Compare commits

..

4 Commits

Author SHA1 Message Date
Michael Legleux
ab3382b116 rm patch 2026-02-11 00:51:41 -08:00
Michael Legleux
6153e2fa11 build image too 2026-02-11 00:47:34 -08:00
Michael Legleux
aab3305abe use currenty generate.py 2026-02-03 15:19:59 -08:00
Michael Legleux
66dbf460b4 feat: Build packages in GitHub 2026-02-03 15:14:52 -08:00
822 changed files with 6203 additions and 8306 deletions

View File

@@ -1,13 +1,14 @@
ignorePaths:
- build/**
- src/libxrpl/crypto
- src/test/** # Will be removed in the future
- CMakeUserPresets.json
- Doxyfile
- docs/**/*.puml
- cmake/**
- LICENSE.md
language: en
allowCompoundWords: true # TODO (#6334)
allowCompoundWords: true
ignoreRandomStrings: true
minWordLength: 5
dictionaries:
@@ -15,29 +16,20 @@ dictionaries:
- en_US
- en_GB
ignoreRegExpList:
- /\b[rs][1-9A-HJ-NP-Za-km-z]{25,34}/g # addresses and seeds
- /\bC[A-Z0-9]{15}/g # CTIDs
- /\b(XRPL|BEAST)_[A-Z_0-9]+_H_INCLUDED+/g # include guards
- /\b(XRPL|BEAST)_[A-Z_0-9]+_H+/g # include guards
- /[rs][1-9A-HJ-NP-Za-km-z]{25,34}/g # addresses and seeds
- /(XRPL|BEAST)_[A-Z_0-9]+_H_INCLUDED+/g # include guards
- /(XRPL|BEAST)_[A-Z_0-9]+_H+/g # include guards
- /::[a-z:_]+/g # things from other namespaces
- /\blib[a-z]+/g # libraries
- /\b[0-9]{4}-[0-9]{2}-[0-9]{2}[,:][A-Za-zÀ-ÖØ-öø-ÿ.\s]+/g # copyright dates
- /\b[0-9]{4}[,:]?\s*[A-Za-zÀ-ÖØ-öø-ÿ.\s]+/g # copyright years
- /lib[a-z]+/g # libraries
- /[0-9]{4}-[0-9]{2}-[0-9]{2}[,:][A-Za-zÀ-ÖØ-öø-ÿ.\s]+/g # copyright dates
- /[0-9]{4}[,:]?\s*[A-Za-zÀ-ÖØ-öø-ÿ.\s]+/g # copyright years
- /\[[A-Za-z0-9-]+\]\(https:\/\/github.com\/[A-Za-z0-9-]+\)/g # Github usernames
- /-[DWw][a-zA-Z0-9_-]+=/g # compile flags
- /[\['"`]-[DWw][a-zA-Z0-9_-]+['"`\]]/g # compile flags
- ABCDEFGHIJKLMNOPQRSTUVWXYZ
- ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz
overrides:
- filename: "**/*_test.cpp" # all test files
ignoreRegExpList:
- /"[^"]*"/g # double-quoted strings
- /'[^']*'/g # single-quoted strings
- /`[^`]*`/g # backtick strings
suggestWords:
- xprl->xrpl
- xprld->xrpld # cspell: disable-line not sure what this problem is....
- unsynched->unsynced # cspell: disable-line not sure what this problem is....
- xprld->xrpld
- unsynched->unsynced
- synched->synced
- synch->sync
words:
@@ -59,7 +51,6 @@ words:
- Britto
- Btrfs
- canonicality
- changespq
- checkme
- choco
- chrono
@@ -115,14 +106,12 @@ words:
- inequation
- insuf
- insuff
- invasively
- iou
- ious
- isrdc
- itype
- jemalloc
- jlog
- jtnofill
- keylet
- keylets
- keyvadb
@@ -149,7 +138,6 @@ words:
- Metafuncton
- misprediction
- mptbalance
- MPTDEX
- mptflags
- mptid
- mptissuance
@@ -159,7 +147,6 @@ words:
- mptokenissuance
- mptokens
- mpts
- mtgox
- multisig
- multisign
- multisigned
@@ -187,7 +174,6 @@ words:
- perminute
- permissioned
- pointee
- populator
- preauth
- preauthorization
- preauthorize
@@ -196,7 +182,6 @@ words:
- protobuf
- protos
- ptrs
- pushd
- pyenv
- qalloc
- queuable

8
.github/CODEOWNERS vendored Normal file
View File

@@ -0,0 +1,8 @@
# Allow anyone to review any change by default.
*
# Require the rpc-reviewers team to review changes to the rpc code.
include/xrpl/protocol/ @xrplf/rpc-reviewers
src/libxrpl/protocol/ @xrplf/rpc-reviewers
src/xrpld/rpc/ @xrplf/rpc-reviewers
src/xrpld/app/misc/ @xrplf/rpc-reviewers

View File

@@ -4,11 +4,14 @@ Loop: test.jtx test.toplevel
Loop: test.jtx test.unit_test
test.unit_test == test.jtx
Loop: xrpld.app xrpld.core
xrpld.app > xrpld.core
Loop: xrpld.app xrpld.overlay
xrpld.overlay > xrpld.app
Loop: xrpld.app xrpld.peerfinder
xrpld.peerfinder == xrpld.app
xrpld.peerfinder ~= xrpld.app
Loop: xrpld.app xrpld.rpc
xrpld.rpc > xrpld.app

