mirror of
https://github.com/XRPLF/rippled.git
synced 2026-03-06 21:02:27 +00:00
Compare commits
6 Commits
tapanito/t
...
pratik/ote
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
b1a08cb5d0 | ||
|
|
7b12c00e6b | ||
|
|
5865bd017f | ||
|
|
af0ec7defd | ||
|
|
0c74270b05 | ||
|
|
a6a6a7c0fd |
@@ -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: {}
|
||||
98
.gersemi/definitions.cmake
Normal file
98
.gersemi/definitions.cmake
Normal file
@@ -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}"
|
||||
${ARGN}
|
||||
)
|
||||
endfunction()
|
||||
1
.gersemirc
Normal file
1
.gersemirc
Normal file
@@ -0,0 +1 @@
|
||||
definitions: [.gersemi]
|
||||
@@ -26,11 +26,10 @@ repos:
|
||||
args: [--style=file]
|
||||
"types_or": [c++, c, proto]
|
||||
|
||||
- repo: https://github.com/cheshirekow/cmake-format-precommit
|
||||
rev: e2c2116d86a80e72e7146a06e68b7c228afc6319 # frozen: v0.6.13
|
||||
- repo: https://github.com/BlankSpruce/gersemi
|
||||
rev: 0.26.0
|
||||
hooks:
|
||||
- id: cmake-format
|
||||
additional_dependencies: [PyYAML]
|
||||
- id: gersemi
|
||||
|
||||
- repo: https://github.com/rbubley/mirrors-prettier
|
||||
rev: c2bc67fe8f8f549cc489e00ba8b45aa18ee713b1 # frozen: v3.8.1
|
||||
|
||||
@@ -1,16 +1,16 @@
|
||||
cmake_minimum_required(VERSION 3.16)
|
||||
|
||||
if (POLICY CMP0074)
|
||||
if(POLICY CMP0074)
|
||||
cmake_policy(SET CMP0074 NEW)
|
||||
endif ()
|
||||
if (POLICY CMP0077)
|
||||
endif()
|
||||
if(POLICY CMP0077)
|
||||
cmake_policy(SET CMP0077 NEW)
|
||||
endif ()
|
||||
endif()
|
||||
|
||||
# Fix "unrecognized escape" issues when passing CMAKE_MODULE_PATH on Windows.
|
||||
if (DEFINED CMAKE_MODULE_PATH)
|
||||
if(DEFINED CMAKE_MODULE_PATH)
|
||||
file(TO_CMAKE_PATH "${CMAKE_MODULE_PATH}" CMAKE_MODULE_PATH)
|
||||
endif ()
|
||||
endif()
|
||||
list(APPEND CMAKE_MODULE_PATH "${CMAKE_CURRENT_SOURCE_DIR}/cmake")
|
||||
|
||||
project(xrpl)
|
||||
@@ -21,57 +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)
|
||||
|
||||
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)
|
||||
|
||||
@@ -90,42 +97,46 @@ 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()
|
||||
|
||||
# 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()
|
||||
|
||||
244
OpenTelemetryPlan/00-tracing-fundamentals.md
Normal file
244
OpenTelemetryPlan/00-tracing-fundamentals.md
Normal file
@@ -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)_
|
||||
330
OpenTelemetryPlan/01-architecture-analysis.md
Normal file
330
OpenTelemetryPlan/01-architecture-analysis.md
Normal file
@@ -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)_
|
||||
494
OpenTelemetryPlan/02-design-decisions.md
Normal file
494
OpenTelemetryPlan/02-design-decisions.md
Normal file
@@ -0,0 +1,494 @@
|
||||
# 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
|
||||
|
||||
```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
|
||||
```
|
||||
|
||||
### 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)_
|
||||
451
OpenTelemetryPlan/03-implementation-strategy.md
Normal file
451
OpenTelemetryPlan/03-implementation-strategy.md
Normal file
@@ -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)_
|
||||
982
OpenTelemetryPlan/04-code-samples.md
Normal file
982
OpenTelemetryPlan/04-code-samples.md
Normal file
@@ -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)_
|
||||
936
OpenTelemetryPlan/05-configuration-reference.md
Normal file
936
OpenTelemetryPlan/05-configuration-reference.md
Normal file
@@ -0,0 +1,936 @@
|
||||
# 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
|
||||
|
||||
service:
|
||||
pipelines:
|
||||
traces:
|
||||
receivers: [otlp]
|
||||
processors: [batch]
|
||||
exporters: [logging, jaeger]
|
||||
```
|
||||
|
||||
### 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 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
|
||||
|
||||
# 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/StatsD Metrics
|
||||
|
||||
To correlate traces with existing Beast Insight metrics:
|
||||
|
||||
**Step 1: Export Insight metrics to Prometheus**
|
||||
|
||||
```yaml
|
||||
# prometheus.yaml
|
||||
scrape_configs:
|
||||
- job_name: "rippled-statsd"
|
||||
static_configs:
|
||||
- targets: ["statsd-exporter:9102"]
|
||||
```
|
||||
|
||||
**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)_
|
||||
543
OpenTelemetryPlan/06-implementation-phases.md
Normal file
543
OpenTelemetryPlan/06-implementation-phases.md
Normal file
@@ -0,0 +1,543 @@
|
||||
# Implementation Phases
|
||||
|
||||
> **Parent Document**: [OpenTelemetryPlan.md](./OpenTelemetryPlan.md)
|
||||
> **Related**: [Configuration Reference](./05-configuration-reference.md) | [Observability Backends](./07-observability-backends.md)
|
||||
|
||||
---
|
||||
|
||||
