>Keep errors/slow"] --> C["Batch Export<br/>Reduce I/O"] --> D["Conditional Compile<br/>XRPL_ENABLE_TELEMETRY"]
+
+    style A fill:#1565c0,stroke:#0d47a1,color:#fff
+    style B fill:#2e7d32,stroke:#1b5e20,color:#fff
+    style C fill:#e65100,stroke:#bf360c,color:#fff
+    style D fill:#4a148c,stroke:#2e0d57,color:#fff
+```
+
+### Kill Switches (Rollback Options)
+
+1. **Config Disable**: Set `enabled=0` in config → instant disable, no restart needed for sampling
+2. **Rebuild**: Compile with `XRPL_ENABLE_TELEMETRY=OFF` → zero overhead (no-op)
+3. **Full Revert**: Clean separation allows easy commit reversion
+
+---
+
+## Slide 7: Data Collection & Privacy
+
+### What Data is Collected
+
+| Category        | Attributes Collected                                                               | Purpose                     |
+| --------------- | ---------------------------------------------------------------------------------- | --------------------------- |
+| **Transaction** | `tx.hash`, `tx.type`, `tx.result`, `tx.fee`, `ledger_index`                        | Trace transaction lifecycle |
+| **Consensus**   | `round`, `phase`, `mode`, `proposers`(public key or public node id), `duration_ms` | Analyze consensus timing    |
+| **RPC**         | `command`, `version`, `status`, `duration_ms`                                      | Monitor RPC performance     |
+| **Peer**        | `peer.id`(public key), `latency_ms`, `message.type`, `message.size`                | Network topology analysis   |
+| **Ledger**      | `ledger.hash`, `ledger.index`, `close_time`, `tx_count`                            | Ledger progression tracking |
+| **Job**         | `job.type`, `queue_ms`, `worker`                                                   | JobQueue performance        |
+
+### What is NOT Collected (Privacy Guarantees)
+
+```mermaid
+flowchart LR
+    subgraph notCollected["❌ NOT Collected"]
+        direction LR
+        A["Private Keys"] ~~~ B["Account Balances"] ~~~ C["Transaction Amounts"]
+    end
+
+    subgraph alsoNot["❌ Also Excluded"]
+        direction LR
+        D["IP Addresses<br/>(configurable)"] ~~~ E["Personal Data"] ~~~ F["Raw TX Payloads"]
+    end
+
+    style A fill:#c62828,stroke:#8c2809,color:#fff
+    style B fill:#c62828,stroke:#8c2809,color:#fff
+    style C fill:#c62828,stroke:#8c2809,color:#fff
+    style D fill:#c62828,stroke:#8c2809,color:#fff
+    style E fill:#c62828,stroke:#8c2809,color:#fff
+    style F fill:#c62828,stroke:#8c2809,color:#fff
+```
+
+### Privacy Protection Mechanisms
+
+| Mechanism                  | Description                                                   |
+| -------------------------- | ------------------------------------------------------------- |
+| **Account Hashing**        | `xrpl.tx.account` is hashed at collector level before storage |
+| **Configurable Redaction** | Sensitive fields can be excluded via config                   |
+| **Sampling**               | Only 10% of traces recorded by default (reduces exposure)     |
+| **Local Control**          | Node operators control what gets exported                     |
+| **No Raw Payloads**        | Transaction content is never recorded, only metadata          |
+
+> **Key Principle**: Telemetry collects **operational metadata** (timing, counts, hashes) — never **sensitive content** (keys, balances, amounts).
+
+---
+
+_End of Presentation_

cfg/xrpld-example.cfg

@@ -1529,3 +1529,46 @@ validators.txt
 # set to ssl_verify to 0.
 [ssl_verify]
 1
+#-------------------------------------------------------------------------------
+#
+# 11. Telemetry (OpenTelemetry Tracing)
+#
+#-------------------------------------------------------------------------------
+#
+# Enables distributed tracing via OpenTelemetry. Requires building with
+# -DXRPL_ENABLE_TELEMETRY=ON (telemetry Conan option).
+#
+# [telemetry]
+#
+# enabled=0
+#
+#   Enable or disable telemetry at runtime. Default: 0 (disabled).
+#
+# endpoint=http://localhost:4318/v1/traces
+#
+#   The OpenTelemetry Collector endpoint (OTLP/HTTP). Default: http://localhost:4318/v1/traces.
+#
+# exporter=otlp_http
+#
+#   Exporter type: otlp_http. Default: otlp_http.
+#
+# sampling_ratio=1.0
+#
+#   Fraction of traces to sample (0.0 to 1.0). Default: 1.0 (all traces).
+#
+# trace_rpc=1
+#
+#   Enable RPC request tracing. Default: 1.
+#
+# trace_transactions=1
+#
+#   Enable transaction lifecycle tracing. Default: 1.
+#
+# trace_consensus=1
+#
+#   Enable consensus round tracing. Default: 1.
+#
+# trace_peer=0
+#
+#   Enable peer message tracing (high volume). Default: 0.
+#

cmake/CMakeFuncs.cmake

@@ -1,29 +1,32 @@
-macro (exclude_from_default target_)
+macro(exclude_from_default target_)
     set_target_properties(${target_} PROPERTIES EXCLUDE_FROM_ALL ON)
     set_target_properties(${target_} PROPERTIES EXCLUDE_FROM_DEFAULT_BUILD ON)
-endmacro ()
+endmacro()
 
-macro (exclude_if_included target_)
+macro(exclude_if_included target_)
     get_directory_property(has_parent PARENT_DIRECTORY)
-    if (has_parent)
+    if(has_parent)
         exclude_from_default(${target_})
-    endif ()
-endmacro ()
+    endif()
+endmacro()
 
 find_package(Git)
 
-function (git_branch branch_val)
-    if (NOT GIT_FOUND)
+function(git_branch branch_val)
+    if(NOT GIT_FOUND)
         return()
-    endif ()
+    endif()
     set(_branch "")
-    execute_process(COMMAND ${GIT_EXECUTABLE} "rev-parse" "--abbrev-ref" "HEAD"
-                    WORKING_DIRECTORY ${CMAKE_CURRENT_SOURCE_DIR}
-                    RESULT_VARIABLE _git_exit_code
-                    OUTPUT_VARIABLE _temp_branch
-                    OUTPUT_STRIP_TRAILING_WHITESPACE ERROR_QUIET)
-    if (_git_exit_code EQUAL 0)
+    execute_process(
+        COMMAND ${GIT_EXECUTABLE} "rev-parse" "--abbrev-ref" "HEAD"
+        WORKING_DIRECTORY ${CMAKE_CURRENT_SOURCE_DIR}
+        RESULT_VARIABLE _git_exit_code
+        OUTPUT_VARIABLE _temp_branch
+        OUTPUT_STRIP_TRAILING_WHITESPACE
+        ERROR_QUIET
+    )
+    if(_git_exit_code EQUAL 0)
         set(_branch ${_temp_branch})
-    endif ()
+    endif()
     set(${branch_val} "${_branch}" PARENT_SCOPE)
-endfunction ()
+endfunction()

cmake/Ccache.cmake

@@ -1,50 +1,62 @@
 find_program(CCACHE_PATH "ccache")
-if (NOT CCACHE_PATH)
+if(NOT CCACHE_PATH)
     return()
-endif ()
+endif()
 
 # For Linux and macOS we can use the ccache binary directly.
-if (NOT MSVC)
+if(NOT MSVC)
     set(CMAKE_C_COMPILER_LAUNCHER "${CCACHE_PATH}")
     set(CMAKE_CXX_COMPILER_LAUNCHER "${CCACHE_PATH}")
     message(STATUS "Found ccache: ${CCACHE_PATH}")
     return()
-endif ()
+endif()
 
 # For Windows more effort is required. The code below is a modified version of
 # https://github.com/ccache/ccache/wiki/MS-Visual-Studio#usage-with-cmake.
-if ("${CCACHE_PATH}" MATCHES "chocolatey")
+if("${CCACHE_PATH}" MATCHES "chocolatey")
     message(DEBUG "Ccache path: ${CCACHE_PATH}")
     # Chocolatey uses a shim executable that we cannot use directly, in which case we have to find the executable it
     # points to. If we cannot find the target executable then we cannot use ccache.
     find_program(BASH_PATH "bash")
-    if (NOT BASH_PATH)
+    if(NOT BASH_PATH)
         message(WARNING "Could not find bash.")
         return()
-    endif ()
+    endif()
 
-    execute_process(COMMAND bash -c
-                            "export LC_ALL='en_US.UTF-8'; ${CCACHE_PATH} --shimgen-noop | grep -oP 'path to executable: \\K.+' | head -c -1"
-                    OUTPUT_VARIABLE CCACHE_PATH)
+    execute_process(
+        COMMAND
+            bash -c
+            "export LC_ALL='en_US.UTF-8'; ${CCACHE_PATH} --shimgen-noop | grep -oP 'path to executable: \\K.+' | head -c -1"
+        OUTPUT_VARIABLE CCACHE_PATH
+    )
 
-    if (NOT CCACHE_PATH)
+    if(NOT CCACHE_PATH)
         message(WARNING "Could not find ccache target.")
         return()
-    endif ()
+    endif()
     file(TO_CMAKE_PATH "${CCACHE_PATH}" CCACHE_PATH)
-endif ()
+endif()
 message(STATUS "Found ccache: ${CCACHE_PATH}")
 
 # Tell cmake to use ccache for compiling with Visual Studio.
 file(COPY_FILE ${CCACHE_PATH} ${CMAKE_BINARY_DIR}/cl.exe ONLY_IF_DIFFERENT)
-set(CMAKE_VS_GLOBALS "CLToolExe=cl.exe" "CLToolPath=${CMAKE_BINARY_DIR}" "TrackFileAccess=false"
-                     "UseMultiToolTask=true")
+set(CMAKE_VS_GLOBALS
+    "CLToolExe=cl.exe"
+    "CLToolPath=${CMAKE_BINARY_DIR}"
+    "TrackFileAccess=false"
+    "UseMultiToolTask=true"
+)
 
 # By default Visual Studio generators will use /Zi to capture debug information, which is not compatible with ccache, so
 # tell it to use /Z7 instead.
-if (MSVC)
-    foreach (var_ CMAKE_C_FLAGS_DEBUG CMAKE_C_FLAGS_RELEASE CMAKE_CXX_FLAGS_DEBUG
-                  CMAKE_CXX_FLAGS_RELEASE)
+if(MSVC)
+    foreach(
+        var_
+        CMAKE_C_FLAGS_DEBUG
+        CMAKE_C_FLAGS_RELEASE
+        CMAKE_CXX_FLAGS_DEBUG
+        CMAKE_CXX_FLAGS_RELEASE
+    )
         string(REPLACE "/Zi" "/Z7" ${var_} "${${var_}}")
-    endforeach ()
-endif ()
+    endforeach()
+endif()

cmake/CodeCoverage.cmake

@@ -174,37 +174,45 @@ option(CODE_COVERAGE_VERBOSE "Verbose information" FALSE)
 # Check prereqs
 find_program(GCOVR_PATH gcovr PATHS ${CMAKE_SOURCE_DIR}/scripts/test)
 
-if (DEFINED CODE_COVERAGE_GCOV_TOOL)
+if(DEFINED CODE_COVERAGE_GCOV_TOOL)
     set(GCOV_TOOL "${CODE_COVERAGE_GCOV_TOOL}")
-elseif (DEFINED ENV{CODE_COVERAGE_GCOV_TOOL})
+elseif(DEFINED ENV{CODE_COVERAGE_GCOV_TOOL})
     set(GCOV_TOOL "$ENV{CODE_COVERAGE_GCOV_TOOL}")
-elseif ("${CMAKE_CXX_COMPILER_ID}" MATCHES "(Apple)?[Cc]lang")
-    if (APPLE)
-        execute_process(COMMAND xcrun -f llvm-cov OUTPUT_VARIABLE LLVMCOV_PATH
-                        OUTPUT_STRIP_TRAILING_WHITESPACE)
-    else ()
+elseif("${CMAKE_CXX_COMPILER_ID}" MATCHES "(Apple)?[Cc]lang")
+    if(APPLE)
+        execute_process(
+            COMMAND xcrun -f llvm-cov
+            OUTPUT_VARIABLE LLVMCOV_PATH
+            OUTPUT_STRIP_TRAILING_WHITESPACE
+        )
+    else()
         find_program(LLVMCOV_PATH llvm-cov)
-    endif ()
-    if (LLVMCOV_PATH)
+    endif()
+    if(LLVMCOV_PATH)
         set(GCOV_TOOL "${LLVMCOV_PATH} gcov")
-    endif ()
-elseif ("${CMAKE_CXX_COMPILER_ID}" MATCHES "GNU")
+    endif()
+elseif("${CMAKE_CXX_COMPILER_ID}" MATCHES "GNU")
     find_program(GCOV_PATH gcov)
     set(GCOV_TOOL "${GCOV_PATH}")
-endif ()
+endif()
 
 # Check supported compiler (Clang, GNU and Flang)
 get_property(LANGUAGES GLOBAL PROPERTY ENABLED_LANGUAGES)
-foreach (LANG ${LANGUAGES})
-    if ("${CMAKE_${LANG}_COMPILER_ID}" MATCHES "(Apple)?[Cc]lang")
-        if ("${CMAKE_${LANG}_COMPILER_VERSION}" VERSION_LESS 3)
-            message(FATAL_ERROR "Clang version must be 3.0.0 or greater! Aborting...")
-        endif ()
-    elseif (NOT "${CMAKE_${LANG}_COMPILER_ID}" MATCHES "GNU" AND NOT "${CMAKE_${LANG}_COMPILER_ID}"
-                                                                 MATCHES "(LLVM)?[Ff]lang")
+foreach(LANG ${LANGUAGES})
+    if("${CMAKE_${LANG}_COMPILER_ID}" MATCHES "(Apple)?[Cc]lang")
+        if("${CMAKE_${LANG}_COMPILER_VERSION}" VERSION_LESS 3)
+            message(
+                FATAL_ERROR
+                "Clang version must be 3.0.0 or greater! Aborting..."
+            )
+        endif()
+    elseif(
+        NOT "${CMAKE_${LANG}_COMPILER_ID}" MATCHES "GNU"
+        AND NOT "${CMAKE_${LANG}_COMPILER_ID}" MATCHES "(LLVM)?[Ff]lang"
+    )
         message(FATAL_ERROR "Compiler is not GNU or Flang! Aborting...")
-    endif ()
-endforeach ()
+    endif()
+endforeach()
 
 set(COVERAGE_COMPILER_FLAGS "-g --coverage" CACHE INTERNAL "")
 
@@ -213,7 +221,7 @@ set(COVERAGE_C_COMPILER_FLAGS "")
 set(COVERAGE_CXX_LINKER_FLAGS "")
 set(COVERAGE_C_LINKER_FLAGS "")
 
-if (CMAKE_CXX_COMPILER_ID MATCHES "(GNU|Clang)")
+if(CMAKE_CXX_COMPILER_ID MATCHES "(GNU|Clang)")
     include(CheckCXXCompilerFlag)
     include(CheckCCompilerFlag)
     include(CheckLinkerFlag)
@@ -224,51 +232,77 @@ if (CMAKE_CXX_COMPILER_ID MATCHES "(GNU|Clang)")
     set(COVERAGE_C_LINKER_FLAGS ${COVERAGE_COMPILER_FLAGS})
 
     check_cxx_compiler_flag(-fprofile-abs-path HAVE_cxx_fprofile_abs_path)
-    if (HAVE_cxx_fprofile_abs_path)
-        set(COVERAGE_CXX_COMPILER_FLAGS "${COVERAGE_CXX_COMPILER_FLAGS} -fprofile-abs-path")
-    endif ()
+    if(HAVE_cxx_fprofile_abs_path)
+        set(COVERAGE_CXX_COMPILER_FLAGS
+            "${COVERAGE_CXX_COMPILER_FLAGS} -fprofile-abs-path"
+        )
+    endif()
 
     check_c_compiler_flag(-fprofile-abs-path HAVE_c_fprofile_abs_path)
-    if (HAVE_c_fprofile_abs_path)
-        set(COVERAGE_C_COMPILER_FLAGS "${COVERAGE_C_COMPILER_FLAGS} -fprofile-abs-path")
-    endif ()
+    if(HAVE_c_fprofile_abs_path)
+        set(COVERAGE_C_COMPILER_FLAGS
+            "${COVERAGE_C_COMPILER_FLAGS} -fprofile-abs-path"
+        )
+    endif()
 
     check_linker_flag(CXX -fprofile-abs-path HAVE_cxx_linker_fprofile_abs_path)
-    if (HAVE_cxx_linker_fprofile_abs_path)
-        set(COVERAGE_CXX_LINKER_FLAGS "${COVERAGE_CXX_LINKER_FLAGS} -fprofile-abs-path")
-    endif ()
+    if(HAVE_cxx_linker_fprofile_abs_path)
+        set(COVERAGE_CXX_LINKER_FLAGS
+            "${COVERAGE_CXX_LINKER_FLAGS} -fprofile-abs-path"
+        )
+    endif()
 
     check_linker_flag(C -fprofile-abs-path HAVE_c_linker_fprofile_abs_path)
-    if (HAVE_c_linker_fprofile_abs_path)
-        set(COVERAGE_C_LINKER_FLAGS "${COVERAGE_C_LINKER_FLAGS} -fprofile-abs-path")
-    endif ()
+    if(HAVE_c_linker_fprofile_abs_path)
+        set(COVERAGE_C_LINKER_FLAGS
+            "${COVERAGE_C_LINKER_FLAGS} -fprofile-abs-path"
+        )
+    endif()
 
     check_cxx_compiler_flag(-fprofile-update=atomic HAVE_cxx_fprofile_update)
-    if (HAVE_cxx_fprofile_update)
-        set(COVERAGE_CXX_COMPILER_FLAGS "${COVERAGE_CXX_COMPILER_FLAGS}  -fprofile-update=atomic")
-    endif ()
+    if(HAVE_cxx_fprofile_update)
+        set(COVERAGE_CXX_COMPILER_FLAGS
+            "${COVERAGE_CXX_COMPILER_FLAGS}  -fprofile-update=atomic"
+        )
+    endif()
 
     check_c_compiler_flag(-fprofile-update=atomic HAVE_c_fprofile_update)
-    if (HAVE_c_fprofile_update)
-        set(COVERAGE_C_COMPILER_FLAGS "${COVERAGE_C_COMPILER_FLAGS} -fprofile-update=atomic")
-    endif ()
+    if(HAVE_c_fprofile_update)
+        set(COVERAGE_C_COMPILER_FLAGS
+            "${COVERAGE_C_COMPILER_FLAGS} -fprofile-update=atomic"
+        )
+    endif()
 
-    check_linker_flag(CXX -fprofile-update=atomic HAVE_cxx_linker_fprofile_update)
-    if (HAVE_cxx_linker_fprofile_update)
-        set(COVERAGE_CXX_LINKER_FLAGS "${COVERAGE_CXX_LINKER_FLAGS} -fprofile-update=atomic")
-    endif ()
+    check_linker_flag(
+        CXX
+        -fprofile-update=atomic
+        HAVE_cxx_linker_fprofile_update
+    )
+    if(HAVE_cxx_linker_fprofile_update)
+        set(COVERAGE_CXX_LINKER_FLAGS
+            "${COVERAGE_CXX_LINKER_FLAGS} -fprofile-update=atomic"
+        )
+    endif()
 
     check_linker_flag(C -fprofile-update=atomic HAVE_c_linker_fprofile_update)
-    if (HAVE_c_linker_fprofile_update)
-        set(COVERAGE_C_LINKER_FLAGS "${COVERAGE_C_LINKER_FLAGS} -fprofile-update=atomic")
-    endif ()
+    if(HAVE_c_linker_fprofile_update)
+        set(COVERAGE_C_LINKER_FLAGS
+            "${COVERAGE_C_LINKER_FLAGS} -fprofile-update=atomic"
+        )
+    endif()
+endif()
 
-endif ()
-
-get_property(GENERATOR_IS_MULTI_CONFIG GLOBAL PROPERTY GENERATOR_IS_MULTI_CONFIG)
-if (NOT (CMAKE_BUILD_TYPE STREQUAL "Debug" OR GENERATOR_IS_MULTI_CONFIG))
-    message(WARNING "Code coverage results with an optimised (non-Debug) build may be misleading")
-endif () # NOT (CMAKE_BUILD_TYPE STREQUAL "Debug" OR GENERATOR_IS_MULTI_CONFIG)
+get_property(
+    GENERATOR_IS_MULTI_CONFIG
+    GLOBAL
+    PROPERTY GENERATOR_IS_MULTI_CONFIG
+)
+if(NOT (CMAKE_BUILD_TYPE STREQUAL "Debug" OR GENERATOR_IS_MULTI_CONFIG))
+    message(
+        WARNING
+        "Code coverage results with an optimised (non-Debug) build may be misleading"
+    )
+endif() # NOT (CMAKE_BUILD_TYPE STREQUAL "Debug" OR GENERATOR_IS_MULTI_CONFIG)
 
 # Defines a target for running and collection code coverage information
 # Builds dependencies, runs the given executable and outputs reports.
@@ -292,125 +326,167 @@ endif () # NOT (CMAKE_BUILD_TYPE STREQUAL "Debug" OR GENERATOR_IS_MULTI_CONFIG)
 # )
 # The user can set the variable GCOVR_ADDITIONAL_ARGS to supply additional flags to the
 # GCVOR command.
-function (setup_target_for_coverage_gcovr)
+function(setup_target_for_coverage_gcovr)
     set(options NONE)
     set(oneValueArgs BASE_DIRECTORY NAME FORMAT)
     set(multiValueArgs EXCLUDE EXECUTABLE EXECUTABLE_ARGS DEPENDENCIES)
-    cmake_parse_arguments(Coverage "${options}" "${oneValueArgs}" "${multiValueArgs}" ${ARGN})
+    cmake_parse_arguments(
+        Coverage
+        "${options}"
+        "${oneValueArgs}"
+        "${multiValueArgs}"
+        ${ARGN}
+    )
 
-    if (NOT GCOV_TOOL)
+    if(NOT GCOV_TOOL)
         message(FATAL_ERROR "Could not find gcov or llvm-cov tool! Aborting...")
-    endif ()
+    endif()
 
-    if (NOT GCOVR_PATH)
+    if(NOT GCOVR_PATH)
         message(FATAL_ERROR "Could not find gcovr tool! Aborting...")
-    endif ()
+    endif()
 
     # Set base directory (as absolute path), or default to PROJECT_SOURCE_DIR
-    if (DEFINED Coverage_BASE_DIRECTORY)
+    if(DEFINED Coverage_BASE_DIRECTORY)
         get_filename_component(BASEDIR ${Coverage_BASE_DIRECTORY} ABSOLUTE)
-    else ()
+    else()
         set(BASEDIR ${PROJECT_SOURCE_DIR})
-    endif ()
+    endif()
 
-    if (NOT DEFINED Coverage_FORMAT)
+    if(NOT DEFINED Coverage_FORMAT)
         set(Coverage_FORMAT xml)
-    endif ()
+    endif()
 
-    if (NOT DEFINED Coverage_EXECUTABLE AND DEFINED Coverage_EXECUTABLE_ARGS)
-        message(FATAL_ERROR "EXECUTABLE_ARGS must not be set if EXECUTABLE is not set")
-    endif ()
-
-    if ("--output" IN_LIST GCOVR_ADDITIONAL_ARGS)
-        message(FATAL_ERROR "Unsupported --output option detected in GCOVR_ADDITIONAL_ARGS! Aborting..."
+    if(NOT DEFINED Coverage_EXECUTABLE AND DEFINED Coverage_EXECUTABLE_ARGS)
+        message(
+            FATAL_ERROR
+            "EXECUTABLE_ARGS must not be set if EXECUTABLE is not set"
         )
-    else ()
-        if ((Coverage_FORMAT STREQUAL "html-details") OR (Coverage_FORMAT STREQUAL "html-nested"))
-            set(GCOVR_OUTPUT_FILE ${PROJECT_BINARY_DIR}/${Coverage_NAME}/index.html)
-            set(GCOVR_CREATE_FOLDER ${PROJECT_BINARY_DIR}/${Coverage_NAME})
-        elseif (Coverage_FORMAT STREQUAL "html-single")
-            set(GCOVR_OUTPUT_FILE ${Coverage_NAME}.html)
-        elseif ((Coverage_FORMAT STREQUAL "json-summary") OR (Coverage_FORMAT STREQUAL
-                                                              "json-details")
-                OR (Coverage_FORMAT STREQUAL "coveralls"))
-            set(GCOVR_OUTPUT_FILE ${Coverage_NAME}.json)
-        elseif (Coverage_FORMAT STREQUAL "txt")
-            set(GCOVR_OUTPUT_FILE ${Coverage_NAME}.txt)
-        elseif (Coverage_FORMAT STREQUAL "csv")
-            set(GCOVR_OUTPUT_FILE ${Coverage_NAME}.csv)
-        elseif (Coverage_FORMAT STREQUAL "lcov")
-            set(GCOVR_OUTPUT_FILE ${Coverage_NAME}.lcov)
-        else ()
-            set(GCOVR_OUTPUT_FILE ${Coverage_NAME}.xml)
-        endif ()
-    endif ()
+    endif()
 
-    if ((Coverage_FORMAT STREQUAL "cobertura") OR (Coverage_FORMAT STREQUAL "xml"))
+    if("--output" IN_LIST GCOVR_ADDITIONAL_ARGS)
+        message(
+            FATAL_ERROR
+            "Unsupported --output option detected in GCOVR_ADDITIONAL_ARGS! Aborting..."
+        )
+    else()
+        if(
+            (Coverage_FORMAT STREQUAL "html-details")
+            OR (Coverage_FORMAT STREQUAL "html-nested")
+        )
+            set(GCOVR_OUTPUT_FILE
+                ${PROJECT_BINARY_DIR}/${Coverage_NAME}/index.html
+            )
+            set(GCOVR_CREATE_FOLDER ${PROJECT_BINARY_DIR}/${Coverage_NAME})
+        elseif(Coverage_FORMAT STREQUAL "html-single")
+            set(GCOVR_OUTPUT_FILE ${Coverage_NAME}.html)
+        elseif(
+            (Coverage_FORMAT STREQUAL "json-summary")
+            OR (Coverage_FORMAT STREQUAL "json-details")
+            OR (Coverage_FORMAT STREQUAL "coveralls")
+        )
+            set(GCOVR_OUTPUT_FILE ${Coverage_NAME}.json)
+        elseif(Coverage_FORMAT STREQUAL "txt")
+            set(GCOVR_OUTPUT_FILE ${Coverage_NAME}.txt)
+        elseif(Coverage_FORMAT STREQUAL "csv")
+            set(GCOVR_OUTPUT_FILE ${Coverage_NAME}.csv)
+        elseif(Coverage_FORMAT STREQUAL "lcov")
+            set(GCOVR_OUTPUT_FILE ${Coverage_NAME}.lcov)
+        else()
+            set(GCOVR_OUTPUT_FILE ${Coverage_NAME}.xml)
+        endif()
+    endif()
+
+    if(
+        (Coverage_FORMAT STREQUAL "cobertura")
+        OR (Coverage_FORMAT STREQUAL "xml")
+    )
         list(APPEND GCOVR_ADDITIONAL_ARGS --cobertura "${GCOVR_OUTPUT_FILE}")
         list(APPEND GCOVR_ADDITIONAL_ARGS --cobertura-pretty)
         set(Coverage_FORMAT cobertura) # overwrite xml
-    elseif (Coverage_FORMAT STREQUAL "sonarqube")
+    elseif(Coverage_FORMAT STREQUAL "sonarqube")
         list(APPEND GCOVR_ADDITIONAL_ARGS --sonarqube "${GCOVR_OUTPUT_FILE}")
-    elseif (Coverage_FORMAT STREQUAL "jacoco")
+    elseif(Coverage_FORMAT STREQUAL "jacoco")
         list(APPEND GCOVR_ADDITIONAL_ARGS --jacoco "${GCOVR_OUTPUT_FILE}")
         list(APPEND GCOVR_ADDITIONAL_ARGS --jacoco-pretty)
-    elseif (Coverage_FORMAT STREQUAL "clover")
+    elseif(Coverage_FORMAT STREQUAL "clover")
         list(APPEND GCOVR_ADDITIONAL_ARGS --clover "${GCOVR_OUTPUT_FILE}")
         list(APPEND GCOVR_ADDITIONAL_ARGS --clover-pretty)
-    elseif (Coverage_FORMAT STREQUAL "lcov")
+    elseif(Coverage_FORMAT STREQUAL "lcov")
         list(APPEND GCOVR_ADDITIONAL_ARGS --lcov "${GCOVR_OUTPUT_FILE}")
-    elseif (Coverage_FORMAT STREQUAL "json-summary")
+    elseif(Coverage_FORMAT STREQUAL "json-summary")
         list(APPEND GCOVR_ADDITIONAL_ARGS --json-summary "${GCOVR_OUTPUT_FILE}")
         list(APPEND GCOVR_ADDITIONAL_ARGS --json-summary-pretty)
-    elseif (Coverage_FORMAT STREQUAL "json-details")
+    elseif(Coverage_FORMAT STREQUAL "json-details")
         list(APPEND GCOVR_ADDITIONAL_ARGS --json "${GCOVR_OUTPUT_FILE}")
         list(APPEND GCOVR_ADDITIONAL_ARGS --json-pretty)
-    elseif (Coverage_FORMAT STREQUAL "coveralls")
+    elseif(Coverage_FORMAT STREQUAL "coveralls")
         list(APPEND GCOVR_ADDITIONAL_ARGS --coveralls "${GCOVR_OUTPUT_FILE}")
         list(APPEND GCOVR_ADDITIONAL_ARGS --coveralls-pretty)
-    elseif (Coverage_FORMAT STREQUAL "csv")
+    elseif(Coverage_FORMAT STREQUAL "csv")
         list(APPEND GCOVR_ADDITIONAL_ARGS --csv "${GCOVR_OUTPUT_FILE}")
-    elseif (Coverage_FORMAT STREQUAL "txt")
+    elseif(Coverage_FORMAT STREQUAL "txt")
         list(APPEND GCOVR_ADDITIONAL_ARGS --txt "${GCOVR_OUTPUT_FILE}")
-    elseif (Coverage_FORMAT STREQUAL "html-single")
+    elseif(Coverage_FORMAT STREQUAL "html-single")
         list(APPEND GCOVR_ADDITIONAL_ARGS --html "${GCOVR_OUTPUT_FILE}")
         list(APPEND GCOVR_ADDITIONAL_ARGS --html-self-contained)
-    elseif (Coverage_FORMAT STREQUAL "html-nested")
+    elseif(Coverage_FORMAT STREQUAL "html-nested")
         list(APPEND GCOVR_ADDITIONAL_ARGS --html-nested "${GCOVR_OUTPUT_FILE}")
-    elseif (Coverage_FORMAT STREQUAL "html-details")
+    elseif(Coverage_FORMAT STREQUAL "html-details")
         list(APPEND GCOVR_ADDITIONAL_ARGS --html-details "${GCOVR_OUTPUT_FILE}")
-    else ()
-        message(FATAL_ERROR "Unsupported output style ${Coverage_FORMAT}! Aborting...")
-    endif ()
+    else()
+        message(
+            FATAL_ERROR
+            "Unsupported output style ${Coverage_FORMAT}! Aborting..."
+        )
+    endif()
 
     # Collect excludes (CMake 3.4+: Also compute absolute paths)
     set(GCOVR_EXCLUDES "")
-    foreach (EXCLUDE ${Coverage_EXCLUDE} ${COVERAGE_EXCLUDES} ${COVERAGE_GCOVR_EXCLUDES})
-        if (CMAKE_VERSION VERSION_GREATER 3.4)
-            get_filename_component(EXCLUDE ${EXCLUDE} ABSOLUTE BASE_DIR ${BASEDIR})
-        endif ()
+    foreach(
+        EXCLUDE
+        ${Coverage_EXCLUDE}
+        ${COVERAGE_EXCLUDES}
+        ${COVERAGE_GCOVR_EXCLUDES}
+    )
+        if(CMAKE_VERSION VERSION_GREATER 3.4)
+            get_filename_component(
+                EXCLUDE
+                ${EXCLUDE}
+                ABSOLUTE
+                BASE_DIR ${BASEDIR}
+            )
+        endif()
         list(APPEND GCOVR_EXCLUDES "${EXCLUDE}")
-    endforeach ()
+    endforeach()
     list(REMOVE_DUPLICATES GCOVR_EXCLUDES)
 
     # Combine excludes to several -e arguments
     set(GCOVR_EXCLUDE_ARGS "")
-    foreach (EXCLUDE ${GCOVR_EXCLUDES})
+    foreach(EXCLUDE ${GCOVR_EXCLUDES})
         list(APPEND GCOVR_EXCLUDE_ARGS "-e")
         list(APPEND GCOVR_EXCLUDE_ARGS "${EXCLUDE}")
-    endforeach ()
+    endforeach()
 
     # Set up commands which will be run to generate coverage data
     # If EXECUTABLE is not set, the user is expected to run the tests manually
     # before running the coverage target NAME
-    if (DEFINED Coverage_EXECUTABLE)
-        set(GCOVR_EXEC_TESTS_CMD ${Coverage_EXECUTABLE} ${Coverage_EXECUTABLE_ARGS})
-    endif ()
+    if(DEFINED Coverage_EXECUTABLE)
+        set(GCOVR_EXEC_TESTS_CMD
+            ${Coverage_EXECUTABLE}
+            ${Coverage_EXECUTABLE_ARGS}
+        )
+    endif()
 
     # Create folder
-    if (DEFINED GCOVR_CREATE_FOLDER)
-        set(GCOVR_FOLDER_CMD ${CMAKE_COMMAND} -E make_directory ${GCOVR_CREATE_FOLDER})
-    endif ()
+    if(DEFINED GCOVR_CREATE_FOLDER)
+        set(GCOVR_FOLDER_CMD
+            ${CMAKE_COMMAND}
+            -E
+            make_directory
+            ${GCOVR_CREATE_FOLDER}
+        )
+    endif()
 
     # Running gcovr
     set(GCOVR_CMD
@@ -422,56 +498,95 @@ function (setup_target_for_coverage_gcovr)
         ${BASEDIR}
         ${GCOVR_ADDITIONAL_ARGS}
         ${GCOVR_EXCLUDE_ARGS}
-        --object-directory=${PROJECT_BINARY_DIR})
+        --object-directory=${PROJECT_BINARY_DIR}
+    )
 
-    if (CODE_COVERAGE_VERBOSE)
+    if(CODE_COVERAGE_VERBOSE)
         message(STATUS "Executed command report")
 
-        if (NOT "${GCOVR_EXEC_TESTS_CMD}" STREQUAL "")
+        if(NOT "${GCOVR_EXEC_TESTS_CMD}" STREQUAL "")
             message(STATUS "Command to run tests: ")
-            string(REPLACE ";" " " GCOVR_EXEC_TESTS_CMD_SPACED "${GCOVR_EXEC_TESTS_CMD}")
+            string(
+                REPLACE ";"
+                " "
+                GCOVR_EXEC_TESTS_CMD_SPACED
+                "${GCOVR_EXEC_TESTS_CMD}"
+            )
             message(STATUS "${GCOVR_EXEC_TESTS_CMD_SPACED}")
-        endif ()
+        endif()
 
-        if (NOT "${GCOVR_FOLDER_CMD}" STREQUAL "")
+        if(NOT "${GCOVR_FOLDER_CMD}" STREQUAL "")
             message(STATUS "Command to create a folder: ")
-            string(REPLACE ";" " " GCOVR_FOLDER_CMD_SPACED "${GCOVR_FOLDER_CMD}")
+            string(
+                REPLACE ";"
+                " "
+                GCOVR_FOLDER_CMD_SPACED
+                "${GCOVR_FOLDER_CMD}"
+            )
             message(STATUS "${GCOVR_FOLDER_CMD_SPACED}")
-        endif ()
+        endif()
 
         message(STATUS "Command to generate gcovr coverage data: ")
         string(REPLACE ";" " " GCOVR_CMD_SPACED "${GCOVR_CMD}")
         message(STATUS "${GCOVR_CMD_SPACED}")
-    endif ()
+    endif()
 
-    add_custom_target(${Coverage_NAME}
-                      COMMAND ${GCOVR_EXEC_TESTS_CMD}
-                      COMMAND ${GCOVR_FOLDER_CMD}
-                      COMMAND ${GCOVR_CMD}
-                      BYPRODUCTS ${GCOVR_OUTPUT_FILE}
-                      WORKING_DIRECTORY ${PROJECT_BINARY_DIR}
-                      DEPENDS ${Coverage_DEPENDENCIES}
-                      VERBATIM # Protect arguments to commands
-                      COMMENT "Running gcovr to produce code coverage report.")
+    add_custom_target(
+        ${Coverage_NAME}
+        COMMAND ${GCOVR_EXEC_TESTS_CMD}
+        COMMAND ${GCOVR_FOLDER_CMD}
+        COMMAND ${GCOVR_CMD}
+        BYPRODUCTS ${GCOVR_OUTPUT_FILE}
+        WORKING_DIRECTORY ${PROJECT_BINARY_DIR}
+        DEPENDS ${Coverage_DEPENDENCIES}
+        VERBATIM # Protect arguments to commands
+        COMMENT "Running gcovr to produce code coverage report."
+    )
 
     # Show info where to find the report
     add_custom_command(
-        TARGET ${Coverage_NAME} POST_BUILD COMMAND echo
-        COMMENT "Code coverage report saved in ${GCOVR_OUTPUT_FILE} formatted as ${Coverage_FORMAT}"
+        TARGET ${Coverage_NAME}
+        POST_BUILD
+        COMMAND echo
+        COMMENT
+            "Code coverage report saved in ${GCOVR_OUTPUT_FILE} formatted as ${Coverage_FORMAT}"
     )
-endfunction () # setup_target_for_coverage_gcovr
+endfunction() # setup_target_for_coverage_gcovr
 
-function (add_code_coverage_to_target name scope)
-    separate_arguments(COVERAGE_CXX_COMPILER_FLAGS NATIVE_COMMAND "${COVERAGE_CXX_COMPILER_FLAGS}")
-    separate_arguments(COVERAGE_C_COMPILER_FLAGS NATIVE_COMMAND "${COVERAGE_C_COMPILER_FLAGS}")
-    separate_arguments(COVERAGE_CXX_LINKER_FLAGS NATIVE_COMMAND "${COVERAGE_CXX_LINKER_FLAGS}")
-    separate_arguments(COVERAGE_C_LINKER_FLAGS NATIVE_COMMAND "${COVERAGE_C_LINKER_FLAGS}")
+function(add_code_coverage_to_target name scope)
+    separate_arguments(
+        COVERAGE_CXX_COMPILER_FLAGS
+        NATIVE_COMMAND
+        "${COVERAGE_CXX_COMPILER_FLAGS}"
+    )
+    separate_arguments(
+        COVERAGE_C_COMPILER_FLAGS
+        NATIVE_COMMAND
+        "${COVERAGE_C_COMPILER_FLAGS}"
+    )
+    separate_arguments(
+        COVERAGE_CXX_LINKER_FLAGS
+        NATIVE_COMMAND
+        "${COVERAGE_CXX_LINKER_FLAGS}"
+    )
+    separate_arguments(
+        COVERAGE_C_LINKER_FLAGS
+        NATIVE_COMMAND
+        "${COVERAGE_C_LINKER_FLAGS}"
+    )
 
     # Add compiler options to the target
     target_compile_options(
-        ${name} ${scope} $<$<COMPILE_LANGUAGE:CXX>:${COVERAGE_CXX_COMPILER_FLAGS}>
-        $<$<COMPILE_LANGUAGE:C>:${COVERAGE_C_COMPILER_FLAGS}>)
+        ${name}
+        ${scope}
+        $<$<COMPILE_LANGUAGE:CXX>:${COVERAGE_CXX_COMPILER_FLAGS}>
+        $<$<COMPILE_LANGUAGE:C>:${COVERAGE_C_COMPILER_FLAGS}>
+    )
 
-    target_link_libraries(${name} ${scope} $<$<LINK_LANGUAGE:CXX>:${COVERAGE_CXX_LINKER_FLAGS}>
-                          $<$<LINK_LANGUAGE:C>:${COVERAGE_C_LINKER_FLAGS}>)
-endfunction () # add_code_coverage_to_target
+    target_link_libraries(
+        ${name}
+        ${scope}
+        $<$<LINK_LANGUAGE:CXX>:${COVERAGE_CXX_LINKER_FLAGS}>
+        $<$<LINK_LANGUAGE:C>:${COVERAGE_C_LINKER_FLAGS}>
+    )
+endfunction() # add_code_coverage_to_target

cmake/CompilationEnv.cmake

@@ -14,20 +14,20 @@ set(is_gcc FALSE)
 set(is_msvc FALSE)
 set(is_xcode FALSE)
 
-if (CMAKE_CXX_COMPILER_ID MATCHES ".*Clang") # Clang or AppleClang
+if(CMAKE_CXX_COMPILER_ID MATCHES ".*Clang") # Clang or AppleClang
     set(is_clang TRUE)
-elseif (CMAKE_CXX_COMPILER_ID STREQUAL "GNU")
+elseif(CMAKE_CXX_COMPILER_ID STREQUAL "GNU")
     set(is_gcc TRUE)
-elseif (MSVC)
+elseif(MSVC)
     set(is_msvc TRUE)
-else ()
+else()
     message(FATAL_ERROR "Unsupported C++ compiler: ${CMAKE_CXX_COMPILER_ID}")
-endif ()
+endif()
 
 # Xcode generator detection
-if (CMAKE_GENERATOR STREQUAL "Xcode")
+if(CMAKE_GENERATOR STREQUAL "Xcode")
     set(is_xcode TRUE)
-endif ()
+endif()
 
 # --------------------------------------------------------------------
 # Operating system detection
@@ -36,23 +36,23 @@ set(is_linux FALSE)
 set(is_windows FALSE)
 set(is_macos FALSE)
 
-if (CMAKE_SYSTEM_NAME STREQUAL "Linux")
+if(CMAKE_SYSTEM_NAME STREQUAL "Linux")
     set(is_linux TRUE)
-elseif (CMAKE_SYSTEM_NAME STREQUAL "Windows")
+elseif(CMAKE_SYSTEM_NAME STREQUAL "Windows")
     set(is_windows TRUE)
-elseif (CMAKE_SYSTEM_NAME STREQUAL "Darwin")
+elseif(CMAKE_SYSTEM_NAME STREQUAL "Darwin")
     set(is_macos TRUE)
-endif ()
+endif()
 
 # --------------------------------------------------------------------
 # Architecture
 # --------------------------------------------------------------------
 set(is_amd64 FALSE)
 set(is_arm64 FALSE)
-if (CMAKE_SYSTEM_PROCESSOR MATCHES "x86_64|AMD64")
+if(CMAKE_SYSTEM_PROCESSOR MATCHES "x86_64|AMD64")
     set(is_amd64 TRUE)
-elseif (CMAKE_SYSTEM_PROCESSOR MATCHES "aarch64|arm64|ARM64")
+elseif(CMAKE_SYSTEM_PROCESSOR MATCHES "aarch64|arm64|ARM64")
     set(is_arm64 TRUE)
-else ()
+else()
     message(FATAL_ERROR "Unknown architecture: ${CMAKE_SYSTEM_PROCESSOR}")
-endif ()
+endif()

cmake/GitInfo.cmake

@@ -0,0 +1,28 @@
+include_guard()
+
+set(GIT_BUILD_BRANCH "")
+set(GIT_COMMIT_HASH "")
+
+find_package(Git)
+if(NOT Git_FOUND)
+    message(WARNING "Git not found. Git branch and commit hash will be empty.")
+    return()
+endif()
+
+set(GIT_DIRECTORY ${CMAKE_CURRENT_SOURCE_DIR}/.git)
+
+execute_process(
+    COMMAND
+        ${GIT_EXECUTABLE} --git-dir=${GIT_DIRECTORY} rev-parse --abbrev-ref HEAD
+    OUTPUT_STRIP_TRAILING_WHITESPACE
+    OUTPUT_VARIABLE GIT_BUILD_BRANCH
+)
+
+execute_process(
+    COMMAND ${GIT_EXECUTABLE} --git-dir=${GIT_DIRECTORY} rev-parse HEAD
+    OUTPUT_STRIP_TRAILING_WHITESPACE
+    OUTPUT_VARIABLE GIT_COMMIT_HASH
+)
+
+message(STATUS "Git branch: ${GIT_BUILD_BRANCH}")
+message(STATUS "Git commit hash: ${GIT_COMMIT_HASH}")

cmake/XrplAddTest.cmake

@@ -1,13 +1,22 @@
 include(isolate_headers)
 
-function (xrpl_add_test name)
+function(xrpl_add_test name)
     set(target ${PROJECT_NAME}.test.${name})
 
-    file(GLOB_RECURSE sources CONFIGURE_DEPENDS "${CMAKE_CURRENT_SOURCE_DIR}/${name}/*.cpp"
-         "${CMAKE_CURRENT_SOURCE_DIR}/${name}.cpp")
+    file(
+        GLOB_RECURSE sources
+        CONFIGURE_DEPENDS
+        "${CMAKE_CURRENT_SOURCE_DIR}/${name}/*.cpp"
+        "${CMAKE_CURRENT_SOURCE_DIR}/${name}.cpp"
+    )
     add_executable(${target} ${ARGN} ${sources})
 