View File

@@ -17,15 +17,12 @@ libxrpl.nodestore > xrpl.protocol
libxrpl.protocol > xrpl.basics
libxrpl.protocol > xrpl.json
libxrpl.protocol > xrpl.protocol
libxrpl.rdb > xrpl.basics
libxrpl.rdb > xrpl.rdb
libxrpl.resource > xrpl.basics
libxrpl.resource > xrpl.json
libxrpl.resource > xrpl.resource
libxrpl.server > xrpl.basics
libxrpl.server > xrpl.json
libxrpl.server > xrpl.protocol
libxrpl.server > xrpl.rdb
libxrpl.server > xrpl.server
libxrpl.shamap > xrpl.basics
libxrpl.shamap > xrpl.protocol
@@ -44,9 +41,7 @@ test.app > xrpl.json
test.app > xrpl.ledger
test.app > xrpl.nodestore
test.app > xrpl.protocol
test.app > xrpl.rdb
test.app > xrpl.resource
test.app > xrpl.server
test.basics > test.jtx
test.basics > test.unit_test
test.basics > xrpl.basics
@@ -72,7 +67,6 @@ test.core > xrpl.basics
test.core > xrpl.core
test.core > xrpld.core
test.core > xrpl.json
test.core > xrpl.rdb
test.core > xrpl.server
test.csf > xrpl.basics
test.csf > xrpld.consensus
@@ -101,8 +95,8 @@ test.nodestore > test.jtx
test.nodestore > test.toplevel
test.nodestore > test.unit_test
test.nodestore > xrpl.basics
test.nodestore > xrpld.core
test.nodestore > xrpl.nodestore
test.nodestore > xrpl.rdb
test.overlay > test.jtx
test.overlay > test.toplevel
test.overlay > test.unit_test
@@ -159,8 +153,6 @@ tests.libxrpl > xrpl.json
tests.libxrpl > xrpl.net
xrpl.core > xrpl.basics
xrpl.core > xrpl.json
xrpl.core > xrpl.ledger
xrpl.core > xrpl.protocol
xrpl.json > xrpl.basics
xrpl.ledger > xrpl.basics
xrpl.ledger > xrpl.protocol
@@ -169,17 +161,12 @@ xrpl.nodestore > xrpl.basics
xrpl.nodestore > xrpl.protocol
xrpl.protocol > xrpl.basics
xrpl.protocol > xrpl.json
xrpl.rdb > xrpl.basics
xrpl.rdb > xrpl.core
xrpl.rdb > xrpl.protocol
xrpl.resource > xrpl.basics
xrpl.resource > xrpl.json
xrpl.resource > xrpl.protocol
xrpl.server > xrpl.basics
xrpl.server > xrpl.core
xrpl.server > xrpl.json
xrpl.server > xrpl.protocol
xrpl.server > xrpl.rdb
xrpl.shamap > xrpl.basics
xrpl.shamap > xrpl.nodestore
xrpl.shamap > xrpl.protocol
@@ -188,15 +175,12 @@ xrpld.app > xrpl.basics
xrpld.app > xrpl.core
xrpld.app > xrpld.conditions
xrpld.app > xrpld.consensus
xrpld.app > xrpld.core
xrpld.app > xrpl.json
xrpld.app > xrpl.ledger
xrpld.app > xrpl.net
xrpld.app > xrpl.nodestore
xrpld.app > xrpl.protocol
xrpld.app > xrpl.rdb
xrpld.app > xrpl.resource
xrpld.app > xrpl.server
xrpld.app > xrpl.shamap
xrpld.conditions > xrpl.basics
xrpld.conditions > xrpl.protocol
@@ -208,20 +192,17 @@ xrpld.core > xrpl.core
xrpld.core > xrpl.json
xrpld.core > xrpl.net
xrpld.core > xrpl.protocol
xrpld.core > xrpl.rdb
xrpld.overlay > xrpl.basics
xrpld.overlay > xrpl.core
xrpld.overlay > xrpld.core
xrpld.overlay > xrpld.peerfinder
xrpld.overlay > xrpl.json
xrpld.overlay > xrpl.protocol
xrpld.overlay > xrpl.rdb
xrpld.overlay > xrpl.resource
xrpld.overlay > xrpl.server
xrpld.peerfinder > xrpl.basics
xrpld.peerfinder > xrpld.core
xrpld.peerfinder > xrpl.protocol
xrpld.peerfinder > xrpl.rdb
xrpld.perflog > xrpl.basics
xrpld.perflog > xrpl.core
xrpld.perflog > xrpld.rpc
@@ -234,7 +215,6 @@ xrpld.rpc > xrpl.ledger
xrpld.rpc > xrpl.net
xrpld.rpc > xrpl.nodestore
xrpld.rpc > xrpl.protocol
xrpld.rpc > xrpl.rdb
xrpld.rpc > xrpl.resource
xrpld.rpc > xrpl.server
xrpld.shamap > xrpl.shamap

View File

@@ -1,30 +0,0 @@
#!/bin/bash
# Exit the script as soon as an error occurs.
set -e
# This script checks whether there are no new include guards introduced by a new
# PR, as header files should use "#pragma once" instead. The script assumes any
# include guards will use "XRPL_" as prefix.
# Usage: .github/scripts/rename/include.sh <repository directory>
if [ "$#" -ne 1 ]; then
echo "Usage: $0 <repository directory>"
exit 1
fi
DIRECTORY=$1
echo "Processing directory: ${DIRECTORY}"
if [ ! -d "${DIRECTORY}" ]; then
echo "Error: Directory '${DIRECTORY}' does not exist."
exit 1
fi
find "${DIRECTORY}" -type f \( -name "*.h" -o -name "*.hpp" -o -name "*.ipp" \) | while read -r FILE; do
echo "Processing file: ${FILE}"
if grep -q "#ifndef XRPL_" "${FILE}"; then
echo "Please replace all include guards by #pragma once."
exit 1
fi
done
echo "Checking complete."