## 6.1 Phase Overview
|
||||
|
||||
```mermaid
|
||||
gantt
|
||||
title OpenTelemetry Implementation Timeline
|
||||
dateFormat YYYY-MM-DD
|
||||
axisFormat Week %W
|
||||
|
||||
section Phase 1
|
||||
Core Infrastructure :p1, 2024-01-01, 2w
|
||||
SDK Integration :p1a, 2024-01-01, 4d
|
||||
Telemetry Interface :p1b, after p1a, 3d
|
||||
Configuration & CMake :p1c, after p1b, 3d
|
||||
Unit Tests :p1d, after p1c, 2d
|
||||
|
||||
section Phase 2
|
||||
RPC Tracing :p2, after p1, 2w
|
||||
HTTP Context Extraction :p2a, after p1, 2d
|
||||
RPC Handler Instrumentation :p2b, after p2a, 4d
|
||||
WebSocket Support :p2c, after p2b, 2d
|
||||
Integration Tests :p2d, after p2c, 2d
|
||||
|
||||
section Phase 3
|
||||
Transaction Tracing :p3, after p2, 2w
|
||||
Protocol Buffer Extension :p3a, after p2, 2d
|
||||
PeerImp Instrumentation :p3b, after p3a, 3d
|
||||
Relay Context Propagation :p3c, after p3b, 3d
|
||||
Multi-node Tests :p3d, after p3c, 2d
|
||||
|
||||
section Phase 4
|
||||
Consensus Tracing :p4, after p3, 2w
|
||||
Consensus Round Spans :p4a, after p3, 3d
|
||||
Proposal Handling :p4b, after p4a, 3d
|
||||
Validation Tests :p4c, after p4b, 4d
|
||||
|
||||
section Phase 5
|
||||
Documentation & Deploy :p5, after p4, 1w
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 6.2 Phase 1: Core Infrastructure (Weeks 1-2)
|
||||
|
||||
**Objective**: Establish foundational telemetry infrastructure
|
||||
|
||||
### Tasks
|
||||
|
||||
| Task | Description | Effort | Risk |
|
||||
| ---- | ----------------------------------------------------- | ------ | ------ |
|
||||
| 1.1 | Add OpenTelemetry C++ SDK to Conan/CMake | 2d | Low |
|
||||
| 1.2 | Implement `Telemetry` interface and factory | 2d | Low |
|
||||
| 1.3 | Implement `SpanGuard` RAII wrapper | 1d | Low |
|
||||
| 1.4 | Implement configuration parser | 1d | Low |
|
||||
| 1.5 | Integrate into `ApplicationImp` | 1d | Medium |
|
||||
| 1.6 | Add conditional compilation (`XRPL_ENABLE_TELEMETRY`) | 1d | Low |
|
||||
| 1.7 | Create `NullTelemetry` no-op implementation | 0.5d | Low |
|
||||
| 1.8 | Unit tests for core infrastructure | 1.5d | Low |
|
||||
|
||||
**Total Effort**: 10 days (2 developers)
|
||||
|
||||
### Exit Criteria
|
||||
|
||||
- [ ] OpenTelemetry SDK compiles and links
|
||||
- [ ] Telemetry can be enabled/disabled via config
|
||||
- [ ] Basic span creation works
|
||||
- [ ] No performance regression when disabled
|
||||
- [ ] Unit tests passing
|
||||
|
||||
---
|
||||
|
||||
## 6.3 Phase 2: RPC Tracing (Weeks 3-4)
|
||||
|
||||
**Objective**: Complete tracing for all RPC operations
|
||||
|
||||
### Tasks
|
||||
|
||||
| Task | Description | Effort | Risk |
|
||||
| ---- | -------------------------------------------------- | ------ | ------ |
|
||||
| 2.1 | Implement W3C Trace Context HTTP header extraction | 1d | Low |
|
||||
| 2.2 | Instrument `ServerHandler::onRequest()` | 1d | Low |
|
||||
| 2.3 | Instrument `RPCHandler::doCommand()` | 2d | Medium |
|
||||
| 2.4 | Add RPC-specific attributes | 1d | Low |
|
||||
| 2.5 | Instrument WebSocket handler | 1d | Medium |
|
||||
| 2.6 | Integration tests for RPC tracing | 2d | Low |
|
||||
| 2.7 | Performance benchmarks | 1d | Low |
|
||||
| 2.8 | Documentation | 1d | Low |
|
||||
|
||||
**Total Effort**: 10 days
|
||||
|
||||
### Exit Criteria
|
||||
|
||||
- [ ] All RPC commands traced
|
||||
- [ ] Trace context propagates from HTTP headers
|
||||
- [ ] WebSocket and HTTP both instrumented
|
||||
- [ ] <1ms overhead per RPC call
|
||||
- [ ] Integration tests passing
|
||||
|
||||
---
|
||||
|
||||
## 6.4 Phase 3: Transaction Tracing (Weeks 5-6)
|
||||
|
||||
**Objective**: Trace transaction lifecycle across network
|
||||
|
||||
### Tasks
|
||||
|
||||
| Task | Description | Effort | Risk |
|
||||
| ---- | --------------------------------------------- | ------ | ------ |
|
||||
| 3.1 | Define `TraceContext` Protocol Buffer message | 1d | Low |
|
||||
| 3.2 | Implement protobuf context serialization | 1d | Low |
|
||||
| 3.3 | Instrument `PeerImp::handleTransaction()` | 2d | Medium |
|
||||
| 3.4 | Instrument `NetworkOPs::submitTransaction()` | 1d | Medium |
|
||||
| 3.5 | Instrument HashRouter integration | 1d | Medium |
|
||||
| 3.6 | Implement relay context propagation | 2d | High |
|
||||
| 3.7 | Integration tests (multi-node) | 2d | Medium |
|
||||
| 3.8 | Performance benchmarks | 1d | Low |
|
||||
|
||||
**Total Effort**: 11 days
|
||||
|
||||
### Exit Criteria
|
||||
|
||||
- [ ] Transaction traces span across nodes
|
||||
- [ ] Trace context in Protocol Buffer messages
|
||||
- [ ] HashRouter deduplication visible in traces
|
||||
- [ ] Multi-node integration tests passing
|
||||
- [ ] <5% overhead on transaction throughput