-    isolate_headers(${target} "${CMAKE_SOURCE_DIR}" "${CMAKE_SOURCE_DIR}/tests/${name}" PRIVATE)
+    isolate_headers(
+        ${target}
+        "${CMAKE_SOURCE_DIR}"
+        "${CMAKE_SOURCE_DIR}/tests/${name}"
+        PRIVATE
+    )
 
     add_test(NAME ${target} COMMAND ${target})
-endfunction ()
+endfunction()

cmake/XrplCompiler.cmake

@@ -14,33 +14,42 @@ include(XrplSanitizers)
 # add a single global dependency on this interface lib
 link_libraries(Xrpl::common)
 # Respect CMAKE_POSITION_INDEPENDENT_CODE setting (may be set by Conan toolchain)
-if (NOT DEFINED CMAKE_POSITION_INDEPENDENT_CODE)
+if(NOT DEFINED CMAKE_POSITION_INDEPENDENT_CODE)
     set(CMAKE_POSITION_INDEPENDENT_CODE ON)
-endif ()
-set_target_properties(common PROPERTIES INTERFACE_POSITION_INDEPENDENT_CODE
-                                        ${CMAKE_POSITION_INDEPENDENT_CODE})
+endif()
+set_target_properties(
+    common
+    PROPERTIES
+        INTERFACE_POSITION_INDEPENDENT_CODE ${CMAKE_POSITION_INDEPENDENT_CODE}
+)
 set(CMAKE_CXX_EXTENSIONS OFF)
 target_compile_definitions(
     common
-    INTERFACE $<$<CONFIG:Debug>:DEBUG
-              _DEBUG>
-              #[===[
+    INTERFACE
+        $<$<CONFIG:Debug>:DEBUG
+        _DEBUG>
+        #[===[
     NOTE: CMAKE release builds already have NDEBUG defined, so no need to add it
     explicitly except for the special case of (profile ON) and (assert OFF).
     Presumably this is because we don't want profile builds asserting unless
     asserts were specifically requested.
     ]===]
-              $<$<AND:$<BOOL:${profile}>,$<NOT:$<BOOL:${assert}>>>:NDEBUG>
-              # TODO: Remove once we have migrated functions from OpenSSL 1.x to 3.x.
-              OPENSSL_SUPPRESS_DEPRECATED)
+        $<$<AND:$<BOOL:${profile}>,$<NOT:$<BOOL:${assert}>>>:NDEBUG>
+        # TODO: Remove once we have migrated functions from OpenSSL 1.x to 3.x.
+        OPENSSL_SUPPRESS_DEPRECATED
+)
 
-if (MSVC)
+if(MSVC)
     # remove existing exception flag since we set it to -EHa
     string(REGEX REPLACE "[-/]EH[a-z]+" "" CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS}")
 
-    foreach (var_ CMAKE_C_FLAGS_DEBUG CMAKE_C_FLAGS_RELEASE CMAKE_CXX_FLAGS_DEBUG
-                  CMAKE_CXX_FLAGS_RELEASE)
-
+    foreach(
+        var_
+        CMAKE_C_FLAGS_DEBUG
+        CMAKE_C_FLAGS_RELEASE
+        CMAKE_CXX_FLAGS_DEBUG
+        CMAKE_CXX_FLAGS_RELEASE
+    )
         # also remove dynamic runtime
         string(REGEX REPLACE "[-/]MD[d]*" " " ${var_} "${${var_}}")
 
@@ -48,120 +57,143 @@ if (MSVC)
         string(REPLACE "/ZI" "/Zi" ${var_} "${${var_}}")
 
         # omit debug info completely under CI (not needed)
-        if (is_ci)
+        if(is_ci)
             string(REPLACE "/Zi" " " ${var_} "${${var_}}")
             string(REPLACE "/Z7" " " ${var_} "${${var_}}")
-        endif ()
-    endforeach ()
+        endif()
+    endforeach()
 
     target_compile_options(
         common
         INTERFACE # Increase object file max size
-                  -bigobj
-                  # Floating point behavior
-                  -fp:precise
-                  # __cdecl calling convention
-                  -Gd
-                  # Minimal rebuild: disabled
-                  -Gm-
-                  # Function level linking: disabled
-                  -Gy-
-                  # Multiprocessor compilation
-                  -MP
-                  # pragma omp: disabled
-                  -openmp-
-                  # No error reporting to Internet
-                  -errorReport:none
-                  # Suppress login banner
-                  -nologo
-                  # Disable signed/unsigned comparison warnings
-                  -wd4018
-                  # Disable float to int possible loss of data warnings
-                  -wd4244
-                  # Disable size_t to T possible loss of data warnings
-                  -wd4267
-                  # Disable C4800(int to bool performance)
-                  -wd4800
-                  # Decorated name length exceeded, name was truncated
-                  -wd4503
-                  $<$<COMPILE_LANGUAGE:CXX>:
-                  -EHa
-                  -GR
-                  >
-                  $<$<CONFIG:Release>:-Ox>
-                  $<$<AND:$<COMPILE_LANGUAGE:CXX>,$<CONFIG:Debug>>:
-                  -GS
-                  -Zc:forScope
-                  >
-                  # static runtime
-                  $<$<CONFIG:Debug>:-MTd>
-                  $<$<NOT:$<CONFIG:Debug>>:-MT>
-                  $<$<BOOL:${werr}>:-WX>)
+            -bigobj
+            # Floating point behavior
+            -fp:precise
+            # __cdecl calling convention
+            -Gd
+            # Minimal rebuild: disabled
+            -Gm-
+            # Function level linking: disabled
+            -Gy-
+            # Multiprocessor compilation
+            -MP
+            # pragma omp: disabled
+            -openmp-
+            # No error reporting to Internet
+            -errorReport:none
+            # Suppress login banner
+            -nologo
+            # Disable signed/unsigned comparison warnings
+            -wd4018
+            # Disable float to int possible loss of data warnings
+            -wd4244
+            # Disable size_t to T possible loss of data warnings
+            -wd4267
+            # Disable C4800(int to bool performance)
+            -wd4800
+            # Decorated name length exceeded, name was truncated
+            -wd4503
+            $<$<COMPILE_LANGUAGE:CXX>:
+            -EHa
+            -GR
+            >
+            $<$<CONFIG:Release>:-Ox>
+            $<$<AND:$<COMPILE_LANGUAGE:CXX>,$<CONFIG:Debug>>:
+            -GS
+            -Zc:forScope
+            >
+            # static runtime
+            $<$<CONFIG:Debug>:-MTd>
+            $<$<NOT:$<CONFIG:Debug>>:-MT>
+            $<$<BOOL:${werr}>:-WX>
+    )
     target_compile_definitions(
         common
-        INTERFACE _WIN32_WINNT=0x6000
-                  _SCL_SECURE_NO_WARNINGS
-                  _CRT_SECURE_NO_WARNINGS
-                  WIN32_CONSOLE
-                  WIN32_LEAN_AND_MEAN
-                  NOMINMAX
-                  # TODO: Resolve these warnings, don't just silence them
-                  _SILENCE_ALL_CXX17_DEPRECATION_WARNINGS
-                  $<$<AND:$<COMPILE_LANGUAGE:CXX>,$<CONFIG:Debug>>:_CRTDBG_MAP_ALLOC>)
+        INTERFACE
+            _WIN32_WINNT=0x6000
+            _SCL_SECURE_NO_WARNINGS
+            _CRT_SECURE_NO_WARNINGS
+            WIN32_CONSOLE
+            WIN32_LEAN_AND_MEAN
+            NOMINMAX
+            # TODO: Resolve these warnings, don't just silence them
+            _SILENCE_ALL_CXX17_DEPRECATION_WARNINGS
+            $<$<AND:$<COMPILE_LANGUAGE:CXX>,$<CONFIG:Debug>>:_CRTDBG_MAP_ALLOC>
+    )
     target_link_libraries(common INTERFACE -errorreport:none -machine:X64)
-else ()
+else()
     target_compile_options(
         common
-        INTERFACE -Wall
-                  -Wdeprecated
-                  $<$<BOOL:${is_clang}>:-Wno-deprecated-declarations>
-                  $<$<BOOL:${wextra}>:-Wextra
-                  -Wno-unused-parameter>
-                  $<$<BOOL:${werr}>:-Werror>
-                  -fstack-protector
-                  -Wno-sign-compare
-                  -Wno-unused-but-set-variable
-                  $<$<NOT:$<CONFIG:Debug>>:-fno-strict-aliasing>
-                  # tweak gcc optimization for debug
-                  $<$<AND:$<BOOL:${is_gcc}>,$<CONFIG:Debug>>:-O0>
-                  # Add debug symbols to release config
-                  $<$<CONFIG:Release>:-g>)
+        INTERFACE
+            -Wall
+            -Wdeprecated
+            $<$<BOOL:${is_clang}>:-Wno-deprecated-declarations>
+            $<$<BOOL:${wextra}>:-Wextra
+            -Wno-unused-parameter>
+            $<$<BOOL:${werr}>:-Werror>
+            -fstack-protector
+            -Wno-sign-compare
+            -Wno-unused-but-set-variable
+            $<$<NOT:$<CONFIG:Debug>>:-fno-strict-aliasing>
+            # tweak gcc optimization for debug
+            $<$<AND:$<BOOL:${is_gcc}>,$<CONFIG:Debug>>:-O0>
+            # Add debug symbols to release config
+            $<$<CONFIG:Release>:-g>
+    )
     target_link_libraries(
         common
-        INTERFACE -rdynamic
-                  $<$<BOOL:${is_linux}>:-Wl,-z,relro,-z,now,--build-id>
-                  # link to static libc/c++ iff: * static option set and * NOT APPLE (AppleClang does not support static
-                  # libc/c++) and * NOT SANITIZERS (sanitizers typically don't work with static libc/c++)
-                  $<$<AND:$<BOOL:${static}>,$<NOT:$<BOOL:${APPLE}>>,$<NOT:$<BOOL:${SANITIZERS_ENABLED}>>>:
-                  -static-libstdc++
-                  -static-libgcc
-                  >)
-endif ()
+        INTERFACE
+            -rdynamic
+            $<$<BOOL:${is_linux}>:-Wl,-z,relro,-z,now,--build-id>
+            # link to static libc/c++ iff: * static option set and * NOT APPLE (AppleClang does not support static
+            # libc/c++) and * NOT SANITIZERS (sanitizers typically don't work with static libc/c++)
+            $<$<AND:$<BOOL:${static}>,$<NOT:$<BOOL:${APPLE}>>,$<NOT:$<BOOL:${SANITIZERS_ENABLED}>>>:
+            -static-libstdc++
+            -static-libgcc
+            >
+    )
+endif()
 
 # Antithesis instrumentation will only be built and deployed using machines running Linux.
-if (voidstar)
-    if (NOT CMAKE_BUILD_TYPE STREQUAL "Debug")
-        message(FATAL_ERROR "Antithesis instrumentation requires Debug build type, aborting...")
-    elseif (NOT is_linux)
-        message(FATAL_ERROR "Antithesis instrumentation requires Linux, aborting...")
-    elseif (NOT (is_clang AND CMAKE_CXX_COMPILER_VERSION VERSION_GREATER_EQUAL 16.0))
-        message(FATAL_ERROR "Antithesis instrumentation requires Clang version 16 or later, aborting..."
+if(voidstar)
+    if(NOT CMAKE_BUILD_TYPE STREQUAL "Debug")
+        message(
+            FATAL_ERROR
+            "Antithesis instrumentation requires Debug build type, aborting..."
         )
-    endif ()
-endif ()
+    elseif(NOT is_linux)
+        message(
+            FATAL_ERROR
+            "Antithesis instrumentation requires Linux, aborting..."
+        )
+    elseif(
+        NOT (is_clang AND CMAKE_CXX_COMPILER_VERSION VERSION_GREATER_EQUAL 16.0)
+    )
+        message(
+            FATAL_ERROR
+            "Antithesis instrumentation requires Clang version 16 or later, aborting..."
+        )
+    endif()
+endif()
 
-if (use_mold)
+if(use_mold)
     # use mold linker if available
-    execute_process(COMMAND ${CMAKE_CXX_COMPILER} -fuse-ld=mold -Wl,--version ERROR_QUIET
-                    OUTPUT_VARIABLE LD_VERSION)
-    if ("${LD_VERSION}" MATCHES "mold")
+    execute_process(
+        COMMAND ${CMAKE_CXX_COMPILER} -fuse-ld=mold -Wl,--version
+        ERROR_QUIET
+        OUTPUT_VARIABLE LD_VERSION
+    )
+    if("${LD_VERSION}" MATCHES "mold")
         target_link_libraries(common INTERFACE -fuse-ld=mold)
-    endif ()
+    endif()
     unset(LD_VERSION)
-elseif (use_gold AND is_gcc)
+elseif(use_gold AND is_gcc)
     # use gold linker if available
-    execute_process(COMMAND ${CMAKE_CXX_COMPILER} -fuse-ld=gold -Wl,--version ERROR_QUIET
-                    OUTPUT_VARIABLE LD_VERSION)
+    execute_process(
+        COMMAND ${CMAKE_CXX_COMPILER} -fuse-ld=gold -Wl,--version
+        ERROR_QUIET
+        OUTPUT_VARIABLE LD_VERSION
+    )
     #[=========================================================[
        NOTE: THE gold linker inserts -rpath as DT_RUNPATH by
        default instead of DT_RPATH, so you might have slightly
@@ -175,32 +207,37 @@ elseif (use_gold AND is_gcc)
        disabling would be to figure out all the settings
        required to make gold play nicely with jemalloc.
     #]=========================================================]
-    if (("${LD_VERSION}" MATCHES "GNU gold") AND (NOT jemalloc))
+    if(("${LD_VERSION}" MATCHES "GNU gold") AND (NOT jemalloc))
         target_link_libraries(
             common
-            INTERFACE -fuse-ld=gold
-                      -Wl,--no-as-needed
-                      #[=========================================================[
+            INTERFACE
+                -fuse-ld=gold
+                -Wl,--no-as-needed
+                #[=========================================================[
            see https://bugs.launchpad.net/ubuntu/+source/eglibc/+bug/1253638/comments/5
            DT_RUNPATH does not work great for transitive
            dependencies (of which boost has a few) - so just
            switch to DT_RPATH if doing dynamic linking with gold
         #]=========================================================]
-                      $<$<NOT:$<BOOL:${static}>>:-Wl,--disable-new-dtags>)
-    endif ()
+                $<$<NOT:$<BOOL:${static}>>:-Wl,--disable-new-dtags>
+        )
+    endif()
     unset(LD_VERSION)
-elseif (use_lld)
+elseif(use_lld)
     # use lld linker if available
-    execute_process(COMMAND ${CMAKE_CXX_COMPILER} -fuse-ld=lld -Wl,--version ERROR_QUIET
-                    OUTPUT_VARIABLE LD_VERSION)
-    if ("${LD_VERSION}" MATCHES "LLD")
+    execute_process(
+        COMMAND ${CMAKE_CXX_COMPILER} -fuse-ld=lld -Wl,--version
+        ERROR_QUIET
+        OUTPUT_VARIABLE LD_VERSION
+    )
+    if("${LD_VERSION}" MATCHES "LLD")
         target_link_libraries(common INTERFACE -fuse-ld=lld)
-    endif ()
+    endif()
     unset(LD_VERSION)
-endif ()
+endif()
 
-if (assert)
-    foreach (var_ CMAKE_C_FLAGS_RELEASE CMAKE_CXX_FLAGS_RELEASE)
+if(assert)
+    foreach(var_ CMAKE_C_FLAGS_RELEASE CMAKE_CXX_FLAGS_RELEASE)
         string(REGEX REPLACE "[-/]DNDEBUG" "" ${var_} "${${var_}}")
-    endforeach ()
-endif ()
+    endforeach()
+endif()

cmake/XrplConfig.cmake

@@ -3,50 +3,58 @@ include(CMakeFindDependencyMacro)
 #[=========================================================[
   Boost
 #]=========================================================]
-if (static OR APPLE OR MSVC)
+if(static OR APPLE OR MSVC)
     set(Boost_USE_STATIC_LIBS ON)
-endif ()
+endif()
 set(Boost_USE_MULTITHREADED ON)
-if (static OR MSVC)
+if(static OR MSVC)
     set(Boost_USE_STATIC_RUNTIME ON)
-else ()
+else()
     set(Boost_USE_STATIC_RUNTIME OFF)
-endif ()
-find_dependency(Boost
-                COMPONENTS
-                chrono
-                container
-                context
-                coroutine
-                date_time
-                filesystem
-                program_options
-                regex
-                system
-                thread)
+endif()
+find_dependency(
+    Boost
+    COMPONENTS
+    chrono
+    container
+    context
+    coroutine
+    date_time
+    filesystem
+    program_options
+    regex
+    system
+    thread
+)
 #[=========================================================[
   OpenSSL
 #]=========================================================]
-if (NOT DEFINED OPENSSL_ROOT_DIR)
-    if (DEFINED ENV{OPENSSL_ROOT})
+if(NOT DEFINED OPENSSL_ROOT_DIR)
+    if(DEFINED ENV{OPENSSL_ROOT})
         set(OPENSSL_ROOT_DIR $ENV{OPENSSL_ROOT})
-    elseif (APPLE)
+    elseif(APPLE)
         find_program(homebrew brew)
-        if (homebrew)
-            execute_process(COMMAND ${homebrew} --prefix openssl OUTPUT_VARIABLE OPENSSL_ROOT_DIR
-                            OUTPUT_STRIP_TRAILING_WHITESPACE)
-        endif ()
-    endif ()
+        if(homebrew)
+            execute_process(
+                COMMAND ${homebrew} --prefix openssl
+                OUTPUT_VARIABLE OPENSSL_ROOT_DIR
+                OUTPUT_STRIP_TRAILING_WHITESPACE
+            )
+        endif()
+    endif()
     file(TO_CMAKE_PATH "${OPENSSL_ROOT_DIR}" OPENSSL_ROOT_DIR)
-endif ()
+endif()
 
-if (static OR APPLE OR MSVC)
+if(static OR APPLE OR MSVC)
     set(OPENSSL_USE_STATIC_LIBS ON)
-endif ()
+endif()
 set(OPENSSL_MSVC_STATIC_RT ON)
 find_dependency(OpenSSL REQUIRED)
 find_dependency(ZLIB)
 find_dependency(date)
-if (TARGET ZLIB::ZLIB)
-    set_target_properties(OpenSSL::Crypto PROPERTIES INTERFACE_LINK_LIBRARIES ZLIB::ZLIB)
-endif ()
+if(TARGET ZLIB::ZLIB)
+    set_target_properties(
+        OpenSSL::Crypto
+        PROPERTIES INTERFACE_LINK_LIBRARIES ZLIB::ZLIB
+    )
+endif()

cmake/XrplCore.cmake

@@ -10,25 +10,44 @@ include(target_protobuf_sources)
 # so we just build them as a separate library.
 add_library(xrpl.libpb)
 set_target_properties(xrpl.libpb PROPERTIES UNITY_BUILD OFF)
-target_protobuf_sources(xrpl.libpb xrpl/proto LANGUAGE cpp IMPORT_DIRS include/xrpl/proto
-                        PROTOS include/xrpl/proto/xrpl.proto)
+target_protobuf_sources(
+    xrpl.libpb
+    xrpl/proto
+    LANGUAGE cpp
+    IMPORT_DIRS include/xrpl/proto
+    PROTOS include/xrpl/proto/xrpl.proto
+)
 
 file(GLOB_RECURSE protos "include/xrpl/proto/org/*.proto")
-target_protobuf_sources(xrpl.libpb xrpl/proto LANGUAGE cpp IMPORT_DIRS include/xrpl/proto
-                        PROTOS "${protos}")
 target_protobuf_sources(
-    xrpl.libpb xrpl/proto
+    xrpl.libpb
+    xrpl/proto
+    LANGUAGE cpp
+    IMPORT_DIRS include/xrpl/proto
+    PROTOS "${protos}"
+)
+target_protobuf_sources(
+    xrpl.libpb
+    xrpl/proto
     LANGUAGE grpc
     IMPORT_DIRS include/xrpl/proto
     PROTOS "${protos}"
     PLUGIN protoc-gen-grpc=$<TARGET_FILE:gRPC::grpc_cpp_plugin>
-    GENERATE_EXTENSIONS .grpc.pb.h .grpc.pb.cc)
+    GENERATE_EXTENSIONS .grpc.pb.h .grpc.pb.cc
+)
 
 target_compile_options(
     xrpl.libpb
-    PUBLIC $<$<BOOL:${is_msvc}>:-wd4996> $<$<BOOL:${is_xcode}>:
-           --system-header-prefix="google/protobuf" -Wno-deprecated-dynamic-exception-spec >
-    PRIVATE $<$<BOOL:${is_msvc}>:-wd4065> $<$<NOT:$<BOOL:${is_msvc}>>:-Wno-deprecated-declarations>)
+    PUBLIC
+        $<$<BOOL:${is_msvc}>:-wd4996>
+        $<$<BOOL:${is_xcode}>:
+        --system-header-prefix="google/protobuf"
+        -Wno-deprecated-dynamic-exception-spec
+        >
+    PRIVATE
+        $<$<BOOL:${is_msvc}>:-wd4065>
+        $<$<NOT:$<BOOL:${is_msvc}>>:-Wno-deprecated-declarations>
+)
 
 target_link_libraries(xrpl.libpb PUBLIC protobuf::libprotobuf gRPC::grpc++)
 
@@ -37,19 +56,21 @@ add_library(xrpl.imports.main INTERFACE)
 
 target_link_libraries(
     xrpl.imports.main
-    INTERFACE absl::random_random
-              date::date
-              ed25519::ed25519
-              LibArchive::LibArchive
-              OpenSSL::Crypto
-              Xrpl::boost
-              Xrpl::libs
-              Xrpl::opts
-              Xrpl::syslibs
-              secp256k1::secp256k1
-              xrpl.libpb
-              xxHash::xxhash
-              $<$<BOOL:${voidstar}>:antithesis-sdk-cpp>)
+    INTERFACE
+        absl::random_random
+        date::date
+        ed25519::ed25519
+        LibArchive::LibArchive
+        OpenSSL::Crypto
+        Xrpl::boost
+        Xrpl::libs
+        Xrpl::opts
+        Xrpl::syslibs
+        secp256k1::secp256k1
+        xrpl.libpb
+        xxHash::xxhash
+        $<$<BOOL:${voidstar}>:antithesis-sdk-cpp>
+)
 
 include(add_module)
 include(target_link_modules)
@@ -57,6 +78,23 @@ include(target_link_modules)
 # Level 01
 add_module(xrpl beast)
 target_link_libraries(xrpl.libxrpl.beast PUBLIC xrpl.imports.main)
+# OTelCollector in beast/insight uses OTel Metrics SDK when telemetry is enabled.
+if(telemetry)
+    target_link_libraries(
+        xrpl.libxrpl.beast
+        PUBLIC opentelemetry-cpp::opentelemetry-cpp
+    )
+endif()
+
+include(GitInfo)
+add_module(xrpl git)
+target_compile_definitions(
+    xrpl.libxrpl.git
+    PRIVATE
+        GIT_COMMIT_HASH="${GIT_COMMIT_HASH}"
+        GIT_BUILD_BRANCH="${GIT_BUILD_BRANCH}"
+)
+target_link_libraries(xrpl.libxrpl.git PUBLIC xrpl.imports.main)
 
 # Level 02
 add_module(xrpl basics)
@@ -71,12 +109,17 @@ target_link_libraries(xrpl.libxrpl.crypto PUBLIC xrpl.libxrpl.basics)
 
 # Level 04
 add_module(xrpl protocol)
-target_link_libraries(xrpl.libxrpl.protocol PUBLIC xrpl.libxrpl.crypto xrpl.libxrpl.json)
+target_link_libraries(
+    xrpl.libxrpl.protocol
+    PUBLIC xrpl.libxrpl.crypto xrpl.libxrpl.git xrpl.libxrpl.json
+)
 
 # Level 05
 add_module(xrpl core)
-target_link_libraries(xrpl.libxrpl.core PUBLIC xrpl.libxrpl.basics xrpl.libxrpl.json
-                                               xrpl.libxrpl.protocol)
+target_link_libraries(
+    xrpl.libxrpl.core
+    PUBLIC xrpl.libxrpl.basics xrpl.libxrpl.json xrpl.libxrpl.protocol
+)
 
 # Level 06
 add_module(xrpl resource)
@@ -84,23 +127,46 @@ target_link_libraries(xrpl.libxrpl.resource PUBLIC xrpl.libxrpl.protocol)
 
 # Level 07
 add_module(xrpl net)
-target_link_libraries(xrpl.libxrpl.net PUBLIC xrpl.libxrpl.basics xrpl.libxrpl.json
-                                              xrpl.libxrpl.protocol xrpl.libxrpl.resource)
+target_link_libraries(
+    xrpl.libxrpl.net
+    PUBLIC
+        xrpl.libxrpl.basics
+        xrpl.libxrpl.json
+        xrpl.libxrpl.protocol
+        xrpl.libxrpl.resource
+)
 
 add_module(xrpl nodestore)
-target_link_libraries(xrpl.libxrpl.nodestore PUBLIC xrpl.libxrpl.basics xrpl.libxrpl.json
-                                                    xrpl.libxrpl.protocol)
+target_link_libraries(
+    xrpl.libxrpl.nodestore
+    PUBLIC xrpl.libxrpl.basics xrpl.libxrpl.json xrpl.libxrpl.protocol
+)
 
 add_module(xrpl shamap)
-target_link_libraries(xrpl.libxrpl.shamap PUBLIC xrpl.libxrpl.basics xrpl.libxrpl.crypto
-                                                 xrpl.libxrpl.protocol xrpl.libxrpl.nodestore)
+target_link_libraries(
+    xrpl.libxrpl.shamap
+    PUBLIC
+        xrpl.libxrpl.basics
+        xrpl.libxrpl.crypto
+        xrpl.libxrpl.protocol
+        xrpl.libxrpl.nodestore
+)
 
 add_module(xrpl rdb)
-target_link_libraries(xrpl.libxrpl.rdb PUBLIC xrpl.libxrpl.basics xrpl.libxrpl.core)
+target_link_libraries(
+    xrpl.libxrpl.rdb
+    PUBLIC xrpl.libxrpl.basics xrpl.libxrpl.core
+)
 
 add_module(xrpl server)
-target_link_libraries(xrpl.libxrpl.server PUBLIC xrpl.libxrpl.protocol xrpl.libxrpl.core
-                                                 xrpl.libxrpl.rdb xrpl.libxrpl.resource)
+target_link_libraries(
+    xrpl.libxrpl.server
+    PUBLIC
+        xrpl.libxrpl.protocol
+        xrpl.libxrpl.core
+        xrpl.libxrpl.rdb
+        xrpl.libxrpl.resource
+)
 
 add_module(xrpl conditions)
 target_link_libraries(xrpl.libxrpl.conditions PUBLIC xrpl.libxrpl.server)
@@ -108,23 +174,46 @@ target_link_libraries(xrpl.libxrpl.conditions PUBLIC xrpl.libxrpl.server)
 add_module(xrpl ledger)
 target_link_libraries(
     xrpl.libxrpl.ledger
-    PUBLIC xrpl.libxrpl.basics
-           xrpl.libxrpl.json
-           xrpl.libxrpl.protocol
-           xrpl.libxrpl.rdb
-           xrpl.libxrpl.server
-           xrpl.libxrpl.shamap
-           xrpl.libxrpl.conditions)
+    PUBLIC
+        xrpl.libxrpl.basics
+        xrpl.libxrpl.json
+        xrpl.libxrpl.protocol
+        xrpl.libxrpl.rdb
+        xrpl.libxrpl.server
+        xrpl.libxrpl.shamap
+        xrpl.libxrpl.conditions
+)
 
 add_module(xrpl tx)
 target_link_libraries(xrpl.libxrpl.tx PUBLIC xrpl.libxrpl.ledger)
 
+# Telemetry module — OpenTelemetry distributed tracing support.
+# Sources: include/xrpl/telemetry/ (headers), src/libxrpl/telemetry/ (impl).
+# When telemetry=ON, links the Conan-provided umbrella target
+# opentelemetry-cpp::opentelemetry-cpp (individual component targets like
+# ::api, ::sdk are not available in the Conan package).
+add_module(xrpl telemetry)
+target_link_libraries(
+    xrpl.libxrpl.telemetry
+    PUBLIC xrpl.libxrpl.basics xrpl.libxrpl.beast
+)
+if(telemetry)
+    target_link_libraries(
+        xrpl.libxrpl.telemetry
+        PUBLIC opentelemetry-cpp::opentelemetry-cpp
+    )
+endif()
+
 add_library(xrpl.libxrpl)
 set_target_properties(xrpl.libxrpl PROPERTIES OUTPUT_NAME xrpl)
 
 add_library(xrpl::libxrpl ALIAS xrpl.libxrpl)
 
-file(GLOB_RECURSE sources CONFIGURE_DEPENDS "${CMAKE_CURRENT_SOURCE_DIR}/src/libxrpl/*.cpp")
+file(
+    GLOB_RECURSE sources
+    CONFIGURE_DEPENDS
+    "${CMAKE_CURRENT_SOURCE_DIR}/src/libxrpl/*.cpp"
+)
 target_sources(xrpl.libxrpl PRIVATE ${sources})
 
 target_link_modules(
@@ -135,6 +224,7 @@ target_link_modules(
     conditions
     core
     crypto
+    git
     json
     ledger
     net
@@ -144,7 +234,9 @@ target_link_modules(
     resource
     server
     shamap
-    tx)
+    telemetry
+    tx
+)
 
 # All headers in libxrpl are in modules.
 # Uncomment this stanza if you have not yet moved new headers into a module.
@@ -155,34 +247,51 @@ target_link_modules(
 #     $<BUILD_INTERFACE:${CMAKE_CURRENT_SOURCE_DIR}/include>
 #     $<INSTALL_INTERFACE:include>)
 
-if (xrpld)
+if(xrpld)
     add_executable(xrpld)
-    if (tests)
+    if(tests)
         target_compile_definitions(xrpld PUBLIC ENABLE_TESTS)
-        target_compile_definitions(xrpld PRIVATE UNIT_TEST_REFERENCE_FEE=${UNIT_TEST_REFERENCE_FEE})
-    endif ()
-    target_include_directories(xrpld PRIVATE $<BUILD_INTERFACE:${CMAKE_CURRENT_SOURCE_DIR}/src>)
+        target_compile_definitions(
+            xrpld
+            PRIVATE UNIT_TEST_REFERENCE_FEE=${UNIT_TEST_REFERENCE_FEE}
+        )
+    endif()
+    target_include_directories(
+        xrpld
+        PRIVATE $<BUILD_INTERFACE:${CMAKE_CURRENT_SOURCE_DIR}/src>
+    )
 
-    file(GLOB_RECURSE sources CONFIGURE_DEPENDS "${CMAKE_CURRENT_SOURCE_DIR}/src/xrpld/*.cpp")
+    file(
+        GLOB_RECURSE sources
+        CONFIGURE_DEPENDS
+        "${CMAKE_CURRENT_SOURCE_DIR}/src/xrpld/*.cpp"
+    )
     target_sources(xrpld PRIVATE ${sources})
 
-    if (tests)
-        file(GLOB_RECURSE sources CONFIGURE_DEPENDS "${CMAKE_CURRENT_SOURCE_DIR}/src/test/*.cpp")
+    if(tests)
+        file(
+            GLOB_RECURSE sources
+            CONFIGURE_DEPENDS
+            "${CMAKE_CURRENT_SOURCE_DIR}/src/test/*.cpp"
+        )
         target_sources(xrpld PRIVATE ${sources})
-    endif ()
+    endif()
 
     target_link_libraries(xrpld Xrpl::boost Xrpl::opts Xrpl::libs xrpl.libxrpl)
     exclude_if_included(xrpld)
     # define a macro for tests that might need to
     # be excluded or run differently in CI environment
-    if (is_ci)
+    if(is_ci)
         target_compile_definitions(xrpld PRIVATE XRPL_RUNNING_IN_CI)
-    endif ()
+    endif()
 
-    if (voidstar)
+    if(voidstar)
         target_compile_options(xrpld PRIVATE -fsanitize-coverage=trace-pc-guard)
         # xrpld requires access to antithesis-sdk-cpp implementation file
         # antithesis_instrumentation.h, which is not exported as INTERFACE
-        target_include_directories(xrpld PRIVATE ${CMAKE_SOURCE_DIR}/external/antithesis-sdk)
-    endif ()
-endif ()
+        target_include_directories(
+            xrpld
+            PRIVATE ${CMAKE_SOURCE_DIR}/external/antithesis-sdk
+        )
+    endif()
+endif()

cmake/XrplCov.cmake

@@ -2,14 +2,17 @@
    coverage report target
 #]===================================================================]
 
-if (NOT coverage)
+if(NOT coverage)
     message(FATAL_ERROR "Code coverage not enabled! Aborting ...")
-endif ()
+endif()
 
-if (CMAKE_CXX_COMPILER_ID MATCHES "MSVC")
-    message(WARNING "Code coverage on Windows is not supported, ignoring 'coverage' flag")
+if(CMAKE_CXX_COMPILER_ID MATCHES "MSVC")
+    message(
+        WARNING
+        "Code coverage on Windows is not supported, ignoring 'coverage' flag"
+    )
     return()
-endif ()
+endif()
 
 include(ProcessorCount)
 ProcessorCount(PROCESSOR_COUNT)
@@ -21,32 +24,30 @@ include(CodeCoverage)
 # `CodeCoverage.cmake`)
 
 set(GCOVR_ADDITIONAL_ARGS ${coverage_extra_args})
-if (NOT GCOVR_ADDITIONAL_ARGS STREQUAL "")
+if(NOT GCOVR_ADDITIONAL_ARGS STREQUAL "")
     separate_arguments(GCOVR_ADDITIONAL_ARGS)
-endif ()
+endif()
 
-list(APPEND
-     GCOVR_ADDITIONAL_ARGS
-     --exclude-throw-branches
-     --exclude-noncode-lines
-     --exclude-unreachable-branches
-     -s
-     -j
-     ${PROCESSOR_COUNT})
+list(
+    APPEND GCOVR_ADDITIONAL_ARGS
+    --exclude-throw-branches
+    --exclude-noncode-lines
+    --exclude-unreachable-branches
+    -s
+    -j
+    ${PROCESSOR_COUNT}
+)
 
 setup_target_for_coverage_gcovr(
-    NAME
-    coverage
-    FORMAT
-    ${coverage_format}
+    NAME coverage
+    FORMAT ${coverage_format}
     EXCLUDE
-    "src/test"
-    "src/tests"
-    "include/xrpl/beast/test"
-    "include/xrpl/beast/unit_test"
-    "${CMAKE_BINARY_DIR}/pb-xrpl.libpb"
-    DEPENDENCIES
-    xrpld
-    xrpl.tests)
+        "src/test"
+        "src/tests"
+        "include/xrpl/beast/test"
+        "include/xrpl/beast/unit_test"
+        "${CMAKE_BINARY_DIR}/pb-xrpl.libpb"
+    DEPENDENCIES xrpld xrpl.tests
+)
 
 add_code_coverage_to_target(opts INTERFACE)

cmake/XrplDocs.cmake

@@ -2,71 +2,90 @@
    docs target (optional)
 #]===================================================================]
 
-if (NOT only_docs)
+if(NOT only_docs)
     return()
-endif ()
+endif()
 
 find_package(Doxygen)
-if (NOT TARGET Doxygen::doxygen)
+if(NOT TARGET Doxygen::doxygen)
     message(STATUS "doxygen executable not found -- skipping docs target")
     return()
-endif ()
+endif()
 
 set(doxygen_output_directory "${CMAKE_BINARY_DIR}/docs")
 set(doxygen_include_path "${CMAKE_CURRENT_SOURCE_DIR}/src")
 set(doxygen_index_file "${doxygen_output_directory}/html/index.html")
 set(doxyfile "${CMAKE_CURRENT_SOURCE_DIR}/docs/Doxyfile")
 
-file(GLOB_RECURSE
-     doxygen_input
-     docs/*.md
-     include/*.h
-     include/*.cpp
-     include/*.md
-     src/*.h
-     src/*.cpp
-     src/*.md
-     Builds/*.md
-     *.md)
+file(
+    GLOB_RECURSE doxygen_input
+    docs/*.md
+    include/*.h
+    include/*.cpp
+    include/*.md
+    src/*.h
+    src/*.cpp
+    src/*.md
+    Builds/*.md
+    *.md
+)
 list(APPEND doxygen_input external/README.md)
 set(dependencies "${doxygen_input}" "${doxyfile}")
 
-function (verbose_find_path variable name)
+function(verbose_find_path variable name)
     # find_path sets a CACHE variable, so don't try using a "local" variable.
     find_path(${variable} "${name}" ${ARGN})
-    if (NOT ${variable})
+    if(NOT ${variable})
         message(NOTICE "could not find ${name}")
-    else ()
+    else()
         message(STATUS "found ${name}: ${${variable}}/${name}")
-    endif ()
-endfunction ()
+    endif()
+endfunction()
 
-verbose_find_path(doxygen_plantuml_jar_path plantuml.jar PATH_SUFFIXES share/plantuml)
+verbose_find_path(
+    doxygen_plantuml_jar_path
+    plantuml.jar
+    PATH_SUFFIXES share/plantuml
+)
 verbose_find_path(doxygen_dot_path dot)
 
 # https://en.cppreference.com/w/Cppreference:Archives
 # https://stackoverflow.com/questions/60822559/how-to-move-a-file-download-from-configure-step-to-build-step
 set(download_script "${CMAKE_BINARY_DIR}/docs/download-cppreference.cmake")
-file(WRITE "${download_script}"
-     "file(DOWNLOAD \
+file(
+    WRITE "${download_script}"
+    "file(DOWNLOAD \
     https://github.com/PeterFeicht/cppreference-doc/releases/download/v20250209/html-book-20250209.zip \
     ${CMAKE_BINARY_DIR}/docs/cppreference.zip \
     EXPECTED_HASH MD5=bda585f72fbca4b817b29a3d5746567b \
   )\n \
   execute_process( \
     COMMAND \"${CMAKE_COMMAND}\" -E tar -xf cppreference.zip \
-  )\n")
+  )\n"
+)
 set(tagfile "${CMAKE_BINARY_DIR}/docs/cppreference-doxygen-web.tag.xml")
-add_custom_command(OUTPUT "${tagfile}" COMMAND "${CMAKE_COMMAND}" -P "${download_script}"
-                   WORKING_DIRECTORY "${CMAKE_BINARY_DIR}/docs")
+add_custom_command(
+    OUTPUT "${tagfile}"
+    COMMAND "${CMAKE_COMMAND}" -P "${download_script}"
+    WORKING_DIRECTORY "${CMAKE_BINARY_DIR}/docs"
+)
 set(doxygen_tagfiles "${tagfile}=http://en.cppreference.com/w/")
 
 add_custom_command(
     OUTPUT "${doxygen_index_file}"
-    COMMAND "${CMAKE_COMMAND}" -E env "DOXYGEN_OUTPUT_DIRECTORY=${doxygen_output_directory}"
-            "DOXYGEN_INCLUDE_PATH=${doxygen_include_path}" "DOXYGEN_TAGFILES=${doxygen_tagfiles}"
-            "DOXYGEN_PLANTUML_JAR_PATH=${doxygen_plantuml_jar_path}"
-            "DOXYGEN_DOT_PATH=${doxygen_dot_path}" "${DOXYGEN_EXECUTABLE}" "${doxyfile}"
+    COMMAND
+        "${CMAKE_COMMAND}" -E env
+        "DOXYGEN_OUTPUT_DIRECTORY=${doxygen_output_directory}"
+        "DOXYGEN_INCLUDE_PATH=${doxygen_include_path}"
+        "DOXYGEN_TAGFILES=${doxygen_tagfiles}"
+        "DOXYGEN_PLANTUML_JAR_PATH=${doxygen_plantuml_jar_path}"
+        "DOXYGEN_DOT_PATH=${doxygen_dot_path}" "${DOXYGEN_EXECUTABLE}"
+        "${doxyfile}"
     WORKING_DIRECTORY "${CMAKE_CURRENT_SOURCE_DIR}"
-    DEPENDS "${dependencies}" "${tagfile}")
-add_custom_target(docs DEPENDS "${doxygen_index_file}" SOURCES "${dependencies}")
+    DEPENDS "${dependencies}" "${tagfile}"
+)
+add_custom_target(
+    docs
+    DEPENDS "${doxygen_index_file}"
+    SOURCES "${dependencies}"
+)

cmake/XrplInstall.cmake

@@ -6,56 +6,72 @@ include(create_symbolic_link)
 
 # If no suffix is defined for executables (e.g. Windows uses .exe but Linux
 # and macOS use none), then explicitly set it to the empty string.
-if (NOT DEFINED suffix)
+if(NOT DEFINED suffix)
     set(suffix "")
-endif ()
+endif()
 
-install(TARGETS common
-                opts
-                xrpl_boost
-                xrpl_libs
-                xrpl_syslibs
-                xrpl.imports.main
-                xrpl.libpb
-                xrpl.libxrpl
-                xrpl.libxrpl.basics
-                xrpl.libxrpl.beast
-                xrpl.libxrpl.conditions
-                xrpl.libxrpl.core
-                xrpl.libxrpl.crypto
-                xrpl.libxrpl.json
-                xrpl.libxrpl.rdb
-                xrpl.libxrpl.ledger
-                xrpl.libxrpl.net
-                xrpl.libxrpl.nodestore
-                xrpl.libxrpl.protocol
-                xrpl.libxrpl.resource
-                xrpl.libxrpl.server
-                xrpl.libxrpl.shamap
-                xrpl.libxrpl.tx
-                antithesis-sdk-cpp
-        EXPORT XrplExports
-        LIBRARY DESTINATION lib
-        ARCHIVE DESTINATION lib
-        RUNTIME DESTINATION bin
-        INCLUDES
-        DESTINATION include)
+install(
+    TARGETS
+        common
+        opts
+        xrpl_boost
+        xrpl_libs
+        xrpl_syslibs
+        xrpl.imports.main
+        xrpl.libpb
+        xrpl.libxrpl
+        xrpl.libxrpl.basics
+        xrpl.libxrpl.beast
+        xrpl.libxrpl.conditions
+        xrpl.libxrpl.core
+        xrpl.libxrpl.crypto
+        xrpl.libxrpl.git
+        xrpl.libxrpl.json
+        xrpl.libxrpl.rdb
+        xrpl.libxrpl.ledger
+        xrpl.libxrpl.net
+        xrpl.libxrpl.nodestore
+        xrpl.libxrpl.protocol
+        xrpl.libxrpl.resource
+        xrpl.libxrpl.server
+        xrpl.libxrpl.shamap
+        xrpl.libxrpl.telemetry
+        xrpl.libxrpl.tx
+        antithesis-sdk-cpp
+    EXPORT XrplExports
+    LIBRARY DESTINATION lib
+    ARCHIVE DESTINATION lib
+    RUNTIME DESTINATION bin
+    INCLUDES DESTINATION include
+)
 
-install(DIRECTORY "${CMAKE_CURRENT_SOURCE_DIR}/include/xrpl"
-        DESTINATION "${CMAKE_INSTALL_INCLUDEDIR}")
+install(
+    DIRECTORY "${CMAKE_CURRENT_SOURCE_DIR}/include/xrpl"
+    DESTINATION "${CMAKE_INSTALL_INCLUDEDIR}"
+)
 
-install(EXPORT XrplExports FILE XrplTargets.cmake NAMESPACE Xrpl:: DESTINATION lib/cmake/xrpl)
+install(
+    EXPORT XrplExports
+    FILE XrplTargets.cmake
+    NAMESPACE Xrpl::
+    DESTINATION lib/cmake/xrpl
+)
 include(CMakePackageConfigHelpers)
-write_basic_package_version_file(XrplConfigVersion.cmake VERSION ${xrpld_version}
-                                 COMPATIBILITY SameMajorVersion)
+write_basic_package_version_file(
+    XrplConfigVersion.cmake
+    VERSION ${xrpld_version}
+    COMPATIBILITY SameMajorVersion
+)
 
-if (is_root_project AND TARGET xrpld)
+if(is_root_project AND TARGET xrpld)
     install(TARGETS xrpld RUNTIME DESTINATION bin)
     set_target_properties(xrpld PROPERTIES INSTALL_RPATH_USE_LINK_PATH ON)
     # sample configs should not overwrite existing files
     # install if-not-exists workaround as suggested by
     # https://cmake.org/Bug/view.php?id=12646
-    install(CODE "
+    install(
+        CODE
+            "
     macro (copy_if_not_exists SRC DEST NEWNAME)
       if (NOT EXISTS \"\$ENV{DESTDIR}\${CMAKE_INSTALL_PREFIX}/\${DEST}/\${NEWNAME}\")
         file (INSTALL FILE_PERMISSIONS OWNER_READ OWNER_WRITE DESTINATION \"\${CMAKE_INSTALL_PREFIX}/\${DEST}\" FILES \"\${SRC}\" RENAME \"\${NEWNAME}\")
@@ -65,14 +81,22 @@ if (is_root_project AND TARGET xrpld)
     endmacro()
     copy_if_not_exists(\"${CMAKE_CURRENT_SOURCE_DIR}/cfg/xrpld-example.cfg\" etc xrpld.cfg)
     copy_if_not_exists(\"${CMAKE_CURRENT_SOURCE_DIR}/cfg/validators-example.txt\" etc validators.txt)
-  ")
-    install(CODE "
+  "
+    )
+    install(
+        CODE
+            "
     set(CMAKE_MODULE_PATH \"${CMAKE_MODULE_PATH}\")
     include(create_symbolic_link)
     create_symbolic_link(xrpld${suffix} \
        \$ENV{DESTDIR}\${CMAKE_INSTALL_PREFIX}/${CMAKE_INSTALL_BINDIR}/rippled${suffix})
-  ")
-endif ()
+  "
+    )
+endif()
 