View File

@@ -51,20 +51,22 @@ def generate_strategy_matrix(all: bool, config: Config) -> list:
# Only generate a subset of configurations in PRs.
if not all:
# Debian:
# - Bookworm using GCC 13: Release on linux/amd64, set the reference
# fee to 500.
# - Bookworm using GCC 15: Debug on linux/amd64, enable code
# coverage (which will be done below).
# - Bookworm using Clang 16: Debug on linux/arm64, enable voidstar.
# - Bookworm using Clang 17: Release on linux/amd64, set the
# reference fee to 1000.
# - Bookworm using Clang 20: Debug on linux/amd64.
# - Bookworm using GCC 13: Release and Unity on linux/amd64, set
# the reference fee to 500.
# - Bookworm using GCC 15: Debug and no Unity on linux/amd64, enable
# code coverage (which will be done below).
# - Bookworm using Clang 16: Debug and no Unity on linux/arm64,
# enable voidstar.
# - Bookworm using Clang 17: Release and no Unity on linux/amd64,
# set the reference fee to 1000.
# - Bookworm using Clang 20: Debug and Unity on linux/amd64.
if os["distro_name"] == "debian":
skip = True
if os["distro_version"] == "bookworm":
if (
f"{os['compiler_name']}-{os['compiler_version']}" == "gcc-13"
and build_type == "Release"
and "-Dunity=ON" in cmake_args
and architecture["platform"] == "linux/amd64"
):
cmake_args = f"-DUNIT_TEST_REFERENCE_FEE=500 {cmake_args}"
@@ -72,12 +74,14 @@ def generate_strategy_matrix(all: bool, config: Config) -> list:
if (
f"{os['compiler_name']}-{os['compiler_version']}" == "gcc-15"
and build_type == "Debug"
and "-Dunity=OFF" in cmake_args
and architecture["platform"] == "linux/amd64"
):
skip = False
if (
f"{os['compiler_name']}-{os['compiler_version']}" == "clang-16"
and build_type == "Debug"
and "-Dunity=OFF" in cmake_args
and architecture["platform"] == "linux/arm64"
):
cmake_args = f"-Dvoidstar=ON {cmake_args}"
@@ -85,6 +89,7 @@ def generate_strategy_matrix(all: bool, config: Config) -> list:
if (
f"{os['compiler_name']}-{os['compiler_version']}" == "clang-17"
and build_type == "Release"
and "-Dunity=ON" in cmake_args
and architecture["platform"] == "linux/amd64"
):
cmake_args = f"-DUNIT_TEST_REFERENCE_FEE=1000 {cmake_args}"
@@ -92,6 +97,7 @@ def generate_strategy_matrix(all: bool, config: Config) -> list:
if (
f"{os['compiler_name']}-{os['compiler_version']}" == "clang-20"
and build_type == "Debug"
and "-Dunity=ON" in cmake_args
and architecture["platform"] == "linux/amd64"
):
skip = False
@@ -99,14 +105,15 @@ def generate_strategy_matrix(all: bool, config: Config) -> list:
continue
# RHEL:
# - 9 using GCC 12: Debug on linux/amd64.
# - 10 using Clang: Release on linux/amd64.
# - 9 using GCC 12: Debug and Unity on linux/amd64.
# - 10 using Clang: Release and no Unity on linux/amd64.
if os["distro_name"] == "rhel":
skip = True
if os["distro_version"] == "9":
if (
f"{os['compiler_name']}-{os['compiler_version']}" == "gcc-12"
and build_type == "Debug"
and "-Dunity=ON" in cmake_args
and architecture["platform"] == "linux/amd64"
):
skip = False
@@ -114,6 +121,7 @@ def generate_strategy_matrix(all: bool, config: Config) -> list:
if (
f"{os['compiler_name']}-{os['compiler_version']}" == "clang-any"
and build_type == "Release"
and "-Dunity=OFF" in cmake_args
and architecture["platform"] == "linux/amd64"
):
skip = False
@@ -121,16 +129,17 @@ def generate_strategy_matrix(all: bool, config: Config) -> list:
continue
# Ubuntu:
# - Jammy using GCC 12: Debug on linux/arm64.
# - Noble using GCC 14: Release on linux/amd64.
# - Noble using Clang 18: Debug on linux/amd64.
# - Noble using Clang 19: Release on linux/arm64.
# - Jammy using GCC 12: Debug and no Unity on linux/arm64.
# - Noble using GCC 14: Release and Unity on linux/amd64.
# - Noble using Clang 18: Debug and no Unity on linux/amd64.
# - Noble using Clang 19: Release and Unity on linux/arm64.
if os["distro_name"] == "ubuntu":
skip = True
if os["distro_version"] == "jammy":
if (
f"{os['compiler_name']}-{os['compiler_version']}" == "gcc-12"
and build_type == "Debug"
and "-Dunity=OFF" in cmake_args
and architecture["platform"] == "linux/arm64"
):
skip = False
@@ -138,18 +147,21 @@ def generate_strategy_matrix(all: bool, config: Config) -> list:
if (
f"{os['compiler_name']}-{os['compiler_version']}" == "gcc-14"
and build_type == "Release"
and "-Dunity=ON" in cmake_args
and architecture["platform"] == "linux/amd64"
):
skip = False
if (
f"{os['compiler_name']}-{os['compiler_version']}" == "clang-18"
and build_type == "Debug"
and "-Dunity=OFF" in cmake_args
and architecture["platform"] == "linux/amd64"
):
skip = False
if (
f"{os['compiler_name']}-{os['compiler_version']}" == "clang-19"
and build_type == "Release"
and "-Dunity=ON" in cmake_args
and architecture["platform"] == "linux/arm64"
):
skip = False
@@ -157,16 +169,20 @@ def generate_strategy_matrix(all: bool, config: Config) -> list:
continue
# MacOS:
# - Debug on macos/arm64.
# - Debug and no Unity on macos/arm64.
if os["distro_name"] == "macos" and not (
build_type == "Debug" and architecture["platform"] == "macos/arm64"
build_type == "Debug"
and "-Dunity=OFF" in cmake_args
and architecture["platform"] == "macos/arm64"
):
continue
# Windows:
# - Release on windows/amd64.
# - Release and Unity on windows/amd64.
if os["distro_name"] == "windows" and not (
build_type == "Release" and architecture["platform"] == "windows/amd64"
build_type == "Release"
and "-Dunity=ON" in cmake_args
and architecture["platform"] == "windows/amd64"
):
continue
@@ -193,28 +209,18 @@ def generate_strategy_matrix(all: bool, config: Config) -> list:
):
continue
# Enable code coverage for Debian Bookworm using GCC 15 in Debug on
# linux/amd64
# Enable code coverage for Debian Bookworm using GCC 15 in Debug and no
# Unity on linux/amd64
if (
f"{os['distro_name']}-{os['distro_version']}" == "debian-bookworm"
and f"{os['compiler_name']}-{os['compiler_version']}" == "gcc-15"
f"{os['compiler_name']}-{os['compiler_version']}" == "gcc-15"
and build_type == "Debug"
and "-Dunity=OFF" in cmake_args
and architecture["platform"] == "linux/amd64"
):
cmake_args = f"{cmake_args} -Dcoverage=ON -Dcoverage_format=xml -DCODE_COVERAGE_VERBOSE=ON -DCMAKE_C_FLAGS=-O0 -DCMAKE_CXX_FLAGS=-O0"
# Enable unity build for Ubuntu Jammy using GCC 12 in Debug on
# linux/amd64.
if (
f"{os['distro_name']}-{os['distro_version']}" == "ubuntu-jammy"
and f"{os['compiler_name']}-{os['compiler_version']}" == "gcc-12"
and build_type == "Debug"
and architecture["platform"] == "linux/amd64"
):
cmake_args = f"{cmake_args} -Dunity=ON"
cmake_args = f"-Dcoverage=ON -Dcoverage_format=xml -DCODE_COVERAGE_VERBOSE=ON -DCMAKE_C_FLAGS=-O0 -DCMAKE_CXX_FLAGS=-O0 {cmake_args}"
# Generate a unique name for the configuration, e.g. macos-arm64-debug
# or debian-bookworm-gcc-12-amd64-release.
# or debian-bookworm-gcc-12-amd64-release-unity.
config_name = os["distro_name"]
if (n := os["distro_version"]) != "":
config_name += f"-{n}"