|
||||
|
||||
---
|
||||
|
||||
## 6.5 Phase 4: Consensus Tracing (Weeks 7-8)
|
||||
|
||||
**Objective**: Full observability into consensus rounds
|
||||
|
||||
### Tasks
|
||||
|
||||
| Task | Description | Effort | Risk |
|
||||
| ---- | ---------------------------------------------- | ------ | ------ |
|
||||
| 4.1 | Instrument `RCLConsensusAdaptor::startRound()` | 1d | Medium |
|
||||
| 4.2 | Instrument phase transitions | 2d | Medium |
|
||||
| 4.3 | Instrument proposal handling | 2d | High |
|
||||
| 4.4 | Instrument validation handling | 1d | Medium |
|
||||
| 4.5 | Add consensus-specific attributes | 1d | Low |
|
||||
| 4.6 | Correlate with transaction traces | 1d | Medium |
|
||||
| 4.7 | Multi-validator integration tests | 2d | High |
|
||||
| 4.8 | Performance validation | 1d | Medium |
|
||||
|
||||
**Total Effort**: 11 days
|
||||
|
||||
### Exit Criteria
|
||||
|
||||
- [ ] Complete consensus round traces
|
||||
- [ ] Phase transitions visible
|
||||
- [ ] Proposals and validations traced
|
||||
- [ ] No impact on consensus timing
|
||||
- [ ] Multi-validator test network validated
|
||||
|
||||
---
|
||||
|
||||
## 6.6 Phase 5: Documentation & Deployment (Week 9)
|
||||
|
||||
**Objective**: Production readiness
|
||||
|
||||
### Tasks
|
||||
|
||||
| Task | Description | Effort | Risk |
|
||||
| ---- | ----------------------------- | ------ | ---- |
|
||||
| 5.1 | Operator runbook | 1d | Low |
|
||||
| 5.2 | Grafana dashboards | 1d | Low |
|
||||
| 5.3 | Alert definitions | 0.5d | Low |
|
||||
| 5.4 | Collector deployment examples | 0.5d | Low |
|
||||
| 5.5 | Developer documentation | 1d | Low |
|
||||
| 5.6 | Training materials | 0.5d | Low |
|
||||
| 5.7 | Final integration testing | 0.5d | Low |
|
||||
|
||||
**Total Effort**: 5 days
|
||||
|
||||
---
|
||||
|
||||
## 6.7 Risk Assessment
|
||||
|
||||
```mermaid
|
||||
quadrantChart
|
||||
title Risk Assessment Matrix
|
||||
x-axis Low Impact --> High Impact
|
||||
y-axis Low Likelihood --> High Likelihood
|
||||
quadrant-1 Monitor Closely
|
||||
quadrant-2 Mitigate Immediately
|
||||
quadrant-3 Accept Risk
|
||||
quadrant-4 Plan Mitigation
|
||||
|
||||
SDK Compatibility: [0.25, 0.2]
|
||||
Protocol Changes: [0.75, 0.65]
|
||||
Performance Overhead: [0.65, 0.45]
|
||||
Context Propagation: [0.5, 0.5]
|
||||
Memory Leaks: [0.8, 0.2]
|
||||
```
|
||||
|
||||
### Risk Details
|
||||
|
||||
| Risk | Likelihood | Impact | Mitigation |
|
||||
| ------------------------------------ | ---------- | ------ | --------------------------------------- |
|
||||
| Protocol changes break compatibility | Medium | High | Use high field numbers, optional fields |
|
||||
| Performance overhead unacceptable | Medium | Medium | Sampling, conditional compilation |
|
||||
| Context propagation complexity | Medium | Medium | Phased rollout, extensive testing |
|
||||
| SDK compatibility issues | Low | Medium | Pin SDK version, fallback to no-op |
|
||||
| Memory leaks in long-running nodes | Low | High | Memory profiling, bounded queues |
|
||||
|
||||
---
|
||||
|
||||
## 6.8 Success Metrics
|
||||
|
||||
| Metric | Target | Measurement |
|
||||
| ------------------------ | ------------------------------ | --------------------- |
|
||||
| Trace coverage | >95% of transactions | Sampling verification |
|
||||
| CPU overhead | <3% | Benchmark tests |
|
||||
| Memory overhead | <5 MB | Memory profiling |
|
||||
| Latency impact (p99) | <2% | Performance tests |
|
||||
| Trace completeness | >99% spans with required attrs | Validation script |
|
||||
| Cross-node trace linkage | >90% of multi-hop transactions | Integration tests |
|
||||
|
||||
---
|
||||
|
||||
## 6.9 Effort Summary
|
||||
|
||||
<div align="center">
|
||||
|
||||
```mermaid
|
||||
%%{init: {'pie': {'textPosition': 0.75}}}%%
|
||||
pie showData
|
||||
"Phase 1: Core Infrastructure" : 10
|
||||
"Phase 2: RPC Tracing" : 10
|
||||
"Phase 3: Transaction Tracing" : 11
|
||||
"Phase 4: Consensus Tracing" : 11
|
||||
"Phase 5: Documentation" : 5
|
||||
```
|
||||
|
||||
**Total Effort Distribution (47 developer-days)**
|
||||
|
||||
</div>
|
||||
|
||||
### Resource Requirements
|
||||
|
||||
| Phase | Developers | Duration | Total Effort |
|
||||
| --------- | ---------- | ----------- | ------------ |
|
||||
| 1 | 2 | 2 weeks | 10 days |
|
||||
| 2 | 1-2 | 2 weeks | 10 days |
|
||||
| 3 | 2 | 2 weeks | 11 days |
|
||||
| 4 | 2 | 2 weeks | 11 days |
|
||||
| 5 | 1 | 1 week | 5 days |
|
||||
| **Total** | **2** | **9 weeks** | **47 days** |
|
||||
|
||||
---
|
||||
|
||||
## 6.10 Quick Wins and Crawl-Walk-Run Strategy
|
||||
|
||||
This section outlines a prioritized approach to maximize ROI with minimal initial investment.