-install(FILES ${CMAKE_CURRENT_SOURCE_DIR}/cmake/XrplConfig.cmake
-              ${CMAKE_CURRENT_BINARY_DIR}/XrplConfigVersion.cmake DESTINATION lib/cmake/xrpl)
+install(
+    FILES
+        ${CMAKE_CURRENT_SOURCE_DIR}/cmake/XrplConfig.cmake
+        ${CMAKE_CURRENT_BINARY_DIR}/XrplConfigVersion.cmake
+    DESTINATION lib/cmake/xrpl
+)

cmake/XrplInterface.cmake

@@ -5,47 +5,55 @@
 include(CompilationEnv)
 
 # Set defaults for optional variables to avoid uninitialized variable warnings
-if (NOT DEFINED voidstar)
+if(NOT DEFINED voidstar)
     set(voidstar OFF)
-endif ()
+endif()
 
 add_library(opts INTERFACE)
 add_library(Xrpl::opts ALIAS opts)
 target_compile_definitions(
     opts
-    INTERFACE BOOST_ASIO_DISABLE_HANDLER_TYPE_REQUIREMENTS
-              BOOST_ASIO_USE_TS_EXECUTOR_AS_DEFAULT
-              BOOST_CONTAINER_FWD_BAD_DEQUE
-              HAS_UNCAUGHT_EXCEPTIONS=1
-              $<$<BOOL:${boost_show_deprecated}>:
-              BOOST_ASIO_NO_DEPRECATED
-              BOOST_FILESYSTEM_NO_DEPRECATED
-              >
-              $<$<NOT:$<BOOL:${boost_show_deprecated}>>:
-              BOOST_COROUTINES_NO_DEPRECATION_WARNING
-              BOOST_BEAST_ALLOW_DEPRECATED
-              BOOST_FILESYSTEM_DEPRECATED
-              >
-              $<$<BOOL:${beast_no_unit_test_inline}>:BEAST_NO_UNIT_TEST_INLINE=1>
-              $<$<BOOL:${beast_disable_autolink}>:BEAST_DONT_AUTOLINK_TO_WIN32_LIBRARIES=1>
-              $<$<BOOL:${single_io_service_thread}>:XRPL_SINGLE_IO_SERVICE_THREAD=1>
-              $<$<BOOL:${voidstar}>:ENABLE_VOIDSTAR>)
+    INTERFACE
+        BOOST_ASIO_DISABLE_HANDLER_TYPE_REQUIREMENTS
+        BOOST_ASIO_USE_TS_EXECUTOR_AS_DEFAULT
+        BOOST_CONTAINER_FWD_BAD_DEQUE
+        HAS_UNCAUGHT_EXCEPTIONS=1
+        $<$<BOOL:${boost_show_deprecated}>:
+        BOOST_ASIO_NO_DEPRECATED
+        BOOST_FILESYSTEM_NO_DEPRECATED
+        >
+        $<$<NOT:$<BOOL:${boost_show_deprecated}>>:
+        BOOST_COROUTINES_NO_DEPRECATION_WARNING
+        BOOST_BEAST_ALLOW_DEPRECATED
+        BOOST_FILESYSTEM_DEPRECATED
+        >
+        $<$<BOOL:${beast_no_unit_test_inline}>:BEAST_NO_UNIT_TEST_INLINE=1>
+        $<$<BOOL:${beast_disable_autolink}>:BEAST_DONT_AUTOLINK_TO_WIN32_LIBRARIES=1>
+        $<$<BOOL:${single_io_service_thread}>:XRPL_SINGLE_IO_SERVICE_THREAD=1>
+        $<$<BOOL:${voidstar}>:ENABLE_VOIDSTAR>
+)
 target_compile_options(
     opts
-    INTERFACE $<$<AND:$<BOOL:${is_gcc}>,$<COMPILE_LANGUAGE:CXX>>:-Wsuggest-override>
-              $<$<BOOL:${is_gcc}>:-Wno-maybe-uninitialized>
-              $<$<BOOL:${perf}>:-fno-omit-frame-pointer>
-              $<$<BOOL:${profile}>:-pg>
-              $<$<AND:$<BOOL:${is_gcc}>,$<BOOL:${profile}>>:-p>)
+    INTERFACE
+        $<$<AND:$<BOOL:${is_gcc}>,$<COMPILE_LANGUAGE:CXX>>:-Wsuggest-override>
+        $<$<BOOL:${is_gcc}>:-Wno-maybe-uninitialized>
+        $<$<BOOL:${perf}>:-fno-omit-frame-pointer>
+        $<$<BOOL:${profile}>:-pg>
+        $<$<AND:$<BOOL:${is_gcc}>,$<BOOL:${profile}>>:-p>
+)
 
-target_link_libraries(opts INTERFACE $<$<BOOL:${profile}>:-pg>
-                                     $<$<AND:$<BOOL:${is_gcc}>,$<BOOL:${profile}>>:-p>)
+target_link_libraries(
+    opts
+    INTERFACE
+        $<$<BOOL:${profile}>:-pg>
+        $<$<AND:$<BOOL:${is_gcc}>,$<BOOL:${profile}>>:-p>
+)
 
-if (jemalloc)
+if(jemalloc)
     find_package(jemalloc REQUIRED)
     target_compile_definitions(opts INTERFACE PROFILE_JEMALLOC)
     target_link_libraries(opts INTERFACE jemalloc::jemalloc)
-endif ()
+endif()
 
 #[===================================================================[
    xrpld transitive library deps via an interface library
@@ -55,31 +63,33 @@ add_library(xrpl_syslibs INTERFACE)
 add_library(Xrpl::syslibs ALIAS xrpl_syslibs)
 target_link_libraries(
     xrpl_syslibs
-    INTERFACE $<$<BOOL:${is_msvc}>:
-              legacy_stdio_definitions.lib
-              Shlwapi
-              kernel32
-              user32
-              gdi32
-              winspool
-              comdlg32
-              advapi32
-              shell32
-              ole32
-              oleaut32
-              uuid
-              odbc32
-              odbccp32
-              crypt32
-              >
-              $<$<NOT:$<BOOL:${is_msvc}>>:dl>
-              $<$<NOT:$<OR:$<BOOL:${is_msvc}>,$<BOOL:${is_macos}>>>:rt>)
+    INTERFACE
+        $<$<BOOL:${is_msvc}>:
+        legacy_stdio_definitions.lib
+        Shlwapi
+        kernel32
+        user32
+        gdi32
+        winspool
+        comdlg32
+        advapi32
+        shell32
+        ole32
+        oleaut32
+        uuid
+        odbc32
+        odbccp32
+        crypt32
+        >
+        $<$<NOT:$<BOOL:${is_msvc}>>:dl>
+        $<$<NOT:$<OR:$<BOOL:${is_msvc}>,$<BOOL:${is_macos}>>>:rt>
+)
 
-if (NOT is_msvc)
+if(NOT is_msvc)
     set(THREADS_PREFER_PTHREAD_FLAG ON)
     find_package(Threads)
     target_link_libraries(xrpl_syslibs INTERFACE Threads::Threads)
-endif ()
+endif()
 
 add_library(xrpl_libs INTERFACE)
 add_library(Xrpl::libs ALIAS xrpl_libs)

cmake/XrplSanitizers.cmake

@@ -44,23 +44,26 @@ include(CompilationEnv)
 
 # Read environment variable
 set(SANITIZERS "")
-if (DEFINED ENV{SANITIZERS})
+if(DEFINED ENV{SANITIZERS})
     set(SANITIZERS "$ENV{SANITIZERS}")
-endif ()
+endif()
 
 # Set SANITIZERS_ENABLED flag for use in other modules
-if (SANITIZERS MATCHES "address|thread|undefinedbehavior")
+if(SANITIZERS MATCHES "address|thread|undefinedbehavior")
     set(SANITIZERS_ENABLED TRUE)
-else ()
+else()
     set(SANITIZERS_ENABLED FALSE)
     return()
-endif ()
+endif()
 
 # Sanitizers are not supported on Windows/MSVC
-if (is_msvc)
-    message(FATAL_ERROR "Sanitizers are not supported on Windows/MSVC. "
-                        "Please unset the SANITIZERS environment variable.")
-endif ()
+if(is_msvc)
+    message(
+        FATAL_ERROR
+        "Sanitizers are not supported on Windows/MSVC. "
+        "Please unset the SANITIZERS environment variable."
+    )
+endif()
 
 message(STATUS "Configuring sanitizers: ${SANITIZERS}")
 
@@ -74,24 +77,30 @@ set(san_list "${SANITIZERS}")
 string(REPLACE "," ";" san_list "${san_list}")
 separate_arguments(san_list)
 
-foreach (san IN LISTS san_list)
-    if (san STREQUAL "address")
+foreach(san IN LISTS san_list)
+    if(san STREQUAL "address")
         set(enable_asan TRUE)
-    elseif (san STREQUAL "thread")
+    elseif(san STREQUAL "thread")
         set(enable_tsan TRUE)
-    elseif (san STREQUAL "undefinedbehavior")
+    elseif(san STREQUAL "undefinedbehavior")
         set(enable_ubsan TRUE)
-    else ()
-        message(FATAL_ERROR "Unsupported sanitizer type: ${san}"
-                            "Supported: address, thread, undefinedbehavior and their combinations.")
-    endif ()
-endforeach ()
+    else()
+        message(
+            FATAL_ERROR
+            "Unsupported sanitizer type: ${san}"
+            "Supported: address, thread, undefinedbehavior and their combinations."
+        )
+    endif()
+endforeach()
 
 # Validate sanitizer compatibility
-if (enable_asan AND enable_tsan)
-    message(FATAL_ERROR "AddressSanitizer and ThreadSanitizer are incompatible and cannot be enabled simultaneously. "
-                        "Use 'address' or 'thread', optionally with 'undefinedbehavior'.")
-endif ()
+if(enable_asan AND enable_tsan)
+    message(
+        FATAL_ERROR
+        "AddressSanitizer and ThreadSanitizer are incompatible and cannot be enabled simultaneously. "
+        "Use 'address' or 'thread', optionally with 'undefinedbehavior'."
+    )
+endif()
 
 # Frame pointer is required for meaningful stack traces. Sanitizers recommend minimum of -O1 for reasonable performance
 set(SANITIZERS_COMPILE_FLAGS "-fno-omit-frame-pointer" "-O1")
@@ -99,66 +108,79 @@ set(SANITIZERS_COMPILE_FLAGS "-fno-omit-frame-pointer" "-O1")
 # Build the sanitizer flags list
 set(SANITIZER_TYPES)
 
-if (enable_asan)
+if(enable_asan)
     list(APPEND SANITIZER_TYPES "address")
-elseif (enable_tsan)
+elseif(enable_tsan)
     list(APPEND SANITIZER_TYPES "thread")
-endif ()
+endif()
 
-if (enable_ubsan)
+if(enable_ubsan)
     # UB sanitizer flags
     list(APPEND SANITIZER_TYPES "undefined" "float-divide-by-zero")
-    if (is_clang)
+    if(is_clang)
         # Clang supports additional UB checks. More info here
         # https://clang.llvm.org/docs/UndefinedBehaviorSanitizer.html
         list(APPEND SANITIZER_TYPES "unsigned-integer-overflow")
-    endif ()
-endif ()
+    endif()
+endif()
 
 # Configure code model for GCC on amd64 Use large code model for ASAN to avoid relocation errors Use medium code model
 # for TSAN (large is not compatible with TSAN)
 set(SANITIZERS_RELOCATION_FLAGS)
 
 # Compiler-specific configuration
-if (is_gcc)
+if(is_gcc)
     # Disable mold, gold and lld linkers for GCC with sanitizers Use default linker (bfd/ld) which is more lenient with
     # mixed code models This is needed since the size of instrumented binary exceeds the limits set by mold, lld and
     # gold linkers
     set(use_mold OFF CACHE BOOL "Use mold linker" FORCE)
     set(use_gold OFF CACHE BOOL "Use gold linker" FORCE)
     set(use_lld OFF CACHE BOOL "Use lld linker" FORCE)
-    message(STATUS "  Disabled mold, gold, and lld linkers for GCC with sanitizers")
+    message(
+        STATUS
+        "  Disabled mold, gold, and lld linkers for GCC with sanitizers"
+    )
 
     # Suppress false positive warnings in GCC with stringop-overflow
     list(APPEND SANITIZERS_COMPILE_FLAGS "-Wno-stringop-overflow")
 
-    if (is_amd64 AND enable_asan)
+    if(is_amd64 AND enable_asan)
         message(STATUS "  Using large code model (-mcmodel=large)")
         list(APPEND SANITIZERS_COMPILE_FLAGS "-mcmodel=large")
         list(APPEND SANITIZERS_RELOCATION_FLAGS "-mcmodel=large")
-    elseif (enable_tsan)
+    elseif(enable_tsan)
         # GCC doesn't support atomic_thread_fence with tsan. Suppress warnings.
         list(APPEND SANITIZERS_COMPILE_FLAGS "-Wno-tsan")
         message(STATUS "  Using medium code model (-mcmodel=medium)")
         list(APPEND SANITIZERS_COMPILE_FLAGS "-mcmodel=medium")
         list(APPEND SANITIZERS_RELOCATION_FLAGS "-mcmodel=medium")
-    endif ()
+    endif()
 
     # Join sanitizer flags with commas for -fsanitize option
     list(JOIN SANITIZER_TYPES "," SANITIZER_TYPES_STR)
 
     # Add sanitizer to compile and link flags
     list(APPEND SANITIZERS_COMPILE_FLAGS "-fsanitize=${SANITIZER_TYPES_STR}")
-    set(SANITIZERS_LINK_FLAGS "${SANITIZERS_RELOCATION_FLAGS}" "-fsanitize=${SANITIZER_TYPES_STR}")
-
-elseif (is_clang)
+    set(SANITIZERS_LINK_FLAGS
+        "${SANITIZERS_RELOCATION_FLAGS}"
+        "-fsanitize=${SANITIZER_TYPES_STR}"
+    )
+elseif(is_clang)
     # Add ignorelist for Clang (GCC doesn't support this) Use CMAKE_SOURCE_DIR to get the path to the ignorelist
-    set(IGNORELIST_PATH "${CMAKE_SOURCE_DIR}/sanitizers/suppressions/sanitizer-ignorelist.txt")
-    if (NOT EXISTS "${IGNORELIST_PATH}")
-        message(FATAL_ERROR "Sanitizer ignorelist not found: ${IGNORELIST_PATH}")
-    endif ()
+    set(IGNORELIST_PATH
+        "${CMAKE_SOURCE_DIR}/sanitizers/suppressions/sanitizer-ignorelist.txt"
+    )
+    if(NOT EXISTS "${IGNORELIST_PATH}")
+        message(
+            FATAL_ERROR
+            "Sanitizer ignorelist not found: ${IGNORELIST_PATH}"
+        )
+    endif()
 
-    list(APPEND SANITIZERS_COMPILE_FLAGS "-fsanitize-ignorelist=${IGNORELIST_PATH}")
+    list(
+        APPEND SANITIZERS_COMPILE_FLAGS
+        "-fsanitize-ignorelist=${IGNORELIST_PATH}"
+    )
     message(STATUS "  Using sanitizer ignorelist: ${IGNORELIST_PATH}")
 
     # Join sanitizer flags with commas for -fsanitize option
@@ -167,31 +189,35 @@ elseif (is_clang)
     # Add sanitizer to compile and link flags
     list(APPEND SANITIZERS_COMPILE_FLAGS "-fsanitize=${SANITIZER_TYPES_STR}")
     set(SANITIZERS_LINK_FLAGS "-fsanitize=${SANITIZER_TYPES_STR}")
-endif ()
+endif()
 
 message(STATUS "  Compile flags: ${SANITIZERS_COMPILE_FLAGS}")
 message(STATUS "  Link flags: ${SANITIZERS_LINK_FLAGS}")
 
 # Apply the sanitizer flags to the 'common' interface library This is the same library used by XrplCompiler.cmake
-target_compile_options(common INTERFACE $<$<COMPILE_LANGUAGE:CXX>:${SANITIZERS_COMPILE_FLAGS}>
-                                        $<$<COMPILE_LANGUAGE:C>:${SANITIZERS_COMPILE_FLAGS}>)
+target_compile_options(
+    common
+    INTERFACE
+        $<$<COMPILE_LANGUAGE:CXX>:${SANITIZERS_COMPILE_FLAGS}>
+        $<$<COMPILE_LANGUAGE:C>:${SANITIZERS_COMPILE_FLAGS}>
+)
 
 # Apply linker flags
 target_link_options(common INTERFACE ${SANITIZERS_LINK_FLAGS})
 
 # Define SANITIZERS macro for BuildInfo.cpp
 set(sanitizers_list)
-if (enable_asan)
+if(enable_asan)
     list(APPEND sanitizers_list "ASAN")
-endif ()
-if (enable_tsan)
+endif()
+if(enable_tsan)
     list(APPEND sanitizers_list "TSAN")
-endif ()
-if (enable_ubsan)
+endif()
+if(enable_ubsan)
     list(APPEND sanitizers_list "UBSAN")
-endif ()
+endif()
 
-if (sanitizers_list)
+if(sanitizers_list)
     list(JOIN sanitizers_list "." sanitizers_str)
     target_compile_definitions(common INTERFACE SANITIZERS=${sanitizers_str})
-endif ()
+endif()

cmake/XrplSanity.cmake

@@ -7,40 +7,49 @@ include(CompilationEnv)
 get_property(is_multiconfig GLOBAL PROPERTY GENERATOR_IS_MULTI_CONFIG)
 
 set(CMAKE_CONFIGURATION_TYPES "Debug;Release" CACHE STRING "" FORCE)
-if (NOT is_multiconfig)
-    if (NOT CMAKE_BUILD_TYPE)
+if(NOT is_multiconfig)
+    if(NOT CMAKE_BUILD_TYPE)
         message(STATUS "Build type not specified - defaulting to Release")
         set(CMAKE_BUILD_TYPE Release CACHE STRING "build type" FORCE)
-    elseif (NOT (CMAKE_BUILD_TYPE STREQUAL Debug OR CMAKE_BUILD_TYPE STREQUAL Release))
+    elseif(
+        NOT (CMAKE_BUILD_TYPE STREQUAL Debug OR CMAKE_BUILD_TYPE STREQUAL Release)
+    )
         # for simplicity, these are the only two config types we care about. Limiting the build types simplifies dealing
         # with external project builds especially
-        message(FATAL_ERROR " *** Only Debug or Release build types are currently supported ***")
-    endif ()
-endif ()
+        message(
+            FATAL_ERROR
+            " *** Only Debug or Release build types are currently supported ***"
+        )
+    endif()
+endif()
 
-if (is_clang) # both Clang and AppleClang
-    if ("${CMAKE_CXX_COMPILER_ID}" STREQUAL "Clang" AND CMAKE_CXX_COMPILER_VERSION VERSION_LESS
-                                                        16.0)
+if(is_clang) # both Clang and AppleClang
+    if(
+        "${CMAKE_CXX_COMPILER_ID}" STREQUAL "Clang"
+        AND CMAKE_CXX_COMPILER_VERSION VERSION_LESS 16.0
+    )
         message(FATAL_ERROR "This project requires clang 16 or later")
-    endif ()
-elseif (is_gcc)
-    if (CMAKE_CXX_COMPILER_VERSION VERSION_LESS 12.0)
+    endif()
+elseif(is_gcc)
+    if(CMAKE_CXX_COMPILER_VERSION VERSION_LESS 12.0)
         message(FATAL_ERROR "This project requires GCC 12 or later")
-    endif ()
-endif ()
+    endif()
+endif()
 
 # check for in-source build and fail
-if ("${CMAKE_CURRENT_SOURCE_DIR}" STREQUAL "${CMAKE_BINARY_DIR}")
-    message(FATAL_ERROR "Builds (in-source) are not allowed in "
-                        "${CMAKE_CURRENT_SOURCE_DIR}. Please remove CMakeCache.txt and the CMakeFiles "
-                        "directory from ${CMAKE_CURRENT_SOURCE_DIR} and try building in a separate directory."
+if("${CMAKE_CURRENT_SOURCE_DIR}" STREQUAL "${CMAKE_BINARY_DIR}")
+    message(
+        FATAL_ERROR
+        "Builds (in-source) are not allowed in "
+        "${CMAKE_CURRENT_SOURCE_DIR}. Please remove CMakeCache.txt and the CMakeFiles "
+        "directory from ${CMAKE_CURRENT_SOURCE_DIR} and try building in a separate directory."
     )
-endif ()
+endif()
 
-if (MSVC AND CMAKE_GENERATOR_PLATFORM STREQUAL "Win32")
+if(MSVC AND CMAKE_GENERATOR_PLATFORM STREQUAL "Win32")
     message(FATAL_ERROR "Visual Studio 32-bit build is not supported.")
-endif ()
+endif()
 
-if (APPLE AND NOT HOMEBREW)
+if(APPLE AND NOT HOMEBREW)
     find_program(HOMEBREW brew)
-endif ()
+endif()

cmake/XrplSettings.cmake

@@ -5,59 +5,67 @@
 include(CompilationEnv)
 
 set(is_ci FALSE)
-if (DEFINED ENV{CI})
-    if ("$ENV{CI}" STREQUAL "true")
+if(DEFINED ENV{CI})
+    if("$ENV{CI}" STREQUAL "true")
         set(is_ci TRUE)
-    endif ()
-endif ()
+    endif()
+endif()
 
 get_directory_property(has_parent PARENT_DIRECTORY)
-if (has_parent)
+if(has_parent)
     set(is_root_project OFF)
-else ()
+else()
     set(is_root_project ON)
-endif ()
+endif()
 
 option(assert "Enables asserts, even in release builds" OFF)
 
 option(xrpld "Build xrpld" ON)
 
 option(tests "Build tests" ON)
-if (tests)
+if(tests)
     # This setting allows making a separate workflow to test fees other than default 10
-    if (NOT UNIT_TEST_REFERENCE_FEE)
+    if(NOT UNIT_TEST_REFERENCE_FEE)
         set(UNIT_TEST_REFERENCE_FEE "10" CACHE STRING "")
-    endif ()
-endif ()
+    endif()
+endif()
 
 option(unity "Creates a build using UNITY support in cmake." OFF)
-if (unity)
-    if (NOT is_ci)
+if(unity)
+    if(NOT is_ci)
         set(CMAKE_UNITY_BUILD_BATCH_SIZE 15 CACHE STRING "")
-    endif ()
+    endif()
     set(CMAKE_UNITY_BUILD ON CACHE BOOL "Do a unity build")
-endif ()
+endif()
 
-if (is_clang AND is_linux)
+if(is_clang AND is_linux)
     option(voidstar "Enable Antithesis instrumentation." OFF)
-endif ()
+endif()
 
-if (is_gcc OR is_clang)
+if(is_gcc OR is_clang)
     include(ProcessorCount)
     ProcessorCount(PROCESSOR_COUNT)
 
     option(coverage "Generates coverage info." OFF)
     option(profile "Add profiling flags" OFF)
-    set(coverage_format "html-details" CACHE STRING "Output format of the coverage report.")
-    set(coverage_extra_args "" CACHE STRING "Additional arguments to pass to gcovr.")
+    set(coverage_format
+        "html-details"
+        CACHE STRING
+        "Output format of the coverage report."
+    )
+    set(coverage_extra_args
+        ""
+        CACHE STRING
+        "Additional arguments to pass to gcovr."
+    )
     option(wextra "compile with extra gcc/clang warnings enabled" ON)
-else ()
+else()
     set(profile OFF CACHE BOOL "gcc/clang only" FORCE)
     set(coverage OFF CACHE BOOL "gcc/clang only" FORCE)
     set(wextra OFF CACHE BOOL "gcc/clang only" FORCE)
-endif ()
+endif()
 
-if (is_linux AND NOT SANITIZER)
+if(is_linux AND NOT SANITIZER)
     option(BUILD_SHARED_LIBS "build shared xrpl libraries" OFF)
     option(static "link protobuf, openssl, libc++, and boost statically" ON)
     option(perf "Enables flags that assist with perf recording" OFF)
@@ -65,53 +73,83 @@ if (is_linux AND NOT SANITIZER)
     option(use_mold "enables detection of mold (binutils) linker" ON)
     # Set a default value for the log flag based on the build type. This provides a sensible default (on for debug, off
     # for release) while still allowing the user to override it for any build.
-    if (CMAKE_BUILD_TYPE STREQUAL "Debug")
+    if(CMAKE_BUILD_TYPE STREQUAL "Debug")
         set(TRUNCATED_LOGS_DEFAULT ON)
-    else ()
+    else()
         set(TRUNCATED_LOGS_DEFAULT OFF)
-    endif ()
-    option(TRUNCATED_THREAD_NAME_LOGS "Show warnings about truncated thread names on Linux."
-           ${TRUNCATED_LOGS_DEFAULT})
-    if (TRUNCATED_THREAD_NAME_LOGS)
+    endif()
+    option(
+        TRUNCATED_THREAD_NAME_LOGS
+        "Show warnings about truncated thread names on Linux."
+        ${TRUNCATED_LOGS_DEFAULT}
+    )
+    if(TRUNCATED_THREAD_NAME_LOGS)
         add_compile_definitions(TRUNCATED_THREAD_NAME_LOGS)
-    endif ()
-else ()
+    endif()
+else()
     # we are not ready to allow shared-libs on windows because it would require export declarations. On macos it's more
     # feasible, but static openssl produces odd linker errors, thus we disable shared lib builds for now.
-    set(BUILD_SHARED_LIBS OFF CACHE BOOL "build shared xrpl libraries - OFF for win/macos" FORCE)
+    set(BUILD_SHARED_LIBS
+        OFF
+        CACHE BOOL
+        "build shared xrpl libraries - OFF for win/macos"
+        FORCE
+    )
     set(static ON CACHE BOOL "static link, linux only. ON for WIN/macos" FORCE)
     set(perf OFF CACHE BOOL "perf flags, linux only" FORCE)
     set(use_gold OFF CACHE BOOL "gold linker, linux only" FORCE)
     set(use_mold OFF CACHE BOOL "mold linker, linux only" FORCE)
-endif ()
+endif()
 
-if (is_clang)
+if(is_clang)
     option(use_lld "enables detection of lld linker" ON)
-else ()
+else()
     set(use_lld OFF CACHE BOOL "try lld linker, clang only" FORCE)
-endif ()
+endif()
 
 option(jemalloc "Enables jemalloc for heap profiling" OFF)
 option(werr "treat warnings as errors" OFF)
-option(local_protobuf
-       "Force a local build of protobuf instead of looking for an installed version." OFF)
-option(local_grpc "Force a local build of gRPC instead of looking for an installed version." OFF)
+option(
+    local_protobuf
+    "Force a local build of protobuf instead of looking for an installed version."
+    OFF
+)
+option(
+    local_grpc
+    "Force a local build of gRPC instead of looking for an installed version."
+    OFF
+)
 
 # the remaining options are obscure and rarely used
-option(beast_no_unit_test_inline
-       "Prevents unit test definitions from being inserted into global table" OFF)
-option(single_io_service_thread "Restricts the number of threads calling io_context::run to one. \
-  This can be useful when debugging." OFF)
-option(boost_show_deprecated "Allow boost to fail on deprecated usage. Only useful if you're trying\
-  to find deprecated calls." OFF)
+option(
+    beast_no_unit_test_inline
+    "Prevents unit test definitions from being inserted into global table"
+    OFF
+)
+option(
+    single_io_service_thread
+    "Restricts the number of threads calling io_context::run to one. \
+  This can be useful when debugging."
+    OFF
+)
+option(
+    boost_show_deprecated
+    "Allow boost to fail on deprecated usage. Only useful if you're trying\
+  to find deprecated calls."
+    OFF
+)
 
-if (WIN32)
-    option(beast_disable_autolink "Disables autolinking of system libraries on WIN32" OFF)
-else ()
+if(WIN32)
+    option(
+        beast_disable_autolink
+        "Disables autolinking of system libraries on WIN32"
+        OFF
+    )
+else()
     set(beast_disable_autolink OFF CACHE BOOL "WIN32 only" FORCE)
-endif ()
+endif()
 
-if (coverage)
+if(coverage)
     message(STATUS "coverage build requested - forcing Debug build")
     set(CMAKE_BUILD_TYPE Debug CACHE STRING "build type" FORCE)
-endif ()
+endif()

cmake/XrplValidatorKeys.cmake

@@ -1,20 +1,26 @@
-option(validator_keys
-       "Enables building of validator-keys tool as a separate target (imported via FetchContent)"
-       OFF)
+option(
+    validator_keys
+    "Enables building of validator-keys tool as a separate target (imported via FetchContent)"
+    OFF
+)
 
-if (validator_keys)
+if(validator_keys)
     git_branch(current_branch)
     # default to tracking VK master branch unless we are on release
-    if (NOT (current_branch STREQUAL "release"))
+    if(NOT (current_branch STREQUAL "release"))
         set(current_branch "master")
-    endif ()
+    endif()
     message(STATUS "Tracking ValidatorKeys branch: ${current_branch}")
 
     FetchContent_Declare(
-        validator_keys GIT_REPOSITORY https://github.com/ripple/validator-keys-tool.git
-        GIT_TAG "${current_branch}")
+        validator_keys
+        GIT_REPOSITORY https://github.com/ripple/validator-keys-tool.git
+        GIT_TAG "${current_branch}"
+    )
     FetchContent_MakeAvailable(validator_keys)
-    set_target_properties(validator-keys PROPERTIES RUNTIME_OUTPUT_DIRECTORY "${CMAKE_BINARY_DIR}")
+    set_target_properties(
+        validator-keys
+        PROPERTIES RUNTIME_OUTPUT_DIRECTORY "${CMAKE_BINARY_DIR}"
+    )
     install(TARGETS validator-keys RUNTIME DESTINATION ${CMAKE_INSTALL_BINDIR})
-
-endif ()
+endif()

cmake/XrplVersion.cmake

@@ -3,13 +3,13 @@
 #]===================================================================]
 
 file(STRINGS src/libxrpl/protocol/BuildInfo.cpp BUILD_INFO)
-foreach (line_ ${BUILD_INFO})
-    if (line_ MATCHES "versionString[ ]*=[ ]*\"(.+)\"")
+foreach(line_ ${BUILD_INFO})
+    if(line_ MATCHES "versionString[ ]*=[ ]*\"(.+)\"")
         set(xrpld_version ${CMAKE_MATCH_1})
-    endif ()
-endforeach ()
-if (xrpld_version)
+    endif()
+endforeach()
+if(xrpld_version)
     message(STATUS "xrpld version: ${xrpld_version}")
-else ()
+else()
     message(FATAL_ERROR "unable to determine xrpld version")
-endif ()
+endif()

cmake/add_module.cmake

@@ -12,15 +12,29 @@ include(isolate_headers)
 # add_module(parent a)
 # add_module(parent b)
 # target_link_libraries(project.libparent.b PUBLIC project.libparent.a)
-function (add_module parent name)
+function(add_module parent name)
     set(target ${PROJECT_NAME}.lib${parent}.${name})
     add_library(${target} OBJECT)
-    file(GLOB_RECURSE sources CONFIGURE_DEPENDS
-         "${CMAKE_CURRENT_SOURCE_DIR}/src/lib${parent}/${name}/*.cpp")
+    file(
+        GLOB_RECURSE sources
+        CONFIGURE_DEPENDS
+        "${CMAKE_CURRENT_SOURCE_DIR}/src/lib${parent}/${name}/*.cpp"
+    )
     target_sources(${target} PRIVATE ${sources})
-    target_include_directories(${target} PUBLIC "$<INSTALL_INTERFACE:${CMAKE_INSTALL_INCLUDEDIR}>")
-    isolate_headers(${target} "${CMAKE_CURRENT_SOURCE_DIR}/include"
-                    "${CMAKE_CURRENT_SOURCE_DIR}/include/${parent}/${name}" PUBLIC)
-    isolate_headers(${target} "${CMAKE_CURRENT_SOURCE_DIR}/src"
-                    "${CMAKE_CURRENT_SOURCE_DIR}/src/lib${parent}/${name}" PRIVATE)
-endfunction ()
+    target_include_directories(
+        ${target}
+        PUBLIC "$<INSTALL_INTERFACE:${CMAKE_INSTALL_INCLUDEDIR}>"
+    )
+    isolate_headers(
+        ${target}
+        "${CMAKE_CURRENT_SOURCE_DIR}/include"
+        "${CMAKE_CURRENT_SOURCE_DIR}/include/${parent}/${name}"
+        PUBLIC
+    )
+    isolate_headers(
+        ${target}
+        "${CMAKE_CURRENT_SOURCE_DIR}/src"
+        "${CMAKE_CURRENT_SOURCE_DIR}/src/lib${parent}/${name}"
+        PRIVATE
+    )
+endfunction()

cmake/create_symbolic_link.cmake

@@ -1,19 +1,21 @@
 # file(CREATE_SYMLINK) only works on Windows with administrator privileges. https://stackoverflow.com/a/61244115/618906
-function (create_symbolic_link target link)
-    if (WIN32)
-        if (NOT IS_SYMLINK "${link}")
-            if (NOT IS_ABSOLUTE "${target}")
+function(create_symbolic_link target link)
+    if(WIN32)
+        if(NOT IS_SYMLINK "${link}")
+            if(NOT IS_ABSOLUTE "${target}")
                 # Relative links work do not work on Windows.
                 set(target "${link}/../${target}")
-            endif ()
+            endif()
             file(TO_NATIVE_PATH "${target}" target)
             file(TO_NATIVE_PATH "${link}" link)
-            execute_process(COMMAND cmd.exe /c mklink /J "${link}" "${target}")
-        endif ()
-    else ()
+            execute_process(
+                COMMAND cmd.exe /c mklink /J "${link}" "${target}"
+            )
+        endif()
+    else()
         file(CREATE_LINK "${target}" "${link}" SYMBOLIC)
-    endif ()
-    if (NOT IS_SYMLINK "${link}")
+    endif()
+    if(NOT IS_SYMLINK "${link}")
         message(ERROR "failed to create symlink: <${link}>")
-    endif ()
-endfunction ()
+    endif()
+endfunction()

cmake/deps/Boost.cmake

@@ -1,45 +1,60 @@
 include(CompilationEnv)
 include(XrplSanitizers)
 
-find_package(Boost REQUIRED
-             COMPONENTS chrono
-                        container
-                        coroutine
-                        date_time
-                        filesystem
-                        json
-                        program_options
-                        regex
-                        system
-                        thread)
+find_package(
+    Boost
+    REQUIRED
+    COMPONENTS
+        chrono
+        container
+        coroutine
+        date_time
+        filesystem
+        json
+        program_options
+        regex
+        system
+        thread
+)
 
 add_library(xrpl_boost INTERFACE)
 add_library(Xrpl::boost ALIAS xrpl_boost)
 
 target_link_libraries(
     xrpl_boost
-    INTERFACE Boost::headers
-              Boost::chrono
-              Boost::container
-              Boost::coroutine
-              Boost::date_time
-              Boost::filesystem
-              Boost::json
-              Boost::process
-              Boost::program_options
-              Boost::regex
-              Boost::thread)
-if (Boost_COMPILER)
+    INTERFACE
+        Boost::headers
+        Boost::chrono
+        Boost::container
+        Boost::coroutine
+        Boost::date_time
+        Boost::filesystem
+        Boost::json
+        Boost::process
+        Boost::program_options
+        Boost::regex
+        Boost::thread
+)
+if(Boost_COMPILER)
     target_link_libraries(xrpl_boost INTERFACE Boost::disable_autolinking)
-endif ()
-if (SANITIZERS_ENABLED AND is_clang)
+endif()
+if(SANITIZERS_ENABLED AND is_clang)
     # TODO: gcc does not support -fsanitize-blacklist...can we do something else for gcc ?
-    if (NOT Boost_INCLUDE_DIRS AND TARGET Boost::headers)
-        get_target_property(Boost_INCLUDE_DIRS Boost::headers INTERFACE_INCLUDE_DIRECTORIES)
-    endif ()
+    if(NOT Boost_INCLUDE_DIRS AND TARGET Boost::headers)
+        get_target_property(
+            Boost_INCLUDE_DIRS
+            Boost::headers
+            INTERFACE_INCLUDE_DIRECTORIES
+        )
+    endif()
     message(STATUS "Adding [${Boost_INCLUDE_DIRS}] to sanitizer blacklist")
-    file(WRITE ${CMAKE_CURRENT_BINARY_DIR}/san_bl.txt "src:${Boost_INCLUDE_DIRS}/*")
+    file(
+        WRITE ${CMAKE_CURRENT_BINARY_DIR}/san_bl.txt
+        "src:${Boost_INCLUDE_DIRS}/*"
+    )
     target_compile_options(
-        opts INTERFACE # ignore boost headers for sanitizing
-                       -fsanitize-blacklist=${CMAKE_CURRENT_BINARY_DIR}/san_bl.txt)
-endif ()
+        opts
+        INTERFACE # ignore boost headers for sanitizing
+            -fsanitize-blacklist=${CMAKE_CURRENT_BINARY_DIR}/san_bl.txt
+    )
+endif()

cmake/isolate_headers.cmake

@@ -37,7 +37,7 @@ include(create_symbolic_link)
 # `${CMAKE_CURRENT_BINARY_DIR}/include/${target}`.
 #
 # isolate_headers(target A B scope)
-function (isolate_headers target A B scope)
+function(isolate_headers target A B scope)
     file(RELATIVE_PATH C "${A}" "${B}")
     set(X "${CMAKE_CURRENT_BINARY_DIR}/modules/${target}")
     set(Y "${X}/${C}")
@@ -45,4 +45,4 @@ function (isolate_headers target A B scope)
     file(MAKE_DIRECTORY "${parent}")
     create_symbolic_link("${B}" "${Y}")
     target_include_directories(${target} ${scope} "$<BUILD_INTERFACE:${X}>")
-endfunction ()
+endfunction()

cmake/target_link_modules.cmake

@@ -6,9 +6,9 @@
 # target_link_libraries(project.libparent.b PUBLIC project.libparent.a)
 # add_library(project.libparent)
 # target_link_modules(parent PUBLIC a b)
-function (target_link_modules parent scope)
+function(target_link_modules parent scope)
     set(library ${PROJECT_NAME}.lib${parent})
-    foreach (name ${ARGN})
+    foreach(name ${ARGN})
         set(module ${library}.${name})
         get_target_property(sources ${library} SOURCES)
         list(LENGTH sources before)
@@ -17,8 +17,11 @@ function (target_link_modules parent scope)
         list(REMOVE_ITEM sources ${dupes})
         list(LENGTH sources after)
         math(EXPR actual "${before} - ${after}")
-        message(STATUS "${module} with ${expected} sources took ${actual} sources from ${library}")
+        message(
+            STATUS
+            "${module} with ${expected} sources took ${actual} sources from ${library}"
+        )
         set_target_properties(${library} PROPERTIES SOURCES "${sources}")
         target_link_libraries(${library} ${scope} ${module})
-    endforeach ()
-endfunction ()
+    endforeach()
+endfunction()

cmake/target_protobuf_sources.cmake

@@ -35,20 +35,31 @@ find_package(Protobuf REQUIRED)
 #     This prefix should appear at the start of all your consumer includes.
 # ARGN:
 #     A list of .proto files.
-function (target_protobuf_sources target prefix)
+function(target_protobuf_sources target prefix)
     set(dir "${CMAKE_CURRENT_BINARY_DIR}/pb-${target}")
     file(MAKE_DIRECTORY "${dir}/${prefix}")
 