View File

@@ -17,196 +17,13 @@
"compiler_version": "12",
"image_sha": "ab4d1f0"
},
{
"distro_name": "debian",
"distro_version": "bookworm",
"compiler_name": "gcc",
"compiler_version": "13",
"image_sha": "ab4d1f0"
},
{
"distro_name": "debian",
"distro_version": "bookworm",
"compiler_name": "gcc",
"compiler_version": "14",
"image_sha": "ab4d1f0"
},
{
"distro_name": "debian",
"distro_version": "bookworm",
"compiler_name": "gcc",
"compiler_version": "15",
"image_sha": "ab4d1f0"
},
{
"distro_name": "debian",
"distro_version": "bookworm",
"compiler_name": "clang",
"compiler_version": "16",
"image_sha": "ab4d1f0"
},
{
"distro_name": "debian",
"distro_version": "bookworm",
"compiler_name": "clang",
"compiler_version": "17",
"image_sha": "ab4d1f0"
},
{
"distro_name": "debian",
"distro_version": "bookworm",
"compiler_name": "clang",
"compiler_version": "18",
"image_sha": "ab4d1f0"
},
{
"distro_name": "debian",
"distro_version": "bookworm",
"compiler_name": "clang",
"compiler_version": "19",
"image_sha": "ab4d1f0"
},
{
"distro_name": "debian",
"distro_version": "bookworm",
"compiler_name": "clang",
"compiler_version": "20",
"image_sha": "ab4d1f0"
},
{
"distro_name": "debian",
"distro_version": "trixie",
"compiler_name": "gcc",
"compiler_version": "14",
"image_sha": "ab4d1f0"
},
{
"distro_name": "debian",
"distro_version": "trixie",
"compiler_name": "gcc",
"compiler_version": "15",
"image_sha": "ab4d1f0"
},
{
"distro_name": "debian",
"distro_version": "trixie",
"compiler_name": "clang",
"compiler_version": "20",
"image_sha": "ab4d1f0"
},
{
"distro_name": "debian",
"distro_version": "trixie",
"compiler_name": "clang",
"compiler_version": "21",
"image_sha": "ab4d1f0"
},
{
"distro_name": "rhel",
"distro_version": "8",
"compiler_name": "gcc",
"compiler_version": "14",
"image_sha": "ab4d1f0"
},
{
"distro_name": "rhel",
"distro_version": "8",
"compiler_name": "clang",
"compiler_version": "any",
"image_sha": "ab4d1f0"
},
{
"distro_name": "rhel",
"distro_version": "9",
"compiler_name": "gcc",
"compiler_version": "12",
"image_sha": "ab4d1f0"
},
{
"distro_name": "rhel",
"distro_version": "9",
"compiler_name": "gcc",
"compiler_version": "13",
"image_sha": "ab4d1f0"
},
{
"distro_name": "rhel",
"distro_version": "9",
"compiler_name": "gcc",
"compiler_version": "14",
"image_sha": "ab4d1f0"
},
{
"distro_name": "rhel",
"distro_version": "9",
"compiler_name": "clang",
"compiler_version": "any",
"image_sha": "ab4d1f0"
},
{
"distro_name": "rhel",
"distro_version": "10",
"compiler_name": "gcc",
"compiler_version": "14",
"image_sha": "ab4d1f0"
},
{
"distro_name": "rhel",
"distro_version": "10",
"compiler_name": "clang",
"compiler_version": "any",
"image_sha": "ab4d1f0"
},
{
"distro_name": "ubuntu",
"distro_version": "jammy",
"compiler_name": "gcc",
"compiler_version": "12",
"image_sha": "ab4d1f0"
},
{
"distro_name": "ubuntu",
"distro_version": "noble",
"compiler_name": "gcc",
"compiler_version": "13",
"image_sha": "ab4d1f0"
},
{
"distro_name": "ubuntu",
"distro_version": "noble",
"compiler_name": "gcc",
"compiler_version": "14",
"image_sha": "ab4d1f0"
},
{
"distro_name": "ubuntu",
"distro_version": "noble",
"compiler_name": "clang",
"compiler_version": "16",
"image_sha": "ab4d1f0"
},
{
"distro_name": "ubuntu",
"distro_version": "noble",
"compiler_name": "clang",
"compiler_version": "17",
"image_sha": "ab4d1f0"
},
{
"distro_name": "ubuntu",
"distro_version": "noble",
"compiler_name": "clang",
"compiler_version": "18",
"image_sha": "ab4d1f0"
},
{
"distro_name": "ubuntu",
"distro_version": "noble",
"compiler_name": "clang",
"compiler_version": "19",
"image_sha": "ab4d1f0"
"compiler_version": "12"
}
],
"build_type": ["Debug", "Release"],
"cmake_args": [""]
"cmake_args": ["-Dunity=OFF", "-Dunity=ON"]
}

View File

@@ -15,5 +15,8 @@
}
],
"build_type": ["Debug", "Release"],
"cmake_args": ["-DCMAKE_POLICY_VERSION_MINIMUM=3.5"]
"cmake_args": [
"-Dunity=OFF -DCMAKE_POLICY_VERSION_MINIMUM=3.5",
"-Dunity=ON -DCMAKE_POLICY_VERSION_MINIMUM=3.5"
]
}

View File

@@ -15,5 +15,5 @@
}
],
"build_type": ["Debug", "Release"],
"cmake_args": [""]
"cmake_args": ["-Dunity=OFF", "-Dunity=ON"]
}

View File

@@ -1,11 +1,14 @@
# This workflow runs all workflows to check, build and test the project on
# various Linux flavors, as well as on MacOS and Windows, on every push to a
# This workflow runs all workflows to check, build, package and test the project on
# various Linux flavors, as well as on macOS and Windows, on every push to a
# user branch. However, it will not run if the pull request is a draft unless it
# has the 'DraftRunCI' label. For commits to PRs that target a release branch,
# it also uploads the libxrpl recipe to the Conan remote.
name: PR
on:
push:
branches:
- legleux/build
merge_group:
types:
- checks_requested
@@ -65,6 +68,9 @@ jobs:
.github/workflows/reusable-build.yml
.github/workflows/reusable-build-test-config.yml
.github/workflows/reusable-build-test.yml
.github/workflows/reusable-build-pkg.yml
.github/workflows/reusable-pkg.yml
.github/workflows/reusable-package.yml
.github/workflows/reusable-strategy-matrix.yml
.github/workflows/reusable-test.yml
.github/workflows/reusable-upload-recipe.yml
@@ -73,6 +79,7 @@ jobs:
conan/**
external/**
include/**
pkgs/**
src/**
tests/**
CMakeLists.txt
@@ -97,68 +104,57 @@ jobs:
outputs:
go: ${{ steps.go.outputs.go == 'true' }}
check-levelization:
needs: should-run
if: ${{ needs.should-run.outputs.go == 'true' }}
uses: ./.github/workflows/reusable-check-levelization.yml
# check-levelization:
# needs: should-run
# if: ${{ needs.should-run.outputs.go == 'true' }}
# uses: ./.github/workflows/reusable-check-levelization.yml
check-rename:
needs: should-run
if: ${{ needs.should-run.outputs.go == 'true' }}
uses: ./.github/workflows/reusable-check-rename.yml
# build-test:
# needs: should-run
# if: ${{ needs.should-run.outputs.go == 'true' }}
# uses: ./.github/workflows/reusable-build-test.yml
# strategy:
# matrix:
# os: [linux, macos, windows]
# with:
# os: ${{ matrix.os }}
# secrets:
# CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
build-test:
build-package:
name: Build ${{ matrix.pkg_type }} ${{ matrix.arch }} packages
needs: should-run
if: ${{ needs.should-run.outputs.go == 'true' }}
uses: ./.github/workflows/reusable-build-test.yml
uses: ./.github/workflows/reusable-build-pkg.yml
secrets: inherit
strategy:
fail-fast: false
matrix:
os: [linux, macos, windows]
# pkg_type: [rpm]
pkg_type: [deb, rpm]
arch: [amd64]
# arch: [amd64, arm64]
with:
# Enable ccache only for events targeting the XRPLF repository, since
# other accounts will not have access to our remote cache storage.
ccache_enabled: ${{ github.repository_owner == 'XRPLF' }}
os: ${{ matrix.os }}
secrets:
CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
pkg_type: ${{ matrix.pkg_type }}
arch: ${{ matrix.arch }}
upload-recipe:
needs:
- should-run
- build-test
# Only run when committing to a PR that targets a release branch in the
# XRPLF repository.
if: ${{ github.repository_owner == 'XRPLF' && needs.should-run.outputs.go == 'true' && startsWith(github.ref, 'refs/heads/release') }}
uses: ./.github/workflows/reusable-upload-recipe.yml
secrets:
remote_username: ${{ secrets.CONAN_REMOTE_USERNAME }}
remote_password: ${{ secrets.CONAN_REMOTE_PASSWORD }}
notify-clio:
needs: upload-recipe
runs-on: ubuntu-latest
steps:
# Notify the Clio repository about the newly proposed release version, so
# it can be checked for compatibility before the release is actually made.
- name: Notify Clio
env:
GH_TOKEN: ${{ secrets.CLIO_NOTIFY_TOKEN }}
PR_URL: ${{ github.event.pull_request.html_url }}
run: |
gh api --method POST -H "Accept: application/vnd.github+json" -H "X-GitHub-Api-Version: 2022-11-28" \
/repos/xrplf/clio/dispatches -f "event_type=check_libxrpl" \
-F "client_payload[ref]=${{ needs.upload-recipe.outputs.recipe_ref }}" \
-F "client_payload[pr_url]=${PR_URL}"
# notify-clio:
# needs:
# - should-run
# - build-test
# if: ${{ needs.should-run.outputs.go == 'true' && contains(fromJSON('["release", "master"]'), github.ref_name) }}
# uses: ./.github/workflows/reusable-notify-clio.yml
# secrets:
# clio_notify_token: ${{ secrets.CLIO_NOTIFY_TOKEN }}
# conan_remote_username: ${{ secrets.CONAN_REMOTE_USERNAME }}
# conan_remote_password: ${{ secrets.CONAN_REMOTE_PASSWORD }}
passed:
if: failure() || cancelled()
needs:
- check-levelization
- check-rename
- build-test
- upload-recipe
- notify-clio
# - build-test
# - check-levelization
- build-package
runs-on: ubuntu-latest
steps:
- name: Fail