|
||||
|
||||
### 6.10.1 Crawl-Walk-Run Overview
|
||||
|
||||
<div align="center">
|
||||
|
||||
```mermaid
|
||||
flowchart TB
|
||||
subgraph crawl["🐢 CRAWL (Week 1-2)"]
|
||||
direction LR
|
||||
c1[Core SDK Setup] ~~~ c2[RPC Tracing Only] ~~~ c3[Single Node]
|
||||
end
|
||||
|
||||
subgraph walk["🚶 WALK (Week 3-5)"]
|
||||
direction LR
|
||||
w1[Transaction Tracing] ~~~ w2[Cross-Node Context] ~~~ w3[Basic Dashboards]
|
||||
end
|
||||
|
||||
subgraph run["🏃 RUN (Week 6-9)"]
|
||||
direction LR
|
||||
r1[Consensus Tracing] ~~~ r2[Full Correlation] ~~~ r3[Production Deploy]
|
||||
end
|
||||
|
||||
crawl --> walk --> run
|
||||
|
||||
style crawl fill:#1b5e20,stroke:#0d3d14,color:#fff
|
||||
style walk fill:#bf360c,stroke:#8c2809,color:#fff
|
||||
style run fill:#0d47a1,stroke:#082f6a,color:#fff
|
||||
style c1 fill:#1b5e20,stroke:#0d3d14,color:#fff
|
||||
style c2 fill:#1b5e20,stroke:#0d3d14,color:#fff
|
||||
style c3 fill:#1b5e20,stroke:#0d3d14,color:#fff
|
||||
style w1 fill:#ffe0b2,stroke:#ffcc80,color:#1e293b
|
||||
style w2 fill:#ffe0b2,stroke:#ffcc80,color:#1e293b
|
||||
style w3 fill:#ffe0b2,stroke:#ffcc80,color:#1e293b
|
||||
style r1 fill:#0d47a1,stroke:#082f6a,color:#fff
|
||||
style r2 fill:#0d47a1,stroke:#082f6a,color:#fff
|
||||
style r3 fill:#0d47a1,stroke:#082f6a,color:#fff
|
||||
```
|
||||
|
||||
</div>
|
||||
|
||||
### 6.10.2 Quick Wins (Immediate Value)
|
||||
|
||||
| Quick Win | Effort | Value | When to Deploy |
|
||||
| ------------------------------ | -------- | ------ | -------------- |
|
||||
| **RPC Command Tracing** | 2 days | High | Week 2 |
|
||||
| **RPC Latency Histograms** | 0.5 days | High | Week 2 |
|
||||
| **Error Rate Dashboard** | 0.5 days | Medium | Week 2 |
|
||||
| **Transaction Submit Tracing** | 1 day | High | Week 3 |
|
||||
| **Consensus Round Duration** | 1 day | Medium | Week 6 |
|
||||
|
||||
### 6.10.3 CRAWL Phase (Weeks 1-2)
|
||||
|
||||
**Goal**: Get basic tracing working with minimal code changes.
|
||||
|
||||
**What You Get**:
|
||||
|
||||
- RPC request/response traces for all commands
|
||||
- Latency breakdown per RPC command
|
||||
- Error visibility with stack traces
|
||||
- Basic Grafana dashboard
|
||||
|
||||
**Code Changes**: ~15 lines in `ServerHandler.cpp`, ~40 lines in new telemetry module
|
||||
|
||||
**Why Start Here**:
|
||||
|
||||
- RPC is the lowest-risk, highest-visibility component
|
||||
- Immediate value for debugging client issues
|
||||
- No cross-node complexity
|
||||
- Single file modification to existing code
|
||||
|
||||
### 6.10.4 WALK Phase (Weeks 3-5)
|
||||
|
||||
**Goal**: Add transaction lifecycle tracing across nodes.
|
||||
|
||||
**What You Get**:
|
||||
|
||||
- End-to-end transaction traces from submit to relay
|
||||
- Cross-node correlation (see transaction path)
|
||||
- HashRouter deduplication visibility
|
||||
- Relay latency metrics
|
||||
|
||||
**Code Changes**: ~120 lines across 4 files, plus protobuf extension
|
||||
|
||||
**Why Do This Second**:
|
||||
|
||||
- Builds on RPC tracing (transactions submitted via RPC)
|
||||
- Moderate complexity (requires context propagation)