-    protobuf_generate(TARGET ${target} PROTOC_OUT_DIR "${dir}/${prefix}" "${ARGN}")
+    protobuf_generate(
+        TARGET ${target}
+        PROTOC_OUT_DIR "${dir}/${prefix}"
+        "${ARGN}"
+    )
     target_include_directories(
-        ${target} SYSTEM
+        ${target}
+        SYSTEM
         PUBLIC # Allows #include <package/path/to/file.proto> used by consumer files.
-               $<BUILD_INTERFACE:${dir}>
-               # Allows #include "path/to/file.proto" used by generated files.
-               $<BUILD_INTERFACE:${dir}/${prefix}>
-               # Allows #include <package/path/to/file.proto> used by consumer files.
-               $<INSTALL_INTERFACE:${CMAKE_INSTALL_INCLUDEDIR}>
-               # Allows #include "path/to/file.proto" used by generated files.
-               $<INSTALL_INTERFACE:${CMAKE_INSTALL_INCLUDEDIR}/${prefix}>)
-    install(DIRECTORY ${dir}/ DESTINATION ${CMAKE_INSTALL_INCLUDEDIR} FILES_MATCHING PATTERN "*.h")
-endfunction ()
+            $<BUILD_INTERFACE:${dir}>
+            # Allows #include "path/to/file.proto" used by generated files.
+            $<BUILD_INTERFACE:${dir}/${prefix}>
+            # Allows #include <package/path/to/file.proto> used by consumer files.
+            $<INSTALL_INTERFACE:${CMAKE_INSTALL_INCLUDEDIR}>
+            # Allows #include "path/to/file.proto" used by generated files.
+            $<INSTALL_INTERFACE:${CMAKE_INSTALL_INCLUDEDIR}/${prefix}>
+    )
+    install(
+        DIRECTORY ${dir}/
+        DESTINATION ${CMAKE_INSTALL_INCLUDEDIR}
+        FILES_MATCHING
+        PATTERN "*.h"
+    )
+endfunction()

conan.lock

@@ -10,10 +10,13 @@
         "rocksdb/10.5.1#4a197eca381a3e5ae8adf8cffa5aacd0%1765850186.86",
         "re2/20230301#ca3b241baec15bd31ea9187150e0b333%1765850148.103",
         "protobuf/6.32.1#f481fd276fc23a33b85a3ed1e898b693%1765850161.038",
-        "openssl/3.5.5#05a4ac5b7323f7a329b2db1391d9941f%1769599205.414",
+        "opentelemetry-cpp/1.18.0#efd9851e173f8a13b9c7d35232de8cf1%1750409186.472",
+        "openssl/3.5.5#05a4ac5b7323f7a329b2db1391d9941f%1770229825.601",
         "nudb/2.0.9#0432758a24204da08fee953ec9ea03cb%1769436073.32",
+        "nlohmann_json/3.11.3#45828be26eb619a2e04ca517bb7b828d%1701220705.259",
         "lz4/1.10.0#59fc63cac7f10fbe8e05c7e62c2f3504%1765850143.914",
         "libiconv/1.17#1e65319e945f2d31941a9d28cc13c058%1765842973.492",
+        "libcurl/8.18.0#364bc3755cb9ef84ed9a7ae9c7efc1c1%1770984390.024",
         "libbacktrace/cci.20210118#a7691bfccd8caaf66309df196790a5a1%1765842973.03",
         "libarchive/3.8.1#ffee18995c706e02bf96e7a2f7042e0d%1765850144.736",
         "jemalloc/5.3.0#e951da9cf599e956cebc117880d2d9f8%1729241615.244",
@@ -30,9 +33,15 @@
         "zlib/1.3.1#b8bc2603263cf7eccbd6e17e66b0ed76%1765850150.075",
         "strawberryperl/5.32.1.1#707032463aa0620fa17ec0d887f5fe41%1765850165.196",
         "protobuf/6.32.1#f481fd276fc23a33b85a3ed1e898b693%1765850161.038",
+        "pkgconf/2.5.1#93c2051284cba1279494a43a4fcfeae2%1757684701.089",
+        "opentelemetry-proto/1.4.0#4096a3b05916675ef9628f3ffd571f51%1732731336.11",
+        "ninja/1.13.2#c8c5dc2a52ed6e4e42a66d75b4717ceb%1764096931.974",
         "nasm/2.16.01#31e26f2ee3c4346ecd347911bd126904%1765850144.707",
         "msys2/cci.latest#eea83308ad7e9023f7318c60d5a9e6cb%1770199879.083",
+        "meson/1.10.0#60786758ea978964c24525de19603cf4%1768294926.103",
         "m4/1.4.19#70dc8bbb33e981d119d2acc0175cf381%1763158052.846",
+        "libtool/2.4.7#14e7739cc128bc1623d2ed318008e47e%1755679003.847",
+        "gnu-config/cci.20210814#466e9d4d7779e1c142443f7ea44b4284%1762363589.329",
         "cmake/4.2.0#ae0a44f44a1ef9ab68fd4b3e9a1f8671%1765850153.937",
         "cmake/3.31.10#313d16a1aa16bbdb2ca0792467214b76%1765850153.479",
         "b2/5.3.3#107c15377719889654eb9a162a673975%1765850144.355",

conanfile.py

@@ -22,6 +22,7 @@ class Xrpl(ConanFile):
         "rocksdb": [True, False],
         "shared": [True, False],
         "static": [True, False],
+        "telemetry": [True, False],
         "tests": [True, False],
         "unity": [True, False],
         "xrpld": [True, False],
@@ -54,6 +55,7 @@ class Xrpl(ConanFile):
         "rocksdb": True,
         "shared": False,
         "static": True,
+        "telemetry": True,
         "tests": False,
         "unity": False,
         "xrpld": False,
@@ -140,6 +142,10 @@ class Xrpl(ConanFile):
             self.requires("jemalloc/5.3.0")
         if self.options.rocksdb:
             self.requires("rocksdb/10.5.1")
+        # OpenTelemetry C++ SDK for distributed tracing (optional).
+        # Provides OTLP/HTTP exporter, batch span processor, and trace API.
+        if self.options.telemetry:
+            self.requires("opentelemetry-cpp/1.18.0")
         self.requires("xxhash/0.8.3", **transitive_headers_opt)
 
     exports_sources = (
@@ -168,6 +174,7 @@ class Xrpl(ConanFile):
         tc.variables["rocksdb"] = self.options.rocksdb
         tc.variables["BUILD_SHARED_LIBS"] = self.options.shared
         tc.variables["static"] = self.options.static
+        tc.variables["telemetry"] = self.options.telemetry
         tc.variables["unity"] = self.options.unity
         tc.variables["xrpld"] = self.options.xrpld
         tc.generate()
@@ -220,3 +227,5 @@ class Xrpl(ConanFile):
         ]
         if self.options.rocksdb:
             libxrpl.requires.append("rocksdb::librocksdb")
+        if self.options.telemetry:
+            libxrpl.requires.append("opentelemetry-cpp::opentelemetry-cpp")

cspell.config.yaml

@@ -87,6 +87,8 @@ words:
   - daria
   - dcmake
   - dearmor
+  - Dedup
+  - dedup
   - deleteme
   - demultiplexer
   - deserializaton
@@ -97,6 +99,7 @@ words:
   - doxyfile
   - dxrpl
   - endmacro
+  - EOCFG
   - exceptioned
   - Falco
   - finalizers
@@ -140,6 +143,7 @@ words:
   - libxrpl
   - llection
   - LOCALGOOD
+  - logql
   - logwstream
   - lseq
   - lsmf
@@ -180,6 +184,7 @@ words:
   - NOLINTNEXTLINE
   - nonxrp
   - noripple
+  - nostd
   - nudb
   - nullptr
   - nunl
@@ -192,8 +197,11 @@ words:
   - permdex
   - perminute
   - permissioned
+  - pgrep
+  - pkill
   - pointee
   - populator
+  - pratik
   - preauth
   - preauthorization
   - preauthorize
@@ -208,6 +216,7 @@ words:
   - queuable
   - Raphson
   - replayer
+  - reqps
   - rerere
   - retriable
   - RIPD
@@ -302,6 +311,10 @@ words:
   - xchain
   - ximinez
   - EXPECT_STREQ
+  - Gantt
+  - gantt
+  - otelc
+  - traceql
   - XMACRO
   - xrpkuwait
   - xrpl
@@ -309,3 +322,5 @@ words:
   - xrplf
   - xxhash
   - xxhasher
+  - xychart
+  - zpages

docker/telemetry/TESTING.md

@@ -0,0 +1,703 @@
+# OpenTelemetry Integration Testing Guide
+
+This document describes how to verify the rippled OpenTelemetry telemetry
+pipeline end-to-end, from span generation through the observability stack
+(otel-collector, Jaeger, Prometheus, Grafana).
+
+---
+
+## Prerequisites
+
+### Build xrpld with telemetry
+
+```bash
+conan install . --build=missing -o telemetry=True
+cmake --preset default -Dtelemetry=ON
+cmake --build --preset default --target xrpld
+```
+
+The binary is at `.build/xrpld`.
+
+### Required tools
+
+- **Docker** with `docker compose` (v2)
+- **curl**
+- **jq** (JSON processor)
+
+### Verify binary
+
+```bash
+.build/xrpld --version
+```
+
+---
+
+## Test 1: Single-Node Standalone (Quick Verification)
+
+This test verifies RPC and transaction spans in standalone mode. Consensus
+spans will not fire because standalone mode does not run consensus.
+
+### Step 1: Start the observability stack
+
+```bash
+docker compose -f docker/telemetry/docker-compose.yml up -d
+```
+
+Wait for services to be ready:
+
+```bash
+# otel-collector health
+curl -sf http://localhost:13133/ && echo "collector ready"
+
+# Jaeger UI
+curl -sf http://localhost:16686/ > /dev/null && echo "jaeger ready"
+```
+
+### Step 2: Start xrpld in standalone mode
+
+```bash
+.build/xrpld --conf docker/telemetry/xrpld-telemetry.cfg -a --start
+```
+
+Wait a few seconds for the node to initialize.
+
+### Step 3: Exercise RPC spans
+
+```bash
+# server_info
+curl -s http://localhost:5005 \
+  -d '{"method":"server_info"}' | jq .result.info.server_state
+
+# server_state
+curl -s http://localhost:5005 \
+  -d '{"method":"server_state"}' | jq .result.state.server_state
+
+# ledger
+curl -s http://localhost:5005 \
+  -d '{"method":"ledger","params":[{"ledger_index":"current"}]}' \
+  | jq .result.ledger_current_index
+```
+
+### Step 4: Submit a transaction
+
+Close the ledger first (required in standalone mode):
+
+```bash
+curl -s http://localhost:5005 -d '{"method":"ledger_accept"}'
+```
+
+Submit a Payment from the genesis account:
+
+```bash
+curl -s http://localhost:5005 -d '{
+  "method": "submit",
+  "params": [{
+    "secret": "snoPBrXtMeMyMHUVTgbuqAfg1SUTb",
+    "tx_json": {
+      "TransactionType": "Payment",
+      "Account": "rHb9CJAWyB4rj91VRWn96DkukG4bwdtyTh",
+      "Destination": "rPMh7Pi9ct699iZUTWzJaUMR1o42VEfGqF",
+      "Amount": "10000000"
+    }
+  }]
+}' | jq .result.engine_result
+```
+
+Expected result: `"tesSUCCESS"`.
+
+Close the ledger again to finalize:
+
+```bash
+curl -s http://localhost:5005 -d '{"method":"ledger_accept"}'
+```
+
+### Step 5: Verify traces in Jaeger
+
+Wait 5 seconds for the batch export, then:
+
+```bash
+JAEGER="http://localhost:16686"
+
+# Check rippled service is registered
+curl -s "$JAEGER/api/services" | jq '.data'
+
+# Check RPC spans
+curl -s "$JAEGER/api/traces?service=rippled&operation=rpc.request&limit=5&lookback=1h" \
+  | jq '.data | length'
+
+curl -s "$JAEGER/api/traces?service=rippled&operation=rpc.process&limit=5&lookback=1h" \
+  | jq '.data | length'
+
+curl -s "$JAEGER/api/traces?service=rippled&operation=rpc.command.server_info&limit=5&lookback=1h" \
+  | jq '.data | length'
+
+# Check transaction spans
+curl -s "$JAEGER/api/traces?service=rippled&operation=tx.process&limit=5&lookback=1h" \
+  | jq '.data | length'
+```
+
+Or open the Jaeger UI: http://localhost:16686
+
+### Step 6: Teardown
+
+```bash
+# Kill xrpld (Ctrl+C or)
+kill $(pgrep -f 'xrpld.*xrpld-telemetry')
+
+# Stop observability stack
+docker compose -f docker/telemetry/docker-compose.yml down
+
+# Clean xrpld data
+rm -rf data/
+```
+
+### Expected spans (standalone mode)
+
+| Span Name                   | Expected | Notes                         |
+| --------------------------- | -------- | ----------------------------- |
+| `rpc.request`               | Yes      | Every HTTP RPC call           |
+| `rpc.process`               | Yes      | Every RPC processing          |
+| `rpc.command.server_info`   | Yes      | server_info RPC               |
+| `rpc.command.server_state`  | Yes      | server_state RPC              |
+| `rpc.command.ledger`        | Yes      | ledger RPC                    |
+| `rpc.command.submit`        | Yes      | submit RPC                    |
+| `rpc.command.ledger_accept` | Yes      | ledger_accept RPC             |
+| `tx.process`                | Yes      | Transaction submission        |
+| `tx.receive`                | No       | No peers in standalone        |
+| `consensus.*`               | No       | Consensus disabled standalone |
+
+---
+
+## Test 2: 6-Node Consensus Network (Full Verification)
+
+This test verifies ALL span categories including consensus and peer
+transaction relay, using a 6-node validator network.
+
+### Automated
+
+Run the integration test script:
+
+```bash
+bash docker/telemetry/integration-test.sh
+```
+
+The script will:
+
+1. Start the observability stack
+2. Generate 6 validator key pairs
+3. Create config files for each node
+4. Start all 6 nodes
+5. Wait for consensus ("proposing" state)
+6. Exercise RPC, submit transactions
+7. Verify all span categories in Jaeger
+8. Verify spanmetrics in Prometheus
+9. Print results and leave the stack running
+
+### Manual
+
+If you prefer to run the steps manually:
+
+#### Step 1: Start observability stack
+
+```bash
+docker compose -f docker/telemetry/docker-compose.yml up -d
+```
+
+#### Step 2: Generate validator keys
+
+Start a temporary standalone xrpld:
+
+```bash
+.build/xrpld --conf docker/telemetry/xrpld-telemetry.cfg -a --start &
+TEMP_PID=$!
+sleep 5
+```
+
+Generate 6 key pairs:
+
+```bash
+for i in $(seq 1 6); do
+  curl -s http://localhost:5005 \
+    -d '{"method":"validation_create"}' | jq '.result'
+done
+```
+
+Record the `validation_seed` and `validation_public_key` for each.
+Kill the temporary node:
+
+```bash
+kill $TEMP_PID
+rm -rf data/
+```
+
+#### Step 3: Create node configs
+
+For each node (1-6), create a config file. Template:
+
+```ini
+[server]
+port_rpc
+port_peer
+
+[port_rpc]
+port = {5004 + node_number}
+ip = 127.0.0.1
+admin = 127.0.0.1
+protocol = http
+
+[port_peer]
+port = {51234 + node_number}
+ip = 0.0.0.0
+protocol = peer
+
+[node_db]
+type=NuDB
+path=/tmp/xrpld-integration/node{N}/nudb
+online_delete=256
+
+[database_path]
+/tmp/xrpld-integration/node{N}/db
+
+[debug_logfile]
+/tmp/xrpld-integration/node{N}/debug.log
+
+[validation_seed]
+{seed from step 2}
+
+[validators_file]
+/tmp/xrpld-integration/validators.txt
+
+[ips_fixed]
+127.0.0.1 51235
+127.0.0.1 51236
+127.0.0.1 51237
+127.0.0.1 51238
+127.0.0.1 51239
+127.0.0.1 51240
+
+[peer_private]
+1
+
+[telemetry]
+enabled=1
+endpoint=http://localhost:4318/v1/traces
+exporter=otlp_http
+sampling_ratio=1.0
+batch_size=512
+batch_delay_ms=2000
+max_queue_size=2048
+trace_rpc=1
+trace_transactions=1
+trace_consensus=1
+trace_peer=0
+trace_ledger=1
+
+[rpc_startup]
+{ "command": "log_level", "severity": "warning" }
+
+[ssl_verify]
+0
+```
+
+#### Step 4: Create validators.txt
+
+```ini
+[validators]
+{public_key_1}
+{public_key_2}
+{public_key_3}
+{public_key_4}
+{public_key_5}
+{public_key_6}
+```
+
+#### Step 5: Start all 6 nodes
+
+```bash
+for i in $(seq 1 6); do
+  .build/xrpld --conf /tmp/xrpld-integration/node$i/xrpld.cfg --start &
+  echo $! > /tmp/xrpld-integration/node$i/xrpld.pid
+done
+```
+
+#### Step 6: Wait for consensus
+
+Poll each node until `server_state` = `"proposing"`:
+
+```bash
+for port in 5005 5006 5007 5008 5009 5010; do
+  while true; do
+    state=$(curl -s http://localhost:$port \
+      -d '{"method":"server_info"}' \
+      | jq -r '.result.info.server_state')
+    echo "Port $port: $state"
+    [ "$state" = "proposing" ] && break
+    sleep 5
+  done
+done
+```
+
+#### Step 7: Exercise RPC and submit transaction
+
+```bash
+# RPC calls
+curl -s http://localhost:5005 -d '{"method":"server_info"}'
+curl -s http://localhost:5005 -d '{"method":"server_state"}'
+curl -s http://localhost:5005 -d '{"method":"ledger","params":[{"ledger_index":"current"}]}'
+
+# Submit transaction
+curl -s http://localhost:5005 -d '{
+  "method": "submit",
+  "params": [{
+    "secret": "snoPBrXtMeMyMHUVTgbuqAfg1SUTb",
+    "tx_json": {
+      "TransactionType": "Payment",
+      "Account": "rHb9CJAWyB4rj91VRWn96DkukG4bwdtyTh",
+      "Destination": "rPMh7Pi9ct699iZUTWzJaUMR1o42VEfGqF",
+      "Amount": "10000000"
+    }
+  }]
+}'
+```
+
+Wait 15 seconds for consensus and batch export.
+
+#### Step 8: Verify in Jaeger
+
+See the "Verification Queries" section below.
+
+---
+
+## Expected Span Catalog
+
+All 16 production span names instrumented across Phases 2-5:
+
+| Span Name                   | Source File           | Phase | Key Attributes                                                                    | How to Trigger            |
+| --------------------------- | --------------------- | ----- | --------------------------------------------------------------------------------- | ------------------------- |
+| `rpc.request`               | ServerHandler.cpp:271 | 2     | --                                                                                | Any HTTP RPC call         |
+| `rpc.process`               | ServerHandler.cpp:573 | 2     | --                                                                                | Any HTTP RPC call         |
+| `rpc.ws_message`            | ServerHandler.cpp:384 | 2     | --                                                                                | WebSocket RPC message     |
+| `rpc.command.<name>`        | RPCHandler.cpp:161    | 2     | `xrpl.rpc.command`, `xrpl.rpc.version`, `xrpl.rpc.role`                           | Any RPC command           |
+| `tx.process`                | NetworkOPs.cpp:1227   | 3     | `xrpl.tx.hash`, `xrpl.tx.local`, `xrpl.tx.path`                                   | Submit transaction        |
+| `tx.receive`                | PeerImp.cpp:1273      | 3     | `xrpl.peer.id`                                                                    | Peer relays transaction   |
+| `consensus.proposal.send`   | RCLConsensus.cpp:177  | 4     | `xrpl.consensus.round`                                                            | Consensus proposing phase |
+| `consensus.ledger_close`    | RCLConsensus.cpp:282  | 4     | `xrpl.consensus.ledger.seq`, `xrpl.consensus.mode`                                | Ledger close event        |
+| `consensus.accept`          | RCLConsensus.cpp:395  | 4     | `xrpl.consensus.proposers`, `xrpl.consensus.round_time_ms`                        | Ledger accepted           |
+| `consensus.validation.send` | RCLConsensus.cpp:753  | 4     | `xrpl.consensus.ledger.seq`, `xrpl.consensus.proposing`                           | Validation sent           |
+| `consensus.accept.apply`    | RCLConsensus.cpp:453  | 4     | `xrpl.consensus.close_time`, `close_time_correct`, `close_resolution_ms`, `state` | Ledger apply + close time |
+| `tx.apply`                  | BuildLedger.cpp:88    | 5     | `xrpl.ledger.tx_count`, `xrpl.ledger.tx_failed`                                   | Ledger close (tx set)     |
+| `ledger.build`              | BuildLedger.cpp:31    | 5     | `xrpl.ledger.seq`                                                                 | Ledger build              |
+| `ledger.validate`           | LedgerMaster.cpp:915  | 5     | `xrpl.ledger.seq`, `xrpl.ledger.validations`                                      | Ledger validated          |
+| `ledger.store`              | LedgerMaster.cpp:409  | 5     | `xrpl.ledger.seq`                                                                 | Ledger stored             |
+| `peer.proposal.receive`     | PeerImp.cpp:1667      | 5     | `xrpl.peer.id`, `xrpl.peer.proposal.trusted`                                      | Peer sends proposal       |
+| `peer.validation.receive`   | PeerImp.cpp:2264      | 5     | `xrpl.peer.id`, `xrpl.peer.validation.trusted`                                    | Peer sends validation     |
+
+---
+
+## Verification Queries
+
+### Jaeger API
+
+Base URL: `http://localhost:16686`
+
+```bash
+JAEGER="http://localhost:16686"
+
+# List all services
+curl -s "$JAEGER/api/services" | jq '.data'
+
+# List operations for rippled
+curl -s "$JAEGER/api/services/rippled/operations" | jq '.data'
+
+# Query traces by operation
+for op in "rpc.request" "rpc.process" \
+          "rpc.command.server_info" "rpc.command.server_state" "rpc.command.ledger" \
+          "tx.process" "tx.receive" "tx.apply" \
+          "consensus.proposal.send" "consensus.ledger_close" \
+          "consensus.accept" "consensus.accept.apply" \
+          "consensus.validation.send" \
+          "ledger.build" "ledger.validate" "ledger.store" \
+          "peer.proposal.receive" "peer.validation.receive"; do
+  count=$(curl -s "$JAEGER/api/traces?service=rippled&operation=$op&limit=5&lookback=1h" \
+    | jq '.data | length')
+  printf "%-35s %s traces\n" "$op" "$count"
+done
+```
+
+### Prometheus API
+
+Base URL: `http://localhost:9090`
+
+```bash
+PROM="http://localhost:9090"
+
+# Span call counts (from spanmetrics connector)
+curl -s "$PROM/api/v1/query?query=traces_span_metrics_calls_total" \
+  | jq '.data.result[] | {span: .metric.span_name, count: .value[1]}'
+
+# Latency histogram
+curl -s "$PROM/api/v1/query?query=traces_span_metrics_duration_milliseconds_count" \
+  | jq '.data.result[] | {span: .metric.span_name, count: .value[1]}'
+
+# RPC calls by command
+curl -s "$PROM/api/v1/query?query=traces_span_metrics_calls_total{span_name=~\"rpc.command.*\"}" \
+  | jq '.data.result[] | {command: .metric["xrpl.rpc.command"], count: .value[1]}'
+```
+
+### System Metrics (beast::insight via OTel native)
+
+rippled's built-in `beast::insight` framework exports metrics natively via OTLP/HTTP to the OTel Collector
+on port 4318 (same endpoint as traces). These appear in Prometheus alongside spanmetrics.
+
+Requires `[insight]` config in `xrpld.cfg`:
+
+```ini
+[insight]
+server=otel
+endpoint=http://localhost:4318/v1/metrics
+prefix=rippled
+```
+
+Verify system metrics in Prometheus:
+
+```bash
+# Ledger age gauge
+curl -s "$PROM/api/v1/query?query=rippled_LedgerMaster_Validated_Ledger_Age" | jq '.data.result'
+
+# Peer counts
+curl -s "$PROM/api/v1/query?query=rippled_Peer_Finder_Active_Inbound_Peers" | jq '.data.result'
+
+# RPC request counter
+curl -s "$PROM/api/v1/query?query=rippled_rpc_requests" | jq '.data.result'
+
+# State accounting
+curl -s "$PROM/api/v1/query?query=rippled_State_Accounting_Full_duration" | jq '.data.result'
+
+# Overlay traffic
+curl -s "$PROM/api/v1/query?query=rippled_total_Bytes_In" | jq '.data.result'
+```
+
+Key system metrics (prefix `rippled_`):
+
+| Metric                                | Type      | Source                                    |
+| ------------------------------------- | --------- | ----------------------------------------- |
+| `LedgerMaster_Validated_Ledger_Age`   | gauge     | LedgerMaster.h:373                        |
+| `LedgerMaster_Published_Ledger_Age`   | gauge     | LedgerMaster.h:374                        |
+| `State_Accounting_{Mode}_duration`    | gauge     | NetworkOPs.cpp:774                        |
+| `State_Accounting_{Mode}_transitions` | gauge     | NetworkOPs.cpp:780                        |
+| `Peer_Finder_Active_Inbound_Peers`    | gauge     | PeerfinderManager.cpp:214                 |
+| `Peer_Finder_Active_Outbound_Peers`   | gauge     | PeerfinderManager.cpp:215                 |
+| `Overlay_Peer_Disconnects`            | gauge     | OverlayImpl.h:557                         |
+| `job_count`                           | gauge     | JobQueue.cpp:26                           |
+| `rpc_requests`                        | counter   | ServerHandler.cpp:108                     |
+| `rpc_time`                            | histogram | ServerHandler.cpp:110                     |
+| `rpc_size`                            | histogram | ServerHandler.cpp:109                     |
+| `ios_latency`                         | histogram | Application.cpp:438                       |
+| `pathfind_fast`                       | histogram | PathRequests.h:23                         |
+| `pathfind_full`                       | histogram | PathRequests.h:24                         |
+| `ledger_fetches`                      | counter   | InboundLedgers.cpp:44                     |
+| `ledger_history_mismatch`             | counter   | LedgerHistory.cpp:16                      |
+| `warn`                                | counter   | Logic.h:33                                |
+| `drop`                                | counter   | Logic.h:34                                |
+| `{category}_Bytes_In/Out`             | gauge     | OverlayImpl.h:535 (57 traffic categories) |
+| `{category}_Messages_In/Out`          | gauge     | OverlayImpl.h:535 (57 traffic categories) |
+
+### Grafana
+
+Open http://localhost:3000 (anonymous admin access enabled).
+
+Pre-configured dashboards (span-derived):
+
+- **RPC Performance**: Request rates, latency percentiles by command, top commands, WebSocket rate
+- **Transaction Overview**: Transaction processing rates, apply duration, peer relay, failed tx rate
+- **Consensus Health**: Consensus round duration, proposer counts, mode tracking, accept heatmap
+- **Ledger Operations**: Build/validate/store rates and durations, TX apply metrics
+- **Peer Network**: Proposal/validation receive rates, trusted vs untrusted breakdown (requires `trace_peer=1`)
+
+Pre-configured dashboards (system metrics):
+
+- **Node Health (System Metrics)**: Validated/published ledger age, operating mode, I/O latency, job queue
+- **Network Traffic (System Metrics)**: Peer counts, disconnects, overlay traffic by category
+- **RPC & Pathfinding (System Metrics)**: RPC request rate/time/size, pathfinding duration, resource warnings
+
+Pre-configured datasources:
+
+- **Jaeger**: Trace data at `http://jaeger:16686`
+- **Tempo**: Trace data at `http://tempo:3200` (via Grafana Explore)
+- **Prometheus**: Metrics at `http://prometheus:9090`
+- **Loki**: Log data at `http://loki:3100` (via Grafana Explore)
+
+---
+
+## Test 3: Log-Trace Correlation (Phase 8)
+
+Phase 8 injects `trace_id` and `span_id` into rippled's log output when
+a log line is emitted within an active OTel span. This test verifies the
+end-to-end log-trace correlation pipeline.
+
+### Step 1: Verify trace_id in log output
+
+After running Test 1 or Test 2 (which generate RPC spans), check the
+rippled debug.log for trace context:
+
+```bash
+grep 'trace_id=[a-f0-9]\{32\} span_id=[a-f0-9]\{16\}' /path/to/debug.log
+```
+
+Expected: log lines with `trace_id=<32hex> span_id=<16hex>` between the
+severity code and the message. Example:
+
+```
+2024-01-15T10:30:45.123Z RPCHandler:NFO trace_id=abc123def456789012345678abcdef01 span_id=0123456789abcdef Calling server_info
+```
+
+Lines emitted outside of an active span (background tasks, startup) will
+NOT have trace context — this is expected.
+
+### Step 2: Cross-check trace_id in Jaeger
+
+Extract a `trace_id` from the log and verify it exists in Jaeger:
+
+```bash
+TRACE_ID=$(grep -o 'trace_id=[a-f0-9]\{32\}' /path/to/debug.log | head -1 | cut -d= -f2)
+echo "Checking trace: $TRACE_ID"
+curl -s "http://localhost:16686/api/traces/$TRACE_ID" | jq '.data | length'
+```
+
+Expected result: `1` (the trace exists in Jaeger).
+
+### Step 3: Verify Loki log ingestion
+
+The OTel Collector's filelog receiver tails rippled's debug.log and
+exports parsed entries to Loki. Verify Loki has received entries:
+
+```bash
+# Query Loki for any rippled logs
+curl -sG "http://localhost:3100/loki/api/v1/query" \
+  --data-urlencode 'query={job="rippled"}' \
+  --data-urlencode 'limit=5' | jq '.data.result | length'
+```
+
+Expected: > 0 results.
+
+### Step 4: Verify Grafana Tempo-to-Loki correlation
+
+1. Open Grafana at http://localhost:3000
+2. Navigate to **Explore** -> select **Tempo** datasource
+3. Search for a trace (e.g., operation `rpc.command.server_info`)
+4. Click **"Logs for this trace"** in the trace detail view
+5. Verify that Loki log lines appear, filtered by the trace's `trace_id`
+
+### Step 5: Verify Grafana Loki-to-Tempo correlation
+
+1. In Grafana **Explore**, select **Loki** datasource
+2. Query: `{job="rippled"} |= "trace_id="`
+3. In the log results, click the **TraceID** derived field link
+4. Verify it navigates to the full trace in Tempo
+
+### Expected results
+
+| Check                          | Expected                                 |
+| ------------------------------ | ---------------------------------------- |
+| `trace_id=` in debug.log       | Present in log lines within active spans |
+| `span_id=` in debug.log        | Present alongside trace_id               |
+| Logs without active span       | No trace_id/span_id fields               |
+| trace_id in Jaeger             | Matches a valid trace                    |
+| Loki log ingestion             | Logs visible via LogQL                   |
+| Tempo -> Loki "Logs for trace" | Shows correlated log lines               |
+| Loki -> Tempo TraceID link     | Navigates to correct trace               |
+
+---
+
+## Troubleshooting
+
+### No traces in Jaeger
+
+1. Check otel-collector logs:
+   ```bash
+   docker compose -f docker/telemetry/docker-compose.yml logs otel-collector
+   ```
+2. Verify xrpld telemetry config has `enabled=1` and correct endpoint
+3. Check that otel-collector port 4318 is accessible:
+   ```bash
+   curl -sf http://localhost:4318 && echo "reachable"
+   ```
+4. Increase `batch_delay_ms` or decrease `batch_size` in xrpld config
+
+### Nodes not reaching "proposing" state
+
+1. Check that all peer ports (51235-51240) are not in use:
+   ```bash
+   for p in 51235 51236 51237 51238 51239 51240; do
+     ss -tlnp | grep ":$p " && echo "port $p in use"
+   done
+   ```
+2. Verify `[ips_fixed]` lists all 6 peer ports
+3. Verify `validators.txt` has all 6 public keys
+4. Check node debug logs: `tail -50 /tmp/xrpld-integration/node1/debug.log`
+5. Ensure `[peer_private]` is set to `1` (prevents reaching out to public network)
+
+### Transaction not processing
+
+1. Verify genesis account exists:
+   ```bash
+   curl -s http://localhost:5005 \
+     -d '{"method":"account_info","params":[{"account":"rHb9CJAWyB4rj91VRWn96DkukG4bwdtyTh"}]}' \
+     | jq .result.account_data.Balance
+   ```
+2. Check submit response for error codes
+3. In standalone mode, remember to call `ledger_accept` after submitting
+
+### No trace_id in log output (Phase 8)
+
+1. Verify rippled was built with `telemetry=ON` (`-Dtelemetry=ON` in CMake)
+2. Verify `enabled=1` in the `[telemetry]` config section
+3. Log lines only contain trace context when emitted inside an active span.
+   Background logs (startup, periodic tasks outside spans) will not have
+   `trace_id`/`span_id`.
+4. Ensure the trace category is enabled (e.g., `trace_rpc=1` for RPC logs)
+
+### No logs in Loki (Phase 8)
+
+1. Verify the log file mount in docker-compose.yml:
+   ```yaml
+   volumes:
+     - /tmp/xrpld-integration:/var/log/rippled:ro
+   ```
+2. Check OTel Collector logs for filelog receiver errors:
+   ```bash
+   docker compose -f docker/telemetry/docker-compose.yml logs otel-collector | grep -i "filelog\|loki\|error"
+   ```
+3. Verify Loki is running:
+   ```bash
+   curl -s http://localhost:3100/ready
+   ```
+4. Verify the filelog receiver glob pattern matches your log files:
+   The default pattern is `/var/log/rippled/*/debug.log`
+
+### Grafana trace-log links not working (Phase 8)
+
+1. Verify `tracesToLogs` is configured in the Tempo datasource provisioning
+   (`docker/telemetry/grafana/provisioning/datasources/tempo.yaml`)
+2. Verify `derivedFields` is configured in the Loki datasource provisioning
+   (`docker/telemetry/grafana/provisioning/datasources/loki.yaml`)
+3. Restart Grafana after changing provisioning files:
+   ```bash
+   docker compose -f docker/telemetry/docker-compose.yml restart grafana
+   ```
+
+### Spanmetrics not appearing in Prometheus
+
+1. Verify otel-collector config has `spanmetrics` connector
+2. Check that the metrics pipeline is configured:
+   ```yaml
+   service:
+     pipelines:
+       metrics:
+         receivers: [otlp, spanmetrics]
+         exporters: [prometheus]
+   ```
+3. Verify Prometheus can reach collector:
+   ```bash
+   curl -s http://localhost:9090/api/v1/targets | jq '.data.activeTargets'
+   ```

docker/telemetry/docker-compose.workload.yaml

@@ -0,0 +1,137 @@
+# Docker Compose workload harness for Phase 10 telemetry validation.
+#
+# Runs a 5-node validator cluster with full OTel telemetry stack:
+#   - 5 rippled validator nodes (consensus network)
+#   - OTel Collector (traces + StatsD metrics)
+#   - Jaeger (trace search UI)
+#   - Tempo (production trace backend)
+#   - Prometheus (metrics)
+#   - Loki (log aggregation for log-trace correlation)
+#   - Grafana (dashboards + trace/log exploration)
+#
+# Usage:
+#   # Start the harness (requires pre-built xrpld image or mount binary):
+#   docker compose -f docker/telemetry/docker-compose.workload.yaml up -d
+#
+#   # Or use the orchestrator:
+#   docker/telemetry/workload/run-full-validation.sh
+#
+# Prerequisites:
+#   - xrpld binary built with -DXRPL_ENABLE_TELEMETRY=ON
+#   - Validator keys generated via generate-validator-keys.sh
+#   - Node configs generated by run-full-validation.sh
+
+version: "3.8"
+
+services:
+  # ---------------------------------------------------------------------------
+  # Telemetry Backend Stack
+  # ---------------------------------------------------------------------------
+
+  otel-collector:
+    image: otel/opentelemetry-collector-contrib:latest
+    command: ["--config=/etc/otel-collector-config.yaml"]
+    ports:
+      - "4317:4317" # OTLP gRPC
+      - "4318:4318" # OTLP HTTP
+      - "8125:8125/udp" # StatsD UDP (beast::insight metrics)
+      - "8889:8889" # Prometheus metrics endpoint
+      - "13133:13133" # Health check
+    volumes:
+      - ../otel-collector-config.yaml:/etc/otel-collector-config.yaml:ro
+    depends_on:
+      - jaeger
+      - tempo
+    networks:
+      - workload-net
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:13133/"]
+      interval: 5s
+      timeout: 3s
+      retries: 10
+
+  jaeger:
+    image: jaegertracing/all-in-one:latest
+    environment:
+      - COLLECTOR_OTLP_ENABLED=true
+    ports:
+      - "16686:16686" # Jaeger UI
+      - "14250:14250" # gRPC
+    networks:
+      - workload-net
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:16686/"]
+      interval: 5s
+      timeout: 3s
+      retries: 10
+
+  tempo:
+    image: grafana/tempo:2.7.2
+    command: ["-config.file=/etc/tempo.yaml"]
+    ports:
+      - "3200:3200" # Tempo HTTP API
+    volumes:
+      - ../tempo.yaml:/etc/tempo.yaml:ro
+      - tempo-data:/var/tempo
+    networks:
+      - workload-net
+
+  prometheus:
+    image: prom/prometheus:latest
+    ports:
+      - "9090:9090"
+    volumes:
+      - ../prometheus.yml:/etc/prometheus/prometheus.yml:ro
+    depends_on:
+      otel-collector:
+        condition: service_healthy
+    networks:
+      - workload-net
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:9090/-/healthy"]
+      interval: 5s
+      timeout: 3s
+      retries: 10
+
+  loki:
+    image: grafana/loki:2.9.4
+    ports:
+      - "3100:3100" # Loki HTTP API
+    command: ["-config.file=/etc/loki/local-config.yaml"]
+    networks:
+      - workload-net
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:3100/ready"]
+      interval: 5s
+      timeout: 3s
+      retries: 10
+
+  grafana:
+    image: grafana/grafana:latest
+    environment:
+      - GF_AUTH_ANONYMOUS_ENABLED=true
+      - GF_AUTH_ANONYMOUS_ORG_ROLE=Admin
+    ports:
+      - "3000:3000"
+    volumes:
+      - ../grafana/provisioning:/etc/grafana/provisioning:ro
+      - ../grafana/dashboards:/var/lib/grafana/dashboards:ro
+    depends_on:
+      - jaeger
+      - tempo
+      - prometheus
+      - loki
+    networks:
+      - workload-net
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:3000/api/health"]
+      interval: 5s
+      timeout: 3s
+      retries: 10
+
+volumes:
+  tempo-data:
+
+networks:
+  workload-net:
+    driver: bridge

docker/telemetry/docker-compose.yml

@@ -0,0 +1,118 @@
+# Docker Compose stack for rippled OpenTelemetry observability.
+#
+# Provides services for local development:
+#   - otel-collector: receives OTLP traces from rippled, batches and
+#     forwards them to Jaeger and Tempo. Also tails rippled log files
+#     via filelog receiver and exports to Loki. Listens on ports
+#     4317 (gRPC), 4318 (HTTP), and 8125 (StatsD UDP).
+#   - jaeger: all-in-one tracing backend with UI on port 16686.
+#   - tempo: Grafana Tempo tracing backend, queryable via Grafana Explore
+#     on port 3000. Recommended for production (S3/GCS storage, TraceQL).
+#   - loki: Grafana Loki log aggregation backend for centralized log
+#     ingestion and log-trace correlation (Phase 8).
+#   - grafana: dashboards on port 3000, pre-configured with Jaeger, Tempo,
+#     Prometheus, and Loki datasources.
+#
+# Usage:
+#   docker compose -f docker/telemetry/docker-compose.yml up -d
+#
+# Configure rippled to export traces by adding to xrpld.cfg:
+#   [telemetry]
+#   enabled=1
+#   endpoint=http://localhost:4318/v1/traces
+
+version: "3.8"
+
+services:
+  otel-collector:
+    image: otel/opentelemetry-collector-contrib:latest
+    command: ["--config=/etc/otel-collector-config.yaml"]
+    ports:
+      - "4317:4317" # OTLP gRPC
+      - "4318:4318" # OTLP HTTP (traces + native OTel metrics)
+      - "8889:8889" # Prometheus metrics (spanmetrics + OTLP)
+      - "13133:13133" # Health check
+      # StatsD UDP port removed — beast::insight now uses native OTLP.
+      # Uncomment if using server=statsd fallback:
+      # - "8125:8125/udp"
+    volumes:
+      - ./otel-collector-config.yaml:/etc/otel-collector-config.yaml:ro
+      # Phase 8: Mount rippled log directory for filelog receiver.
+      # The integration test writes logs to /tmp/xrpld-integration/;
+      # mount it read-only so the collector can tail debug.log files.
+      - /tmp/xrpld-integration:/var/log/rippled:ro
+    depends_on:
+      - jaeger
+      - tempo
+      - loki
+    networks:
+      - rippled-telemetry
+
+  jaeger:
+    image: jaegertracing/all-in-one:latest
+    environment:
+      - COLLECTOR_OTLP_ENABLED=true
+    ports:
+      - "16686:16686" # Jaeger UI
+      - "14250:14250" # gRPC
+    networks:
+      - rippled-telemetry
+
+  tempo:
+    image: grafana/tempo:2.7.2
+    command: ["-config.file=/etc/tempo.yaml"]
+    ports:
+      - "3200:3200" # Tempo HTTP API (health, query)
+    volumes:
+      - ./tempo.yaml:/etc/tempo.yaml:ro
+      - tempo-data:/var/tempo
+    networks:
+      - rippled-telemetry
+
+  # Phase 8: Grafana Loki for centralized log ingestion and log-trace
+  # correlation. Loki 3.x supports native OTLP ingestion, so the OTel
+  # Collector exports via otlphttp to Loki's /otlp endpoint.
+  # Query logs via Grafana Explore -> Loki at http://localhost:3000.
+  loki:
+    image: grafana/loki:3.4.2
+    ports:
+      - "3100:3100"
+    command: -config.file=/etc/loki/local-config.yaml
+    networks:
+      - rippled-telemetry
+
+  prometheus:
+    image: prom/prometheus:latest
+    ports:
+      - "9090:9090"
+    volumes:
+      - ./prometheus.yml:/etc/prometheus/prometheus.yml:ro
+    depends_on:
+      - otel-collector
+    networks:
+      - rippled-telemetry
+
+  grafana:
+    image: grafana/grafana:latest
+    environment:
+      - GF_AUTH_ANONYMOUS_ENABLED=true
+      - GF_AUTH_ANONYMOUS_ORG_ROLE=Admin
+    ports:
+      - "3000:3000"
+    volumes:
+      - ./grafana/provisioning:/etc/grafana/provisioning:ro
+      - ./grafana/dashboards:/var/lib/grafana/dashboards:ro
+    depends_on:
+      - jaeger
+      - tempo
+      - prometheus
+      - loki
+    networks:
+      - rippled-telemetry
+
+volumes:
+  tempo-data:
+
+networks:
+  rippled-telemetry:
+    driver: bridge

docker/telemetry/grafana/dashboards/consensus-health.json

@@ -0,0 +1,440 @@
+{
+  "annotations": {
+    "list": []
+  },
+  "editable": true,
+  "fiscalYearStartMonth": 0,
+  "graphTooltip": 1,
+  "id": null,
+  "links": [],
+  "panels": [
+    {
+      "title": "Consensus Round Duration",
+      "description": "p95 and p50 duration of consensus accept rounds. The consensus.accept span (RCLConsensus.cpp:395) measures the time to process an accepted ledger including transaction application and state finalization. The span carries xrpl.consensus.proposers and xrpl.consensus.round_time_ms attributes. Normal range is 3-6 seconds on mainnet.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 0
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "histogram_quantile(0.95, sum by (le) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", span_name=\"consensus.accept\"}[5m])))",
+          "legendFormat": "P95 Round Duration"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "histogram_quantile(0.50, sum by (le) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", span_name=\"consensus.accept\"}[5m])))",
+          "legendFormat": "P50 Round Duration"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "ms",
+          "custom": {
+            "axisLabel": "Duration (ms)",
+            "spanNulls": true,
+            "insertNulls": false,
+            "showPoints": "auto",
+            "pointSize": 3
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Consensus Proposals Sent Rate",
+      "description": "Rate at which this node sends consensus proposals to the network. Sourced from the consensus.proposal.send span (RCLConsensus.cpp:177) which fires each time the node proposes a transaction set. The span carries xrpl.consensus.round identifying the consensus round number. A healthy proposing node should show steady proposal output.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 0
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "sum(rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", span_name=\"consensus.proposal.send\"}[5m]))",
+          "legendFormat": "Proposals / Sec"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "ops",
+          "custom": {
+            "axisLabel": "Proposals / Sec",
+            "spanNulls": true,
+            "insertNulls": false,
+            "showPoints": "auto",
+            "pointSize": 3
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Ledger Close Duration",
+      "description": "p95 duration of the ledger close event. The consensus.ledger_close span (RCLConsensus.cpp:282) measures the time from when consensus triggers a ledger close to completion. Carries xrpl.consensus.ledger.seq and xrpl.consensus.mode attributes. Compare with Consensus Round Duration to understand how close timing relates to overall round time.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 8
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "histogram_quantile(0.95, sum by (le) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", span_name=\"consensus.ledger_close\"}[5m])))",
+          "legendFormat": "P95 Close Duration"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "ms",
+          "custom": {
+            "axisLabel": "Duration (ms)",
+            "spanNulls": true,
+            "insertNulls": false,
+            "showPoints": "auto",
+            "pointSize": 3
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Validation Send Rate",
+      "description": "Rate at which this node sends ledger validations to the network. Sourced from the consensus.validation.send span (RCLConsensus.cpp:753). Each validation confirms the node has fully validated a ledger. The span carries xrpl.consensus.ledger.seq and xrpl.consensus.proposing. Should closely track the ledger close rate when the node is healthy.",
+      "type": "stat",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 8
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "sum(rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", span_name=\"consensus.validation.send\"}[5m]))",
+          "legendFormat": "Validations / Sec"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "ops"
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Ledger Apply Duration (doAccept)",
+      "description": "Time spent applying the consensus result to build a new ledger. Measured by the consensus.accept.apply span in doAccept().",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 16
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "histogram_quantile(0.95, sum by (le) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", span_name=\"consensus.accept.apply\"}[5m])))",
+          "legendFormat": "P95 Apply Duration"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "histogram_quantile(0.50, sum by (le) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", span_name=\"consensus.accept.apply\"}[5m])))",
+          "legendFormat": "P50 Apply Duration"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "ms"
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Close Time Agreement",
+      "description": "Rate of close time agreement vs disagreement across consensus rounds. Based on xrpl.consensus.close_time_correct attribute (true = validators agreed, false = agreed to disagree per avCT_CONSENSUS_PCT).",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 16
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "sum(rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", span_name=\"consensus.accept.apply\"}[5m]))",
+          "legendFormat": "Total Rounds / Sec"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "ops"
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Consensus Mode Over Time",
+      "description": "Breakdown of consensus ledger close events by the node's consensus mode (proposing, observing, wrongLedger, switchedLedger). Grouped by the xrpl.consensus.mode span attribute from consensus.ledger_close. A healthy validator should be predominantly in 'proposing' mode. Frequent 'wrongLedger' or 'switchedLedger' indicates sync issues.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 24
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "sum by (xrpl_consensus_mode) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", span_name=\"consensus.ledger_close\"}[5m]))",
+          "legendFormat": "{{xrpl_consensus_mode}}"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "ops",
+          "custom": {
+            "axisLabel": "Events / Sec",
+            "spanNulls": true,
+            "insertNulls": false,
+            "showPoints": "auto",
+            "pointSize": 3
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Accept vs Close Rate",
+      "description": "Compares the rate of consensus.accept (ledger accepted after consensus) vs consensus.ledger_close (ledger close initiated). These should track closely in a healthy network. A divergence means some close events are not completing the accept phase, potentially indicating consensus failures or timeouts.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 24
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "sum(rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", span_name=\"consensus.accept\"}[5m]))",
+          "legendFormat": "Accepts / Sec"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "sum(rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", span_name=\"consensus.ledger_close\"}[5m]))",
+          "legendFormat": "Closes / Sec"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "ops",
+          "custom": {
+            "axisLabel": "Events / Sec",
+            "spanNulls": true,
+            "insertNulls": false,
+            "showPoints": "auto",
+            "pointSize": 3
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Validation vs Close Rate",
+      "description": "Compares the rate of consensus.validation.send vs consensus.ledger_close. Each validated ledger should produce one validation message. If validations lag behind closes, the node may be falling behind on validation or experiencing issues with the validation pipeline.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 32
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "sum(rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", span_name=\"consensus.validation.send\"}[5m]))",
+          "legendFormat": "Validations / Sec"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "sum(rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", span_name=\"consensus.ledger_close\"}[5m]))",
+          "legendFormat": "Closes / Sec"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "ops",
+          "custom": {
+            "axisLabel": "Events / Sec",
+            "spanNulls": true,
+            "insertNulls": false,
+            "showPoints": "auto",
+            "pointSize": 3
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Consensus Accept Duration Heatmap",
+      "description": "Heatmap showing the distribution of consensus.accept span durations across histogram buckets over time. Each cell represents how many accept events fell into that duration bucket in a 5m window. Useful for detecting outlier consensus rounds that take abnormally long.",
+      "type": "heatmap",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 32
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        },
+        "yAxis": {
+          "axisLabel": "Duration (ms)"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "sum(increase(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", span_name=\"consensus.accept\"}[5m])) by (le)",
+          "legendFormat": "{{le}}",
+          "format": "heatmap"
+        }
+      ]
+    }
+  ],
+  "schemaVersion": 39,
+  "tags": ["rippled", "consensus", "telemetry"],
+  "templating": {
+    "list": [
+      {
+        "name": "node",
+        "label": "Node",
+        "description": "Filter by rippled node (service.instance.id \u2014 e.g. Node-1)",
+        "type": "query",
+        "query": "label_values(traces_span_metrics_calls_total, exported_instance)",
+        "datasource": {
+          "type": "prometheus",
+          "uid": "prometheus"
+        },
+        "includeAll": true,
+        "allValue": ".*",
+        "current": {
+          "text": "All",
+          "value": "$__all"
+        },
+        "multi": true,
+        "refresh": 2,
+        "sort": 1
+      },
+      {
+        "name": "consensus_mode",
+        "label": "Consensus Mode",
+        "description": "Filter by consensus mode (proposing, observing, wrongLedger, switchedLedger)",
+        "type": "query",
+        "query": "label_values(traces_span_metrics_calls_total{span_name=\"consensus.ledger_close\"}, xrpl_consensus_mode)",
+        "datasource": {
+          "type": "prometheus",
+          "uid": "prometheus"
+        },
+        "includeAll": true,
+        "allValue": ".*",
+        "current": {
+          "text": "All",
+          "value": "$__all"
+        },
+        "multi": true,
+        "refresh": 2,
+        "sort": 1
+      }
+    ]
+  },
+  "time": {
+    "from": "now-1h",
+    "to": "now"
+  },
+  "title": "Consensus Health",
+  "uid": "rippled-consensus"
+}