97
.github/workflows/on-trigger.new.yml vendored Normal file
View File

@@ -0,0 +1,97 @@
# This workflow runs all workflows to build and test the code on various Linux
# flavors, as well as on MacOS and Windows, on a scheduled basis, on merge into
# the 'develop' or 'release*' branches, or when requested manually. Upon pushes
# to the develop branch it also uploads the libxrpl recipe to the Conan remote.
name: Trigger
on:
push:
branches:
- legleux/linux_packages
- develop
- release
- master
paths:
# These paths are unique to `on-trigger.yml`.
- ".github/workflows/on-trigger.yml"
# Keep the paths below in sync with those in `on-pr.yml`.
- ".github/actions/build-deps/**"
- ".github/actions/build-test/**"
- ".github/actions/generate-version/**"
- ".github/actions/setup-conan/**"
- ".github/scripts/strategy-matrix/**"
- ".github/workflows/reusable-build.yml"
- ".github/workflows/reusable-build-test-config.yml"
- ".github/workflows/reusable-build-test.yml"
- ".github/workflows/reusable-build-pkg.yml"
- ".github/workflows/reusable-pkg.yml"
- ".github/workflows/reusable-package.yml"
- ".github/workflows/reusable-strategy-matrix.yml"
- ".github/workflows/reusable-test.yml"
- ".github/workflows/reusable-upload-recipe.yml"
- ".codecov.yml"
- "cmake/**"
- "conan/**"
- "external/**"
- "include/**"
- "pkgs/**"
- "src/**"
- "tests/**"
- "CMakeLists.txt"
- "conanfile.py"
- "conan.lock"
# Run at 06:32 UTC on every day of the week from Monday through Friday. This
# will force all dependencies to be rebuilt, which is useful to verify that
# all dependencies can be built successfully. Only the dependencies that
# are actually missing from the remote will be uploaded.
schedule:
- cron: "32 6 * * 1-5"
# Run when manually triggered via the GitHub UI or API.
workflow_dispatch:
concurrency:
# When a PR is merged into the develop branch it will be assigned a unique
# group identifier, so execution will continue even if another PR is merged
# while it is still running. In all other cases the group identifier is shared
# per branch, so that any in-progress runs are cancelled when a new commit is
# pushed.
group: ${{ github.workflow }}-${{ github.event_name == 'push' && github.ref == 'refs/heads/develop' && github.sha || github.ref }}
cancel-in-progress: true
defaults:
run:
shell: bash
jobs:
# check-missing-commits:
# if: ${{ github.event_name == 'push' && github.ref_type == 'branch' && contains(fromJSON('["develop", "release"]'), github.ref_name) }}
# uses: ./.github/workflows/reusable-check-missing-commits.yml
# build-test:
# uses: ./.github/workflows/reusable-build-test.yml
# strategy:
# matrix:
# os: [linux, macos, windows]
# with:
# os: ${{ matrix.os }}
# strategy_matrix: ${{ github.event_name == 'schedule' && 'all' || 'minimal' }}
# secrets:
# CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
build-package:
name: Build ${{ matrix.pkg_type }} ${{ matrix.arch }} packages
uses: ./.github/workflows/reusable-build-pkg.yml
secrets: inherit
strategy:
fail-fast: ${{ github.event_name == 'merge_group' }}
matrix:
# pkg_type: [rpm]
pkg_type: [deb, rpm]
arch: [amd64]
# arch: [amd64, arm64]
with:
pkg_type: ${{ matrix.pkg_type }}
arch: ${{ matrix.arch }}

View File

@@ -9,6 +9,7 @@ on:
branches:
- "develop"
- "release*"
- "linux_packages_squashed"
paths:
# These paths are unique to `on-trigger.yml`.
- ".github/workflows/on-trigger.yml"
@@ -22,6 +23,9 @@ on:
- ".github/workflows/reusable-build.yml"
- ".github/workflows/reusable-build-test-config.yml"
- ".github/workflows/reusable-build-test.yml"
- ".github/workflows/reusable-build-pkg.yml"
- ".github/workflows/reusable-pkg.yml"
- ".github/workflows/reusable-package.yml"
- ".github/workflows/reusable-strategy-matrix.yml"
- ".github/workflows/reusable-test.yml"
- ".github/workflows/reusable-upload-recipe.yml"
@@ -30,6 +34,7 @@ on:
- "conan/**"
- "external/**"
- "include/**"
- "pkgs/**"
- "src/**"
- "tests/**"
- "CMakeLists.txt"
@@ -78,6 +83,21 @@ jobs:
secrets:
CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
build-package:
name: Build ${{ matrix.pkg_type }} ${{ matrix.arch }} packages
uses: ./.github/workflows/reusable-build-pkg.yml
secrets: inherit
strategy:
fail-fast: ${{ github.event_name == 'merge_group' }}
matrix:
# pkg_type: [rpm]
pkg_type: [deb, rpm]
arch: [amd64]
# arch: [amd64, arm64]
with:
pkg_type: ${{ matrix.pkg_type }}
arch: ${{ matrix.arch }}
upload-recipe:
needs: build-test
# Only run when pushing to the develop branch in the XRPLF repository.