|
||||
- High value for debugging transaction issues
|
||||
|
||||
### 6.10.5 RUN Phase (Weeks 6-9)
|
||||
|
||||
**Goal**: Full observability including consensus.
|
||||
|
||||
**What You Get**:
|
||||
|
||||
- Complete consensus round visibility
|
||||
- Phase transition timing
|
||||
- Validator proposal tracking
|
||||
- Full end-to-end traces (client → RPC → TX → consensus → ledger)
|
||||
|
||||
**Code Changes**: ~100 lines across 3 consensus files
|
||||
|
||||
**Why Do This Last**:
|
||||
|
||||
- Highest complexity (consensus is critical path)
|
||||
- Requires thorough testing
|
||||
- Lower relative value (consensus issues are rarer)
|
||||
|
||||
### 6.10.6 ROI Prioritization Matrix
|
||||
|
||||
```mermaid
|
||||
quadrantChart
|
||||
title Implementation ROI Matrix
|
||||
x-axis Low Effort --> High Effort
|
||||
y-axis Low Value --> High Value
|
||||
quadrant-1 Quick Wins - Do First
|
||||
quadrant-2 Major Projects - Plan Carefully
|
||||
quadrant-3 Nice to Have - Optional
|
||||
quadrant-4 Time Sinks - Avoid
|
||||
|
||||
RPC Tracing: [0.15, 0.9]
|
||||
TX Submit Trace: [0.25, 0.85]
|
||||
TX Relay Trace: [0.5, 0.8]
|
||||
Consensus Trace: [0.7, 0.75]
|
||||
Peer Message Trace: [0.85, 0.3]
|
||||
Ledger Acquire: [0.55, 0.5]
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 6.11 Definition of Done
|
||||
|
||||
Clear, measurable criteria for each phase.
|
||||
|
||||
### 6.11.1 Phase 1: Core Infrastructure
|
||||
|
||||
| Criterion | Measurement | Target |
|
||||
| --------------- | ---------------------------------------------------------- | ---------------------------- |
|
||||
| SDK Integration | `cmake --build` succeeds with `-DXRPL_ENABLE_TELEMETRY=ON` | ✅ Compiles |
|
||||
| Runtime Toggle | `enabled=0` produces zero overhead | <0.1% CPU difference |
|
||||
| Span Creation | Unit test creates and exports span | Span appears in Jaeger |
|
||||
| Configuration | All config options parsed correctly | Config validation tests pass |
|
||||
| Documentation | Developer guide exists | PR approved |
|
||||
|
||||
**Definition of Done**: All criteria met, PR merged, no regressions in CI.
|
||||
|
||||
### 6.11.2 Phase 2: RPC Tracing
|
||||
|
||||
| Criterion | Measurement | Target |
|
||||
| ------------------ | ---------------------------------- | -------------------------- |
|
||||
| Coverage | All RPC commands instrumented | 100% of commands |
|
||||
| Context Extraction | traceparent header propagates | Integration test passes |
|
||||
| Attributes | Command, status, duration recorded | Validation script confirms |
|
||||
| Performance | RPC latency overhead | <1ms p99 |
|
||||
| Dashboard | Grafana dashboard deployed | Screenshot in docs |
|
||||
|
||||
**Definition of Done**: RPC traces visible in Jaeger/Tempo for all commands, dashboard shows latency distribution.
|
||||
|
||||
### 6.11.3 Phase 3: Transaction Tracing
|
||||
|
||||
| Criterion | Measurement | Target |
|
||||
| ---------------- | ------------------------------- | ---------------------------------- |
|
||||
| Local Trace | Submit → validate → TxQ traced | Single-node test passes |
|
||||
| Cross-Node | Context propagates via protobuf | Multi-node test passes |
|
||||
| Relay Visibility | relay_count attribute correct | Spot check 100 txs |
|
||||
| HashRouter | Deduplication visible in trace | Duplicate txs show suppressed=true |
|
||||
| Performance | TX throughput overhead | <5% degradation |
|
||||
|
||||
**Definition of Done**: Transaction traces span 3+ nodes in test network, performance within bounds.
|
||||
|
||||
### 6.11.4 Phase 4: Consensus Tracing
|
||||
|
||||
| Criterion | Measurement | Target |
|
||||
| -------------------- | ----------------------------- | ------------------------- |