docker/telemetry/grafana/dashboards/ledger-operations.json

@@ -0,0 +1,347 @@
+{
+  "annotations": {
+    "list": []
+  },
+  "editable": true,
+  "fiscalYearStartMonth": 0,
+  "graphTooltip": 1,
+  "id": null,
+  "links": [],
+  "panels": [
+    {
+      "title": "Ledger Build Rate",
+      "description": "Rate at which new ledgers are being built. The ledger.build span (BuildLedger.cpp:31) wraps the entire buildLedgerImpl() function which creates a new ledger from a parent, applies transactions, flushes SHAMap nodes, and sets the accepted state. Should match the consensus close rate (~0.25/sec on mainnet with ~4s rounds).",
+      "type": "stat",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 0
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "sum(rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", span_name=\"ledger.build\"}[5m]))",
+          "legendFormat": "Builds / Sec"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "ops"
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Ledger Build Duration",
+      "description": "p95 and p50 duration of ledger builds. Measures the full buildLedgerImpl() call including transaction application, SHAMap flushing, and ledger acceptance. The span records xrpl.ledger.seq as an attribute. Long build times indicate expensive transaction sets or I/O pressure from SHAMap flushes.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 0
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "histogram_quantile(0.95, sum by (le) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", span_name=\"ledger.build\"}[5m])))",
+          "legendFormat": "P95 Build Duration"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "histogram_quantile(0.50, sum by (le) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", span_name=\"ledger.build\"}[5m])))",
+          "legendFormat": "P50 Build Duration"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "ms",
+          "custom": {
+            "axisLabel": "Duration (ms)",
+            "spanNulls": true,
+            "insertNulls": false,
+            "showPoints": "auto",
+            "pointSize": 3
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Ledger Validation Rate",
+      "description": "Rate at which ledgers pass the validation threshold and are accepted as fully validated. The ledger.validate span (LedgerMaster.cpp:915) fires in checkAccept() only after the ledger receives sufficient trusted validations (>= quorum). Records xrpl.ledger.seq and xrpl.ledger.validations (the number of validations received).",
+      "type": "stat",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 8
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "sum(rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", span_name=\"ledger.validate\"}[5m]))",
+          "legendFormat": "Validations / Sec"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "ops"
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Ledger Build Duration Heatmap",
+      "description": "Heatmap showing the distribution of ledger.build durations across histogram buckets over time. Each cell represents the count of ledger builds that fell into that duration bucket in a 5m window. Useful for spotting occasional slow ledger builds that may not appear in percentile charts.",
+      "type": "heatmap",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 8
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        },
+        "yAxis": {
+          "axisLabel": "Duration (ms)"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "sum(increase(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", span_name=\"ledger.build\"}[5m])) by (le)",
+          "legendFormat": "{{le}}",
+          "format": "heatmap"
+        }
+      ]
+    },
+    {
+      "title": "Transaction Apply Duration",
+      "description": "p95 and p50 duration of applying the consensus transaction set during ledger building. The tx.apply span (BuildLedger.cpp:88) wraps applyTransactions() which iterates through the CanonicalTXSet with multiple retry passes. Records xrpl.ledger.tx_count (successful) and xrpl.ledger.tx_failed (failed) as attributes.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 16
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "histogram_quantile(0.95, sum by (le) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", span_name=\"tx.apply\"}[5m])))",
+          "legendFormat": "P95 tx.apply"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "histogram_quantile(0.50, sum by (le) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", span_name=\"tx.apply\"}[5m])))",
+          "legendFormat": "P50 tx.apply"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "ms",
+          "custom": {
+            "axisLabel": "Duration (ms)",
+            "spanNulls": true,
+            "insertNulls": false,
+            "showPoints": "auto",
+            "pointSize": 3
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Transaction Apply Rate",
+      "description": "Rate of tx.apply span invocations, reflecting how frequently the transaction application phase runs during ledger building. Each ledger build triggers one tx.apply call. Should closely match the ledger build rate.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 16
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "sum(rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", span_name=\"tx.apply\"}[5m]))",
+          "legendFormat": "tx.apply / Sec"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "ops",
+          "custom": {
+            "axisLabel": "Operations / Sec",
+            "spanNulls": true,
+            "insertNulls": false,
+            "showPoints": "auto",
+            "pointSize": 3
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Ledger Store Rate",
+      "description": "Rate at which ledgers are stored into the ledger history. The ledger.store span (LedgerMaster.cpp:409) wraps storeLedger() which inserts the ledger into the LedgerHistory cache. Records xrpl.ledger.seq. Should match the ledger build rate under normal operation.",
+      "type": "stat",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 24
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "sum(rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", span_name=\"ledger.store\"}[5m]))",
+          "legendFormat": "Stores / Sec"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "ops"
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Build vs Close Duration",
+      "description": "Compares p95 durations of ledger.build (the actual ledger construction in BuildLedger.cpp) vs consensus.ledger_close (the consensus close event in RCLConsensus.cpp). Build time is a subset of close time. A large gap between them indicates overhead in the consensus pipeline outside of ledger construction itself.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 24
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "histogram_quantile(0.95, sum by (le) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", span_name=\"ledger.build\"}[5m])))",
+          "legendFormat": "P95 ledger.build"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "histogram_quantile(0.95, sum by (le) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", span_name=\"consensus.ledger_close\"}[5m])))",
+          "legendFormat": "P95 consensus.ledger_close"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "ms",
+          "custom": {
+            "axisLabel": "Duration (ms)",
+            "spanNulls": true,
+            "insertNulls": false,
+            "showPoints": "auto",
+            "pointSize": 3
+          }
+        },
+        "overrides": []
+      }
+    }
+  ],
+  "schemaVersion": 39,
+  "tags": ["rippled", "ledger", "telemetry"],
+  "templating": {
+    "list": [
+      {
+        "name": "node",
+        "label": "Node",
+        "description": "Filter by rippled node (service.instance.id \u2014 e.g. Node-1)",
+        "type": "query",
+        "query": "label_values(traces_span_metrics_calls_total, exported_instance)",
+        "datasource": {
+          "type": "prometheus",
+          "uid": "prometheus"
+        },
+        "includeAll": true,
+        "allValue": ".*",
+        "current": {
+          "text": "All",
+          "value": "$__all"
+        },
+        "multi": true,
+        "refresh": 2,
+        "sort": 1
+      }
+    ]
+  },
+  "time": {
+    "from": "now-1h",
+    "to": "now"
+  },
+  "title": "Ledger Operations",
+  "uid": "rippled-ledger-ops"
+}

docker/telemetry/grafana/dashboards/peer-network.json

@@ -0,0 +1,195 @@
+{
+  "annotations": {
+    "list": []
+  },
+  "description": "Requires trace_peer=1 in the [telemetry] config section.",
+  "editable": true,
+  "fiscalYearStartMonth": 0,
+  "graphTooltip": 1,
+  "id": null,
+  "links": [],
+  "panels": [
+    {
+      "title": "Peer Proposal Receive Rate",
+      "description": "Rate of consensus proposals received from network peers. The peer.proposal.receive span (PeerImp.cpp:1667) fires in onMessage(TMProposeSet) for each incoming proposal. Records xrpl.peer.id (sending peer) and xrpl.peer.proposal.trusted (whether the proposer is in our UNL). Requires trace_peer=1 in the telemetry config.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 0
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "sum(rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", span_name=\"peer.proposal.receive\"}[5m]))",
+          "legendFormat": "Proposals Received / Sec"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "ops",
+          "custom": {
+            "axisLabel": "Proposals / Sec",
+            "spanNulls": true,
+            "insertNulls": false,
+            "showPoints": "auto",
+            "pointSize": 3
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Peer Validation Receive Rate",
+      "description": "Rate of ledger validations received from network peers. The peer.validation.receive span (PeerImp.cpp:2264) fires in onMessage(TMValidation) for each incoming validation message. Records xrpl.peer.id (sending peer) and xrpl.peer.validation.trusted (whether the validator is trusted). Requires trace_peer=1 in the telemetry config.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 0
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "sum(rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", span_name=\"peer.validation.receive\"}[5m]))",
+          "legendFormat": "Validations Received / Sec"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "ops",
+          "custom": {
+            "axisLabel": "Validations / Sec",
+            "spanNulls": true,
+            "insertNulls": false,
+            "showPoints": "auto",
+            "pointSize": 3
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Proposals Trusted vs Untrusted",
+      "description": "Pie chart showing the ratio of proposals received from trusted validators (in our UNL) vs untrusted validators. Grouped by the xrpl.peer.proposal.trusted span attribute (true/false). A healthy node connected to a well-configured UNL should see a significant portion of trusted proposals. Note: proposals that fail early validation may not have the trusted attribute set.",
+      "type": "piechart",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 8
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "sum by (xrpl_peer_proposal_trusted) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", span_name=\"peer.proposal.receive\"}[5m]))",
+          "legendFormat": "Trusted = {{xrpl_peer_proposal_trusted}}"
+        }
+      ]
+    },
+    {
+      "title": "Validations Trusted vs Untrusted",
+      "description": "Pie chart showing the ratio of validations received from trusted validators (in our UNL) vs untrusted validators. Grouped by the xrpl.peer.validation.trusted span attribute (true/false). Monitoring this helps detect if the node is receiving validations from the expected set of trusted validators. Note: validations that fail early checks may not have the trusted attribute set.",
+      "type": "piechart",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 8
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "sum by (xrpl_peer_validation_trusted) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", span_name=\"peer.validation.receive\"}[5m]))",
+          "legendFormat": "Trusted = {{xrpl_peer_validation_trusted}}"
+        }
+      ]
+    }
+  ],
+  "schemaVersion": 39,
+  "tags": ["rippled", "peer", "telemetry"],
+  "templating": {
+    "list": [
+      {
+        "name": "node",
+        "label": "Node",
+        "description": "Filter by rippled node (service.instance.id \u2014 e.g. Node-1)",
+        "type": "query",
+        "query": "label_values(traces_span_metrics_calls_total, exported_instance)",
+        "datasource": {
+          "type": "prometheus",
+          "uid": "prometheus"
+        },
+        "includeAll": true,
+        "allValue": ".*",
+        "current": {
+          "text": "All",
+          "value": "$__all"
+        },
+        "multi": true,
+        "refresh": 2,
+        "sort": 1
+      },
+      {
+        "name": "proposal_trusted",
+        "label": "Proposal Trusted",
+        "description": "Filter by proposal trust status (true = from trusted validator)",
+        "type": "query",
+        "query": "label_values(traces_span_metrics_calls_total{span_name=\"peer.proposal.receive\"}, xrpl_peer_proposal_trusted)",
+        "datasource": {
+          "type": "prometheus",
+          "uid": "prometheus"
+        },
+        "includeAll": true,
+        "allValue": ".*",
+        "current": {
+          "text": "All",
+          "value": "$__all"
+        },
+        "multi": true,
+        "refresh": 2,
+        "sort": 1
+      }
+    ]
+  },
+  "time": {
+    "from": "now-1h",
+    "to": "now"
+  },
+  "title": "Peer Network",
+  "uid": "rippled-peer-net"
+}

docker/telemetry/grafana/dashboards/rippled-fee-market.json

@@ -0,0 +1,338 @@
+{
+  "annotations": {
+    "list": []
+  },
+  "description": "Fee market dynamics: TxQ depth/capacity, fee escalation levels, and load factor breakdown. Sourced from OTel MetricsRegistry observable gauges (Phase 9).",
+  "editable": true,
+  "fiscalYearStartMonth": 0,
+  "graphTooltip": 1,
+  "id": null,
+  "links": [],
+  "panels": [
+    {
+      "title": "Transaction Queue Depth",
+      "description": "Current number of transactions waiting in the queue vs. maximum capacity. Sourced from MetricsRegistry txq_metrics observable gauge with metric=txq_count and metric=txq_max_size.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 0
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_txq_metrics{exported_instance=~\"$node\", metric=\"txq_count\"}",
+          "legendFormat": "Queue Depth"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_txq_metrics{exported_instance=~\"$node\", metric=\"txq_max_size\"}",
+          "legendFormat": "Max Capacity"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "short",
+          "custom": {
+            "drawStyle": "line",
+            "lineWidth": 2,
+            "fillOpacity": 10
+          },
+          "color": {
+            "mode": "palette-classic"
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Transactions Per Ledger",
+      "description": "Transactions in the current open ledger vs. expected per-ledger count. Sourced from txq_metrics with metric=txq_in_ledger and metric=txq_per_ledger.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 0
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_txq_metrics{exported_instance=~\"$node\", metric=\"txq_in_ledger\"}",
+          "legendFormat": "In Ledger"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_txq_metrics{exported_instance=~\"$node\", metric=\"txq_per_ledger\"}",
+          "legendFormat": "Expected Per Ledger"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "short",
+          "custom": {
+            "drawStyle": "line",
+            "lineWidth": 2,
+            "fillOpacity": 10
+          },
+          "color": {
+            "mode": "palette-classic"
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Fee Escalation Levels",
+      "description": "Fee levels that control transaction queue admission. Reference fee level is the baseline; open ledger fee level triggers escalation. Sourced from txq_metrics observable gauge.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 24,
+        "x": 0,
+        "y": 8
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_txq_metrics{exported_instance=~\"$node\", metric=\"txq_reference_fee_level\"}",
+          "legendFormat": "Reference Fee Level"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_txq_metrics{exported_instance=~\"$node\", metric=\"txq_min_processing_fee_level\"}",
+          "legendFormat": "Min Processing Fee Level"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_txq_metrics{exported_instance=~\"$node\", metric=\"txq_med_fee_level\"}",
+          "legendFormat": "Median Fee Level"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_txq_metrics{exported_instance=~\"$node\", metric=\"txq_open_ledger_fee_level\"}",
+          "legendFormat": "Open Ledger Fee Level"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "short",
+          "custom": {
+            "drawStyle": "line",
+            "lineWidth": 2,
+            "fillOpacity": 5,
+            "scaleDistribution": {
+              "type": "log",
+              "log": 2
+            }
+          },
+          "color": {
+            "mode": "palette-classic"
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Load Factor Breakdown",
+      "description": "Decomposed load factor components: server (max of local, net, cluster), fee escalation, fee queue, and combined. Values are unitless multipliers where 1.0 = no load. Sourced from load_factor_metrics observable gauge.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 16
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_load_factor_metrics{exported_instance=~\"$node\", metric=\"load_factor\"}",
+          "legendFormat": "Combined Load Factor"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_load_factor_metrics{exported_instance=~\"$node\", metric=\"load_factor_server\"}",
+          "legendFormat": "Server"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_load_factor_metrics{exported_instance=~\"$node\", metric=\"load_factor_fee_escalation\"}",
+          "legendFormat": "Fee Escalation"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_load_factor_metrics{exported_instance=~\"$node\", metric=\"load_factor_fee_queue\"}",
+          "legendFormat": "Fee Queue"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "short",
+          "custom": {
+            "drawStyle": "line",
+            "lineWidth": 2,
+            "fillOpacity": 5
+          },
+          "color": {
+            "mode": "palette-classic"
+          },
+          "thresholds": {
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              },
+              {
+                "color": "yellow",
+                "value": 2
+              },
+              {
+                "color": "red",
+                "value": 10
+              }
+            ]
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Load Factor Components",
+      "description": "Individual load factor contributors: local server load, network load, and cluster load. Only differ from 1.0 under load conditions. Sourced from load_factor_metrics observable gauge.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 16
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_load_factor_metrics{exported_instance=~\"$node\", metric=\"load_factor_local\"}",
+          "legendFormat": "Local"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_load_factor_metrics{exported_instance=~\"$node\", metric=\"load_factor_net\"}",
+          "legendFormat": "Network"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_load_factor_metrics{exported_instance=~\"$node\", metric=\"load_factor_cluster\"}",
+          "legendFormat": "Cluster"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "short",
+          "custom": {
+            "drawStyle": "line",
+            "lineWidth": 2,
+            "fillOpacity": 5
+          },
+          "color": {
+            "mode": "palette-classic"
+          }
+        },
+        "overrides": []
+      }
+    }
+  ],
+  "schemaVersion": 39,
+  "tags": ["rippled", "otel", "fee-market"],
+  "templating": {
+    "list": [
+      {
+        "name": "node",
+        "label": "Node",
+        "description": "Filter by rippled node (service.instance.id)",
+        "type": "query",
+        "query": "label_values(exported_instance)",
+        "datasource": {
+          "type": "prometheus",
+          "uid": "prometheus"
+        },
+        "includeAll": true,
+        "allValue": ".*",
+        "current": {
+          "text": "All",
+          "value": "$__all"
+        },
+        "multi": true,
+        "refresh": 2,
+        "sort": 1
+      }
+    ]
+  },
+  "time": {
+    "from": "now-1h",
+    "to": "now"
+  },
+  "timepicker": {},
+  "timezone": "browser",
+  "title": "rippled - Fee Market & TxQ",
+  "uid": "rippled-fee-market",
+  "version": 1
+}

docker/telemetry/grafana/dashboards/rippled-job-queue.json

@@ -0,0 +1,365 @@
+{
+  "annotations": {
+    "list": []
+  },
+  "description": "Job queue analysis: per-job-type throughput rates, queue wait times, and execution times. Sourced from OTel MetricsRegistry synchronous counters and histograms (Phase 9).",
+  "editable": true,
+  "fiscalYearStartMonth": 0,
+  "graphTooltip": 1,
+  "id": null,
+  "links": [],
+  "panels": [
+    {
+      "title": "Job Throughput Rate (per second)",
+      "description": "Rate of jobs queued, started, and finished across all job types. Computed as rate() over the OTel counter values. High queue rates with low finish rates indicate backlog.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 24,
+        "x": 0,
+        "y": 0
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "sum(rate(rippled_job_queued_total{exported_instance=~\"$node\"}[5m]))",
+          "legendFormat": "Queued/s"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "sum(rate(rippled_job_started_total{exported_instance=~\"$node\"}[5m]))",
+          "legendFormat": "Started/s"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "sum(rate(rippled_job_finished_total{exported_instance=~\"$node\"}[5m]))",
+          "legendFormat": "Finished/s"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "ops",
+          "custom": {
+            "drawStyle": "line",
+            "lineWidth": 2,
+            "fillOpacity": 10
+          },
+          "color": {
+            "mode": "palette-classic"
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Per-Job-Type Queued Rate",
+      "description": "Rate of jobs queued broken down by job_type label. Identifies which job types contribute most to queue activity.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 8
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        },
+        "legend": {
+          "displayMode": "table",
+          "placement": "right",
+          "calcs": ["mean", "max"]
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "topk(10, rate(rippled_job_queued_total{exported_instance=~\"$node\"}[5m]))",
+          "legendFormat": "{{job_type}}"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "ops",
+          "custom": {
+            "drawStyle": "line",
+            "lineWidth": 1,
+            "fillOpacity": 5
+          },
+          "color": {
+            "mode": "palette-classic"
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Per-Job-Type Finish Rate",
+      "description": "Rate of jobs completing broken down by job_type. Compare with queued rate to identify backlog per type.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 8
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        },
+        "legend": {
+          "displayMode": "table",
+          "placement": "right",
+          "calcs": ["mean", "max"]
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "topk(10, rate(rippled_job_finished_total{exported_instance=~\"$node\"}[5m]))",
+          "legendFormat": "{{job_type}}"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "ops",
+          "custom": {
+            "drawStyle": "line",
+            "lineWidth": 1,
+            "fillOpacity": 5
+          },
+          "color": {
+            "mode": "palette-classic"
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Job Queue Wait Time (p50, p95, p99)",
+      "description": "Histogram quantiles for time jobs spend waiting in the queue before execution starts. High values indicate thread pool saturation.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 16
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "histogram_quantile(0.50, sum by (le) (rate(rippled_job_queued_duration_us_bucket{exported_instance=~\"$node\"}[5m])))",
+          "legendFormat": "p50"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "histogram_quantile(0.95, sum by (le) (rate(rippled_job_queued_duration_us_bucket{exported_instance=~\"$node\"}[5m])))",
+          "legendFormat": "p95"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "histogram_quantile(0.99, sum by (le) (rate(rippled_job_queued_duration_us_bucket{exported_instance=~\"$node\"}[5m])))",
+          "legendFormat": "p99"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "us",
+          "custom": {
+            "drawStyle": "line",
+            "lineWidth": 2,
+            "fillOpacity": 5
+          },
+          "color": {
+            "mode": "palette-classic"
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Job Execution Time (p50, p95, p99)",
+      "description": "Histogram quantiles for actual job execution time. High values indicate expensive operations or resource contention.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 16
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "histogram_quantile(0.50, sum by (le) (rate(rippled_job_running_duration_us_bucket{exported_instance=~\"$node\"}[5m])))",
+          "legendFormat": "p50"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "histogram_quantile(0.95, sum by (le) (rate(rippled_job_running_duration_us_bucket{exported_instance=~\"$node\"}[5m])))",
+          "legendFormat": "p95"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "histogram_quantile(0.99, sum by (le) (rate(rippled_job_running_duration_us_bucket{exported_instance=~\"$node\"}[5m])))",
+          "legendFormat": "p99"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "us",
+          "custom": {
+            "drawStyle": "line",
+            "lineWidth": 2,
+            "fillOpacity": 5
+          },
+          "color": {
+            "mode": "palette-classic"
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Per-Job-Type Execution Time (p95)",
+      "description": "95th percentile execution time broken down by job type. Identifies the slowest job types.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 24,
+        "x": 0,
+        "y": 24
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        },
+        "legend": {
+          "displayMode": "table",
+          "placement": "right",
+          "calcs": ["mean", "max"]
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "topk(10, histogram_quantile(0.95, sum by (le, job_type) (rate(rippled_job_running_duration_us_bucket{exported_instance=~\"$node\"}[5m]))))",
+          "legendFormat": "{{job_type}}"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "us",
+          "custom": {
+            "drawStyle": "line",
+            "lineWidth": 1,
+            "fillOpacity": 5
+          },
+          "color": {
+            "mode": "palette-classic"
+          }
+        },
+        "overrides": []
+      }
+    }
+  ],
+  "schemaVersion": 39,
+  "tags": ["rippled", "otel", "job-queue"],
+  "templating": {
+    "list": [
+      {
+        "name": "node",
+        "label": "Node",
+        "description": "Filter by rippled node (service.instance.id)",
+        "type": "query",
+        "query": "label_values(exported_instance)",
+        "datasource": {
+          "type": "prometheus",
+          "uid": "prometheus"
+        },
+        "includeAll": true,
+        "allValue": ".*",
+        "current": {
+          "text": "All",
+          "value": "$__all"
+        },
+        "multi": true,
+        "refresh": 2,
+        "sort": 1
+      },
+      {
+        "name": "job_type",
+        "label": "Job Type",
+        "description": "Filter by job type",
+        "type": "query",
+        "query": "label_values(rippled_job_queued_total, job_type)",
+        "datasource": {
+          "type": "prometheus",
+          "uid": "prometheus"
+        },
+        "includeAll": true,
+        "allValue": ".*",
+        "current": {
+          "text": "All",
+          "value": "$__all"
+        },
+        "multi": true,
+        "refresh": 2,
+        "sort": 1
+      }
+    ]
+  },
+  "time": {
+    "from": "now-1h",
+    "to": "now"
+  },
+  "timepicker": {},
+  "timezone": "browser",
+  "title": "rippled - Job Queue Analysis",
+  "uid": "rippled-job-queue",
+  "version": 1
+}

docker/telemetry/grafana/dashboards/rippled-rpc-perf.json

@@ -0,0 +1,374 @@
+{
+  "annotations": {
+    "list": []
+  },
+  "description": "Per-RPC-method performance: call rates, error rates, and latency distributions. Sourced from OTel MetricsRegistry synchronous counters and histograms (Phase 9).",
+  "editable": true,
+  "fiscalYearStartMonth": 0,
+  "graphTooltip": 1,
+  "id": null,
+  "links": [],
+  "panels": [
+    {
+      "title": "RPC Call Rate (all methods)",
+      "description": "Aggregate rate of RPC calls started, finished, and errored across all methods. Computed as rate() over OTel counters.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 24,
+        "x": 0,
+        "y": 0
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "sum(rate(rippled_rpc_method_started_total{exported_instance=~\"$node\"}[5m]))",
+          "legendFormat": "Started/s"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "sum(rate(rippled_rpc_method_finished_total{exported_instance=~\"$node\"}[5m]))",
+          "legendFormat": "Finished/s"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "sum(rate(rippled_rpc_method_errored_total{exported_instance=~\"$node\"}[5m]))",
+          "legendFormat": "Errored/s"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "ops",
+          "custom": {
+            "drawStyle": "line",
+            "lineWidth": 2,
+            "fillOpacity": 10
+          },
+          "color": {
+            "mode": "palette-classic"
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Per-Method Call Rate (Top 10)",
+      "description": "Per-method RPC call rate, showing the 10 most active methods. Useful for identifying hot paths.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 8
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        },
+        "legend": {
+          "displayMode": "table",
+          "placement": "right",
+          "calcs": ["mean", "max"]
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "topk(10, rate(rippled_rpc_method_started_total{exported_instance=~\"$node\"}[5m]))",
+          "legendFormat": "{{method}}"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "ops",
+          "custom": {
+            "drawStyle": "line",
+            "lineWidth": 1,
+            "fillOpacity": 5
+          },
+          "color": {
+            "mode": "palette-classic"
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Per-Method Error Rate (Top 10)",
+      "description": "Per-method RPC error rate. Non-zero values warrant investigation. Common culprits: invalid parameters, resource exhaustion.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 8
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        },
+        "legend": {
+          "displayMode": "table",
+          "placement": "right",
+          "calcs": ["mean", "max"]
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "topk(10, rate(rippled_rpc_method_errored_total{exported_instance=~\"$node\"}[5m]))",
+          "legendFormat": "{{method}}"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "ops",
+          "custom": {
+            "drawStyle": "line",
+            "lineWidth": 1,
+            "fillOpacity": 5
+          },
+          "color": {
+            "mode": "palette-classic"
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "RPC Latency (p50, p95, p99) - All Methods",
+      "description": "Histogram quantiles for RPC execution time across all methods. Sourced from rpc_method_duration_us histogram.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 16
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "histogram_quantile(0.50, sum by (le) (rate(rippled_rpc_method_duration_us_bucket{exported_instance=~\"$node\"}[5m])))",
+          "legendFormat": "p50"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "histogram_quantile(0.95, sum by (le) (rate(rippled_rpc_method_duration_us_bucket{exported_instance=~\"$node\"}[5m])))",
+          "legendFormat": "p95"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "histogram_quantile(0.99, sum by (le) (rate(rippled_rpc_method_duration_us_bucket{exported_instance=~\"$node\"}[5m])))",
+          "legendFormat": "p99"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "us",
+          "custom": {
+            "drawStyle": "line",
+            "lineWidth": 2,
+            "fillOpacity": 5
+          },
+          "color": {
+            "mode": "palette-classic"
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Per-Method Latency p95 (Top 10 Slowest)",
+      "description": "95th percentile execution time per method. Identifies the slowest RPC endpoints.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 16
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        },
+        "legend": {
+          "displayMode": "table",
+          "placement": "right",
+          "calcs": ["mean", "max"]
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "topk(10, histogram_quantile(0.95, sum by (le, method) (rate(rippled_rpc_method_duration_us_bucket{exported_instance=~\"$node\"}[5m]))))",
+          "legendFormat": "{{method}}"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "us",
+          "custom": {
+            "drawStyle": "line",
+            "lineWidth": 1,
+            "fillOpacity": 5
+          },
+          "color": {
+            "mode": "palette-classic"
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "RPC Error Ratio by Method",
+      "description": "Error ratio (errors / total started) per method. Values above 0.05 (5%) warrant investigation.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 24,
+        "x": 0,
+        "y": 24
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        },
+        "legend": {
+          "displayMode": "table",
+          "placement": "right",
+          "calcs": ["mean", "max"]
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "topk(10, rate(rippled_rpc_method_errored_total{exported_instance=~\"$node\"}[5m]) / (rate(rippled_rpc_method_started_total{exported_instance=~\"$node\"}[5m]) > 0))",
+          "legendFormat": "{{method}}"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "percentunit",
+          "min": 0,
+          "max": 1,
+          "custom": {
+            "drawStyle": "line",
+            "lineWidth": 1,
+            "fillOpacity": 5
+          },
+          "color": {
+            "mode": "palette-classic"
+          },
+          "thresholds": {
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              },
+              {
+                "color": "yellow",
+                "value": 0.05
+              },
+              {
+                "color": "red",
+                "value": 0.25
+              }
+            ]
+          }
+        },
+        "overrides": []
+      }
+    }
+  ],
+  "schemaVersion": 39,
+  "tags": ["rippled", "otel", "rpc"],
+  "templating": {
+    "list": [
+      {
+        "name": "node",
+        "label": "Node",
+        "description": "Filter by rippled node (service.instance.id)",
+        "type": "query",
+        "query": "label_values(exported_instance)",
+        "datasource": {
+          "type": "prometheus",
+          "uid": "prometheus"
+        },
+        "includeAll": true,
+        "allValue": ".*",
+        "current": {
+          "text": "All",
+          "value": "$__all"
+        },
+        "multi": true,
+        "refresh": 2,
+        "sort": 1
+      },
+      {
+        "name": "method",
+        "label": "RPC Method",
+        "description": "Filter by RPC method",
+        "type": "query",
+        "query": "label_values(rippled_rpc_method_started_total, method)",
+        "datasource": {
+          "type": "prometheus",
+          "uid": "prometheus"
+        },
+        "includeAll": true,
+        "allValue": ".*",
+        "current": {
+          "text": "All",
+          "value": "$__all"
+        },
+        "multi": true,
+        "refresh": 2,
+        "sort": 1
+      }
+    ]
+  },
+  "time": {
+    "from": "now-1h",
+    "to": "now"
+  },
+  "timepicker": {},
+  "timezone": "browser",
+  "title": "rippled - RPC Performance (OTel)",
+  "uid": "rippled-rpc-perf",
+  "version": 1
+}

docker/telemetry/grafana/dashboards/rpc-performance.json

@@ -0,0 +1,376 @@
+{
+  "annotations": {
+    "list": []
+  },
+  "editable": true,
+  "fiscalYearStartMonth": 0,
+  "graphTooltip": 1,
+  "id": null,
+  "links": [],
+  "panels": [
+    {
+      "title": "RPC Request Rate by Command",
+      "description": "Per-second rate of RPC command executions, broken down by command name (e.g. server_info, submit). Calculated as rate(traces_span_metrics_calls_total{span_name=~\"rpc.command.*\"}) over a 5m window, grouped by the xrpl.rpc.command span attribute.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 0
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "sum by (xrpl_rpc_command) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", xrpl_rpc_command=~\"$command\", span_name=~\"rpc.command.*\"}[5m]))",
+          "legendFormat": "{{xrpl_rpc_command}}"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "reqps",
+          "custom": {
+            "axisLabel": "Requests / Sec",
+            "spanNulls": true,
+            "insertNulls": false,
+            "showPoints": "auto",
+            "pointSize": 3
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "RPC Latency p95 by Command",
+      "description": "95th percentile response time for each RPC command. Computed from the spanmetrics duration histogram using histogram_quantile(0.95) over rpc.command.* spans, grouped by xrpl.rpc.command. High values indicate slow commands that may need optimization.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 0
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "histogram_quantile(0.95, sum by (le, xrpl_rpc_command) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", xrpl_rpc_command=~\"$command\", span_name=~\"rpc.command.*\"}[5m])))",
+          "legendFormat": "P95 {{xrpl_rpc_command}}"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "ms",
+          "custom": {
+            "axisLabel": "Latency (ms)",
+            "spanNulls": true,
+            "insertNulls": false,
+            "showPoints": "auto",
+            "pointSize": 3
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "RPC Error Rate",
+      "description": "Percentage of RPC commands that completed with an error status, per command. Calculated as (error calls / total calls) * 100, where errors have status_code=STATUS_CODE_ERROR. Thresholds: green < 1%, yellow 1-5%, red > 5%.",
+      "type": "bargauge",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 8
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "sum by (xrpl_rpc_command) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", xrpl_rpc_command=~\"$command\", span_name=~\"rpc.command.*\", status_code=\"STATUS_CODE_ERROR\"}[5m])) / sum by (xrpl_rpc_command) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", xrpl_rpc_command=~\"$command\", span_name=~\"rpc.command.*\"}[5m])) * 100",
+          "legendFormat": "{{xrpl_rpc_command}}"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "percent",
+          "thresholds": {
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              },
+              {
+                "color": "yellow",
+                "value": 1
+              },
+              {
+                "color": "red",
+                "value": 5
+              }
+            ]
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "RPC Latency Heatmap",
+      "description": "Distribution of RPC command response times across histogram buckets. Shows the density of requests at each latency level over time. Each cell represents the count of requests that fell into that duration bucket in a 5m window. Useful for spotting bimodal latency patterns.",
+      "type": "heatmap",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 8
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        },
+        "yAxis": {
+          "axisLabel": "Duration (ms)"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "sum(increase(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", xrpl_rpc_command=~\"$command\", span_name=~\"rpc.command.*\"}[5m])) by (le)",
+          "legendFormat": "{{le}}",
+          "format": "heatmap"
+        }
+      ]
+    },
+    {
+      "title": "Overall RPC Throughput",
+      "description": "Aggregate RPC throughput showing two layers of the request pipeline. rpc.request is the outer HTTP handler (ServerHandler.cpp:271) that accepts incoming connections. rpc.process is the inner processing layer (ServerHandler.cpp:573) that parses and dispatches. A gap between the two indicates requests being queued or rejected before processing.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 16
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "sum(rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", xrpl_rpc_command=~\"$command\", span_name=\"rpc.request\"}[5m]))",
+          "legendFormat": "rpc.request / Sec"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "sum(rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", xrpl_rpc_command=~\"$command\", span_name=\"rpc.process\"}[5m]))",
+          "legendFormat": "rpc.process / Sec"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "reqps",
+          "custom": {
+            "axisLabel": "Requests / Sec",
+            "spanNulls": true,
+            "insertNulls": false,
+            "showPoints": "auto",
+            "pointSize": 3
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "RPC Success vs Error",
+      "description": "Aggregate rate of successful vs failed RPC commands across all command types. Success = status_code UNSET (OpenTelemetry default for OK spans). Error = status_code STATUS_CODE_ERROR. A sustained error rate warrants investigation via per-command breakdown above.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 16
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "sum(rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", xrpl_rpc_command=~\"$command\", span_name=~\"rpc.command.*\", status_code=\"STATUS_CODE_UNSET\"}[5m]))",
+          "legendFormat": "Success"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "sum(rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", xrpl_rpc_command=~\"$command\", span_name=~\"rpc.command.*\", status_code=\"STATUS_CODE_ERROR\"}[5m]))",
+          "legendFormat": "Error"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "ops",
+          "custom": {
+            "axisLabel": "Commands / Sec",
+            "spanNulls": true,
+            "insertNulls": false,
+            "showPoints": "auto",
+            "pointSize": 3
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Top Commands by Volume",
+      "description": "Top 10 most frequently called RPC commands by total invocation count over the last 5 minutes. Uses topk(10, increase(calls_total)) to rank commands. Helps identify the hottest API endpoints driving load on the node.",
+      "type": "bargauge",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 24
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "topk(10, sum by (xrpl_rpc_command) (increase(traces_span_metrics_calls_total{exported_instance=~\"$node\", xrpl_rpc_command=~\"$command\", span_name=~\"rpc.command.*\"}[5m])))",
+          "legendFormat": "{{xrpl_rpc_command}}"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "short"
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "WebSocket Message Rate",
+      "description": "Rate of incoming WebSocket RPC messages processed by the server. Sourced from the rpc.ws_message span (ServerHandler.cpp:384). Only active when clients connect via WebSocket instead of HTTP. Zero is normal if only HTTP RPC is in use.",
+      "type": "stat",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 24
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "sum(rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", xrpl_rpc_command=~\"$command\", span_name=\"rpc.ws_message\"}[5m]))",
+          "legendFormat": "WS Messages / Sec"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "ops"
+        },
+        "overrides": []
+      }
+    }
+  ],
+  "schemaVersion": 39,
+  "tags": ["rippled", "rpc", "telemetry"],
+  "templating": {
+    "list": [
+      {
+        "name": "node",
+        "label": "Node",
+        "description": "Filter by rippled node (service.instance.id \u2014 e.g. Node-1)",
+        "type": "query",
+        "query": "label_values(traces_span_metrics_calls_total, exported_instance)",
+        "datasource": {
+          "type": "prometheus",
+          "uid": "prometheus"
+        },
+        "includeAll": true,
+        "allValue": ".*",
+        "current": {
+          "text": "All",
+          "value": "$__all"
+        },
+        "multi": true,
+        "refresh": 2,
+        "sort": 1
+      },
+      {
+        "name": "command",
+        "label": "RPC Command",
+        "description": "Filter by RPC command name (e.g., server_info, submit)",
+        "type": "query",
+        "query": "label_values(traces_span_metrics_calls_total{span_name=~\"rpc.command.*\"}, xrpl_rpc_command)",
+        "datasource": {
+          "type": "prometheus",
+          "uid": "prometheus"
+        },
+        "includeAll": true,
+        "allValue": ".*",
+        "current": {
+          "text": "All",
+          "value": "$__all"
+        },
+        "multi": true,
+        "refresh": 2,
+        "sort": 1
+      }
+    ]
+  },
+  "time": {
+    "from": "now-1h",
+    "to": "now"
+  },
+  "title": "RPC Performance",
+  "uid": "rippled-rpc-perf"
+}

docker/telemetry/grafana/dashboards/system-ledger-data-sync.json

@@ -0,0 +1,527 @@
+{
+  "annotations": {
+    "list": []
+  },
+  "description": "Ledger data exchange and object fetch traffic from beast::insight System Metrics. Covers ledger sync, node data retrieval, and transaction set exchange. Requires [insight] server=otel in rippled config.",
+  "editable": true,
+  "fiscalYearStartMonth": 0,
+  "graphTooltip": 1,
+  "id": null,
+  "links": [],
+  "panels": [
+    {
+      "title": "Ledger Data Exchange (Bytes In)",
+      "description": "Inbound bytes for ledger data sub-categories. 'ledger_data' = aggregated ledger data, sub-types include Transaction_Set_candidate (proposed tx sets), Transaction_Node (tx tree nodes), and Account_State_Node (state tree nodes). High Account_State_Node traffic indicates state sync; high Transaction_Set_candidate indicates consensus catch-up. Sourced from TrafficCount.h ledger_data_* categories.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 0
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_ledger_data_get_Bytes_In{exported_instance=~\"$node\"}",
+          "legendFormat": "Ledger Data Get"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_ledger_data_share_Bytes_In{exported_instance=~\"$node\"}",
+          "legendFormat": "Ledger Data Share"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_ledger_data_Transaction_Set_candidate_get_Bytes_In{exported_instance=~\"$node\"}",
+          "legendFormat": "TX Set Candidate Get"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_ledger_data_Transaction_Set_candidate_share_Bytes_In{exported_instance=~\"$node\"}",
+          "legendFormat": "TX Set Candidate Share"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_ledger_data_Transaction_Node_get_Bytes_In{exported_instance=~\"$node\"}",
+          "legendFormat": "TX Node Get"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_ledger_data_Transaction_Node_share_Bytes_In{exported_instance=~\"$node\"}",
+          "legendFormat": "TX Node Share"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_ledger_data_Account_State_Node_get_Bytes_In{exported_instance=~\"$node\"}",
+          "legendFormat": "Account State Node Get"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_ledger_data_Account_State_Node_share_Bytes_In{exported_instance=~\"$node\"}",
+          "legendFormat": "Account State Node Share"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "decbytes",
+          "custom": {
+            "axisLabel": "Bytes In",
+            "spanNulls": true,
+            "insertNulls": false,
+            "showPoints": "auto",
+            "pointSize": 3
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Ledger Share/Get Traffic (Bytes)",
+      "description": "Legacy ledger share and get traffic by sub-type. These are the older ledger fetch protocol categories (as opposed to ledger_data_* which is the newer protocol). Sub-types: Transaction_Set_candidate, Transaction_node, Account_State_node, plus aggregate ledger_share and ledger_get. Sourced from TrafficCount.h ledger_* categories.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 0
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_ledger_share_Bytes_In{exported_instance=~\"$node\"}",
+          "legendFormat": "Ledger Share In"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_ledger_get_Bytes_In{exported_instance=~\"$node\"}",
+          "legendFormat": "Ledger Get In"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_ledger_Transaction_Set_candidate_share_Bytes_In{exported_instance=~\"$node\"}",
+          "legendFormat": "TX Set Candidate Share"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_ledger_Transaction_Set_candidate_get_Bytes_In{exported_instance=~\"$node\"}",
+          "legendFormat": "TX Set Candidate Get"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_ledger_Transaction_node_share_Bytes_In{exported_instance=~\"$node\"}",
+          "legendFormat": "TX Node Share"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_ledger_Transaction_node_get_Bytes_In{exported_instance=~\"$node\"}",
+          "legendFormat": "TX Node Get"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_ledger_Account_State_node_share_Bytes_In{exported_instance=~\"$node\"}",
+          "legendFormat": "Account State Share"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_ledger_Account_State_node_get_Bytes_In{exported_instance=~\"$node\"}",
+          "legendFormat": "Account State Get"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "decbytes",
+          "custom": {
+            "axisLabel": "Bytes In",
+            "spanNulls": true,
+            "insertNulls": false,
+            "showPoints": "auto",
+            "pointSize": 3
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "GetObject Traffic by Type (Bytes In)",
+      "description": "Object fetch traffic by object type. GetObject is the protocol for fetching specific SHAMap nodes. Types: Ledger (full ledger headers), Transaction (individual txs), Transaction_node (tx tree nodes), Account_State_node (state tree nodes), CAS (Content Addressable Storage objects), Fetch_Pack (batch fetch during catch-up), Transactions (bulk tx fetch). High Fetch_Pack traffic indicates a node is catching up. Sourced from TrafficCount.h getobject_* categories.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 8
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_getobject_Ledger_get_Bytes_In{exported_instance=~\"$node\"}",
+          "legendFormat": "Ledger Get"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_getobject_Ledger_share_Bytes_In{exported_instance=~\"$node\"}",
+          "legendFormat": "Ledger Share"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_getobject_Transaction_get_Bytes_In{exported_instance=~\"$node\"}",
+          "legendFormat": "Transaction Get"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_getobject_Transaction_share_Bytes_In{exported_instance=~\"$node\"}",
+          "legendFormat": "Transaction Share"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_getobject_Transaction_node_get_Bytes_In{exported_instance=~\"$node\"}",
+          "legendFormat": "TX Node Get"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_getobject_Transaction_node_share_Bytes_In{exported_instance=~\"$node\"}",
+          "legendFormat": "TX Node Share"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_getobject_Account_State_node_get_Bytes_In{exported_instance=~\"$node\"}",
+          "legendFormat": "Account State Get"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_getobject_Account_State_node_share_Bytes_In{exported_instance=~\"$node\"}",
+          "legendFormat": "Account State Share"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "decbytes",
+          "custom": {
+            "axisLabel": "Bytes In",
+            "spanNulls": true,
+            "insertNulls": false,
+            "showPoints": "auto",
+            "pointSize": 3
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "GetObject Aggregate & Special Types (Bytes In)",
+      "description": "Aggregate getobject traffic plus special categories: CAS (Content Addressable Storage) for SHAMap node fetch, Fetch_Pack for bulk batch downloads during catch-up, Transactions for bulk tx fetch, and the aggregate getobject_get/getobject_share totals. Sourced from TrafficCount.h getobject_* categories.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 8
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_getobject_CAS_get_Bytes_In{exported_instance=~\"$node\"}",
+          "legendFormat": "CAS Get"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_getobject_CAS_share_Bytes_In{exported_instance=~\"$node\"}",
+          "legendFormat": "CAS Share"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_getobject_Fetch_Pack_share_Bytes_In{exported_instance=~\"$node\"}",
+          "legendFormat": "Fetch Pack Share"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_getobject_Fetch_Pack_get_Bytes_In{exported_instance=~\"$node\"}",
+          "legendFormat": "Fetch Pack Get"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_getobject_Transactions_get_Bytes_In{exported_instance=~\"$node\"}",
+          "legendFormat": "Transactions Get"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_getobject_get_Bytes_In{exported_instance=~\"$node\"}",
+          "legendFormat": "Aggregate Get"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_getobject_share_Bytes_In{exported_instance=~\"$node\"}",
+          "legendFormat": "Aggregate Share"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "decbytes",
+          "custom": {
+            "axisLabel": "Bytes In",
+            "spanNulls": true,
+            "insertNulls": false,
+            "showPoints": "auto",
+            "pointSize": 3
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "GetObject Messages by Type",
+      "description": "Message counts for object fetch operations. Shows how many individual fetch requests and responses are exchanged per type. High message counts with low byte counts indicate small object fetches; the inverse indicates large batch transfers. Sourced from TrafficCount.h getobject_* categories.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 16
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_getobject_Ledger_get_Messages_In{exported_instance=~\"$node\"}",
+          "legendFormat": "Ledger Get"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_getobject_Transaction_get_Messages_In{exported_instance=~\"$node\"}",
+          "legendFormat": "Transaction Get"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_getobject_Transaction_node_get_Messages_In{exported_instance=~\"$node\"}",
+          "legendFormat": "TX Node Get"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_getobject_Account_State_node_get_Messages_In{exported_instance=~\"$node\"}",
+          "legendFormat": "Account State Get"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_getobject_CAS_get_Messages_In{exported_instance=~\"$node\"}",
+          "legendFormat": "CAS Get"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_getobject_Fetch_Pack_get_Messages_In{exported_instance=~\"$node\"}",
+          "legendFormat": "Fetch Pack Get"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_getobject_Transactions_get_Messages_In{exported_instance=~\"$node\"}",
+          "legendFormat": "Transactions Get"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "short",
+          "custom": {
+            "axisLabel": "Messages In",
+            "spanNulls": true,
+            "insertNulls": false,
+            "showPoints": "auto",
+            "pointSize": 3
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Overlay Traffic Heatmap (All Categories, Bytes In)",
+      "description": "Bar gauge showing all overlay traffic categories ranked by inbound bytes. Provides a complete at-a-glance view of which protocol message types consume the most bandwidth across all 57+ traffic categories. Sourced from all TrafficCount.h categories via wildcard match.",
+      "type": "bargauge",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 16
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        },
+        "displayMode": "gradient",
+        "orientation": "horizontal",
+        "reduceOptions": {
+          "calcs": ["lastNotNull"],
+          "fields": "",
+          "values": false
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "topk(20, {exported_instance=~\"$node\", __name__=~\"rippled_.*_Bytes_In\", __name__!~\"rippled_total_.*\"})",
+          "legendFormat": "{{__name__}}"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "decbytes",
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              },
+              {
+                "color": "yellow",
+                "value": 1048576
+              },
+              {
+                "color": "red",
+                "value": 104857600
+              }
+            ]
+          }
+        },
+        "overrides": []
+      }
+    }
+  ],
+  "schemaVersion": 39,
+  "tags": ["rippled", "statsd", "ledger", "sync", "telemetry"],
+  "templating": {
+    "list": [
+      {
+        "name": "node",
+        "label": "Node",
+        "description": "Filter by rippled node (service.instance.id)",
+        "type": "query",
+        "query": "label_values(exported_instance)",
+        "datasource": {
+          "type": "prometheus",
+          "uid": "prometheus"
+        },
+        "includeAll": true,
+        "allValue": ".*",
+        "current": {
+          "text": "All",
+          "value": "$__all"
+        },
+        "multi": true,
+        "refresh": 2,
+        "sort": 1
+      }
+    ]
+  },
+  "time": {
+    "from": "now-1h",
+    "to": "now"
+  },
+  "title": "Ledger Data & Sync (System Metrics)",
+  "uid": "rippled-system-ledger-sync"
+}