34
.github/workflows/package-test.yml vendored Normal file
View File

@@ -0,0 +1,34 @@
name: Test rippled
on:
workflow_call:
inputs:
pkg_type:
description: "Whether to run unit tests"
required: true
type: boolean
arch:
description: Runner to run the job on as a JSON string
required: true
type: string
jobs:
test:
name: Test ${{ inputs.pkg_type }}-${{ inputs.arch }}
strategy:
fail-fast: false
matrix:
include:
- { pkg: rpm, distro: "rocky:9" }
- { pkg: deb, distro: "ubuntu:jammy" }
- { pkg: deb, distro: "debian:trixie" }
runs-on: ubuntu-latest
container: ${{ matrix.distro }}
steps:
- name: run unittests
run: |
ls -lh
# - name: Download rippled artifact
# uses: actions/download-artifact@d3f86a106a0bac45b974a628896c90dbdf5c8093 # v4.3.0
# with:
# name: rippled-${{ inputs.config_name }}

148
.github/workflows/reusable-build-pkg.yml vendored Normal file
View File

@@ -0,0 +1,148 @@
on:
workflow_call:
inputs:
pkg_type:
required: false
type: string
arch:
required: false
type: string
# secrets:
# GPG_KEY_B64:
# description: "The gpg key to sign packages."
# required: true
# GPG_KEY_PASS_B64:
# description: "The gpg key passphrase."
# required: true
defaults:
run:
shell: bash
jobs:
build:
name: Build ${{ inputs.pkg_type }} ${{ inputs.arch }} package
runs-on: heavy${{ inputs.arch == 'arm64' && '-arm64' || '' }}
container: ghcr.io/xrplf/ci/${{ inputs.pkg_type == 'rpm' && 'rhel-9' || 'ubuntu-jammy' }}:gcc-12
steps:
- name: Checkout repository
uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
- name: Build packages
run: |
./pkgs/build.sh
cat build_vars >> $GITHUB_STEP_SUMMARY
- uses: actions/upload-artifact@v4
with:
name: ${{ inputs.pkg_type }}-${{ inputs.arch }}
path: |
*.deb
*.ddeb
if-no-files-found: error
if: inputs.pkg_type == 'deb'
- uses: actions/upload-artifact@v4
with:
name: ${{ inputs.pkg_type }}-${{ inputs.arch }}
path: "*${{ inputs.arch }}.${{ inputs.pkg_type }}"
if-no-files-found: error
if: inputs.pkg_type == 'rpm'
test:
name: Test ${{ inputs.pkg_type }} ${{ inputs.arch }} package
needs: build
runs-on: heavy${{ inputs.arch == 'arm64' && '-arm64' || '' }}
container: ghcr.io/xrplf/ci/${{ inputs.pkg_type == 'rpm' && 'rhel-9' || 'ubuntu-jammy' }}:gcc-12
steps:
- uses: actions/download-artifact@v4
with:
name: ${{ inputs.pkg_type }}-${{ inputs.arch }}
- name: Running tests
run: echo "Running tests..."
sign:
name: Sign ${{ inputs.pkg_type }} ${{ inputs.arch }} package
needs: build
runs-on: ubuntu-latest
container: ghcr.io/astral-sh/uv:python3.13-bookworm-slim
steps:
- name: Install gpg & rpm
run: apt-get update && apt-get install -y gpg rpm
- name: Checkout repository
uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
- uses: actions/download-artifact@v4
with:
name: ${{ inputs.pkg_type }}-${{ inputs.arch }}
- name: Sign
env:
PYTHONUNBUFFERED: 1
GPG_KEY_B64: ${{ secrets.GPG_KEY_B64 }}
GPG_KEY_PASS_B64: ${{ secrets.GPG_KEY_PASS_B64 }}
run: |
if [ "${{ inputs.pkg_type }}" = "rpm" ]; then
for i in $(find . -maxdepth 1 -type f -name "rippled-[0-9]*.rpm"); do
echo "found $i"
./pkgs/sign_packages.py "$i"
done
elif [ "${{ inputs.pkg_type }}" = "deb" ]; then
for i in $(find . -maxdepth 1 -type f -name "rippled_*.deb"); do
echo "found $i"
./pkgs/sign_packages.py "$i"
done
fi
- uses: actions/upload-artifact@v4
with:
name: signed-rippled-${{ inputs.pkg_type }}-${{ inputs.arch }}
path: |
*.deb
*.ddeb
if-no-files-found: error
if: inputs.pkg_type == 'deb'
- uses: actions/upload-artifact@v4
with:
name: signed-rippled-${{ inputs.pkg_type }}-${{ inputs.arch }}
path: "*${{ inputs.arch }}.${{ inputs.pkg_type }}"
if-no-files-found: error
if: inputs.pkg_type == 'rpm'
docker:
name: Build Docker image
if: inputs.pkg_type == 'deb'
needs: build
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
- uses: actions/download-artifact@v4
with:
name: deb-${{ inputs.arch }}
- uses: docker/setup-buildx-action@v3
- uses: docker/login-action@v3
with:
registry: ghcr.io
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
- uses: docker/metadata-action@v5
id: meta
with:
images: ghcr.io/${{ github.repository_owner }}/rippled
tags: |
type=ref,event=branch
type=ref,event=tag
type=sha
- uses: docker/build-push-action@v6
with:
context: .
file: pkgs/docker/Dockerfile
push: ${{ github.event_name != 'pull_request' }}
tags: ${{ steps.meta.outputs.tags }}
labels: ${{ steps.meta.outputs.labels }}

View File

@@ -31,8 +31,6 @@ jobs:
run: .github/scripts/rename/namespace.sh .
- name: Check config name
run: .github/scripts/rename/config.sh .
- name: Check include guards
run: .github/scripts/rename/include.sh .
- name: Check for differences
env:
MESSAGE: |

69
.github/workflows/reusable-package.yml vendored Normal file
View File

@@ -0,0 +1,69 @@
name: Package rippled
on:
workflow_call:
inputs:
build_type:
description: 'The build type to use ("Debug", "Release").'
required: false
type: string
default: 'Release'
cmake_args:
description: "Additional arguments to pass to CMake."
required: false
type: string
cmake_target:
description: "The CMake target to build."
required: false
type: string
runs_on:
description: Runner to run the job on as a JSON string
required: true
type: string
image:
description: "The image to run in (leave empty to run natively)"
required: false
type: string
default: ''
config_name:
description: "The name of the configuration."
required: false
type: string
defaults:
run:
shell: bash
jobs:
build:
name: Package ${{ inputs.config_name }}
runs-on: ${{ fromJSON(inputs.runs_on) }}
container: ${{ inputs.image != '' && inputs.image || null }}
steps:
- name: Checkout repository
uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
- name: Build packages
run: |
export BUILD_TYPE=${{ inputs.build_type }}
export CMAKE_ARGS=${{ inputs.cmake_args }}
export CMAKE_TARGETS=${{ inputs.cmake_target }}
./pkgs/build.sh
{
echo "<table>"
while IFS='=' read -r k v; do
printf '<tr><td>%s</td><td align="right"><code>%s</code></td></tr>\n' "$k" "$v"
done < build_vars
echo "</table>"
} >> "$GITHUB_STEP_SUMMARY"
- uses: actions/upload-artifact@v4
with:
name: ${{ inputs.config_name }}
path: '**/*.{deb,rpm}'
if-no-files-found: error