|
||||
| Round Tracing | startRound creates root span | Unit test passes |
|
||||
| Phase Visibility | All phases have child spans | Integration test confirms |
|
||||
| Proposer Attribution | Proposer ID in attributes | Spot check 50 rounds |
|
||||
| Timing Accuracy | Phase durations match PerfLog | <5% variance |
|
||||
| No Consensus Impact | Round timing unchanged | Performance test passes |
|
||||
|
||||
**Definition of Done**: Consensus rounds fully traceable, no impact on consensus timing.
|
||||
|
||||
### 6.11.5 Phase 5: Production Deployment
|
||||
|
||||
| Criterion | Measurement | Target |
|
||||
| ------------ | ---------------------------- | -------------------------- |
|
||||
| Collector HA | Multiple collectors deployed | No single point of failure |
|
||||
| Sampling | Tail sampling configured | 10% base + errors + slow |
|
||||
| Retention | Data retained per policy | 7 days hot, 30 days warm |
|
||||
| Alerting | Alerts configured | Error spike, high latency |
|
||||
| Runbook | Operator documentation | Approved by ops team |
|
||||
| Training | Team trained | Session completed |
|
||||
|
||||
**Definition of Done**: Telemetry running in production, operators trained, alerts active.
|
||||
|
||||
### 6.11.6 Success Metrics Summary
|
||||
|
||||
| Phase | Primary Metric | Secondary Metric | Deadline |
|
||||
| ------- | ---------------------- | --------------------------- | ------------- |
|
||||
| Phase 1 | SDK compiles and runs | Zero overhead when disabled | End of Week 2 |
|
||||
| Phase 2 | 100% RPC coverage | <1ms latency overhead | End of Week 4 |
|
||||
| Phase 3 | Cross-node traces work | <5% throughput impact | End of Week 6 |
|
||||
| Phase 4 | Consensus fully traced | No consensus timing impact | End of Week 8 |
|
||||
| Phase 5 | Production deployment | Operators trained | End of Week 9 |
|
||||
|
||||
---
|
||||
|
||||
## 6.12 Recommended Implementation Order
|
||||
|
||||
Based on ROI analysis, implement in this exact order:
|
||||
|
||||
```mermaid
|
||||
flowchart TB
|
||||
subgraph week1["Week 1"]
|
||||
t1[1. OpenTelemetry SDK<br/>Conan/CMake integration]
|
||||
t2[2. Telemetry interface<br/>SpanGuard, config]
|
||||
end
|
||||
|
||||
subgraph week2["Week 2"]
|
||||
t3[3. RPC ServerHandler<br/>instrumentation]
|
||||
t4[4. Basic Jaeger setup<br/>for testing]
|
||||
end
|
||||
|
||||
subgraph week3["Week 3"]
|
||||
t5[5. Transaction submit<br/>tracing]
|
||||
t6[6. Grafana dashboard<br/>v1]
|
||||
end
|
||||
|
||||
subgraph week4["Week 4"]
|
||||
t7[7. Protobuf context<br/>extension]
|
||||
t8[8. PeerImp tx.relay<br/>instrumentation]
|
||||
end
|
||||
|
||||
subgraph week5["Week 5"]
|
||||
t9[9. Multi-node<br/>integration tests]
|
||||
t10[10. Performance<br/>benchmarks]
|
||||
end
|
||||
|
||||
subgraph week6_8["Weeks 6-8"]
|
||||
t11[11. Consensus<br/>instrumentation]
|
||||
t12[12. Full integration<br/>testing]
|
||||
end
|
||||
|
||||
subgraph week9["Week 9"]
|
||||
t13[13. Production<br/>deployment]
|
||||
t14[14. Documentation<br/>& training]
|
||||
end
|
||||
|
||||
t1 --> t2 --> t3 --> t4
|
||||
t4 --> t5 --> t6
|
||||
t6 --> t7 --> t8
|
||||
t8 --> t9 --> t10
|
||||
t10 --> t11 --> t12
|
||||
t12 --> t13 --> t14
|
||||
|
||||
style week1 fill:#1b5e20,stroke:#0d3d14,color:#fff
|
||||
style week2 fill:#1b5e20,stroke:#0d3d14,color:#fff
|
||||
style week3 fill:#bf360c,stroke:#8c2809,color:#fff
|
||||
style week4 fill:#bf360c,stroke:#8c2809,color:#fff
|
||||
style week5 fill:#bf360c,stroke:#8c2809,color:#fff
|
||||
style week6_8 fill:#0d47a1,stroke:#082f6a,color:#fff
|
||||
style week9 fill:#4a148c,stroke:#2e0d57,color:#fff
|
||||
style t1 fill:#1b5e20,stroke:#0d3d14,color:#fff
|
||||
style t2 fill:#1b5e20,stroke:#0d3d14,color:#fff
|
||||
style t3 fill:#1b5e20,stroke:#0d3d14,color:#fff
|
||||
style t4 fill:#1b5e20,stroke:#0d3d14,color:#fff
|
||||
style t5 fill:#ffe0b2,stroke:#ffcc80,color:#1e293b
|
||||
style t6 fill:#ffe0b2,stroke:#ffcc80,color:#1e293b
|
||||
style t7 fill:#ffe0b2,stroke:#ffcc80,color:#1e293b
|
||||
style t8 fill:#ffe0b2,stroke:#ffcc80,color:#1e293b
|
||||
style t9 fill:#ffe0b2,stroke:#ffcc80,color:#1e293b
|
||||
style t10 fill:#ffe0b2,stroke:#ffcc80,color:#1e293b
|
||||
style t11 fill:#0d47a1,stroke:#082f6a,color:#fff
|
||||
style t12 fill:#0d47a1,stroke:#082f6a,color:#fff
|
||||
style t13 fill:#4a148c,stroke:#2e0d57,color:#fff
|
||||
style t14 fill:#4a148c,stroke:#2e0d57,color:#fff
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
_Previous: [Configuration Reference](./05-configuration-reference.md)_ | _Next: [Observability Backends](./07-observability-backends.md)_ | _Back to: [Overview](./OpenTelemetryPlan.md)_
|
||||
595
OpenTelemetryPlan/07-observability-backends.md
Normal file
595
OpenTelemetryPlan/07-observability-backends.md
Normal file
@@ -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)_
|
||||
133
OpenTelemetryPlan/08-appendix.md
Normal file
133
OpenTelemetryPlan/08-appendix.md
Normal file
@@ -0,0 +1,133 @@
|
||||
# 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 |
|
||||
|
||||
---
|
||||
|
||||
## 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 |
|
||||
|
||||
---
|
||||
|
||||
## 8.5 Document Index
|
||||
|
||||
| Document | Description |
|
||||
| ---------------------------------------------------------------- | ------------------------------------------ |
|
||||
| [OpenTelemetryPlan.md](./OpenTelemetryPlan.md) | Master overview and executive summary |
|
||||
| [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 |
|
||||
|
||||
---
|
||||
|
||||
_Previous: [Observability Backends](./07-observability-backends.md)_ | _Back to: [Overview](./OpenTelemetryPlan.md)_
|
||||
190
OpenTelemetryPlan/OpenTelemetryPlan.md
Normal file
190
OpenTelemetryPlan/OpenTelemetryPlan.md
Normal file
@@ -0,0 +1,190 @@
|
||||
# [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"]
|
||||
end
|
||||
|
||||
overview --> analysis
|
||||
overview --> impl
|
||||
overview --> deploy
|
||||
|
||||
arch --> design
|
||||
design --> strategy
|
||||
strategy --> code
|
||||
code --> config
|
||||
config --> phases
|
||||
phases --> backends
|
||||
backends --> appendix
|
||||
|
||||
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
|
||||
```
|
||||
|
||||
</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 |
|
||||
|
||||
---
|
||||
|
||||
## 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 9 weeks across 5 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 |
|
||||
|
||||
**Total Effort**: 47 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)**
|
||||
|
||||
---
|
||||
|
||||
_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._
|
||||
610
OpenTelemetryPlan/POC_taskList.md
Normal file
610
OpenTelemetryPlan/POC_taskList.md
Normal file
@@ -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 |
|
||||
@@ -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} "${_branch}" PARENT_SCOPE)
|
||||
endfunction ()
|
||||
endfunction()
|
||||
|
||||
@@ -1,50 +1,62 @@
|
||||
find_program(CCACHE_PATH "ccache")
|
||||
if (NOT CCACHE_PATH)
|
||||
if(NOT CCACHE_PATH)
|
||||
return()
|
||||
endif ()
|
||||
endif()