docker/telemetry/grafana/dashboards/system-network-traffic.json

@@ -0,0 +1,692 @@
+{
+  "annotations": {
+    "list": []
+  },
+  "description": "Network traffic and peer metrics from beast::insight System Metrics. Requires [insight] server=otel in rippled config.",
+  "editable": true,
+  "fiscalYearStartMonth": 0,
+  "graphTooltip": 1,
+  "id": null,
+  "links": [],
+  "panels": [
+    {
+      "title": "Active Peers",
+      "description": "Number of active inbound and outbound peer connections. Sourced from Peer_Finder.Active_Inbound_Peers and Peer_Finder.Active_Outbound_Peers gauges (PeerfinderManager.cpp:214-215). A healthy mainnet node typically has 10-21 outbound and 0-85 inbound peers depending on configuration.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 0
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_Peer_Finder_Active_Inbound_Peers{exported_instance=~\"$node\"}",
+          "legendFormat": "Inbound Peers"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_Peer_Finder_Active_Outbound_Peers{exported_instance=~\"$node\"}",
+          "legendFormat": "Outbound Peers"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "short",
+          "custom": {
+            "axisLabel": "Peers",
+            "spanNulls": true,
+            "insertNulls": false,
+            "showPoints": "auto",
+            "pointSize": 3
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Peer Disconnects",
+      "description": "Cumulative count of peer disconnections. Sourced from the Overlay.Peer_Disconnects gauge (OverlayImpl.h:557). A rising trend indicates network instability, aggressive peer management, or resource exhaustion causing connection drops.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 0
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_Overlay_Peer_Disconnects{exported_instance=~\"$node\"}",
+          "legendFormat": "Disconnects"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "short",
+          "custom": {
+            "axisLabel": "Disconnects",
+            "spanNulls": true,
+            "insertNulls": false,
+            "showPoints": "auto",
+            "pointSize": 3
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Total Network Bytes",
+      "description": "Total bytes sent and received across all peer connections. Sourced from the total.Bytes_In and total.Bytes_Out traffic category gauges (OverlayImpl.h:535-548). Provides a high-level view of network bandwidth consumption.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 8
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_total_Bytes_In{exported_instance=~\"$node\"}",
+          "legendFormat": "Bytes In"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_total_Bytes_Out{exported_instance=~\"$node\"}",
+          "legendFormat": "Bytes Out"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "decbytes",
+          "custom": {
+            "axisLabel": "Bytes",
+            "spanNulls": true,
+            "insertNulls": false,
+            "showPoints": "auto",
+            "pointSize": 3
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Total Network Messages",
+      "description": "Total messages sent and received across all peer connections. Sourced from the total.Messages_In and total.Messages_Out traffic category gauges (OverlayImpl.h:535-548). Shows the overall message throughput of the overlay network.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 8
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_total_Messages_In{exported_instance=~\"$node\"}",
+          "legendFormat": "Messages In"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_total_Messages_Out{exported_instance=~\"$node\"}",
+          "legendFormat": "Messages Out"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "short",
+          "custom": {
+            "axisLabel": "Messages",
+            "spanNulls": true,
+            "insertNulls": false,
+            "showPoints": "auto",
+            "pointSize": 3
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Transaction Traffic",
+      "description": "Bytes and messages for transaction-related overlay traffic. Includes the transactions traffic category (OverlayImpl/TrafficCount.h). Spikes indicate high transaction volume on the network or transaction flooding.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 16
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_transactions_Messages_In{exported_instance=~\"$node\"}",
+          "legendFormat": "TX Messages In"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_transactions_Messages_Out{exported_instance=~\"$node\"}",
+          "legendFormat": "TX Messages Out"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_transactions_duplicate_Messages_In{exported_instance=~\"$node\"}",
+          "legendFormat": "TX Duplicate In"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "short",
+          "custom": {
+            "axisLabel": "Messages",
+            "spanNulls": true,
+            "insertNulls": false,
+            "showPoints": "auto",
+            "pointSize": 3
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Proposal Traffic",
+      "description": "Messages for consensus proposal overlay traffic. Includes proposals, proposals_untrusted, and proposals_duplicate categories (TrafficCount.h). High untrusted or duplicate counts may indicate UNL misconfiguration or network spam.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 16
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_proposals_Messages_In{exported_instance=~\"$node\"}",
+          "legendFormat": "Proposals In"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_proposals_Messages_Out{exported_instance=~\"$node\"}",
+          "legendFormat": "Proposals Out"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_proposals_untrusted_Messages_In{exported_instance=~\"$node\"}",
+          "legendFormat": "Untrusted In"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_proposals_duplicate_Messages_In{exported_instance=~\"$node\"}",
+          "legendFormat": "Duplicate In"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "short",
+          "custom": {
+            "axisLabel": "Messages",
+            "spanNulls": true,
+            "insertNulls": false,
+            "showPoints": "auto",
+            "pointSize": 3
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Validation Traffic",
+      "description": "Messages for validation overlay traffic. Includes validations, validations_untrusted, and validations_duplicate categories (TrafficCount.h). Monitoring trusted vs untrusted validation traffic helps detect UNL health issues.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 24
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_validations_Messages_In{exported_instance=~\"$node\"}",
+          "legendFormat": "Validations In"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_validations_Messages_Out{exported_instance=~\"$node\"}",
+          "legendFormat": "Validations Out"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_validations_untrusted_Messages_In{exported_instance=~\"$node\"}",
+          "legendFormat": "Untrusted In"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_validations_duplicate_Messages_In{exported_instance=~\"$node\"}",
+          "legendFormat": "Duplicate In"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "short",
+          "custom": {
+            "axisLabel": "Messages",
+            "spanNulls": true,
+            "insertNulls": false,
+            "showPoints": "auto",
+            "pointSize": 3
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Overlay Traffic by Category (Bytes In)",
+      "description": "Top traffic categories by inbound bytes. Includes all 57 overlay traffic categories from TrafficCount.h. Shows which protocol message types consume the most bandwidth. Categories include transactions, proposals, validations, ledger data, getobject, and overlay overhead.",
+      "type": "bargauge",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 24
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "topk(10, {exported_instance=~\"$node\", __name__=~\"rippled_.*_Bytes_In\", __name__!~\"rippled_total_.*\"})",
+          "legendFormat": "{{__name__}}"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "decbytes"
+        },
+        "overrides": [
+          {
+            "matcher": {
+              "id": "byName",
+              "options": "rippled_transactions_Bytes_In"
+            },
+            "properties": [
+              {
+                "id": "displayName",
+                "value": "Transactions"
+              }
+            ]
+          },
+          {
+            "matcher": {
+              "id": "byName",
+              "options": "rippled_proposals_Bytes_In"
+            },
+            "properties": [
+              {
+                "id": "displayName",
+                "value": "Proposals"
+              }
+            ]
+          },
+          {
+            "matcher": {
+              "id": "byName",
+              "options": "rippled_validations_Bytes_In"
+            },
+            "properties": [
+              {
+                "id": "displayName",
+                "value": "Validations"
+              }
+            ]
+          },
+          {
+            "matcher": {
+              "id": "byName",
+              "options": "rippled_overhead_Bytes_In"
+            },
+            "properties": [
+              {
+                "id": "displayName",
+                "value": "Overhead"
+              }
+            ]
+          },
+          {
+            "matcher": {
+              "id": "byName",
+              "options": "rippled_overhead_overlay_Bytes_In"
+            },
+            "properties": [
+              {
+                "id": "displayName",
+                "value": "Overhead Overlay"
+              }
+            ]
+          },
+          {
+            "matcher": {
+              "id": "byName",
+              "options": "rippled_ping_Bytes_In"
+            },
+            "properties": [
+              {
+                "id": "displayName",
+                "value": "Ping"
+              }
+            ]
+          },
+          {
+            "matcher": {
+              "id": "byName",
+              "options": "rippled_status_Bytes_In"
+            },
+            "properties": [
+              {
+                "id": "displayName",
+                "value": "Status"
+              }
+            ]
+          },
+          {
+            "matcher": {
+              "id": "byName",
+              "options": "rippled_getObject_Bytes_In"
+            },
+            "properties": [
+              {
+                "id": "displayName",
+                "value": "Get Object"
+              }
+            ]
+          },
+          {
+            "matcher": {
+              "id": "byName",
+              "options": "rippled_haveTxSet_Bytes_In"
+            },
+            "properties": [
+              {
+                "id": "displayName",
+                "value": "Have Tx Set"
+              }
+            ]
+          },
+          {
+            "matcher": {
+              "id": "byName",
+              "options": "rippled_ledgerData_Bytes_In"
+            },
+            "properties": [
+              {
+                "id": "displayName",
+                "value": "Ledger Data"
+              }
+            ]
+          },
+          {
+            "matcher": {
+              "id": "byName",
+              "options": "rippled_ledger_share_Bytes_In"
+            },
+            "properties": [
+              {
+                "id": "displayName",
+                "value": "Ledger Share"
+              }
+            ]
+          },
+          {
+            "matcher": {
+              "id": "byName",
+              "options": "rippled_ledger_data_get_Bytes_In"
+            },
+            "properties": [
+              {
+                "id": "displayName",
+                "value": "Ledger Data Get"
+              }
+            ]
+          },
+          {
+            "matcher": {
+              "id": "byName",
+              "options": "rippled_ledger_data_share_Bytes_In"
+            },
+            "properties": [
+              {
+                "id": "displayName",
+                "value": "Ledger Data Share"
+              }
+            ]
+          },
+          {
+            "matcher": {
+              "id": "byName",
+              "options": "rippled_ledger_data_Account_State_Node_get_Bytes_In"
+            },
+            "properties": [
+              {
+                "id": "displayName",
+                "value": "Account State Node Get"
+              }
+            ]
+          },
+          {
+            "matcher": {
+              "id": "byName",
+              "options": "rippled_ledger_data_Account_State_Node_share_Bytes_In"
+            },
+            "properties": [
+              {
+                "id": "displayName",
+                "value": "Account State Node Share"
+              }
+            ]
+          },
+          {
+            "matcher": {
+              "id": "byName",
+              "options": "rippled_ledger_data_Transaction_Node_get_Bytes_In"
+            },
+            "properties": [
+              {
+                "id": "displayName",
+                "value": "Transaction Node Get"
+              }
+            ]
+          },
+          {
+            "matcher": {
+              "id": "byName",
+              "options": "rippled_ledger_data_Transaction_Node_share_Bytes_In"
+            },
+            "properties": [
+              {
+                "id": "displayName",
+                "value": "Transaction Node Share"
+              }
+            ]
+          },
+          {
+            "matcher": {
+              "id": "byName",
+              "options": "rippled_ledger_data_Transaction_Set_candidate_get_Bytes_In"
+            },
+            "properties": [
+              {
+                "id": "displayName",
+                "value": "Tx Set Candidate Get"
+              }
+            ]
+          },
+          {
+            "matcher": {
+              "id": "byName",
+              "options": "rippled_ledger_Account_State_node_share_Bytes_In"
+            },
+            "properties": [
+              {
+                "id": "displayName",
+                "value": "Account State Node Share (Legacy)"
+              }
+            ]
+          },
+          {
+            "matcher": {
+              "id": "byName",
+              "options": "rippled_ledger_Transaction_Set_candidate_share_Bytes_In"
+            },
+            "properties": [
+              {
+                "id": "displayName",
+                "value": "Tx Set Candidate Share"
+              }
+            ]
+          },
+          {
+            "matcher": {
+              "id": "byName",
+              "options": "rippled_ledger_Transaction_node_share_Bytes_In"
+            },
+            "properties": [
+              {
+                "id": "displayName",
+                "value": "Transaction Node Share (Legacy)"
+              }
+            ]
+          },
+          {
+            "matcher": {
+              "id": "byName",
+              "options": "rippled_set_get_Bytes_In"
+            },
+            "properties": [
+              {
+                "id": "displayName",
+                "value": "Set Get"
+              }
+            ]
+          }
+        ]
+      }
+    }
+  ],
+  "schemaVersion": 39,
+  "tags": ["rippled", "statsd", "network", "telemetry"],
+  "templating": {
+    "list": [
+      {
+        "name": "node",
+        "label": "Node",
+        "description": "Filter by rippled node (service.instance.id)",
+        "type": "query",
+        "query": "label_values(exported_instance)",
+        "datasource": {
+          "type": "prometheus",
+          "uid": "prometheus"
+        },
+        "includeAll": true,
+        "allValue": ".*",
+        "current": {
+          "text": "All",
+          "value": "$__all"
+        },
+        "multi": true,
+        "refresh": 2,
+        "sort": 1
+      }
+    ]
+  },
+  "time": {
+    "from": "now-1h",
+    "to": "now"
+  },
+  "title": "Network Traffic (System Metrics)",
+  "uid": "rippled-system-network"
+}

docker/telemetry/grafana/dashboards/system-node-health.json

@@ -0,0 +1,744 @@
+{
+  "annotations": {
+    "list": []
+  },
+  "description": "Node health metrics from beast::insight System Metrics. Requires [insight] server=otel in rippled config.",
+  "editable": true,
+  "fiscalYearStartMonth": 0,
+  "graphTooltip": 1,
+  "id": null,
+  "links": [],
+  "panels": [
+    {
+      "title": "Validated Ledger Age",
+      "description": "Age of the most recently validated ledger in seconds. Sourced from the LedgerMaster.Validated_Ledger_Age gauge (LedgerMaster.h:373) which is updated every collection interval via the insight hook. Values above 20s indicate the node is falling behind the network.",
+      "type": "stat",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 0
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_LedgerMaster_Validated_Ledger_Age{exported_instance=~\"$node\"}",
+          "legendFormat": "Validated Age"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "s",
+          "thresholds": {
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              },
+              {
+                "color": "yellow",
+                "value": 10
+              },
+              {
+                "color": "red",
+                "value": 20
+              }
+            ]
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Published Ledger Age",
+      "description": "Age of the most recently published ledger in seconds. Sourced from the LedgerMaster.Published_Ledger_Age gauge (LedgerMaster.h:374). Published ledger age should track close to validated ledger age. A growing gap indicates publish pipeline backlog.",
+      "type": "stat",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 0
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_LedgerMaster_Published_Ledger_Age{exported_instance=~\"$node\"}",
+          "legendFormat": "Published Age"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "s",
+          "thresholds": {
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              },
+              {
+                "color": "yellow",
+                "value": 10
+              },
+              {
+                "color": "red",
+                "value": 20
+              }
+            ]
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Operating Mode Duration",
+      "description": "Cumulative time spent in each operating mode (Disconnected, Connected, Syncing, Tracking, Full). Sourced from State_Accounting.*_duration gauges (NetworkOPs.cpp:774-778). A healthy node should spend the vast majority of time in Full mode.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 8
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_State_Accounting_Full_duration{exported_instance=~\"$node\"}",
+          "legendFormat": "Full"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_State_Accounting_Tracking_duration{exported_instance=~\"$node\"}",
+          "legendFormat": "Tracking"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_State_Accounting_Syncing_duration{exported_instance=~\"$node\"}",
+          "legendFormat": "Syncing"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_State_Accounting_Connected_duration{exported_instance=~\"$node\"}",
+          "legendFormat": "Connected"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_State_Accounting_Disconnected_duration{exported_instance=~\"$node\"}",
+          "legendFormat": "Disconnected"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "s",
+          "custom": {
+            "axisLabel": "Duration (Sec)",
+            "spanNulls": true,
+            "insertNulls": false,
+            "showPoints": "auto",
+            "pointSize": 3
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Operating Mode Transitions",
+      "description": "Count of transitions into each operating mode. Sourced from State_Accounting.*_transitions gauges (NetworkOPs.cpp:780-786). Frequent transitions out of Full mode indicate instability. Transitions to Disconnected or Syncing warrant investigation.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 8
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_State_Accounting_Full_transitions{exported_instance=~\"$node\"}",
+          "legendFormat": "Full"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_State_Accounting_Tracking_transitions{exported_instance=~\"$node\"}",
+          "legendFormat": "Tracking"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_State_Accounting_Syncing_transitions{exported_instance=~\"$node\"}",
+          "legendFormat": "Syncing"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_State_Accounting_Connected_transitions{exported_instance=~\"$node\"}",
+          "legendFormat": "Connected"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_State_Accounting_Disconnected_transitions{exported_instance=~\"$node\"}",
+          "legendFormat": "Disconnected"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "short",
+          "custom": {
+            "axisLabel": "Transitions",
+            "spanNulls": true,
+            "insertNulls": false,
+            "showPoints": "auto",
+            "pointSize": 3
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "I/O Latency",
+      "description": "P95 and P50 of the I/O service loop latency in milliseconds. Sourced from the ios_latency event (Application.cpp:438) which measures how long it takes for the io_context to process a timer callback. Values above 10ms are logged; above 500ms trigger warnings. High values indicate thread pool saturation or blocking operations.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 16
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_ios_latency{exported_instance=~\"$node\", quantile=\"0.95\"}",
+          "legendFormat": "P95 I/O Latency"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_ios_latency{exported_instance=~\"$node\", quantile=\"0.5\"}",
+          "legendFormat": "P50 I/O Latency"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "ms",
+          "custom": {
+            "axisLabel": "Latency (ms)",
+            "spanNulls": true,
+            "insertNulls": false,
+            "showPoints": "auto",
+            "pointSize": 3
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Job Queue Depth",
+      "description": "Current number of jobs waiting in the job queue. Sourced from the job_count gauge (JobQueue.cpp:26). A sustained high value indicates the node cannot process work fast enough \u2014 common during ledger replay or heavy RPC load.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 16
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_job_count{exported_instance=~\"$node\"}",
+          "legendFormat": "Job Queue Depth"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "short",
+          "custom": {
+            "axisLabel": "Jobs",
+            "spanNulls": true,
+            "insertNulls": false,
+            "showPoints": "auto",
+            "pointSize": 3
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Ledger Fetch Rate",
+      "description": "Rate of ledger fetch requests initiated by the node. Sourced from the ledger_fetches counter (InboundLedgers.cpp:44) which increments each time the node requests a ledger from a peer. High rates indicate the node is catching up or missing ledgers.",
+      "type": "stat",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 24
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rate(rippled_ledger_fetches_total{exported_instance=~\"$node\"}[5m])",
+          "legendFormat": "Fetches / Sec"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "ops"
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Ledger History Mismatches",
+      "description": "Rate of ledger history hash mismatches. Sourced from the ledger.history.mismatch counter (LedgerHistory.cpp:16) which increments when a built ledger hash does not match the expected validated hash. Non-zero values indicate consensus divergence or database corruption.",
+      "type": "stat",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 24
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rate(rippled_ledger_history_mismatch_total{exported_instance=~\"$node\"}[5m])",
+          "legendFormat": "Mismatches / Sec"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "ops",
+          "thresholds": {
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              },
+              {
+                "color": "red",
+                "value": 0.01
+              }
+            ]
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "--- OTel: NodeStore I/O ---",
+      "type": "row",
+      "gridPos": {
+        "h": 1,
+        "w": 24,
+        "x": 0,
+        "y": 32
+      },
+      "collapsed": false,
+      "panels": []
+    },
+    {
+      "title": "NodeStore Read/Write Totals",
+      "description": "Cumulative NodeStore read and write operation counts. Sourced from MetricsRegistry nodestore_state observable gauge with metric=node_reads_total, node_writes, node_reads_hit.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 33
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_nodestore_state{exported_instance=~\"$node\", metric=\"node_reads_total\"}",
+          "legendFormat": "Reads Total"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_nodestore_state{exported_instance=~\"$node\", metric=\"node_reads_hit\"}",
+          "legendFormat": "Reads Hit (cache)"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_nodestore_state{exported_instance=~\"$node\", metric=\"node_writes\"}",
+          "legendFormat": "Writes Total"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "short",
+          "custom": {
+            "drawStyle": "line",
+            "lineWidth": 2,
+            "fillOpacity": 10
+          },
+          "color": {
+            "mode": "palette-classic"
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "NodeStore Write Load & Read Queue",
+      "description": "Instantaneous write load score and read queue depth. High write load indicates backend pressure. High read queue indicates prefetch thread saturation.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 33
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_nodestore_state{exported_instance=~\"$node\", metric=\"write_load\"}",
+          "legendFormat": "Write Load"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_nodestore_state{exported_instance=~\"$node\", metric=\"read_queue\"}",
+          "legendFormat": "Read Queue"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "short",
+          "custom": {
+            "drawStyle": "line",
+            "lineWidth": 2,
+            "fillOpacity": 10
+          },
+          "color": {
+            "mode": "palette-classic"
+          },
+          "thresholds": {
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              },
+              {
+                "color": "yellow",
+                "value": 100
+              },
+              {
+                "color": "red",
+                "value": 1000
+              }
+            ]
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "--- OTel: Cache Hit Rates ---",
+      "type": "row",
+      "gridPos": {
+        "h": 1,
+        "w": 24,
+        "x": 0,
+        "y": 41
+      },
+      "collapsed": false,
+      "panels": []
+    },
+    {
+      "title": "Cache Hit Rates",
+      "description": "Hit rates for SLE cache, Ledger cache, and AcceptedLedger cache. Values from 0.0 to 1.0. Low values indicate cache thrashing. Sourced from MetricsRegistry cache_metrics observable gauge.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 42
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_cache_metrics{exported_instance=~\"$node\", metric=\"SLE_hit_rate\"}",
+          "legendFormat": "SLE Hit Rate"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_cache_metrics{exported_instance=~\"$node\", metric=\"ledger_hit_rate\"}",
+          "legendFormat": "Ledger Hit Rate"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_cache_metrics{exported_instance=~\"$node\", metric=\"AL_hit_rate\"}",
+          "legendFormat": "AcceptedLedger Hit Rate"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "percentunit",
+          "min": 0,
+          "max": 1,
+          "custom": {
+            "drawStyle": "line",
+            "lineWidth": 2,
+            "fillOpacity": 10
+          },
+          "color": {
+            "mode": "palette-classic"
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Cache Sizes",
+      "description": "TreeNode cache size, TreeNode track size, and FullBelow cache size. Sourced from MetricsRegistry cache_metrics observable gauge.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 42
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_cache_metrics{exported_instance=~\"$node\", metric=\"treenode_cache_size\"}",
+          "legendFormat": "TreeNode Cache"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_cache_metrics{exported_instance=~\"$node\", metric=\"treenode_track_size\"}",
+          "legendFormat": "TreeNode Track"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_cache_metrics{exported_instance=~\"$node\", metric=\"fullbelow_size\"}",
+          "legendFormat": "FullBelow"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "short",
+          "custom": {
+            "drawStyle": "line",
+            "lineWidth": 2,
+            "fillOpacity": 10
+          },
+          "color": {
+            "mode": "palette-classic"
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "--- OTel: Object Instance Counts ---",
+      "type": "row",
+      "gridPos": {
+        "h": 1,
+        "w": 24,
+        "x": 0,
+        "y": 50
+      },
+      "collapsed": false,
+      "panels": []
+    },
+    {
+      "title": "Object Instance Counts",
+      "description": "Live instance counts for key internal object types tracked by CountedObject<T>. Sourced from MetricsRegistry object_count observable gauge. High counts may indicate memory pressure or object leaks.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 24,
+        "x": 0,
+        "y": 51
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        },
+        "legend": {
+          "displayMode": "table",
+          "placement": "right",
+          "calcs": ["last", "max"]
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "topk(15, rippled_object_count{exported_instance=~\"$node\"})",
+          "legendFormat": "{{type}}"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "short",
+          "custom": {
+            "drawStyle": "line",
+            "lineWidth": 1,
+            "fillOpacity": 5
+          },
+          "color": {
+            "mode": "palette-classic"
+          }
+        },
+        "overrides": []
+      }
+    }
+  ],
+  "schemaVersion": 39,
+  "tags": ["rippled", "statsd", "otel", "node-health", "telemetry"],
+  "templating": {
+    "list": [
+      {
+        "name": "node",
+        "label": "Node",
+        "description": "Filter by rippled node (service.instance.id)",
+        "type": "query",
+        "query": "label_values(exported_instance)",
+        "datasource": {
+          "type": "prometheus",
+          "uid": "prometheus"
+        },
+        "includeAll": true,
+        "allValue": ".*",
+        "current": {
+          "text": "All",
+          "value": "$__all"
+        },
+        "multi": true,
+        "refresh": 2,
+        "sort": 1
+      }
+    ]
+  },
+  "time": {
+    "from": "now-1h",
+    "to": "now"
+  },
+  "title": "Node Health (System Metrics)",
+  "uid": "rippled-system-node-health"
+}

docker/telemetry/grafana/dashboards/system-overlay-traffic-detail.json

@@ -0,0 +1,587 @@
+{
+  "annotations": {
+    "list": []
+  },
+  "description": "Detailed overlay traffic breakdown for categories not covered by the main Network Traffic dashboard. Includes squelch, overhead, validator lists, object fetch, ledger sync, and protocol negotiation traffic. Requires [insight] server=otel in rippled config.",
+  "editable": true,
+  "fiscalYearStartMonth": 0,
+  "graphTooltip": 1,
+  "id": null,
+  "links": [],
+  "panels": [
+    {
+      "title": "Squelch Traffic (Messages)",
+      "description": "Squelch-related overlay messages. Squelch is the peer traffic management protocol that suppresses redundant message forwarding. 'squelch' = squelch control messages, 'squelch_suppressed' = messages suppressed by squelch, 'squelch_ignored' = squelch directives that were ignored. High suppressed counts indicate effective bandwidth savings; high ignored counts may indicate misconfigured peers. Sourced from TrafficCount.h squelch categories.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 0
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_squelch_Messages_In{exported_instance=~\"$node\"}",
+          "legendFormat": "Squelch In"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_squelch_Messages_Out{exported_instance=~\"$node\"}",
+          "legendFormat": "Squelch Out"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_squelch_suppressed_Messages_In{exported_instance=~\"$node\"}",
+          "legendFormat": "Suppressed In"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_squelch_suppressed_Messages_Out{exported_instance=~\"$node\"}",
+          "legendFormat": "Suppressed Out"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_squelch_ignored_Messages_In{exported_instance=~\"$node\"}",
+          "legendFormat": "Ignored In"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_squelch_ignored_Messages_Out{exported_instance=~\"$node\"}",
+          "legendFormat": "Ignored Out"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "short",
+          "custom": {
+            "axisLabel": "Messages",
+            "spanNulls": true,
+            "insertNulls": false,
+            "showPoints": "auto",
+            "pointSize": 3
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Overhead Traffic Breakdown (Bytes)",
+      "description": "Overlay protocol overhead by sub-category. 'overhead' = base protocol overhead (ping, status, etc.), 'overhead_cluster' = intra-cluster communication overhead, 'overhead_manifest' = validator manifest distribution overhead. High cluster overhead may indicate frequent cluster state syncs; high manifest overhead occurs during UNL changes. Sourced from TrafficCount.h overhead categories.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 0
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_overhead_Bytes_In{exported_instance=~\"$node\"}",
+          "legendFormat": "Base Overhead In"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_overhead_Bytes_Out{exported_instance=~\"$node\"}",
+          "legendFormat": "Base Overhead Out"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_overhead_cluster_Bytes_In{exported_instance=~\"$node\"}",
+          "legendFormat": "Cluster In"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_overhead_cluster_Bytes_Out{exported_instance=~\"$node\"}",
+          "legendFormat": "Cluster Out"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_overhead_manifest_Bytes_In{exported_instance=~\"$node\"}",
+          "legendFormat": "Manifest In"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_overhead_manifest_Bytes_Out{exported_instance=~\"$node\"}",
+          "legendFormat": "Manifest Out"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "decbytes",
+          "custom": {
+            "axisLabel": "Bytes",
+            "spanNulls": true,
+            "insertNulls": false,
+            "showPoints": "auto",
+            "pointSize": 3
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Validator List Traffic",
+      "description": "Validator list (UNL) distribution traffic. Validator lists are exchanged when peers share their trusted validator configurations. Spikes occur during UNL updates or when new peers connect. Sourced from TrafficCount.h validator_lists category.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 8
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_validator_lists_Bytes_In{exported_instance=~\"$node\"}",
+          "legendFormat": "Bytes In"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_validator_lists_Bytes_Out{exported_instance=~\"$node\"}",
+          "legendFormat": "Bytes Out"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_validator_lists_Messages_In{exported_instance=~\"$node\"}",
+          "legendFormat": "Messages In"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_validator_lists_Messages_Out{exported_instance=~\"$node\"}",
+          "legendFormat": "Messages Out"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "short",
+          "custom": {
+            "axisLabel": "Count",
+            "spanNulls": true,
+            "insertNulls": false,
+            "showPoints": "auto",
+            "pointSize": 3
+          }
+        },
+        "overrides": [
+          {
+            "matcher": {
+              "id": "byRegexp",
+              "options": "/Bytes/"
+            },
+            "properties": [
+              {
+                "id": "custom.axisPlacement",
+                "value": "right"
+              },
+              {
+                "id": "unit",
+                "value": "decbytes"
+              }
+            ]
+          }
+        ]
+      }
+    },
+    {
+      "title": "Set Get/Share Traffic (Bytes)",
+      "description": "Transaction set get and share traffic. 'set_get' = requests to fetch transaction sets (sent during ledger close), 'set_share' = responses sharing transaction sets. High set_get traffic indicates peers frequently requesting missing transaction sets, which may signal sync delays. Sourced from TrafficCount.h set_get/set_share categories.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 8
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_set_get_Bytes_In{exported_instance=~\"$node\"}",
+          "legendFormat": "Set Get In"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_set_get_Bytes_Out{exported_instance=~\"$node\"}",
+          "legendFormat": "Set Get Out"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_set_share_Bytes_In{exported_instance=~\"$node\"}",
+          "legendFormat": "Set Share In"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_set_share_Bytes_Out{exported_instance=~\"$node\"}",
+          "legendFormat": "Set Share Out"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "decbytes",
+          "custom": {
+            "axisLabel": "Bytes",
+            "spanNulls": true,
+            "insertNulls": false,
+            "showPoints": "auto",
+            "pointSize": 3
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Have/Requested Transactions (Messages)",
+      "description": "Transaction availability protocol messages. 'have_transactions' = advertisements that a peer has specific transactions available, 'requested_transactions' = explicit requests for transaction data. A high ratio of requested to have may indicate peers are behind on transaction propagation. Sourced from TrafficCount.h have_transactions/requested_transactions categories.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 16
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_have_transactions_Messages_In{exported_instance=~\"$node\"}",
+          "legendFormat": "Have TX In"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_have_transactions_Messages_Out{exported_instance=~\"$node\"}",
+          "legendFormat": "Have TX Out"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_requested_transactions_Messages_In{exported_instance=~\"$node\"}",
+          "legendFormat": "Requested TX In"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_requested_transactions_Messages_Out{exported_instance=~\"$node\"}",
+          "legendFormat": "Requested TX Out"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "short",
+          "custom": {
+            "axisLabel": "Messages",
+            "spanNulls": true,
+            "insertNulls": false,
+            "showPoints": "auto",
+            "pointSize": 3
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Unknown / Unclassified Traffic",
+      "description": "Traffic that does not match any known overlay message category. Non-zero values may indicate protocol version mismatches, corrupted messages, or new message types not yet classified. Sourced from TrafficCount.h unknown category.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 16
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_unknown_Bytes_In{exported_instance=~\"$node\"}",
+          "legendFormat": "Unknown Bytes In"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_unknown_Bytes_Out{exported_instance=~\"$node\"}",
+          "legendFormat": "Unknown Bytes Out"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_unknown_Messages_In{exported_instance=~\"$node\"}",
+          "legendFormat": "Unknown Messages In"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_unknown_Messages_Out{exported_instance=~\"$node\"}",
+          "legendFormat": "Unknown Messages Out"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "short",
+          "custom": {
+            "axisLabel": "Count",
+            "spanNulls": true,
+            "insertNulls": false,
+            "showPoints": "auto",
+            "pointSize": 3
+          }
+        },
+        "overrides": [
+          {
+            "matcher": {
+              "id": "byRegexp",
+              "options": "/Bytes/"
+            },
+            "properties": [
+              {
+                "id": "custom.axisPlacement",
+                "value": "right"
+              },
+              {
+                "id": "unit",
+                "value": "decbytes"
+              }
+            ]
+          }
+        ]
+      }
+    },
+    {
+      "title": "Proof Path Traffic",
+      "description": "Proof path request/response traffic for ledger state proof exchange. Used by peers to verify specific ledger entries without downloading the full ledger. High request volume may indicate peers validating state during catch-up. Sourced from TrafficCount.h proof_path_request/proof_path_response categories.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 24
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_proof_path_request_Bytes_In{exported_instance=~\"$node\"}",
+          "legendFormat": "Request Bytes In"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_proof_path_request_Bytes_Out{exported_instance=~\"$node\"}",
+          "legendFormat": "Request Bytes Out"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_proof_path_response_Bytes_In{exported_instance=~\"$node\"}",
+          "legendFormat": "Response Bytes In"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_proof_path_response_Bytes_Out{exported_instance=~\"$node\"}",
+          "legendFormat": "Response Bytes Out"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "decbytes",
+          "custom": {
+            "axisLabel": "Bytes",
+            "spanNulls": true,
+            "insertNulls": false,
+            "showPoints": "auto",
+            "pointSize": 3
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Replay Delta Traffic",
+      "description": "Replay delta request/response traffic for ledger replay protocol. Used during catch-up to efficiently replay ledger state changes. Sourced from TrafficCount.h replay_delta_request/replay_delta_response categories.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 24
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_replay_delta_request_Bytes_In{exported_instance=~\"$node\"}",
+          "legendFormat": "Request Bytes In"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_replay_delta_request_Bytes_Out{exported_instance=~\"$node\"}",
+          "legendFormat": "Request Bytes Out"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_replay_delta_response_Bytes_In{exported_instance=~\"$node\"}",
+          "legendFormat": "Response Bytes In"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_replay_delta_response_Bytes_Out{exported_instance=~\"$node\"}",
+          "legendFormat": "Response Bytes Out"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "decbytes",
+          "custom": {
+            "axisLabel": "Bytes",
+            "spanNulls": true,
+            "insertNulls": false,
+            "showPoints": "auto",
+            "pointSize": 3
+          }
+        },
+        "overrides": []
+      }
+    }
+  ],
+  "schemaVersion": 39,
+  "tags": ["rippled", "statsd", "overlay", "network", "telemetry"],
+  "templating": {
+    "list": [
+      {
+        "name": "node",
+        "label": "Node",
+        "description": "Filter by rippled node (service.instance.id)",
+        "type": "query",
+        "query": "label_values(exported_instance)",
+        "datasource": {
+          "type": "prometheus",
+          "uid": "prometheus"
+        },
+        "includeAll": true,
+        "allValue": ".*",
+        "current": {
+          "text": "All",
+          "value": "$__all"
+        },
+        "multi": true,
+        "refresh": 2,
+        "sort": 1
+      }
+    ]
+  },
+  "time": {
+    "from": "now-1h",
+    "to": "now"
+  },
+  "title": "Overlay Traffic Detail (System Metrics)",
+  "uid": "rippled-system-overlay-detail"
+}

docker/telemetry/grafana/dashboards/system-rpc-pathfinding.json

@@ -0,0 +1,417 @@
+{
+  "annotations": {
+    "list": []
+  },
+  "description": "RPC and pathfinding metrics from beast::insight System Metrics. Requires [insight] server=otel in rippled config.",
+  "editable": true,
+  "fiscalYearStartMonth": 0,
+  "graphTooltip": 1,
+  "id": null,
+  "links": [],
+  "panels": [
+    {
+      "title": "RPC Request Rate (System Metrics)",
+      "description": "Rate of RPC requests as counted by the beast::insight counter. Sourced from rpc.requests (ServerHandler.cpp:108) which increments on every HTTP and WebSocket RPC request. Compare with the span-based rpc.request rate in the RPC Performance dashboard for cross-validation.",
+      "type": "stat",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 0
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rate(rippled_rpc_requests_total{exported_instance=~\"$node\"}[5m])",
+          "legendFormat": "Requests / Sec"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "reqps"
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "RPC Response Time (System Metrics)",
+      "description": "P95 and P50 of RPC response time from the beast::insight timer. Sourced from the rpc.time event (ServerHandler.cpp:110) which records elapsed milliseconds for each RPC response. This measures the full HTTP handler time, not just command execution. Compare with span-based rpc.request duration.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 0
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_rpc_time{exported_instance=~\"$node\", quantile=\"0.95\"}",
+          "legendFormat": "P95 Response Time"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_rpc_time{exported_instance=~\"$node\", quantile=\"0.5\"}",
+          "legendFormat": "P50 Response Time"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "ms",
+          "custom": {
+            "axisLabel": "Latency (ms)",
+            "spanNulls": true,
+            "insertNulls": false,
+            "showPoints": "auto",
+            "pointSize": 3
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "RPC Response Size",
+      "description": "P95 and P50 of RPC response payload size in bytes. Sourced from the rpc.size event (ServerHandler.cpp:109) which records the byte length of each RPC JSON response. Large responses may indicate expensive queries (e.g. account_tx with many results) or API misuse.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 8
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_rpc_size{exported_instance=~\"$node\", quantile=\"0.95\"}",
+          "legendFormat": "P95 Response Size"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_rpc_size{exported_instance=~\"$node\", quantile=\"0.5\"}",
+          "legendFormat": "P50 Response Size"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "decbytes",
+          "custom": {
+            "axisLabel": "Size (Bytes)",
+            "spanNulls": true,
+            "insertNulls": false,
+            "showPoints": "auto",
+            "pointSize": 3
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "RPC Response Time Distribution",
+      "description": "Distribution of RPC response times from the beast::insight timer showing P50, P90, P95, and P99 quantiles. Sourced from the rpc.time event (ServerHandler.cpp:110). Useful for detecting bimodal latency or long-tail requests.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 8
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_rpc_time{exported_instance=~\"$node\", quantile=\"0.5\"}",
+          "legendFormat": "P50"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_rpc_time{exported_instance=~\"$node\", quantile=\"0.9\"}",
+          "legendFormat": "P90"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_rpc_time{exported_instance=~\"$node\", quantile=\"0.95\"}",
+          "legendFormat": "P95"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_rpc_time{exported_instance=~\"$node\", quantile=\"0.99\"}",
+          "legendFormat": "P99"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "ms",
+          "custom": {
+            "axisLabel": "Latency (ms)",
+            "spanNulls": true,
+            "insertNulls": false,
+            "showPoints": "auto",
+            "pointSize": 3
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Pathfinding Fast Duration",
+      "description": "P95 and P50 of fast pathfinding execution time. Sourced from the pathfind_fast event (PathRequests.h:23) which records the duration of the fast pathfinding algorithm. Fast pathfinding uses a simplified search that trades accuracy for speed.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 16
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_pathfind_fast{exported_instance=~\"$node\", quantile=\"0.95\"}",
+          "legendFormat": "P95 Fast Pathfind"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_pathfind_fast{exported_instance=~\"$node\", quantile=\"0.5\"}",
+          "legendFormat": "P50 Fast Pathfind"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "ms",
+          "custom": {
+            "axisLabel": "Duration (ms)",
+            "spanNulls": true,
+            "insertNulls": false,
+            "showPoints": "auto",
+            "pointSize": 3
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Pathfinding Full Duration",
+      "description": "P95 and P50 of full pathfinding execution time. Sourced from the pathfind_full event (PathRequests.h:24) which records the duration of the exhaustive pathfinding search. Full pathfinding is more expensive and can take significantly longer than fast mode.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 16
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_pathfind_full{exported_instance=~\"$node\", quantile=\"0.95\"}",
+          "legendFormat": "P95 Full Pathfind"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rippled_pathfind_full{exported_instance=~\"$node\", quantile=\"0.5\"}",
+          "legendFormat": "P50 Full Pathfind"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "ms",
+          "custom": {
+            "axisLabel": "Duration (ms)",
+            "spanNulls": true,
+            "insertNulls": false,
+            "showPoints": "auto",
+            "pointSize": 3
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Resource Warnings Rate",
+      "description": "Rate of resource warning events from the Resource Manager. Sourced from the warn meter (Logic.h:33) which increments when a consumer (peer or RPC client) exceeds the warning threshold for resource usage. A rising rate indicates aggressive clients that may need throttling. NOTE: This panel will show no data until the |m -> |c fix is applied in System MetricsCollector.cpp:706 (Phase 6 Task 6.1).",
+      "type": "stat",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 24
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rate(rippled_warn_total{exported_instance=~\"$node\"}[5m])",
+          "legendFormat": "Warnings / Sec"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "ops",
+          "thresholds": {
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              },
+              {
+                "color": "yellow",
+                "value": 0.1
+              },
+              {
+                "color": "red",
+                "value": 1
+              }
+            ]
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Resource Drops Rate",
+      "description": "Rate of resource drop events from the Resource Manager. Sourced from the drop meter (Logic.h:34) which increments when a consumer is disconnected or blocked due to excessive resource usage. Non-zero values mean the node is actively rejecting abusive connections. NOTE: This panel will show no data until the |m -> |c fix is applied in System MetricsCollector.cpp:706 (Phase 6 Task 6.1).",
+      "type": "stat",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 24
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "rate(rippled_drop_total{exported_instance=~\"$node\"}[5m])",
+          "legendFormat": "Drops / Sec"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "ops",
+          "thresholds": {
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              },
+              {
+                "color": "yellow",
+                "value": 0.01
+              },
+              {
+                "color": "red",
+                "value": 0.1
+              }
+            ]
+          }
+        },
+        "overrides": []
+      }
+    }
+  ],
+  "schemaVersion": 39,
+  "tags": ["rippled", "statsd", "rpc", "pathfinding", "telemetry"],
+  "templating": {
+    "list": [
+      {
+        "name": "node",
+        "label": "Node",
+        "description": "Filter by rippled node (service.instance.id)",
+        "type": "query",
+        "query": "label_values(exported_instance)",
+        "datasource": {
+          "type": "prometheus",
+          "uid": "prometheus"
+        },
+        "includeAll": true,
+        "allValue": ".*",
+        "current": {
+          "text": "All",
+          "value": "$__all"
+        },
+        "multi": true,
+        "refresh": 2,
+        "sort": 1
+      }
+    ]
+  },
+  "time": {
+    "from": "now-1h",
+    "to": "now"
+  },
+  "title": "RPC & Pathfinding (System Metrics)",
+  "uid": "rippled-system-rpc"
+}