41
.github/workflows/reusable-pkg.yml vendored Normal file
View File

@@ -0,0 +1,41 @@
name: Package
on:
workflow_call:
inputs:
build_dir:
description: "The directory where to build."
required: false
type: string
default: ".build"
os:
description: 'The operating system to use for the build ("linux", "macos", "windows").'
required: false
type: string
default: linux
strategy_matrix_subset:
description: 'The strategy matrix to use for generating a subset of configurations.'
required: false
type: string
default: "package"
jobs:
generate-matrix:
uses: ./.github/workflows/reusable-strategy-matrix.yml
with:
os: ${{ inputs.os }}
strategy_matrix_subset: ${{ inputs.strategy_matrix_subset }}
package:
needs:
- generate-matrix
uses: ./.github/workflows/reusable-package.yml
strategy:
matrix: ${{ fromJson(needs.generate-matrix.outputs.matrix) }}
with:
build_type: ${{ matrix.build_type }}
cmake_args: ${{ matrix.cmake_args }}
cmake_target: ${{ matrix.cmake_target }}
runs_on: ${{ toJSON(matrix.architecture.runner) }}
image: ${{ contains(matrix.architecture.platform, 'linux') && format('ghcr.io/xrplf/ci/{0}-{1}:{2}-{3}-sha-5dd7158', matrix.os.distro_name, matrix.os.distro_version, matrix.os.compiler_name, matrix.os.compiler_version) || '' }}
config_name: ${{ matrix.config_name }}

View File

@@ -13,6 +13,10 @@ on:
required: false
type: string
default: "minimal"
strategy_matrix_subset:
description: 'The strategy matrix to use for generating a subset of configs).'
required: false
type: string
outputs:
matrix:
description: "The generated strategy matrix."
@@ -42,4 +46,5 @@ jobs:
env:
GENERATE_CONFIG: ${{ inputs.os != '' && format('--config={0}.json', inputs.os) || '' }}
GENERATE_OPTION: ${{ inputs.strategy_matrix == 'all' && '--all' || '' }}
run: ./generate.py ${GENERATE_OPTION} ${GENERATE_CONFIG} >> "${GITHUB_OUTPUT}"
GENERATE_SUBSET: ${{ inputs.strategy_matrix_subset != '' && format('--{0}', inputs.strategy_matrix_subset) || '' }}
run: ./generate.py ${{ env.GENERATE_SUBSET }} ${{ env.GENERATE_OPTION }} ${{ env.GENERATE_CONFIG }} >> "${GITHUB_OUTPUT}"

View File

@@ -368,36 +368,6 @@ The workaround for this error is to add two lines to your profile:
tools.build:cxxflags=['-DBOOST_ASIO_DISABLE_CONCEPTS']
```
### Set Up Ccache
To speed up repeated compilations, we recommend that you install
[ccache](https://ccache.dev), a tool that wraps your compiler so that it can
cache build objects locally.
#### Linux
You can install it using the package manager, e.g. `sudo apt install ccache`
(Ubuntu) or `sudo dnf install ccache` (RHEL).
#### macOS
You can install it using Homebrew, i.e. `brew install ccache`.
#### Windows
You can install it using Chocolatey, i.e. `choco install ccache`. If you already
have Ccache installed, then `choco upgrade ccache` will update it to the latest
version. However, if you see an error such as:
```
terminate called after throwing an instance of 'std::bad_alloc'
what(): std::bad_alloc
C:\Program Files\Microsoft Visual Studio\2022\Community\MSBuild\Microsoft\VC\v170\Microsoft.CppCommon.targets(617,5): error MSB6006: "cl.exe" exited with code 3.
```
then please install a specific version of Ccache that we know works, via: `choco
install ccache --version 4.11.3 --allow-downgrade`.
### Build and Test
1. Create a build directory and move into it.
@@ -580,10 +550,10 @@ See [Sanitizers docs](./docs/build/sanitizers.md) for more details.
| `werr` | OFF | Treat compilation warnings as errors |
| `wextra` | OFF | Enable additional compilation warnings |
[Unity builds][5] may be faster for the first build (at the cost of much more
memory) since they concatenate sources into fewer translation units. Non-unity
builds may be faster for incremental builds, and can be helpful for detecting
`#include` omissions.
[Unity builds][5] may be faster for the first build
(at the cost of much more memory) since they concatenate sources into fewer
translation units. Non-unity builds may be faster for incremental builds,
and can be helpful for detecting `#include` omissions.
## Troubleshooting

View File

@@ -1,239 +0,0 @@
# 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)*

View File

@@ -1,328 +0,0 @@
# 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)*

View File

@@ -1,404 +0,0 @@
# 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
```
---
## 2.5 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)*

View File

@@ -1,448 +0,0 @@
# 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)*

View File

@@ -1,982 +0,0 @@
# 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)*

View File

@@ -1,936 +0,0 @@
# 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)*

View File

@@ -1,537 +0,0 @@
# 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)*

View File

@@ -1,590 +0,0 @@
# 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)*

View File

@@ -1,133 +0,0 @@
# 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)*

View File

@@ -1,187 +0,0 @@
# [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.
➡️ **[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.*

View File

@@ -940,7 +940,23 @@
#
# path Location to store the database
#
# Optional keys for NuDB and RocksDB:
# Optional keys
#
# cache_size Size of cache for database records. Default is 16384.
# Setting this value to 0 will use the default value.
#
# cache_age Length of time in minutes to keep database records
# cached. Default is 5 minutes. Setting this value to
# 0 will use the default value.
#
# Note: if neither cache_size nor cache_age is
# specified, the cache for database records will not
# be created. If only one of cache_size or cache_age
# is specified, the cache will be created using the
# default value for the unspecified parameter.
#
# Note: the cache will not be created if online_delete
# is specified.
#
# fast_load Boolean. If set, load the last persisted ledger
# from disk upon process start before syncing to
@@ -948,6 +964,8 @@
# if sufficient IOPS capacity is available.
# Default 0.
#
# Optional keys for NuDB or RocksDB:
#
# earliest_seq The default is 32570 to match the XRP ledger
# network's earliest allowed sequence. Alternate
# networks may set this value. Minimum value of 1.

View File

@@ -466,6 +466,11 @@ function (add_code_coverage_to_target name scope)
target_compile_options(${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}>)
target_link_libraries(
${name}
${scope}
$<$<LINK_LANGUAGE:CXX>:${COVERAGE_CXX_LINKER_FLAGS}
gcov>
$<$<LINK_LANGUAGE:C>:${COVERAGE_C_LINKER_FLAGS}
gcov>)
endfunction () # add_code_coverage_to_target

View File

@@ -9,5 +9,8 @@ function (xrpl_add_test name)
isolate_headers(${target} "${CMAKE_SOURCE_DIR}" "${CMAKE_SOURCE_DIR}/tests/${name}" PRIVATE)
# Make sure the test isn't optimized away in unity builds
set_target_properties(${target} PROPERTIES UNITY_BUILD_MODE GROUP UNITY_BUILD_BATCH_SIZE 0) # Adjust as needed
add_test(NAME ${target} COMMAND ${target})
endfunction ()