|
||||
|
||||
# For Linux and macOS we can use the ccache binary directly.
|
||||
if (NOT MSVC)
|
||||
if(NOT MSVC)
|
||||
set(CMAKE_C_COMPILER_LAUNCHER "${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()
|
||||
|
||||
@@ -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
|
||||
|
||||
@@ -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()
|
||||
|
||||
@@ -4,18 +4,25 @@ set(GIT_BUILD_BRANCH "")
|
||||
set(GIT_COMMIT_HASH "")
|
||||
|
||||
find_package(Git)
|
||||
if (NOT Git_FOUND)
|
||||
if(NOT Git_FOUND)
|
||||
message(WARNING "Git not found. Git branch and commit hash will be empty.")
|
||||
return()
|
||||
endif ()
|
||||
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 --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)
|
||||
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}")
|
||||
|
||||
@@ -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()
|
||||
|
||||
@@ -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()
|
||||
|
||||
@@ -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()
|
||||
|
||||
@@ -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:${voidstar}>:antithesis-sdk-cpp>
|
||||
)
|
||||
|
||||
include(add_module)
|
||||
include(target_link_modules)
|
||||
@@ -60,8 +81,12 @@ target_link_libraries(xrpl.libxrpl.beast PUBLIC xrpl.imports.main)
|
||||
|
||||
include(GitInfo)
|
||||
add_module(xrpl git)
|
||||
target_compile_definitions(xrpl.libxrpl.git PRIVATE GIT_COMMIT_HASH="${GIT_COMMIT_HASH}"
|
||||
GIT_BUILD_BRANCH="${GIT_BUILD_BRANCH}")
|
||||
target_compile_definitions(
|
||||
xrpl.libxrpl.git
|
||||
PRIVATE
|
||||
GIT_COMMIT_HASH="${GIT_COMMIT_HASH}"
|
||||
GIT_BUILD_BRANCH="${GIT_BUILD_BRANCH}"
|
||||
)
|
||||
target_link_libraries(xrpl.libxrpl.git PUBLIC xrpl.imports.main)
|
||||
|
||||
# Level 02
|
||||
@@ -77,13 +102,17 @@ 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.git
|
||||
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)
|
||||
@@ -91,23 +120,46 @@ 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)
|
||||
@@ -115,13 +167,15 @@ 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)
|
||||
@@ -131,7 +185,11 @@ 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(
|
||||
@@ -152,7 +210,8 @@ target_link_modules(
|
||||
resource
|
||||
server
|
||||
shamap
|
||||
tx)
|
||||
tx
|
||||
)
|
||||
|
||||
# All headers in libxrpl are in modules.
|
||||
# Uncomment this stanza if you have not yet moved new headers into a module.
|
||||
@@ -163,34 +222,51 @@ 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()
|
||||
|
||||
@@ -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"
|
||||
"${CMAKE_BINARY_DIR}/pb-xrpl.libpb"
|
||||
DEPENDENCIES xrpld xrpl.tests
|
||||
)
|
||||
|
||||
add_code_coverage_to_target(opts INTERFACE)
|
||||
|
||||
@@ -2,71 +2,90 @@
|
||||
docs target (optional)
|
||||
#]===================================================================]
|
||||
|
||||
if (NOT only_docs)
|
||||
if(NOT only_docs)
|
||||
return()
|
||||
endif ()
|
||||
endif()
|
||||
|
||||
find_package(Doxygen)
|
||||
if (NOT TARGET Doxygen::doxygen)
|
||||
if(NOT TARGET Doxygen::doxygen)
|
||||
message(STATUS "doxygen executable not found -- skipping docs target")
|
||||
return()
|
||||
endif ()
|
||||
endif()
|
||||
|
||||
set(doxygen_output_directory "${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}"
|
||||
)
|
||||
|
||||
@@ -6,57 +6,71 @@ 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.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.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.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 ${xrpld_version}
|
||||
COMPATIBILITY SameMajorVersion
|
||||
)
|
||||
|
||||
if (is_root_project AND TARGET xrpld)
|
||||
if(is_root_project AND TARGET xrpld)
|
||||
install(TARGETS xrpld RUNTIME DESTINATION bin)
|
||||
set_target_properties(xrpld PROPERTIES INSTALL_RPATH_USE_LINK_PATH ON)
|
||||
# sample configs should not overwrite existing files
|
||||
# install if-not-exists workaround as suggested by
|
||||
# https://cmake.org/Bug/view.php?id=12646
|
||||
install(CODE "
|
||||
install(
|
||||
CODE
|
||||
"
|
||||
macro (copy_if_not_exists SRC DEST NEWNAME)
|
||||
if (NOT EXISTS \"\$ENV{DESTDIR}\${CMAKE_INSTALL_PREFIX}/\${DEST}/\${NEWNAME}\")
|
||||
file (INSTALL FILE_PERMISSIONS OWNER_READ OWNER_WRITE DESTINATION \"\${CMAKE_INSTALL_PREFIX}/\${DEST}\" FILES \"\${SRC}\" RENAME \"\${NEWNAME}\")
|
||||
@@ -66,14 +80,22 @@ if (is_root_project AND TARGET xrpld)
|
||||
endmacro()
|
||||
copy_if_not_exists(\"${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
|
||||
)
|
||||
|
||||
@@ -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:${is_macos}>>>:rt>
|
||||
)
|
||||
|
||||
if (NOT is_msvc)
|
||||
if(NOT is_msvc)
|
||||
set(THREADS_PREFER_PTHREAD_FLAG ON)
|
||||
find_package(Threads)
|
||||
target_link_libraries(xrpl_syslibs INTERFACE Threads::Threads)
|
||||
endif ()
|
||||
endif()
|
||||
|
||||
add_library(xrpl_libs INTERFACE)
|
||||
add_library(Xrpl::libs ALIAS xrpl_libs)
|
||||
|
||||
@@ -44,23 +44,26 @@ include(CompilationEnv)
|
||||
|
||||
# Read environment variable
|
||||
set(SANITIZERS "")
|
||||
if (DEFINED ENV{SANITIZERS})
|
||||
if(DEFINED ENV{SANITIZERS})
|
||||
set(SANITIZERS "$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()
|
||||
|
||||
@@ -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 ${CMAKE_CURRENT_SOURCE_DIR} and try building in a separate directory."