docker/telemetry/grafana/dashboards/transaction-overview.json

@@ -0,0 +1,384 @@
+{
+  "annotations": {
+    "list": []
+  },
+  "editable": true,
+  "fiscalYearStartMonth": 0,
+  "graphTooltip": 1,
+  "id": null,
+  "links": [],
+  "panels": [
+    {
+      "title": "Transaction Processing Rate",
+      "description": "Rate of transactions entering the processing pipeline. tx.process (NetworkOPs.cpp:1227) fires when a transaction is submitted locally or received from a peer and enters processTransaction(). tx.receive (PeerImp.cpp:1273) fires when a raw transaction message arrives from a peer before deduplication.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 0
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "sum(rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", span_name=\"tx.process\"}[5m]))",
+          "legendFormat": "tx.process / Sec"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "sum(rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", span_name=\"tx.receive\"}[5m]))",
+          "legendFormat": "tx.receive / Sec"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "ops",
+          "custom": {
+            "axisLabel": "Transactions / Sec",
+            "spanNulls": true,
+            "insertNulls": false,
+            "showPoints": "auto",
+            "pointSize": 3
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Transaction Processing Latency",
+      "description": "p95 and p50 latency of transaction processing (tx.process span). Measures the time from when a transaction enters processTransaction() to completion. Computed via histogram_quantile() over the spanmetrics duration histogram with a 5m rate window.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 0
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "histogram_quantile(0.95, sum by (le) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", span_name=\"tx.process\"}[5m])))",
+          "legendFormat": "P95"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "histogram_quantile(0.50, sum by (le) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", span_name=\"tx.process\"}[5m])))",
+          "legendFormat": "P50"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "ms",
+          "custom": {
+            "axisLabel": "Latency (ms)",
+            "spanNulls": true,
+            "insertNulls": false,
+            "showPoints": "auto",
+            "pointSize": 3
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Transaction Path Distribution",
+      "description": "Breakdown of transactions by origin path. The xrpl.tx.local attribute indicates whether the transaction was submitted locally (true) or received from a peer (false). Helps understand the ratio of locally-originated vs relayed transactions.",
+      "type": "piechart",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 8
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "sum by (xrpl_tx_local) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", span_name=\"tx.process\"}[5m]))",
+          "legendFormat": "Local = {{xrpl_tx_local}}"
+        }
+      ]
+    },
+    {
+      "title": "Transaction Receive vs Suppressed",
+      "description": "Total rate of raw transaction messages received from peers (tx.receive span from PeerImp.cpp:1273). This fires before deduplication via the HashRouter, so the difference between tx.receive and tx.process reflects suppressed duplicate transactions.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 8
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "sum(rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", span_name=\"tx.receive\"}[5m]))",
+          "legendFormat": "Total Received"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "ops",
+          "custom": {
+            "axisLabel": "Transactions / Sec",
+            "spanNulls": true,
+            "insertNulls": false,
+            "showPoints": "auto",
+            "pointSize": 3
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Transaction Processing Duration Heatmap",
+      "description": "Heatmap showing the distribution of tx.process span durations across histogram buckets over time. Each cell represents the count of transactions that completed within that latency bucket in a 5m window. Reveals whether processing times are consistent or exhibit multi-modal patterns.",
+      "type": "heatmap",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 16
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        },
+        "yAxis": {
+          "axisLabel": "Duration (ms)"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "sum(increase(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", span_name=\"tx.process\"}[5m])) by (le)",
+          "legendFormat": "{{le}}",
+          "format": "heatmap"
+        }
+      ]
+    },
+    {
+      "title": "Transaction Apply Duration per Ledger",
+      "description": "p95 and p50 latency of applying the consensus transaction set to a new ledger. The tx.apply span (BuildLedger.cpp:88) wraps the applyTransactions() function that iterates through the CanonicalTXSet and applies each transaction to the OpenView. Long durations indicate heavy transaction sets or expensive transaction processing.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 16
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "histogram_quantile(0.95, sum by (le) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", span_name=\"tx.apply\"}[5m])))",
+          "legendFormat": "P95 tx.apply"
+        },
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "histogram_quantile(0.50, sum by (le) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", span_name=\"tx.apply\"}[5m])))",
+          "legendFormat": "P50 tx.apply"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "ms",
+          "custom": {
+            "axisLabel": "Latency (ms)",
+            "spanNulls": true,
+            "insertNulls": false,
+            "showPoints": "auto",
+            "pointSize": 3
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Peer Transaction Receive Rate",
+      "description": "Rate of transaction messages received from network peers. Sourced from the tx.receive span (PeerImp.cpp:1273) which fires in the onMessage(TMTransaction) handler. High rates may indicate network-wide transaction volume spikes or peer flooding.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 24
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "sum(rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", span_name=\"tx.receive\"}[5m]))",
+          "legendFormat": "tx.receive / Sec"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "ops",
+          "custom": {
+            "axisLabel": "Transactions / Sec",
+            "spanNulls": true,
+            "insertNulls": false,
+            "showPoints": "auto",
+            "pointSize": 3
+          }
+        },
+        "overrides": []
+      }
+    },
+    {
+      "title": "Transaction Apply Failed Rate",
+      "description": "Rate of tx.apply spans completing with error status, indicating transaction application failures during ledger building. The span records xrpl.ledger.tx_failed as an attribute. Thresholds: green < 0.1/sec, yellow 0.1-1/sec, red > 1/sec. Some failures are normal (e.g. conflicting offers) but sustained high rates may indicate issues.",
+      "type": "stat",
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 24
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "sum(rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", span_name=\"tx.apply\", status_code=\"STATUS_CODE_ERROR\"}[5m]))",
+          "legendFormat": "Failed / Sec"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "ops",
+          "thresholds": {
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              },
+              {
+                "color": "yellow",
+                "value": 0.1
+              },
+              {
+                "color": "red",
+                "value": 1
+              }
+            ]
+          }
+        },
+        "overrides": []
+      }
+    }
+  ],
+  "schemaVersion": 39,
+  "tags": ["rippled", "transactions", "telemetry"],
+  "templating": {
+    "list": [
+      {
+        "name": "node",
+        "label": "Node",
+        "description": "Filter by rippled node (service.instance.id \u2014 e.g. Node-1)",
+        "type": "query",
+        "query": "label_values(traces_span_metrics_calls_total, exported_instance)",
+        "datasource": {
+          "type": "prometheus",
+          "uid": "prometheus"
+        },
+        "includeAll": true,
+        "allValue": ".*",
+        "current": {
+          "text": "All",
+          "value": "$__all"
+        },
+        "multi": true,
+        "refresh": 2,
+        "sort": 1
+      },
+      {
+        "name": "tx_origin",
+        "label": "TX Origin",
+        "description": "Filter by transaction origin (true = local submit, false = peer relay)",
+        "type": "query",
+        "query": "label_values(traces_span_metrics_calls_total{span_name=\"tx.process\"}, xrpl_tx_local)",
+        "datasource": {
+          "type": "prometheus",
+          "uid": "prometheus"
+        },
+        "includeAll": true,
+        "allValue": ".*",
+        "current": {
+          "text": "All",
+          "value": "$__all"
+        },
+        "multi": true,
+        "refresh": 2,
+        "sort": 1
+      }
+    ]
+  },
+  "time": {
+    "from": "now-1h",
+    "to": "now"
+  },
+  "title": "Transaction Overview",
+  "uid": "rippled-transactions"
+}

docker/telemetry/grafana/provisioning/dashboards/dashboards.yaml

@@ -0,0 +1,12 @@
+apiVersion: 1
+
+providers:
+  - name: rippled-telemetry
+    orgId: 1
+    folder: rippled
+    type: file
+    disableDeletion: false
+    editable: true
+    options:
+      path: /var/lib/grafana/dashboards
+      foldersFromFilesStructure: false

docker/telemetry/grafana/provisioning/datasources/jaeger.yaml

@@ -0,0 +1,12 @@
+# Grafana datasource provisioning for the rippled telemetry stack.
+# Auto-configures Jaeger as a trace data source on Grafana startup.
+# Access Grafana at http://localhost:3000, then use Explore -> Jaeger
+# to browse rippled traces.
+
+apiVersion: 1
+
+datasources:
+  - name: Jaeger
+    type: jaeger
+    access: proxy
+    url: http://jaeger:16686

docker/telemetry/grafana/provisioning/datasources/loki.yaml

@@ -0,0 +1,24 @@
+# Grafana Loki data source provisioning for rippled log-trace correlation.
+#
+# Phase 8: Log-Trace Correlation and Centralized Log Ingestion
+#
+# Loki ingests rippled logs via OTel Collector's filelog receiver.
+# The derivedFields config links trace_id values in log lines back to
+# Tempo traces, enabling one-click log-to-trace navigation in Grafana.
+#
+# See: OpenTelemetryPlan/Phase8_taskList.md (Tasks 8.2, 8.4)
+
+apiVersion: 1
+
+datasources:
+  - name: Loki
+    type: loki
+    access: proxy
+    url: http://loki:3100
+    uid: loki
+    jsonData:
+      derivedFields:
+        - datasourceUid: tempo
+          matcherRegex: "trace_id=(\\w+)"
+          name: TraceID
+          url: "$${__value.raw}"

docker/telemetry/grafana/provisioning/datasources/prometheus.yaml

@@ -0,0 +1,10 @@
+apiVersion: 1
+
+datasources:
+  - name: Prometheus
+    type: prometheus
+    uid: prometheus
+    access: proxy
+    url: http://prometheus:9090
+    isDefault: false
+    editable: true

docker/telemetry/grafana/provisioning/datasources/tempo.yaml

@@ -0,0 +1,155 @@
+# Grafana datasource provisioning for Grafana Tempo.
+# Auto-configures Tempo as a trace data source on Grafana startup.
+# Access Grafana at http://localhost:3000, then use Explore -> Tempo
+# to browse rippled traces using TraceQL.
+#
+# Search filters provide pre-configured dropdowns in the Explore UI.
+# Each phase adds filters for the span attributes it introduces.
+# Phase 1b (infra): Base filters — node identity, service, span name, status.
+# Phase 2 (RPC):    RPC command, status, role filters.
+# Phase 3 (TX):     Transaction hash, local/peer origin, status.
+# Phase 4 (Cons):   Consensus mode, round, ledger sequence, close time.
+
+apiVersion: 1
+
+datasources:
+  - name: Tempo
+    type: tempo
+    access: proxy
+    url: http://tempo:3200
+    uid: tempo
+    jsonData:
+      nodeGraph:
+        enabled: true
+      serviceMap:
+        datasourceUid: prometheus
+      # Phase 8: Trace-to-log correlation — enables one-click navigation
+      # from a Tempo trace to the corresponding Loki log lines. Filters
+      # by trace_id so only logs from the same trace are shown.
+      tracesToLogs:
+        datasourceUid: loki
+        filterByTraceID: true
+        filterBySpanID: false
+        tags: ["partition", "severity"]
+      tracesToMetrics:
+        datasourceUid: prometheus
+        spanStartTimeShift: "-1h"
+        spanEndTimeShift: "1h"
+      search:
+        filters:
+          # --- Node identification filters ---
+          # service.name: logical service name (default: "rippled").
+          #   Useful when running multiple service types in the same collector.
+          - id: service-name
+            tag: service.name
+            operator: "="
+            scope: resource
+            type: static
+          # service.instance.id: unique node identifier — configurable via
+          #   the service_instance_id setting in [telemetry], defaults to the
+          #   node's public key. E.g. "Node-1" or "nHB1X37...".
+          - id: node-id
+            tag: service.instance.id
+            operator: "="
+            scope: resource
+            type: static
+          # service.version: rippled build version (e.g., "2.4.0-b1").
+          #   Filter traces from specific software releases.
+          - id: node-version
+            tag: service.version
+            operator: "="
+            scope: resource
+            type: dynamic
+          # xrpl.network.id: numeric network identifier
+          #   (0 = mainnet, 1 = testnet, 2 = devnet, etc.).
+          - id: network-id
+            tag: xrpl.network.id
+            operator: "="
+            scope: resource
+            type: dynamic
+          # xrpl.network.type: human-readable network name
+          #   ("mainnet", "testnet", "devnet", "standalone").
+          - id: network-type
+            tag: xrpl.network.type
+            operator: "="
+            scope: resource
+            type: static
+          # --- Span intrinsic filters ---
+          - id: span-name
+            tag: name
+            operator: "="
+            scope: intrinsic
+            type: static
+          - id: span-status
+            tag: status
+            operator: "="
+            scope: intrinsic
+            type: static
+          - id: span-duration
+            tag: duration
+            operator: ">"
+            scope: intrinsic
+            type: static
+          # Phase 2: RPC tracing filters
+          - id: rpc-command
+            tag: xrpl.rpc.command
+            operator: "="
+            scope: span
+            type: static
+          - id: rpc-status
+            tag: xrpl.rpc.status
+            operator: "="
+            scope: span
+            type: dynamic
+          - id: rpc-role
+            tag: xrpl.rpc.role
+            operator: "="
+            scope: span
+            type: dynamic
+          # Phase 3: Transaction tracing filters
+          - id: tx-hash
+            tag: xrpl.tx.hash
+            operator: "="
+            scope: span
+            type: static
+          - id: tx-origin
+            tag: xrpl.tx.local
+            operator: "="
+            scope: span
+            type: dynamic
+          - id: tx-status
+            tag: xrpl.tx.status
+            operator: "="
+            scope: span
+            type: dynamic
+          # Phase 4: Consensus tracing filters
+          - id: consensus-mode
+            tag: xrpl.consensus.mode
+            operator: "="
+            scope: span
+            type: static
+          - id: consensus-round
+            tag: xrpl.consensus.round
+            operator: "="
+            scope: span
+            type: dynamic
+          - id: consensus-ledger-seq
+            tag: xrpl.consensus.ledger.seq
+            operator: "="
+            scope: span
+            type: static
+          - id: consensus-close-time-correct
+            tag: xrpl.consensus.close_time_correct
+            operator: "="
+            scope: span
+            type: dynamic
+          - id: consensus-state
+            tag: xrpl.consensus.state
+            operator: "="
+            scope: span
+            type: dynamic
+          - id: consensus-close-resolution
+            tag: xrpl.consensus.close_resolution_ms
+            operator: "="
+            scope: span
+            type: dynamic

docker/telemetry/integration-test.sh

@@ -0,0 +1,719 @@
+#!/usr/bin/env bash
+# Integration test for rippled OpenTelemetry instrumentation.
+#
+# Launches a 6-node xrpld consensus network with telemetry enabled,
+# exercises RPC / transaction / consensus code paths, then verifies
+# that the expected spans and metrics appear in Jaeger and Prometheus.
+#
+# Usage:
+#   bash docker/telemetry/integration-test.sh
+#
+# Prerequisites:
+#   - .build/xrpld built with telemetry=ON
+#   - docker compose (v2)
+#   - curl, jq
+#
+# The script leaves the observability stack and xrpld nodes running
+# so you can manually inspect Jaeger (localhost:16686) and Grafana
+# (localhost:3000). Run with --cleanup to tear down instead.
+
+set -euo pipefail
+
+# ---------------------------------------------------------------------------
+# Configuration
+# ---------------------------------------------------------------------------
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+REPO_ROOT="$(cd "$SCRIPT_DIR/../.." && pwd)"
+XRPLD="$REPO_ROOT/.build/xrpld"
+COMPOSE_FILE="$SCRIPT_DIR/docker-compose.yml"
+STANDALONE_CFG="$SCRIPT_DIR/xrpld-telemetry.cfg"
+WORKDIR="/tmp/xrpld-integration"
+NUM_NODES=6
+PEER_PORT_BASE=51235
+RPC_PORT_BASE=5005
+CONSENSUS_TIMEOUT=120
+GENESIS_ACCOUNT="rHb9CJAWyB4rj91VRWn96DkukG4bwdtyTh"
+GENESIS_SEED="snoPBrXtMeMyMHUVTgbuqAfg1SUTb"
+DEST_ACCOUNT=""  # Generated dynamically via wallet_propose
+JAEGER="http://localhost:16686"
+PROM="http://localhost:9090"
+
+# Counters for pass/fail
+PASS=0
+FAIL=0
+
+# ---------------------------------------------------------------------------
+# Helpers
+# ---------------------------------------------------------------------------
+log()  { printf "\033[1;34m[INFO]\033[0m  %s\n" "$*"; }
+ok()   { printf "\033[1;32m[PASS]\033[0m  %s\n" "$*"; PASS=$((PASS + 1)); }
+fail() { printf "\033[1;31m[FAIL]\033[0m  %s\n" "$*"; FAIL=$((FAIL + 1)); }
+die()  { printf "\033[1;31m[ERROR]\033[0m %s\n" "$*" >&2; exit 1; }
+
+check_span() {
+    local op="$1"
+    local count
+    count=$(curl -sf "$JAEGER/api/traces?service=rippled&operation=$op&limit=5&lookback=1h" \
+        | jq '.data | length' 2>/dev/null || echo 0)
+    if [ "$count" -gt 0 ]; then
+        ok "$op  ($count traces)"
+    else
+        fail "$op  (0 traces)"
+    fi
+}
+
+# Phase 8: Verify trace_id injection in rippled log output.
+# Greps all node debug.log files for the "trace_id=<hex> span_id=<hex>"
+# pattern that Logs::format() injects when an active OTel span exists.
+# Also cross-checks that a trace_id found in logs matches a trace in Jaeger.
+check_log_correlation() {
+    log "Checking log-trace correlation..."
+
+    local total_matches=0
+    local sample_trace_id=""
+
+    for i in $(seq 1 "$NUM_NODES"); do
+        local logfile="$WORKDIR/node$i/debug.log"
+        if [ ! -f "$logfile" ]; then
+            continue
+        fi
+        local matches
+        matches=$(grep -c 'trace_id=[a-f0-9]\{32\} span_id=[a-f0-9]\{16\}' "$logfile" 2>/dev/null || echo 0)
+        total_matches=$((total_matches + matches))
+        # Capture the first trace_id we find for cross-referencing with Jaeger
+        if [ -z "$sample_trace_id" ] && [ "$matches" -gt 0 ]; then
+            sample_trace_id=$(grep -o 'trace_id=[a-f0-9]\{32\}' "$logfile" | head -1 | cut -d= -f2)
+        fi
+    done
+
+    if [ "$total_matches" -gt 0 ]; then
+        ok "Log correlation: found $total_matches log lines with trace_id"
+    else
+        fail "Log correlation: no trace_id found in any node debug.log"
+    fi
+
+    # Cross-check: verify the sample trace_id exists in Jaeger
+    if [ -n "$sample_trace_id" ]; then
+        local trace_found
+        trace_found=$(curl -sf "$JAEGER/api/traces/$sample_trace_id" \
+            | jq '.data | length' 2>/dev/null || echo 0)
+        if [ "$trace_found" -gt 0 ]; then
+            ok "Log-Jaeger cross-check: trace_id=$sample_trace_id found in Jaeger"
+        else
+            fail "Log-Jaeger cross-check: trace_id=$sample_trace_id NOT found in Jaeger"
+        fi
+    fi
+}
+
+cleanup() {
+    log "Cleaning up..."
+    # Kill xrpld nodes
+    for i in $(seq 1 "$NUM_NODES"); do
+        local pidfile="$WORKDIR/node$i/xrpld.pid"
+        if [ -f "$pidfile" ]; then
+            kill "$(cat "$pidfile")" 2>/dev/null || true
+            rm -f "$pidfile"
+        fi
+    done
+    # Also kill any straggling xrpld processes from our workdir
+    pkill -f "$WORKDIR" 2>/dev/null || true
+    # Stop docker stack
+    docker compose -f "$COMPOSE_FILE" down 2>/dev/null || true
+    # Remove workdir
+    rm -rf "$WORKDIR"
+    log "Cleanup complete."
+}
+
+# Handle --cleanup flag
+if [ "${1:-}" = "--cleanup" ]; then
+    cleanup
+    exit 0
+fi
+
+# ---------------------------------------------------------------------------
+# Step 0: Prerequisites
+# ---------------------------------------------------------------------------
+log "Checking prerequisites..."
+
+command -v docker >/dev/null 2>&1 || die "docker not found"
+docker compose version >/dev/null 2>&1 || die "docker compose (v2) not found"
+command -v curl >/dev/null 2>&1 || die "curl not found"
+command -v jq >/dev/null 2>&1 || die "jq not found"
+[ -x "$XRPLD" ] || die "xrpld binary not found at $XRPLD (build with telemetry=ON)"
+[ -f "$COMPOSE_FILE" ] || die "docker-compose.yml not found at $COMPOSE_FILE"
+[ -f "$STANDALONE_CFG" ] || die "xrpld-telemetry.cfg not found at $STANDALONE_CFG"
+
+log "All prerequisites met."
+
+# ---------------------------------------------------------------------------
+# Step 1: Clean previous run
+# ---------------------------------------------------------------------------
+log "Cleaning previous run data..."
+for i in $(seq 1 "$NUM_NODES"); do
+    pidfile="$WORKDIR/node$i/xrpld.pid"
+    if [ -f "$pidfile" ]; then
+        kill "$(cat "$pidfile")" 2>/dev/null || true
+    fi
+done
+pkill -f "$WORKDIR" 2>/dev/null || true
+# Kill any xrpld using the standalone config (from key generation)
+pkill -f "xrpld-telemetry.cfg" 2>/dev/null || true
+sleep 2
+rm -rf "$WORKDIR"
+mkdir -p "$WORKDIR"
+
+# ---------------------------------------------------------------------------
+# Step 2: Start observability stack
+# ---------------------------------------------------------------------------
+log "Starting observability stack..."
+docker compose -f "$COMPOSE_FILE" up -d
+
+log "Waiting for otel-collector to be ready..."
+for attempt in $(seq 1 30); do
+    # The OTLP HTTP endpoint returns 405 for GET (expects POST), which
+    # means it is listening.  curl -sf would fail on 405, so we check
+    # the HTTP status code explicitly.
+    status=$(curl -so /dev/null -w '%{http_code}' http://localhost:4318/ 2>/dev/null || echo 000)
+    if [ "$status" != "000" ]; then
+        log "otel-collector ready (attempt $attempt, HTTP $status)."
+        break
+    fi
+    if [ "$attempt" -eq 30 ]; then
+        die "otel-collector not ready after 30s"
+    fi
+    sleep 1
+done
+
+log "Waiting for Jaeger to be ready..."
+for attempt in $(seq 1 30); do
+    if curl -sf "$JAEGER/" >/dev/null 2>&1; then
+        log "Jaeger ready (attempt $attempt)."
+        break
+    fi
+    if [ "$attempt" -eq 30 ]; then
+        die "Jaeger not ready after 30s"
+    fi
+    sleep 1
+done
+
+# ---------------------------------------------------------------------------
+# Step 3: Generate validator keys
+# ---------------------------------------------------------------------------
+log "Generating $NUM_NODES validator key pairs..."
+
+# Start a temporary standalone xrpld for key generation
+TEMP_DATA="$WORKDIR/temp-keygen"
+mkdir -p "$TEMP_DATA"
+
+# Create a minimal temp config for key generation
+TEMP_CFG="$TEMP_DATA/xrpld.cfg"
+cat > "$TEMP_CFG" <<EOCFG
+[server]
+port_rpc_temp
+
+[port_rpc_temp]
+port = 5099
+ip = 127.0.0.1
+admin = 127.0.0.1
+protocol = http
+
+[node_db]
+type=NuDB
+path=$TEMP_DATA/nudb
+online_delete=256
+
+[database_path]
+$TEMP_DATA/db
+
+[debug_logfile]
+$TEMP_DATA/debug.log
+
+[ssl_verify]
+0
+EOCFG
+
+"$XRPLD" --conf "$TEMP_CFG" -a --start > "$TEMP_DATA/stdout.log" 2>&1 &
+TEMP_PID=$!
+log "Temporary xrpld started (PID $TEMP_PID), waiting for RPC..."
+
+for attempt in $(seq 1 30); do
+    if curl -sf http://localhost:5099 -d '{"method":"server_info"}' >/dev/null 2>&1; then
+        log "Temporary xrpld RPC ready (attempt $attempt)."
+        break
+    fi
+    if [ "$attempt" -eq 30 ]; then
+        kill "$TEMP_PID" 2>/dev/null || true
+        die "Temporary xrpld RPC not ready after 30s"
+    fi
+    sleep 1
+done
+
+declare -a SEEDS
+declare -a PUBKEYS
+
+for i in $(seq 1 "$NUM_NODES"); do
+    result=$(curl -sf http://localhost:5099 -d '{"method":"validation_create"}')
+    seed=$(echo "$result" | jq -r '.result.validation_seed')
+    pubkey=$(echo "$result" | jq -r '.result.validation_public_key')
+    if [ -z "$seed" ] || [ "$seed" = "null" ]; then
+        kill "$TEMP_PID" 2>/dev/null || true
+        die "Failed to generate key pair $i"
+    fi
+    SEEDS+=("$seed")
+    PUBKEYS+=("$pubkey")
+    log "  Node $i: $pubkey"
+done
+
+kill "$TEMP_PID" 2>/dev/null || true
+wait "$TEMP_PID" 2>/dev/null || true
+rm -rf "$TEMP_DATA"
+log "Key generation complete."
+
+# ---------------------------------------------------------------------------
+# Step 4: Generate node configs and validators.txt
+# ---------------------------------------------------------------------------
+log "Generating node configs..."
+
+# Create shared validators.txt
+VALIDATORS_FILE="$WORKDIR/validators.txt"
+{
+    echo "[validators]"
+    for i in $(seq 0 $((NUM_NODES - 1))); do
+        echo "${PUBKEYS[$i]}"
+    done
+} > "$VALIDATORS_FILE"
+
+# Create per-node configs
+for i in $(seq 1 "$NUM_NODES"); do
+    NODE_DIR="$WORKDIR/node$i"
+    mkdir -p "$NODE_DIR/nudb" "$NODE_DIR/db"
+
+    RPC_PORT=$((RPC_PORT_BASE + i - 1))
+    PEER_PORT=$((PEER_PORT_BASE + i - 1))
+    SEED="${SEEDS[$((i - 1))]}"
+
+    # Build ips_fixed list (all peers except self)
+    IPS_FIXED=""
+    for j in $(seq 1 "$NUM_NODES"); do
+        if [ "$j" -ne "$i" ]; then
+            IPS_FIXED="${IPS_FIXED}127.0.0.1 $((PEER_PORT_BASE + j - 1))
+"
+        fi
+    done
+
+    cat > "$NODE_DIR/xrpld.cfg" <<EOCFG
+[server]
+port_rpc
+port_peer
+
+[port_rpc]
+port = $RPC_PORT
+ip = 127.0.0.1
+admin = 127.0.0.1
+protocol = http
+
+[port_peer]
+port = $PEER_PORT
+ip = 0.0.0.0
+protocol = peer
+
+[node_db]
+type=NuDB
+path=$NODE_DIR/nudb
+online_delete=256
+
+[database_path]
+$NODE_DIR/db
+
+[debug_logfile]
+$NODE_DIR/debug.log
+
+[validation_seed]
+$SEED
+
+[validators_file]
+$VALIDATORS_FILE
+
+[ips_fixed]
+${IPS_FIXED}
+[peer_private]
+1
+
+[telemetry]
+enabled=1
+service_instance_id=Node-${i}
+endpoint=http://localhost:4318/v1/traces
+exporter=otlp_http
+sampling_ratio=1.0
+batch_size=512
+batch_delay_ms=2000
+max_queue_size=2048
+trace_rpc=1
+trace_transactions=1
+trace_consensus=1
+trace_peer=1
+trace_ledger=1
+metrics_endpoint=http://localhost:4318/v1/metrics
+
+[insight]
+server=otel
+endpoint=http://localhost:4318/v1/metrics
+prefix=rippled
+
+[rpc_startup]
+{ "command": "log_level", "severity": "warning" }
+
+[ssl_verify]
+0
+EOCFG
+
+    log "  Node $i config: RPC=$RPC_PORT, Peer=$PEER_PORT"
+done
+
+# ---------------------------------------------------------------------------
+# Step 5: Start all 6 nodes
+# ---------------------------------------------------------------------------
+log "Starting $NUM_NODES xrpld nodes..."
+
+for i in $(seq 1 "$NUM_NODES"); do
+    NODE_DIR="$WORKDIR/node$i"
+    "$XRPLD" --conf "$NODE_DIR/xrpld.cfg" --start > "$NODE_DIR/stdout.log" 2>&1 &
+    echo $! > "$NODE_DIR/xrpld.pid"
+    log "  Node $i started (PID $(cat "$NODE_DIR/xrpld.pid"))"
+done
+
+# Give nodes a moment to initialize
+sleep 5
+
+# ---------------------------------------------------------------------------
+# Step 6: Wait for consensus
+# ---------------------------------------------------------------------------
+log "Waiting for nodes to reach 'proposing' state (timeout: ${CONSENSUS_TIMEOUT}s)..."
+
+start_time=$(date +%s)
+nodes_ready=0
+
+while [ "$nodes_ready" -lt "$NUM_NODES" ]; do
+    elapsed=$(( $(date +%s) - start_time ))
+    if [ "$elapsed" -ge "$CONSENSUS_TIMEOUT" ]; then
+        fail "Consensus timeout after ${CONSENSUS_TIMEOUT}s ($nodes_ready/$NUM_NODES nodes ready)"
+        log "Continuing with partial consensus..."
+        break
+    fi
+
+    nodes_ready=0
+    for i in $(seq 1 "$NUM_NODES"); do
+        RPC_PORT=$((RPC_PORT_BASE + i - 1))
+        state=$(curl -sf "http://localhost:$RPC_PORT" \
+            -d '{"method":"server_info"}' 2>/dev/null \
+            | jq -r '.result.info.server_state' 2>/dev/null || echo "unreachable")
+        if [ "$state" = "proposing" ]; then
+            nodes_ready=$((nodes_ready + 1))
+        fi
+    done
+    printf "\r  %d/%d nodes proposing (%ds elapsed)..." "$nodes_ready" "$NUM_NODES" "$elapsed"
+    if [ "$nodes_ready" -lt "$NUM_NODES" ]; then
+        sleep 3
+    fi
+done
+echo ""
+
+if [ "$nodes_ready" -eq "$NUM_NODES" ]; then
+    ok "All $NUM_NODES nodes reached 'proposing' state"
+else
+    fail "Only $nodes_ready/$NUM_NODES nodes reached 'proposing' state"
+fi
+
+# ---------------------------------------------------------------------------
+# Step 6b: Wait for validated ledger
+# ---------------------------------------------------------------------------
+log "Waiting for first validated ledger..."
+for attempt in $(seq 1 60); do
+    val_seq=$(curl -sf "http://localhost:$RPC_PORT_BASE" \
+        -d '{"method":"server_info"}' 2>/dev/null \
+        | jq -r '.result.info.validated_ledger.seq // 0' 2>/dev/null || echo 0)
+    if [ "$val_seq" -gt 2 ] 2>/dev/null; then
+        ok "First validated ledger: seq $val_seq"
+        break
+    fi
+    if [ "$attempt" -eq 60 ]; then
+        fail "No validated ledger after 60s"
+    fi
+    sleep 1
+done
+
+# ---------------------------------------------------------------------------
+# Step 7: Exercise RPC spans (Phase 2)
+# ---------------------------------------------------------------------------
+log "Exercising RPC spans..."
+
+curl -sf "http://localhost:$RPC_PORT_BASE" \
+    -d '{"method":"server_info"}' > /dev/null
+curl -sf "http://localhost:$RPC_PORT_BASE" \
+    -d '{"method":"server_state"}' > /dev/null
+curl -sf "http://localhost:$RPC_PORT_BASE" \
+    -d '{"method":"ledger","params":[{"ledger_index":"current"}]}' > /dev/null
+
+log "RPC commands sent. Waiting 5s for batch export..."
+sleep 5
+
+# ---------------------------------------------------------------------------
+# Step 8: Submit transaction (Phase 3)
+# ---------------------------------------------------------------------------
+log "Submitting Payment transaction..."
+
+# Generate a destination wallet
+log "  Generating destination wallet..."
+wallet_result=$(curl -sf "http://localhost:$RPC_PORT_BASE" \
+    -d '{"method":"wallet_propose"}')
+DEST_ACCOUNT=$(echo "$wallet_result" | jq -r '.result.account_id' 2>/dev/null)
+if [ -z "$DEST_ACCOUNT" ] || [ "$DEST_ACCOUNT" = "null" ]; then
+    fail "Could not generate destination wallet"
+    DEST_ACCOUNT="rrrrrrrrrrrrrrrrrrrrrhoLvTp"  # ACCOUNT_ZERO fallback
+fi
+log "  Destination: $DEST_ACCOUNT"
+
+# Get genesis account info
+acct_result=$(curl -sf "http://localhost:$RPC_PORT_BASE" \
+    -d "{\"method\":\"account_info\",\"params\":[{\"account\":\"$GENESIS_ACCOUNT\"}]}")
+seq_num=$(echo "$acct_result" | jq -r '.result.account_data.Sequence' 2>/dev/null || echo "unknown")
+log "  Genesis account sequence: $seq_num"
+
+# Submit payment
+submit_result=$(curl -sf "http://localhost:$RPC_PORT_BASE" -d "{
+  \"method\": \"submit\",
+  \"params\": [{
+    \"secret\": \"$GENESIS_SEED\",
+    \"tx_json\": {
+      \"TransactionType\": \"Payment\",
+      \"Account\": \"$GENESIS_ACCOUNT\",
+      \"Destination\": \"$DEST_ACCOUNT\",
+      \"Amount\": \"10000000\"
+    }
+  }]
+}")
+
+engine_result=$(echo "$submit_result" | jq -r '.result.engine_result' 2>/dev/null || echo "unknown")
+tx_hash=$(echo "$submit_result" | jq -r '.result.tx_json.hash' 2>/dev/null || echo "unknown")
+
+if [ "$engine_result" = "tesSUCCESS" ] || [ "$engine_result" = "terQUEUED" ]; then
+    ok "Transaction submitted: $engine_result (hash: ${tx_hash:0:16}...)"
+else
+    fail "Transaction submission: $engine_result"
+    log "  Full response: $(echo "$submit_result" | jq -c .result 2>/dev/null)"
+fi
+
+log "Waiting 15s for consensus round + batch export..."
+sleep 15
+
+# ---------------------------------------------------------------------------
+# Step 9: Verify Jaeger traces
+# ---------------------------------------------------------------------------
+log "Verifying spans in Jaeger..."
+
+# Check service registration
+services=$(curl -sf "$JAEGER/api/services" | jq -r '.data[]' 2>/dev/null || echo "")
+if echo "$services" | grep -q "rippled"; then
+    ok "Service 'rippled' registered in Jaeger"
+else
+    fail "Service 'rippled' NOT found in Jaeger (found: $services)"
+fi
+
+log ""
+log "--- Phase 2: RPC Spans ---"
+check_span "rpc.request"
+check_span "rpc.process"
+check_span "rpc.command.server_info"
+check_span "rpc.command.server_state"
+check_span "rpc.command.ledger"
+
+log ""
+log "--- Phase 3: Transaction Spans ---"
+check_span "tx.process"
+check_span "tx.receive"
+check_span "tx.apply"
+
+log ""
+log "--- Phase 4: Consensus Spans ---"
+check_span "consensus.proposal.send"
+check_span "consensus.ledger_close"
+check_span "consensus.accept"
+check_span "consensus.validation.send"
+
+log ""
+log "--- Phase 5: Ledger Spans ---"
+check_span "ledger.build"
+check_span "ledger.validate"
+check_span "ledger.store"
+
+log ""
+log "--- Phase 5: Peer Spans (trace_peer=1) ---"
+check_span "peer.proposal.receive"
+check_span "peer.validation.receive"
+
+# ---------------------------------------------------------------------------
+# Step 9b: Verify log-trace correlation (Phase 8)
+# ---------------------------------------------------------------------------
+log ""
+log "--- Phase 8: Log-Trace Correlation ---"
+check_log_correlation
+
+# ---------------------------------------------------------------------------
+# Step 10: Verify Prometheus spanmetrics
+# ---------------------------------------------------------------------------
+log ""
+log "--- Phase 5: Spanmetrics ---"
+log "Waiting 20s for Prometheus scrape cycle..."
+sleep 20
+
+calls_count=$(curl -sf "$PROM/api/v1/query?query=traces_span_metrics_calls_total" \
+    | jq '.data.result | length' 2>/dev/null || echo 0)
+if [ "$calls_count" -gt 0 ]; then
+    ok "Prometheus: traces_span_metrics_calls_total ($calls_count series)"
+else
+    fail "Prometheus: traces_span_metrics_calls_total (0 series)"
+fi
+
+duration_count=$(curl -sf "$PROM/api/v1/query?query=traces_span_metrics_duration_milliseconds_count" \
+    | jq '.data.result | length' 2>/dev/null || echo 0)
+if [ "$duration_count" -gt 0 ]; then
+    ok "Prometheus: duration histogram ($duration_count series)"
+else
+    fail "Prometheus: duration histogram (0 series)"
+fi
+
+# Check Grafana
+if curl -sf http://localhost:3000/api/health > /dev/null 2>&1; then
+    ok "Grafana: healthy at localhost:3000"
+else
+    fail "Grafana: not reachable at localhost:3000"
+fi
+
+# ---------------------------------------------------------------------------
+# Step 10b: Verify native OTel metrics in Prometheus (beast::insight)
+# ---------------------------------------------------------------------------
+log ""
+log "--- Phase 7: Native OTel Metrics (beast::insight via OTLP) ---"
+log "Waiting 20s for OTLP metric export + Prometheus scrape..."
+sleep 20
+
+check_otel_metric() {
+    local metric_name="$1"
+    local result
+    result=$(curl -sf "$PROM/api/v1/query?query=$metric_name" \
+        | jq '.data.result | length' 2>/dev/null || echo 0)
+    if [ "$result" -gt 0 ]; then
+        ok "OTel: $metric_name ($result series)"
+    else
+        fail "OTel: $metric_name (0 series)"
+    fi
+}
+
+# Node health gauges (ObservableGauge — no _total suffix)
+check_otel_metric "rippled_LedgerMaster_Validated_Ledger_Age"
+check_otel_metric "rippled_LedgerMaster_Published_Ledger_Age"
+check_otel_metric "rippled_job_count"
+
+# State accounting
+check_otel_metric "rippled_State_Accounting_Full_duration"
+
+# Peer finder
+check_otel_metric "rippled_Peer_Finder_Active_Inbound_Peers"
+check_otel_metric "rippled_Peer_Finder_Active_Outbound_Peers"
+
+# RPC counters (Counter — Prometheus adds _total suffix automatically)
+check_otel_metric "rippled_rpc_requests_total"
+
+# Overlay traffic
+check_otel_metric "rippled_total_Bytes_In"
+
+# Verify StatsD receiver is NOT required (no statsd receiver in pipeline)
+log ""
+log "--- Verify StatsD receiver is not required ---"
+statsd_port_check=$(curl -sf "http://localhost:8125" 2>&1 || echo "refused")
+if echo "$statsd_port_check" | grep -qi "refused\|error\|connection"; then
+    ok "StatsD port 8125 is not listening (not required)"
+else
+    fail "StatsD port 8125 appears to be listening (should not be needed)"
+fi
+
+# ---------------------------------------------------------------------------
+# Step 10c: Verify Phase 9 OTel SDK Metrics
+# ---------------------------------------------------------------------------
+log ""
+log "--- Phase 9: OTel SDK Metrics (MetricsRegistry) ---"
+log "Waiting 15s for OTel metric export + Prometheus scrape..."
+sleep 15
+
+check_otel_metric() {
+    local metric_name="$1"
+    local result
+    result=$(curl -sf "$PROM/api/v1/query?query=$metric_name" \
+        | jq '.data.result | length' 2>/dev/null || echo 0)
+    if [ "$result" -gt 0 ]; then
+        ok "OTel: $metric_name ($result series)"
+    else
+        fail "OTel: $metric_name (0 series)"
+    fi
+}
+
+# Task 9.1: NodeStore I/O
+check_otel_metric 'rippled_nodestore_state{metric="node_reads_total"}'
+check_otel_metric 'rippled_nodestore_state{metric="write_load"}'
+
+# Task 9.2: Cache hit rates
+check_otel_metric 'rippled_cache_metrics{metric="SLE_hit_rate"}'
+check_otel_metric 'rippled_cache_metrics{metric="treenode_cache_size"}'
+
+# Task 9.3: TxQ metrics
+check_otel_metric 'rippled_txq_metrics{metric="txq_count"}'
+check_otel_metric 'rippled_txq_metrics{metric="txq_reference_fee_level"}'
+
+# Task 9.4: Per-RPC metrics
+check_otel_metric "rippled_rpc_method_started_total"
+check_otel_metric "rippled_rpc_method_finished_total"
+
+# Task 9.5: Per-job metrics
+check_otel_metric "rippled_job_queued_total"
+check_otel_metric "rippled_job_finished_total"
+
+# Task 9.6: Counted object instances
+check_otel_metric "rippled_object_count"
+
+# Task 9.7: Load factor breakdown
+check_otel_metric 'rippled_load_factor_metrics{metric="load_factor"}'
+check_otel_metric 'rippled_load_factor_metrics{metric="load_factor_server"}'
+
+# ---------------------------------------------------------------------------
+# Step 11: Summary
+# ---------------------------------------------------------------------------
+echo ""
+echo "==========================================================="
+echo "  INTEGRATION TEST RESULTS"
+echo "==========================================================="
+printf "  \033[1;32mPASSED: %d\033[0m\n" "$PASS"
+printf "  \033[1;31mFAILED: %d\033[0m\n" "$FAIL"
+echo "==========================================================="
+echo ""
+echo "  Observability stack is running:"
+echo ""
+echo "    Jaeger UI:     http://localhost:16686"
+echo "    Grafana:       http://localhost:3000"
+echo "    Prometheus:    http://localhost:9090"
+echo "    Loki:          http://localhost:3100"
+echo ""
+echo "  xrpld nodes (6) are running:"
+for i in $(seq 1 "$NUM_NODES"); do
+    RPC_PORT=$((RPC_PORT_BASE + i - 1))
+    PEER_PORT=$((PEER_PORT_BASE + i - 1))
+    echo "    Node $i: RPC=localhost:$RPC_PORT  Peer=:$PEER_PORT  PID=$(cat "$WORKDIR/node$i/xrpld.pid" 2>/dev/null || echo 'unknown')"
+done
+echo ""
+echo "  To tear down:"
+echo "    bash docker/telemetry/integration-test.sh --cleanup"
+echo ""
+echo "==========================================================="
+
+if [ "$FAIL" -gt 0 ]; then
+    exit 1
+fi

docker/telemetry/otel-collector-config.yaml

@@ -0,0 +1,120 @@
+# OpenTelemetry Collector configuration for rippled development.
+#
+# Pipelines:
+#   traces: OTLP receiver -> batch processor -> debug + Jaeger + Tempo + spanmetrics
+#   metrics: OTLP receiver + spanmetrics connector -> Prometheus exporter
+#   logs:   filelog receiver -> batch processor -> otlphttp/Loki (Phase 8)
+#
+# rippled sends traces via OTLP/HTTP to port 4318. The collector batches
+# them, forwards to both Jaeger and Tempo, and derives RED metrics via the
+# spanmetrics connector, which Prometheus scrapes on port 8889.
+#
+# rippled sends beast::insight metrics natively via OTLP/HTTP to port 4318
+# (same endpoint as traces). The OTLP receiver feeds both the traces and
+# metrics pipelines. Metrics are exported to Prometheus alongside
+# span-derived metrics.
+#
+# For backward compatibility, the StatsD receiver config is preserved below
+# but commented out. If you need StatsD fallback (server=statsd in
+# [insight]), uncomment the statsd receiver and add it to the metrics
+# pipeline receivers list.
+#
+# Phase 8: The filelog receiver tails rippled's debug.log files under
+# /var/log/rippled/ (mounted from the host). A regex_parser operator
+# extracts timestamp, partition, severity, and optional trace_id/span_id
+# fields injected by Logs::format(). Parsed logs are exported to Grafana
+# Loki for log-trace correlation.
+
+receivers:
+  otlp:
+    protocols:
+      grpc:
+        endpoint: 0.0.0.0:4317
+      http:
+        endpoint: 0.0.0.0:4318
+  # StatsD receiver — kept for backward compatibility with server=statsd.
+  # Uncomment and add "statsd" to metrics pipeline receivers if needed.
+  # statsd:
+  #   endpoint: "0.0.0.0:8125"
+  #   aggregation_interval: 15s
+  #   enable_metric_type: true
+  #   is_monotonic_counter: true
+  #   timer_histogram_mapping:
+  #     - statsd_type: "timing"
+  #       observer_type: "summary"
+  #       summary:
+  #         percentiles: [0, 50, 90, 95, 99, 100]
+  #     - statsd_type: "histogram"
+  #       observer_type: "summary"
+  #       summary:
+  #         percentiles: [0, 50, 90, 95, 99, 100]
+  # Phase 8: Filelog receiver tails rippled debug.log files for log-trace
+  # correlation. Extracts structured fields (timestamp, partition, severity,
+  # trace_id, span_id, message) via regex. The trace_id and span_id are
+  # optional — only present when the log was emitted within an active span.
+  filelog:
+    include: [/var/log/rippled/*/debug.log]
+    operators:
+      - type: regex_parser
+        regex: '^(?P<timestamp>\S+)\s+(?P<partition>\S+):(?P<severity>\S+)\s+(?:trace_id=(?P<trace_id>[a-f0-9]+)\s+span_id=(?P<span_id>[a-f0-9]+)\s+)?(?P<message>.*)$'
+        timestamp:
+          parse_from: attributes.timestamp
+          layout: "%Y-%b-%d %H:%M:%S.%f"
+
+processors:
+  batch:
+    timeout: 1s
+    send_batch_size: 100
+
+connectors:
+  spanmetrics:
+    # Expose service.instance.id (node public key) as a Prometheus label so
+    # Grafana dashboards can filter metrics by individual node.
+    resource_metrics_key_attributes:
+      - service.instance.id
+    histogram:
+      explicit:
+        buckets: [1ms, 5ms, 10ms, 25ms, 50ms, 100ms, 250ms, 500ms, 1s, 5s]
+    dimensions:
+      - name: xrpl.rpc.command
+      - name: xrpl.rpc.status
+      - name: xrpl.consensus.mode
+      - name: xrpl.tx.local
+      - name: xrpl.peer.proposal.trusted
+      - name: xrpl.peer.validation.trusted
+
+exporters:
+  debug:
+    verbosity: detailed
+  otlp/jaeger:
+    endpoint: jaeger:4317
+    tls:
+      insecure: true
+  otlp/tempo:
+    endpoint: tempo:4317
+    tls:
+      insecure: true
+  # Phase 8: Export logs to Grafana Loki via OTLP/HTTP. Loki 3.x supports
+  # native OTLP ingestion on its /otlp endpoint, replacing the removed
+  # loki exporter (dropped in otel-collector-contrib v0.147.0).
+  otlphttp/loki:
+    endpoint: http://loki:3100/otlp
+  prometheus:
+    endpoint: 0.0.0.0:8889
+
+service:
+  pipelines:
+    traces:
+      receivers: [otlp]
+      processors: [batch]
+      exporters: [debug, otlp/jaeger, otlp/tempo, spanmetrics]
+    metrics:
+      receivers: [otlp, spanmetrics]
+      processors: [batch]
+      exporters: [prometheus]
+    # Phase 8: Log pipeline ingests rippled debug.log via filelog receiver,
+    # batches entries, and exports to Loki for log-trace correlation.
+    logs:
+      receivers: [filelog]
+      processors: [batch]
+      exporters: [otlphttp/loki]

docker/telemetry/prometheus.yml

@@ -0,0 +1,9 @@
+# Prometheus configuration for scraping spanmetrics from OTel Collector.
+global:
+  scrape_interval: 15s
+  evaluation_interval: 15s
+
+scrape_configs:
+  - job_name: otel-collector
+    static_configs:
+      - targets: ["otel-collector:8889"]

docker/telemetry/tempo.yaml

@@ -0,0 +1,59 @@
+# Grafana Tempo configuration for rippled telemetry stack.
+#
+# Runs in single-binary mode for local development.
+# Receives traces via OTLP/gRPC from the OTel Collector and stores
+# them locally. Queryable via Grafana Explore using the Tempo datasource.
+#
+# Search filters are configured on the Grafana datasource side
+# (grafana/provisioning/datasources/tempo.yaml). Tempo auto-indexes
+# all span attributes for search in single-binary mode.
+#
+# For production, replace local storage with S3/GCS backend and adjust
+# retention via the compactor settings. See:
+# https://grafana.com/docs/tempo/latest/configuration/
+
+stream_over_http_enabled: true
+
+server:
+  http_listen_port: 3200
+
+distributor:
+  receivers:
+    otlp:
+      protocols:
+        grpc:
+          endpoint: 0.0.0.0:4317
+
+ingester:
+  max_block_duration: 5m
+
+compactor:
+  compaction:
+    block_retention: 1h
+
+# Enable metrics generator for service graph and span metrics.
+# Produces RED metrics (rate, errors, duration) per service/span,
+# feeding Grafana's service map visualization.
+metrics_generator:
+  registry:
+    external_labels:
+      source: tempo
+  storage:
+    path: /var/tempo/generator/wal
+    remote_write:
+      - url: http://prometheus:9090/api/v1/write
+
+overrides:
+  defaults:
+    metrics_generator:
+      processors:
+        - service-graphs
+        - span-metrics
+
+storage:
+  trace:
+    backend: local
+    wal:
+      path: /var/tempo/wal
+    local:
+      path: /var/tempo/blocks

docker/telemetry/workload/README.md

@@ -0,0 +1,197 @@
+# Telemetry Workload Tools
+
+Synthetic workload generation and validation tools for rippled's OpenTelemetry telemetry stack. These tools validate that all spans, metrics, dashboards, and log-trace correlation work end-to-end under controlled load.
+
+## Quick Start
+
+```bash
+# Build rippled with telemetry enabled
+conan install . --build=missing -o telemetry=True
+cmake --preset default -Dtelemetry=ON
+cmake --build --preset default
+
+# Run full validation (starts everything, runs load, validates)
+docker/telemetry/workload/run-full-validation.sh --xrpld .build/xrpld
+
+# Cleanup when done
+docker/telemetry/workload/run-full-validation.sh --cleanup
+```
+
+## Architecture
+
+```
+run-full-validation.sh (orchestrator)
+  |
+  |-- docker-compose.workload.yaml
+  |     |-- otel-collector (traces + StatsD)
+  |     |-- jaeger (trace search)
+  |     |-- tempo (trace storage)
+  |     |-- prometheus (metrics)
+  |     |-- loki (log aggregation)
+  |     |-- grafana (dashboards)
+  |
+  |-- generate-validator-keys.sh
+  |     -> validator-keys.json, validators.txt
+  |
+  |-- 5x xrpld nodes (local processes, full telemetry)
+  |
+  |-- rpc_load_generator.py (WebSocket RPC traffic)
+  |-- tx_submitter.py (transaction diversity)
+  |
+  |-- validate_telemetry.py (pass/fail checks)
+  |     -> validation-report.json
+  |
+  |-- benchmark.sh (baseline vs telemetry comparison)
+        -> benchmark-report-*.md
+```
+
+## Tools Reference
+
+### run-full-validation.sh
+
+Orchestrates the complete validation pipeline. Starts the telemetry stack, starts a multi-node rippled cluster, generates load, and validates the results.
+
+```bash
+# Full validation with defaults
+./run-full-validation.sh --xrpld /path/to/xrpld
+
+# Custom load parameters
+./run-full-validation.sh --xrpld /path/to/xrpld \
+    --rpc-rate 100 --rpc-duration 300 \
+    --tx-tps 10 --tx-duration 300
+
+# Include performance benchmarks
+./run-full-validation.sh --xrpld /path/to/xrpld --with-benchmark
+
+# Skip Loki checks (if Phase 8 not deployed)
+./run-full-validation.sh --xrpld /path/to/xrpld --skip-loki
+```
+
+### rpc_load_generator.py
+
+Generates RPC traffic matching realistic production distribution:
+
+- 40% health checks (server_info, fee)
+- 30% wallet queries (account_info, account_lines, account_objects)
+- 15% explorer queries (ledger, ledger_data)
+- 10% transaction lookups (tx, account_tx)
+- 5% DEX queries (book_offers, amm_info)
+
+```bash
+# Basic usage
+python3 rpc_load_generator.py --endpoints ws://localhost:6006 --rate 50 --duration 120
+
+# Multiple endpoints (round-robin)
+python3 rpc_load_generator.py \
+    --endpoints ws://localhost:6006 ws://localhost:6007 \
+    --rate 100 --duration 300
+
+# Custom weights
+python3 rpc_load_generator.py --endpoints ws://localhost:6006 \
+    --weights '{"server_info": 80, "account_info": 20}'
+```
+
+### tx_submitter.py
+
+Submits diverse transaction types to exercise the full span and metric surface:
+
+- Payment (XRP transfers)
+- OfferCreate / OfferCancel (DEX activity)
+- TrustSet (trust line creation)
+- NFTokenMint / NFTokenCreateOffer (NFT activity)
+- EscrowCreate / EscrowFinish (escrow lifecycle)
+- AMMCreate / AMMDeposit (AMM pool operations)
+
+```bash
+# Basic usage
+python3 tx_submitter.py --endpoint ws://localhost:6006 --tps 5 --duration 120
+
+# Custom mix
+python3 tx_submitter.py --endpoint ws://localhost:6006 \
+    --weights '{"Payment": 60, "OfferCreate": 20, "TrustSet": 20}'
+```
+
+### validate_telemetry.py
+
+Automated validation that all expected telemetry data exists:
+
+- **Span validation**: All 16+ span types with required attributes
+- **Metric validation**: SpanMetrics, StatsD, Phase 9 metrics
+- **Log-trace correlation**: trace_id/span_id in Loki logs
+- **Dashboard validation**: All 10 Grafana dashboards accessible
+
+```bash
+# Run all validations
+python3 validate_telemetry.py --report /tmp/report.json
+
+# Skip Loki checks
+python3 validate_telemetry.py --skip-loki --report /tmp/report.json
+```
+
+### benchmark.sh
+
+Compares baseline (no telemetry) vs telemetry-enabled performance:
+
+```bash
+./benchmark.sh --xrpld /path/to/xrpld --duration 300
+```
+
+Thresholds (configurable via environment):
+
+| Metric            | Threshold | Env Variable                |
+| ----------------- | --------- | --------------------------- |
+| CPU overhead      | < 3%      | BENCH_CPU_OVERHEAD_PCT      |
+| Memory overhead   | < 5MB     | BENCH_MEM_OVERHEAD_MB       |
+| RPC p99 latency   | < 2ms     | BENCH_RPC_LATENCY_IMPACT_MS |
+| Throughput impact | < 5%      | BENCH_TPS_IMPACT_PCT        |
+| Consensus impact  | < 1%      | BENCH_CONSENSUS_IMPACT_PCT  |
+
+## Reading Validation Reports
+
+The validation report (`validation-report.json`) is structured as:
+
+```json
+{
+  "summary": {
+    "total": 45,
+    "passed": 42,
+    "failed": 3,
+    "all_passed": false
+  },
+  "checks": [
+    {
+      "name": "span.rpc.request",
+      "category": "span",
+      "passed": true,
+      "message": "rpc.request: 15 traces found",
+      "details": { "trace_count": 15 }
+    }
+  ]
+}
+```
+
+Categories:
+
+- **span**: Span type existence and attribute validation
+- **metric**: Prometheus metric existence
+- **log**: Log-trace correlation checks
+- **dashboard**: Grafana dashboard accessibility
+
+## CI Integration
+
+The validation runs as a GitHub Actions workflow (`.github/workflows/telemetry-validation.yml`):
+
+- Triggered manually or on pushes to telemetry branches
+- Builds rippled, starts the full stack, runs load, validates
+- Uploads reports as artifacts
+- Posts summary to PR
+
+## Configuration Files
+
+| File                           | Purpose                                         |
+| ------------------------------ | ----------------------------------------------- |
+| `expected_spans.json`          | Span inventory (names, attributes, hierarchies) |
+| `expected_metrics.json`        | Metric inventory (SpanMetrics, StatsD, Phase 9) |
+| `test_accounts.json`           | Test account roles (keys generated at runtime)  |
+| `xrpld-validator.cfg.template` | Node config template with placeholders          |
+| `requirements.txt`             | Python dependencies                             |

docker/telemetry/workload/benchmark.sh

@@ -0,0 +1,379 @@
+#!/usr/bin/env bash
+# benchmark.sh — Performance benchmark for rippled telemetry overhead.
+#
+# Runs two identical workloads against a rippled cluster:
+#   1. Baseline: telemetry disabled ([telemetry] enabled=0)
+#   2. Telemetry: full telemetry enabled (traces + StatsD + all categories)
+#
+# Compares CPU, memory, RPC latency, TPS, and consensus round time.
+# Outputs a Markdown table with pass/fail against configured thresholds.
+#
+# Usage:
+#   ./benchmark.sh --xrpld /path/to/xrpld --duration 300
+#
+# Thresholds (configurable via environment variables):
+#   BENCH_CPU_OVERHEAD_PCT=3       CPU overhead < 3%
+#   BENCH_MEM_OVERHEAD_MB=5        Memory overhead < 5MB
+#   BENCH_RPC_LATENCY_IMPACT_MS=2  RPC p99 latency impact < 2ms
+#   BENCH_TPS_IMPACT_PCT=5         Throughput impact < 5%
+#   BENCH_CONSENSUS_IMPACT_PCT=1   Consensus round time impact < 1%
+
+set -euo pipefail
+
+# ---------------------------------------------------------------------------
+# Colored output helpers
+# ---------------------------------------------------------------------------
+log()   { printf "\033[1;34m[BENCH]\033[0m  %s\n" "$*"; }
+ok()    { printf "\033[1;32m[BENCH]\033[0m  %s\n" "$*"; }
+warn()  { printf "\033[1;33m[BENCH]\033[0m  %s\n" "$*"; }
+fail()  { printf "\033[1;31m[BENCH]\033[0m  %s\n" "$*"; }
+die()   { printf "\033[1;31m[BENCH]\033[0m  %s\n" "$*" >&2; exit 1; }
+
+# ---------------------------------------------------------------------------
+# Defaults and thresholds
+# ---------------------------------------------------------------------------
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+REPO_ROOT="$(cd "$SCRIPT_DIR/../../.." && pwd)"
+
+# Configurable thresholds via environment variables.
+CPU_THRESHOLD="${BENCH_CPU_OVERHEAD_PCT:-3}"
+MEM_THRESHOLD="${BENCH_MEM_OVERHEAD_MB:-5}"
+RPC_THRESHOLD="${BENCH_RPC_LATENCY_IMPACT_MS:-2}"
+TPS_THRESHOLD="${BENCH_TPS_IMPACT_PCT:-5}"
+CONSENSUS_THRESHOLD="${BENCH_CONSENSUS_IMPACT_PCT:-1}"
+
+XRPLD="${BENCH_XRPLD:-$REPO_ROOT/.build/xrpld}"
+DURATION=300
+NUM_NODES=3
+WORKDIR="/tmp/xrpld-benchmark"
+RESULTS_DIR="$SCRIPT_DIR/benchmark-results"
+RPC_PORT_BASE=5020
+PEER_PORT_BASE=51250
+
+# ---------------------------------------------------------------------------
+# Argument parsing
+# ---------------------------------------------------------------------------
+usage() {
+    echo "Usage: $0 [OPTIONS]"
+    echo ""
+    echo "Options:"
+    echo "  --xrpld PATH      Path to xrpld binary (default: \$REPO_ROOT/.build/xrpld)"
+    echo "  --duration SECS   Benchmark duration per run (default: 300)"
+    echo "  --nodes NUM       Number of validator nodes (default: 3)"
+    echo "  --output DIR      Results output directory"
+    echo "  -h, --help        Show this help"
+    exit 0
+}
+
+while [ $# -gt 0 ]; do
+    case "$1" in
+        --xrpld)   XRPLD="$2"; shift 2 ;;
+        --duration) DURATION="$2"; shift 2 ;;
+        --nodes)   NUM_NODES="$2"; shift 2 ;;
+        --output)  RESULTS_DIR="$2"; shift 2 ;;
+        -h|--help) usage ;;
+        *) die "Unknown option: $1" ;;
+    esac
+done
+
+# Validate prerequisites.
+[ -x "$XRPLD" ] || die "xrpld not found at $XRPLD"
+command -v jq >/dev/null 2>&1 || die "jq not found"
+command -v bc >/dev/null 2>&1 || die "bc not found"
+command -v curl >/dev/null 2>&1 || die "curl not found"
+
+mkdir -p "$RESULTS_DIR"
+TIMESTAMP=$(date +%Y%m%d_%H%M%S)
+
+# ---------------------------------------------------------------------------
+# Node cluster management
+# ---------------------------------------------------------------------------
+start_cluster() {
+    local telemetry_enabled="$1"
+    local label="$2"
+
+    log "Starting $NUM_NODES-node cluster ($label, telemetry=$telemetry_enabled)..."
+
+    rm -rf "$WORKDIR"
+    mkdir -p "$WORKDIR"
+
+    # Generate keys using first node.
+    bash "$SCRIPT_DIR/generate-validator-keys.sh" "$XRPLD" "$NUM_NODES" "$WORKDIR"
+
+    # Build per-node configs.
+    for i in $(seq 1 "$NUM_NODES"); do
+        local node_dir="$WORKDIR/node$i"
+        mkdir -p "$node_dir/nudb" "$node_dir/db"
+
+        local rpc_port=$((RPC_PORT_BASE + i - 1))
+        local peer_port=$((PEER_PORT_BASE + i - 1))
+        local seed
+        seed=$(jq -r ".[$((i-1))].seed" "$WORKDIR/validator-keys.json")
+
+        # Build ips_fixed list.
+        local ips_fixed=""
+        for j in $(seq 1 "$NUM_NODES"); do
+            if [ "$j" -ne "$i" ]; then
+                ips_fixed="${ips_fixed}127.0.0.1 $((PEER_PORT_BASE + j - 1))
+"
+            fi
+        done
+
+        # Build telemetry section.
+        local telemetry_section=""
+        if [ "$telemetry_enabled" = "1" ]; then
+            telemetry_section="
+[telemetry]
+enabled=1
+service_instance_id=bench-node-${i}
+endpoint=http://localhost:4318/v1/traces
+exporter=otlp_http
+sampling_ratio=1.0
+batch_size=512
+batch_delay_ms=2000
+max_queue_size=2048
+trace_rpc=1
+trace_transactions=1
+trace_consensus=1
+trace_peer=1
+trace_ledger=1
+
+[insight]
+server=statsd
+address=127.0.0.1:8125
+prefix=rippled"
+        else
+            telemetry_section="
+[telemetry]
+enabled=0"
+        fi
+
+        cat > "$node_dir/xrpld.cfg" <<EOCFG
+[server]
+port_rpc
+port_peer
+
+[port_rpc]
+port = $rpc_port
+ip = 127.0.0.1
+admin = 127.0.0.1
+protocol = http
+
+[port_peer]
+port = $peer_port
+ip = 0.0.0.0
+protocol = peer
+
+[node_db]
+type=NuDB
+path=$node_dir/nudb
+online_delete=256
+
+[database_path]
+$node_dir/db
+
+[debug_logfile]
+$node_dir/debug.log
+
+[validation_seed]
+$seed
+
+[validators_file]
+$WORKDIR/validators.txt
+
+[ips_fixed]
+${ips_fixed}
+[peer_private]
+1
+${telemetry_section}
+
+[rpc_startup]
+{ "command": "log_level", "severity": "warning" }
+
+[ssl_verify]
+0
+EOCFG
+
+        "$XRPLD" --conf "$node_dir/xrpld.cfg" --start > "$node_dir/stdout.log" 2>&1 &
+        echo $! > "$node_dir/xrpld.pid"
+    done
+
+    # Wait for consensus.
+    log "Waiting for consensus..."
+    for attempt in $(seq 1 120); do
+        local ready=0
+        for i in $(seq 1 "$NUM_NODES"); do
+            local port=$((RPC_PORT_BASE + i - 1))
+            local state
+            state=$(curl -sf "http://localhost:$port" \
+                -d '{"method":"server_info"}' 2>/dev/null \
+                | jq -r '.result.info.server_state' 2>/dev/null || echo "")
+            if [ "$state" = "proposing" ]; then
+                ready=$((ready + 1))
+            fi
+        done
+        if [ "$ready" -ge "$NUM_NODES" ]; then
+            ok "All $NUM_NODES nodes proposing (attempt $attempt)"
+            break
+        fi
+        if [ "$attempt" -eq 120 ]; then
+            warn "Consensus timeout — $ready/$NUM_NODES nodes ready"
+        fi
+        sleep 1
+    done
+
+    # Let the cluster stabilize.
+    sleep 5
+}
+
+stop_cluster() {
+    log "Stopping cluster..."
+    for i in $(seq 1 "$NUM_NODES"); do
+        local pidfile="$WORKDIR/node$i/xrpld.pid"
+        if [ -f "$pidfile" ]; then
+            kill "$(cat "$pidfile")" 2>/dev/null || true
+        fi
+    done
+    pkill -f "$WORKDIR" 2>/dev/null || true
+    sleep 3
+}
+
+# Build RPC ports CSV string.
+rpc_ports_csv() {
+    local ports=""
+    for i in $(seq 1 "$NUM_NODES"); do
+        [ -n "$ports" ] && ports="$ports,"
+        ports="$ports$((RPC_PORT_BASE + i - 1))"
+    done
+    echo "$ports"
+}
+
+# ---------------------------------------------------------------------------
+# Run benchmark
+# ---------------------------------------------------------------------------
+log "="
+log "  rippled Telemetry Performance Benchmark"
+log "  Nodes: $NUM_NODES | Duration: ${DURATION}s | Binary: $XRPLD"
+log "="
+
+# --- Baseline run ---
+BASELINE_FILE="$RESULTS_DIR/baseline-${TIMESTAMP}.json"
+start_cluster "0" "baseline"
+bash "$SCRIPT_DIR/collect_system_metrics.sh" "$(rpc_ports_csv)" "$DURATION" "$BASELINE_FILE"
+stop_cluster
+
+# --- Telemetry run ---
+TELEMETRY_FILE="$RESULTS_DIR/telemetry-${TIMESTAMP}.json"
+start_cluster "1" "telemetry"
+bash "$SCRIPT_DIR/collect_system_metrics.sh" "$(rpc_ports_csv)" "$DURATION" "$TELEMETRY_FILE"
+stop_cluster
+
+# ---------------------------------------------------------------------------
+# Compare results
+# ---------------------------------------------------------------------------
+log "Comparing results..."
+
+read_metric() {
+    local file="$1"
+    local key="$2"
+    jq -r ".$key // 0" "$file"
+}
+
+BASE_CPU=$(read_metric "$BASELINE_FILE" "cpu_pct_avg")
+TELE_CPU=$(read_metric "$TELEMETRY_FILE" "cpu_pct_avg")
+CPU_DELTA=$(echo "scale=2; $TELE_CPU - $BASE_CPU" | bc 2>/dev/null || echo "0")
+
+BASE_MEM=$(read_metric "$BASELINE_FILE" "memory_rss_mb_peak")
+TELE_MEM=$(read_metric "$TELEMETRY_FILE" "memory_rss_mb_peak")
+MEM_DELTA=$(echo "scale=2; $TELE_MEM - $BASE_MEM" | bc 2>/dev/null || echo "0")
+
+BASE_RPC=$(read_metric "$BASELINE_FILE" "rpc_p99_ms")
+TELE_RPC=$(read_metric "$TELEMETRY_FILE" "rpc_p99_ms")
+RPC_DELTA=$(echo "scale=2; $TELE_RPC - $BASE_RPC" | bc 2>/dev/null || echo "0")
+
+BASE_TPS=$(read_metric "$BASELINE_FILE" "tps")
+TELE_TPS=$(read_metric "$TELEMETRY_FILE" "tps")
+if [ "$(echo "$BASE_TPS > 0" | bc 2>/dev/null)" = "1" ]; then
+    TPS_IMPACT=$(echo "scale=2; ($BASE_TPS - $TELE_TPS) / $BASE_TPS * 100" | bc 2>/dev/null || echo "0")
+else
+    TPS_IMPACT="0"
+fi
+
+BASE_CONS=$(read_metric "$BASELINE_FILE" "consensus_round_p95_ms")
+TELE_CONS=$(read_metric "$TELEMETRY_FILE" "consensus_round_p95_ms")
+if [ "$(echo "$BASE_CONS > 0" | bc 2>/dev/null)" = "1" ]; then
+    CONS_IMPACT=$(echo "scale=2; ($TELE_CONS - $BASE_CONS) / $BASE_CONS * 100" | bc 2>/dev/null || echo "0")
+else
+    CONS_IMPACT="0"
+fi
+
+# ---------------------------------------------------------------------------
+# Pass/fail checks
+# ---------------------------------------------------------------------------
+PASS_COUNT=0
+FAIL_COUNT=0
+
+check_threshold() {
+    local name="$1"
+    local actual="$2"
+    local threshold="$3"
+    local unit="$4"
+
+    # Compare: actual <= threshold
+    if [ "$(echo "$actual <= $threshold" | bc 2>/dev/null)" = "1" ]; then
+        ok "$name: ${actual}${unit} <= ${threshold}${unit} PASS"
+        PASS_COUNT=$((PASS_COUNT + 1))
+        echo "PASS"
+    else
+        fail "$name: ${actual}${unit} > ${threshold}${unit} FAIL"
+        FAIL_COUNT=$((FAIL_COUNT + 1))
+        echo "FAIL"
+    fi
+}
+
+CPU_RESULT=$(check_threshold "CPU overhead" "$CPU_DELTA" "$CPU_THRESHOLD" "%")
+MEM_RESULT=$(check_threshold "Memory overhead" "$MEM_DELTA" "$MEM_THRESHOLD" "MB")
+RPC_RESULT=$(check_threshold "RPC p99 impact" "$RPC_DELTA" "$RPC_THRESHOLD" "ms")
+TPS_RESULT=$(check_threshold "TPS impact" "$TPS_IMPACT" "$TPS_THRESHOLD" "%")
+CONS_RESULT=$(check_threshold "Consensus impact" "$CONS_IMPACT" "$CONSENSUS_THRESHOLD" "%")
+
+# ---------------------------------------------------------------------------
+# Output Markdown table
+# ---------------------------------------------------------------------------
+REPORT_FILE="$RESULTS_DIR/benchmark-report-${TIMESTAMP}.md"
+
+cat > "$REPORT_FILE" <<EOMD
+# Telemetry Performance Benchmark Report
+
+**Date**: $(date -u +"%Y-%m-%d %H:%M:%S UTC")
+**Nodes**: $NUM_NODES | **Duration**: ${DURATION}s per run
+**Binary**: $XRPLD
+
+## Results
+
+| Metric | Baseline | Telemetry | Delta | Threshold | Result |
+|--------|----------|-----------|-------|-----------|--------|
+| CPU (avg %) | ${BASE_CPU}% | ${TELE_CPU}% | ${CPU_DELTA}% | < ${CPU_THRESHOLD}% | ${CPU_RESULT} |
+| Memory RSS (peak MB) | ${BASE_MEM} MB | ${TELE_MEM} MB | ${MEM_DELTA} MB | < ${MEM_THRESHOLD} MB | ${MEM_RESULT} |
+| RPC p99 Latency (ms) | ${BASE_RPC} ms | ${TELE_RPC} ms | ${RPC_DELTA} ms | < ${RPC_THRESHOLD} ms | ${RPC_RESULT} |
+| Throughput (TPS) | ${BASE_TPS} | ${TELE_TPS} | ${TPS_IMPACT}% | < ${TPS_THRESHOLD}% | ${TPS_RESULT} |
+| Consensus Round p95 (ms) | ${BASE_CONS} ms | ${TELE_CONS} ms | ${CONS_IMPACT}% | < ${CONSENSUS_THRESHOLD}% | ${CONS_RESULT} |
+
+## Summary
+
+- **Passed**: $PASS_COUNT / $((PASS_COUNT + FAIL_COUNT))
+- **Failed**: $FAIL_COUNT / $((PASS_COUNT + FAIL_COUNT))
+
+## Raw Data
+
+- Baseline: \`$(basename "$BASELINE_FILE")\`
+- Telemetry: \`$(basename "$TELEMETRY_FILE")\`
+EOMD
+
+ok "Benchmark report written to $REPORT_FILE"
+cat "$REPORT_FILE"
+
+# Exit with failure if any check failed.
+if [ "$FAIL_COUNT" -gt 0 ]; then
+    exit 1
+fi

docker/telemetry/workload/collect_system_metrics.sh

@@ -0,0 +1,233 @@
+#!/usr/bin/env bash
+# collect_system_metrics.sh — Collect CPU, memory, and RPC latency metrics
+# from running xrpld nodes for benchmark comparison.
+#
+# Samples system metrics at regular intervals and writes a JSON summary.
+# Used by benchmark.sh for baseline vs telemetry comparison.
+#
+# Usage:
+#   ./collect_system_metrics.sh <rpc_ports_csv> <duration_seconds> <output_file>
+#
+# Example:
+#   ./collect_system_metrics.sh "5005,5006,5007" 300 /tmp/metrics-baseline.json
+#
+# Output JSON format:
+#   {
+#     "cpu_pct_avg": 12.5,
+#     "memory_rss_mb_peak": 450.2,
+#     "rpc_p99_ms": 15.3,
+#     "tps": 4.8,
+#     "consensus_round_p95_ms": 3200,
+#     "samples": 60
+#   }
+
+set -euo pipefail
+
+# ---------------------------------------------------------------------------
+# Colored output helpers
+# ---------------------------------------------------------------------------
+log()  { printf "\033[1;34m[METRICS]\033[0m %s\n" "$*"; }
+ok()   { printf "\033[1;32m[METRICS]\033[0m %s\n" "$*"; }
+die()  { printf "\033[1;31m[METRICS]\033[0m %s\n" "$*" >&2; exit 1; }
+
+# ---------------------------------------------------------------------------
+# Argument parsing
+# ---------------------------------------------------------------------------
+usage() {
+    echo "Usage: $0 <rpc_ports_csv> <duration_seconds> <output_file>"
+    echo ""
+    echo "Arguments:"
+    echo "  rpc_ports_csv     Comma-separated RPC ports (e.g., 5005,5006,5007)"
+    echo "  duration_seconds  How long to collect metrics"
+    echo "  output_file       Path to write JSON results"
+    exit 1
+}
+
+if [ $# -lt 3 ]; then
+    usage
+fi
+
+RPC_PORTS_CSV="$1"
+DURATION="$2"
+OUTPUT_FILE="$3"
+
+IFS=',' read -ra RPC_PORTS <<< "$RPC_PORTS_CSV"
+SAMPLE_INTERVAL=5
+SAMPLES=$((DURATION / SAMPLE_INTERVAL))
+
+log "Collecting metrics for ${DURATION}s (${SAMPLES} samples, ${#RPC_PORTS[@]} nodes)..."
+
+# ---------------------------------------------------------------------------
+# Temporary files for aggregation
+# ---------------------------------------------------------------------------
+TMPDIR_METRICS="$(mktemp -d)"
+CPU_FILE="$TMPDIR_METRICS/cpu.txt"
+MEM_FILE="$TMPDIR_METRICS/mem.txt"
+RPC_FILE="$TMPDIR_METRICS/rpc.txt"
+LEDGER_FILE="$TMPDIR_METRICS/ledger.txt"
+
+touch "$CPU_FILE" "$MEM_FILE" "$RPC_FILE" "$LEDGER_FILE"
+
+cleanup() {
+    rm -rf "$TMPDIR_METRICS"
+}
+trap cleanup EXIT
+
+# ---------------------------------------------------------------------------
+# Get initial ledger sequence for TPS calculation
+# ---------------------------------------------------------------------------
+INITIAL_SEQ=0
+INITIAL_TIME=$(date +%s)
+for port in "${RPC_PORTS[@]}"; do
+    seq=$(curl -sf "http://localhost:$port" \
+        -d '{"method":"server_info"}' 2>/dev/null \
+        | jq -r '.result.info.validated_ledger.seq // 0' 2>/dev/null || echo 0)
+    if [ "$seq" -gt "$INITIAL_SEQ" ]; then
+        INITIAL_SEQ=$seq
+    fi
+done
+log "Initial validated ledger seq: $INITIAL_SEQ"
+
+# ---------------------------------------------------------------------------
+# Sampling loop
+# ---------------------------------------------------------------------------
+for sample in $(seq 1 "$SAMPLES"); do
+    # Collect CPU usage for xrpld processes.
+    # Uses ps to find all xrpld processes and average their CPU%.
+    cpu_sum=0
+    cpu_count=0
+    while IFS= read -r line; do
+        cpu_val=$(echo "$line" | awk '{print $1}')
+        if [ -n "$cpu_val" ] && [ "$cpu_val" != "0.0" ]; then
+            cpu_sum=$(echo "$cpu_sum + $cpu_val" | bc 2>/dev/null || echo "$cpu_sum")
+            cpu_count=$((cpu_count + 1))
+        fi
+    done < <(ps aux 2>/dev/null | grep '[x]rpld' | awk '{print $3}')
+
+    if [ "$cpu_count" -gt 0 ]; then
+        cpu_avg=$(echo "scale=2; $cpu_sum / $cpu_count" | bc 2>/dev/null || echo "0")
+        echo "$cpu_avg" >> "$CPU_FILE"
+    fi
+
+    # Collect memory RSS for xrpld processes.
+    while IFS= read -r line; do
+        rss_kb=$(echo "$line" | awk '{print $1}')
+        if [ -n "$rss_kb" ] && [ "$rss_kb" != "0" ]; then
+            rss_mb=$(echo "scale=2; $rss_kb / 1024" | bc 2>/dev/null || echo "0")
+            echo "$rss_mb" >> "$MEM_FILE"
+        fi
+    done < <(ps aux 2>/dev/null | grep '[x]rpld' | awk '{print $6}')
+
+    # Collect RPC latency from each node.
+    for port in "${RPC_PORTS[@]}"; do
+        start_ms=$(date +%s%N)
+        curl -sf "http://localhost:$port" \
+            -d '{"method":"server_info"}' > /dev/null 2>&1 || true
+        end_ms=$(date +%s%N)
+        latency_ms=$(( (end_ms - start_ms) / 1000000 ))
+        echo "$latency_ms" >> "$RPC_FILE"
+    done
+
+    # Record current validated ledger seq.
+    for port in "${RPC_PORTS[@]}"; do
+        seq=$(curl -sf "http://localhost:$port" \
+            -d '{"method":"server_info"}' 2>/dev/null \
+            | jq -r '.result.info.validated_ledger.seq // 0' 2>/dev/null || echo 0)
+        echo "$seq" >> "$LEDGER_FILE"
+        break  # Only need one node's seq per sample.
+    done
+
+    # Progress indicator.
+    if [ $((sample % 10)) -eq 0 ]; then
+        log "  Sample $sample/$SAMPLES..."
+    fi
+
+    sleep "$SAMPLE_INTERVAL"
+done
+
+# ---------------------------------------------------------------------------
+# Compute aggregated metrics
+# ---------------------------------------------------------------------------
+log "Computing aggregated metrics..."
+
+# CPU average.
+if [ -s "$CPU_FILE" ]; then
+    CPU_AVG=$(awk '{ sum += $1; n++ } END { if (n>0) printf "%.2f", sum/n; else print "0" }' "$CPU_FILE")
+else
+    CPU_AVG="0"
+fi
+
+# Memory peak RSS (MB).
+if [ -s "$MEM_FILE" ]; then
+    MEM_PEAK=$(sort -n "$MEM_FILE" | tail -1)
+else
+    MEM_PEAK="0"
+fi
+
+# RPC latency p99 (ms).
+if [ -s "$RPC_FILE" ]; then
+    RPC_COUNT=$(wc -l < "$RPC_FILE")
+    P99_INDEX=$(echo "scale=0; $RPC_COUNT * 99 / 100" | bc)
+    RPC_P99=$(sort -n "$RPC_FILE" | sed -n "${P99_INDEX}p")
+    [ -z "$RPC_P99" ] && RPC_P99="0"
+else
+    RPC_P99="0"
+fi
+
+# TPS calculation from ledger sequence advancement.
+FINAL_SEQ=0
+for port in "${RPC_PORTS[@]}"; do
+    seq=$(curl -sf "http://localhost:$port" \
+        -d '{"method":"server_info"}' 2>/dev/null \
+        | jq -r '.result.info.validated_ledger.seq // 0' 2>/dev/null || echo 0)
+    if [ "$seq" -gt "$FINAL_SEQ" ]; then
+        FINAL_SEQ=$seq
+    fi
+done
+FINAL_TIME=$(date +%s)
+ELAPSED=$((FINAL_TIME - INITIAL_TIME))
+LEDGER_ADVANCE=$((FINAL_SEQ - INITIAL_SEQ))
+if [ "$ELAPSED" -gt 0 ] && [ "$LEDGER_ADVANCE" -gt 0 ]; then
+    # Rough TPS: assume ~avg_txs_per_ledger * ledgers / elapsed.
+    # Without tx count, use ledger close rate as proxy.
+    TPS=$(echo "scale=2; $LEDGER_ADVANCE / $ELAPSED" | bc 2>/dev/null || echo "0")
+else
+    TPS="0"
+fi
+
+# Consensus round time p95 (from ledger close interval).
+# Approximate by looking at ledger sequence progression intervals.
+if [ -s "$LEDGER_FILE" ]; then
+    # Calculate intervals between consecutive ledger sequences.
+    LEDGER_COUNT=$(wc -l < "$LEDGER_FILE")
+    # Rough estimate: DURATION / number_of_distinct_ledgers * 1000 ms
+    UNIQUE_LEDGERS=$(sort -u "$LEDGER_FILE" | wc -l)
+    if [ "$UNIQUE_LEDGERS" -gt 1 ]; then
+        CONSENSUS_P95=$(echo "scale=0; $DURATION * 1000 / ($UNIQUE_LEDGERS - 1)" | bc 2>/dev/null || echo "0")
+    else
+        CONSENSUS_P95="0"
+    fi
+else
+    CONSENSUS_P95="0"
+fi
+
+# ---------------------------------------------------------------------------
+# Write output JSON
+# ---------------------------------------------------------------------------
+cat > "$OUTPUT_FILE" <<EOF_JSON
+{
+  "cpu_pct_avg": $CPU_AVG,
+  "memory_rss_mb_peak": $MEM_PEAK,
+  "rpc_p99_ms": $RPC_P99,
+  "tps": $TPS,
+  "consensus_round_p95_ms": $CONSENSUS_P95,
+  "samples": $SAMPLES,
+  "duration_seconds": $DURATION,
+  "node_count": ${#RPC_PORTS[@]},
+  "initial_ledger_seq": $INITIAL_SEQ,
+  "final_ledger_seq": $FINAL_SEQ
+}
+EOF_JSON
+
+ok "Metrics written to $OUTPUT_FILE"
+cat "$OUTPUT_FILE"

docker/telemetry/workload/expected_metrics.json

@@ -0,0 +1,101 @@
+{
+  "description": "Expected metric inventory for rippled telemetry validation. Sourced from 09-data-collection-reference.md.",
+  "spanmetrics": {
+    "description": "SpanMetrics-derived RED metrics from the OTel Collector spanmetrics connector.",
+    "metrics": [
+      "traces_span_metrics_calls_total",
+      "traces_span_metrics_duration_milliseconds_bucket",
+      "traces_span_metrics_duration_milliseconds_count",
+      "traces_span_metrics_duration_milliseconds_sum"
+    ],
+    "required_labels": [
+      "span_name",
+      "status_code",
+      "service_name",
+      "span_kind"
+    ],
+    "dimension_labels": [
+      "xrpl_rpc_command",
+      "xrpl_rpc_status",
+      "xrpl_consensus_mode",
+      "xrpl_tx_local",
+      "xrpl_peer_proposal_trusted",
+      "xrpl_peer_validation_trusted"
+    ]
+  },
+  "statsd_gauges": {
+    "description": "beast::insight gauges emitted via StatsD UDP.",
+    "metrics": [
+      "rippled_LedgerMaster_Validated_Ledger_Age",
+      "rippled_LedgerMaster_Published_Ledger_Age",
+      "rippled_State_Accounting_Full_duration",
+      "rippled_Peer_Finder_Active_Inbound_Peers",
+      "rippled_Peer_Finder_Active_Outbound_Peers",
+      "rippled_job_count"
+    ]
+  },
+  "statsd_counters": {
+    "description": "beast::insight counters emitted via StatsD UDP.",
+    "metrics": ["rippled_rpc_requests", "rippled_ledger_fetches"]
+  },
+  "statsd_histograms": {
+    "description": "beast::insight timers/histograms emitted via StatsD UDP.",
+    "metrics": ["rippled_rpc_time", "rippled_rpc_size", "rippled_ios_latency"]
+  },
+  "overlay_traffic": {
+    "description": "Overlay traffic metrics (subset — full list has 45+ categories).",
+    "metrics": [
+      "rippled_total_Bytes_In",
+      "rippled_total_Bytes_Out",
+      "rippled_total_Messages_In",
+      "rippled_total_Messages_Out"
+    ]
+  },
+  "phase9_nodestore": {
+    "description": "Phase 9 NodeStore I/O metrics (via beast::insight extensions).",
+    "metrics": [
+      "rippled_nodestore_reads_total",
+      "rippled_nodestore_writes",
+      "rippled_nodestore_read_bytes",
+      "rippled_nodestore_written_bytes"
+    ]
+  },
+  "phase9_cache": {
+    "description": "Phase 9 cache hit rate metrics (via OTel MetricsRegistry).",
+    "metrics": ["rippled_cache_SLE_hit_rate", "rippled_cache_treenode_size"]
+  },
+  "phase9_txq": {
+    "description": "Phase 9 transaction queue metrics (via OTel MetricsRegistry).",
+    "metrics": ["rippled_txq_count", "rippled_txq_max_size"]
+  },
+  "phase9_rpc_method": {
+    "description": "Phase 9 per-RPC-method metrics (via OTel Metrics SDK).",
+    "metrics": [
+      "rippled_rpc_method_started_total",
+      "rippled_rpc_method_finished_total"
+    ]
+  },
+  "phase9_objects": {
+    "description": "Phase 9 counted object instances.",
+    "metrics": ["rippled_object_count"]
+  },
+  "phase9_load": {
+    "description": "Phase 9 fee escalation and load factor metrics.",
+    "metrics": ["rippled_load_factor"]
+  },
+  "grafana_dashboards": {
+    "description": "All 10 Grafana dashboards that must render data.",
+    "uids": [
+      "rippled-rpc-perf",
+      "rippled-transactions",
+      "rippled-consensus",
+      "rippled-ledger-ops",
+      "rippled-peer-net",
+      "rippled-statsd-node-health",
+      "rippled-statsd-network",
+      "rippled-statsd-rpc",
+      "rippled-statsd-overlay-detail",
+      "rippled-statsd-ledger-sync"
+    ]
+  }
+}

docker/telemetry/workload/expected_spans.json

@@ -0,0 +1,172 @@
+{
+  "description": "Expected span inventory for rippled telemetry validation. Sourced from 09-data-collection-reference.md.",
+  "spans": [
+    {
+      "name": "rpc.request",
+      "category": "rpc",
+      "parent": null,
+      "required_attributes": [],
+      "config_flag": "trace_rpc"
+    },
+    {
+      "name": "rpc.process",
+      "category": "rpc",
+      "parent": "rpc.request",
+      "required_attributes": [],
+      "config_flag": "trace_rpc"
+    },
+    {
+      "name": "rpc.ws_message",
+      "category": "rpc",
+      "parent": null,
+      "required_attributes": [],
+      "config_flag": "trace_rpc"
+    },
+    {
+      "name": "rpc.command.*",
+      "category": "rpc",
+      "parent": "rpc.process",
+      "required_attributes": [
+        "xrpl.rpc.command",
+        "xrpl.rpc.version",
+        "xrpl.rpc.role",
+        "xrpl.rpc.status",
+        "xrpl.rpc.duration_ms"
+      ],
+      "config_flag": "trace_rpc",
+      "note": "Wildcard — matches rpc.command.server_info, rpc.command.ledger, etc."
+    },
+    {
+      "name": "tx.process",
+      "category": "transaction",
+      "parent": null,
+      "required_attributes": ["xrpl.tx.hash", "xrpl.tx.local", "xrpl.tx.path"],
+      "config_flag": "trace_transactions"
+    },
+    {
+      "name": "tx.receive",
+      "category": "transaction",
+      "parent": null,
+      "required_attributes": [
+        "xrpl.peer.id",
+        "xrpl.tx.hash",
+        "xrpl.tx.suppressed",
+        "xrpl.tx.status"
+      ],
+      "config_flag": "trace_transactions"
+    },
+    {
+      "name": "tx.apply",
+      "category": "transaction",
+      "parent": "ledger.build",
+      "required_attributes": [
+        "xrpl.ledger.seq",
+        "xrpl.ledger.tx_count",
+        "xrpl.ledger.tx_failed"
+      ],
+      "config_flag": "trace_transactions"
+    },
+    {
+      "name": "consensus.proposal.send",
+      "category": "consensus",
+      "parent": null,
+      "required_attributes": ["xrpl.consensus.round"],
+      "config_flag": "trace_consensus"
+    },
+    {
+      "name": "consensus.ledger_close",
+      "category": "consensus",
+      "parent": null,
+      "required_attributes": [
+        "xrpl.consensus.ledger.seq",
+        "xrpl.consensus.mode"
+      ],
+      "config_flag": "trace_consensus"
+    },
+    {
+      "name": "consensus.accept",
+      "category": "consensus",
+      "parent": null,
+      "required_attributes": ["xrpl.consensus.proposers"],
+      "config_flag": "trace_consensus"
+    },
+    {
+      "name": "consensus.validation.send",
+      "category": "consensus",
+      "parent": null,
+      "required_attributes": [
+        "xrpl.consensus.ledger.seq",
+        "xrpl.consensus.proposing"
+      ],
+      "config_flag": "trace_consensus"
+    },
+    {
+      "name": "consensus.accept.apply",
+      "category": "consensus",
+      "parent": null,
+      "required_attributes": [
+        "xrpl.consensus.close_time",
+        "xrpl.consensus.ledger.seq"
+      ],
+      "config_flag": "trace_consensus"
+    },
+    {
+      "name": "ledger.build",
+      "category": "ledger",
+      "parent": null,
+      "required_attributes": [
+        "xrpl.ledger.seq",
+        "xrpl.ledger.tx_count",
+        "xrpl.ledger.tx_failed"
+      ],
+      "config_flag": "trace_ledger"
+    },
+    {
+      "name": "ledger.validate",
+      "category": "ledger",
+      "parent": null,
+      "required_attributes": ["xrpl.ledger.seq", "xrpl.ledger.validations"],
+      "config_flag": "trace_ledger"
+    },
+    {
+      "name": "ledger.store",
+      "category": "ledger",
+      "parent": null,
+      "required_attributes": ["xrpl.ledger.seq"],
+      "config_flag": "trace_ledger"
+    },
+    {
+      "name": "peer.proposal.receive",
+      "category": "peer",
+      "parent": null,
+      "required_attributes": ["xrpl.peer.id", "xrpl.peer.proposal.trusted"],
+      "config_flag": "trace_peer"
+    },
+    {
+      "name": "peer.validation.receive",
+      "category": "peer",
+      "parent": null,
+      "required_attributes": ["xrpl.peer.id", "xrpl.peer.validation.trusted"],
+      "config_flag": "trace_peer"
+    }
+  ],
+  "parent_child_relationships": [
+    {
+      "parent": "rpc.request",
+      "child": "rpc.process",
+      "description": "RPC request contains processing span"
+    },
+    {
+      "parent": "rpc.process",
+      "child": "rpc.command.*",
+      "description": "Processing span contains per-command span"
+    },
+    {
+      "parent": "ledger.build",
+      "child": "tx.apply",
+      "description": "Ledger build contains transaction application"
+    }
+  ],
+  "total_span_types": 17,
+  "total_unique_attributes": 22
+}