|
||||
)
|
||||
endif ()
|
||||
endif()
|
||||
|
||||
if (MSVC AND CMAKE_GENERATOR_PLATFORM STREQUAL "Win32")
|
||||
if(MSVC AND CMAKE_GENERATOR_PLATFORM STREQUAL "Win32")
|
||||
message(FATAL_ERROR "Visual Studio 32-bit build is not supported.")
|
||||
endif ()
|
||||
endif()
|
||||
|
||||
if (APPLE AND NOT HOMEBREW)
|
||||
if(APPLE AND NOT HOMEBREW)
|
||||
find_program(HOMEBREW brew)
|
||||
endif ()
|
||||
endif()
|
||||
|
||||
@@ -5,59 +5,67 @@
|
||||
include(CompilationEnv)
|
||||
|
||||
set(is_ci FALSE)
|
||||
if (DEFINED ENV{CI})
|
||||
if ("$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()
|
||||
|
||||
@@ -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()
|
||||
|
||||
@@ -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()
|
||||
|
||||
@@ -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}/${name}"
|
||||
PRIVATE
|
||||
)
|
||||
endfunction()
|
||||
|
||||
@@ -1,19 +1,21 @@
|
||||
# file(CREATE_SYMLINK) only works on Windows with administrator privileges. https://stackoverflow.com/a/61244115/618906
|
||||
function (create_symbolic_link target link)
|
||||
if (WIN32)
|
||||
if (NOT IS_SYMLINK "${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()
|
||||
|
||||
@@ -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()
|
||||
|
||||
@@ -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()
|
||||
|
||||
@@ -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} ${module})
|
||||
endforeach ()
|
||||
endfunction ()
|
||||
endforeach()
|
||||
endfunction()
|
||||
|
||||
@@ -35,20 +35,31 @@ find_package(Protobuf REQUIRED)
|
||||
# This prefix should appear at the start of all your consumer includes.
|
||||
# ARGN:
|
||||
# A list of .proto files.
|
||||
function (target_protobuf_sources target prefix)
|
||||
function(target_protobuf_sources target prefix)
|
||||
set(dir "${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()
|
||||
|
||||
@@ -180,6 +180,7 @@ words:
|
||||
- NOLINTNEXTLINE
|
||||
- nonxrp
|
||||
- noripple
|
||||
- nostd
|
||||
- nudb
|
||||
- nullptr
|
||||
- nunl
|
||||
@@ -309,3 +310,9 @@ words:
|
||||
- xrplf
|
||||
- xxhash
|
||||
- xxhasher
|
||||
- xychart
|
||||
- otelc
|
||||
- zpages
|
||||
- traceql
|
||||
- Gantt
|
||||
- gantt
|
||||
|
||||
280
presentation.md
Normal file
280
presentation.md
Normal file
@@ -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_
|
||||
@@ -14,7 +14,10 @@ target_link_libraries(xrpl.helpers.test PRIVATE xrpl.libxrpl)
|
||||
|
||||
# Common library dependencies for the rest of the tests.
|
||||
add_library(xrpl.imports.test INTERFACE)
|
||||
target_link_libraries(xrpl.imports.test INTERFACE gtest::gtest xrpl.libxrpl xrpl.helpers.test)
|
||||
target_link_libraries(
|
||||
xrpl.imports.test
|
||||
INTERFACE gtest::gtest xrpl.libxrpl xrpl.helpers.test
|
||||
)
|
||||
|
||||
# One test for each module.
|
||||
xrpl_add_test(basics)
|
||||
@@ -30,8 +33,8 @@ target_link_libraries(xrpl.test.json PRIVATE xrpl.imports.test)
|
||||
add_dependencies(xrpl.tests xrpl.test.json)
|
||||
|
||||
# Network unit tests are currently not supported on Windows
|
||||
if (NOT WIN32)
|
||||
if(NOT WIN32)
|
||||
xrpl_add_test(net)
|
||||
target_link_libraries(xrpl.test.net PRIVATE xrpl.imports.test)
|
||||
add_dependencies(xrpl.tests xrpl.test.net)
|
||||
endif ()
|
||||
endif()
|
||||
|
||||
Reference in New Issue
Block a user