View File

@@ -84,6 +84,9 @@ add_module(xrpl net)
target_link_libraries(xrpl.libxrpl.net PUBLIC xrpl.libxrpl.basics xrpl.libxrpl.json xrpl.libxrpl.protocol
xrpl.libxrpl.resource)
add_module(xrpl server)
target_link_libraries(xrpl.libxrpl.server PUBLIC xrpl.libxrpl.protocol)
add_module(xrpl nodestore)
target_link_libraries(xrpl.libxrpl.nodestore PUBLIC xrpl.libxrpl.basics xrpl.libxrpl.json xrpl.libxrpl.protocol)
@@ -91,15 +94,8 @@ add_module(xrpl shamap)
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)
add_module(xrpl server)
target_link_libraries(xrpl.libxrpl.server PUBLIC xrpl.libxrpl.protocol xrpl.libxrpl.core xrpl.libxrpl.rdb)
add_module(xrpl ledger)
target_link_libraries(xrpl.libxrpl.ledger PUBLIC xrpl.libxrpl.basics xrpl.libxrpl.json xrpl.libxrpl.protocol
xrpl.libxrpl.rdb)
target_link_libraries(xrpl.libxrpl.ledger PUBLIC xrpl.libxrpl.basics xrpl.libxrpl.json xrpl.libxrpl.protocol)
add_library(xrpl.libxrpl)
set_target_properties(xrpl.libxrpl PROPERTIES OUTPUT_NAME xrpl)
@@ -117,14 +113,13 @@ target_link_modules(
core
crypto
json
ledger
net
nodestore
protocol
rdb
resource
server
shamap)
nodestore
shamap
net
ledger)
# All headers in libxrpl are in modules.
# Uncomment this stanza if you have not yet moved new headers into a module.
@@ -165,4 +160,12 @@ if (xrpld)
# antithesis_instrumentation.h, which is not exported as INTERFACE
target_include_directories(xrpld PRIVATE ${CMAKE_SOURCE_DIR}/external/antithesis-sdk)
endif ()
# any files that don't play well with unity should be added here
if (tests)
set_source_files_properties(
# these two seem to produce conflicts in beast teardown template methods
src/test/rpc/ValidatorRPC_test.cpp src/test/ledger/Invariants_test.cpp PROPERTIES SKIP_UNITY_BUILD_INCLUSION
TRUE)
endif ()
endif ()

View File

@@ -23,7 +23,6 @@ install(TARGETS common
xrpl.libxrpl.core
xrpl.libxrpl.crypto
xrpl.libxrpl.json
xrpl.libxrpl.rdb
xrpl.libxrpl.ledger
xrpl.libxrpl.net
xrpl.libxrpl.nodestore

View File

@@ -6,11 +6,11 @@
"sqlite3/3.49.1#8631739a4c9b93bd3d6b753bac548a63%1765850149.926",
"soci/4.0.3#a9f8d773cd33e356b5879a4b0564f287%1765850149.46",
"snappy/1.1.10#968fef506ff261592ec30c574d4a7809%1765850147.878",
"secp256k1/0.7.1#3a61e95e220062ef32c48d019e9c81f7%1770306721.686",
"secp256k1/0.7.0#9c4ab67bdc3860c16ea5b36aed8f74ea%1765850147.928",
"rocksdb/10.5.1#4a197eca381a3e5ae8adf8cffa5aacd0%1765850186.86",
"re2/20230301#ca3b241baec15bd31ea9187150e0b333%1765850148.103",
"protobuf/6.32.1#f481fd276fc23a33b85a3ed1e898b693%1765850161.038",
"openssl/3.5.5#05a4ac5b7323f7a329b2db1391d9941f%1769599205.414",
"openssl/3.5.4#1b986e61b38fdfda3b40bebc1b234393%1768312656.257",
"nudb/2.0.9#0432758a24204da08fee953ec9ea03cb%1769436073.32",
"lz4/1.10.0#59fc63cac7f10fbe8e05c7e62c2f3504%1765850143.914",
"libiconv/1.17#1e65319e945f2d31941a9d28cc13c058%1765842973.492",
@@ -23,7 +23,7 @@
"date/3.0.4#862e11e80030356b53c2c38599ceb32b%1765850143.772",
"c-ares/1.34.5#5581c2b62a608b40bb85d965ab3ec7c8%1765850144.336",
"bzip2/1.0.8#c470882369c2d95c5c77e970c0c7e321%1765850143.837",
"boost/1.90.0#d5e8defe7355494953be18524a7f135b%1769454080.269",
"boost/1.90.0#d5e8defe7355494953be18524a7f135b%1765955095.179",
"abseil/20250127.0#99262a368bd01c0ccca8790dfced9719%1766517936.993"
],
"build_requires": [
@@ -31,7 +31,7 @@
"strawberryperl/5.32.1.1#707032463aa0620fa17ec0d887f5fe41%1765850165.196",
"protobuf/6.32.1#f481fd276fc23a33b85a3ed1e898b693%1765850161.038",
"nasm/2.16.01#31e26f2ee3c4346ecd347911bd126904%1765850144.707",
"msys2/cci.latest#eea83308ad7e9023f7318c60d5a9e6cb%1770199879.083",
"msys2/cci.latest#1996656c3c98e5765b25b60ff5cf77b4%1764840888.758",
"m4/1.4.19#70dc8bbb33e981d119d2acc0175cf381%1763158052.846",
"cmake/4.2.0#ae0a44f44a1ef9ab68fd4b3e9a1f8671%1765850153.937",
"cmake/3.31.10#313d16a1aa16bbdb2ca0792467214b76%1765850153.479",

View File

@@ -32,8 +32,8 @@ class Xrpl(ConanFile):
"grpc/1.72.0",
"libarchive/3.8.1",
"nudb/2.0.9",
"openssl/3.5.5",
"secp256k1/0.7.1",
"openssl/3.5.4",
"secp256k1/0.7.0",
"soci/4.0.3",
"zlib/1.3.1",
]

View File

@@ -1,4 +1,5 @@
#pragma once
#ifndef XRPL_BASICS_ARCHIVE_H_INCLUDED
#define XRPL_BASICS_ARCHIVE_H_INCLUDED
#include <boost/filesystem.hpp>
@@ -15,3 +16,5 @@ void
extractTarLz4(boost::filesystem::path const& src, boost::filesystem::path const& dst);
} // namespace xrpl
#endif

View File

@@ -1,4 +1,5 @@
#pragma once
#ifndef XRPL_BASICS_BASICCONFIG_H_INCLUDED
#define XRPL_BASICS_BASICCONFIG_H_INCLUDED
#include <xrpl/basics/contract.h>
@@ -368,3 +369,5 @@ get_if_exists<bool>(Section const& section, std::string const& name, bool& v)
}
} // namespace xrpl
#endif

View File

@@ -1,4 +1,5 @@
#pragma once
#ifndef XRPL_BASICS_BLOB_H_INCLUDED
#define XRPL_BASICS_BLOB_H_INCLUDED
#include <vector>
@@ -10,3 +11,5 @@ namespace xrpl {
using Blob = std::vector<unsigned char>;
} // namespace xrpl
#endif

View File

@@ -1,4 +1,5 @@
#pragma once
#ifndef XRPL_BASICS_BUFFER_H_INCLUDED
#define XRPL_BASICS_BUFFER_H_INCLUDED
#include <xrpl/basics/Slice.h>
#include <xrpl/beast/utility/instrumentation.h>
@@ -212,3 +213,5 @@ operator!=(Buffer const& lhs, Buffer const& rhs) noexcept
}
} // namespace xrpl
#endif

View File

@@ -1,4 +1,5 @@
#pragma once
#ifndef XRPL_BASICS_BYTEUTILITIES_H_INCLUDED
#define XRPL_BASICS_BYTEUTILITIES_H_INCLUDED
namespace xrpl {
@@ -19,3 +20,5 @@ megabytes(T value) noexcept
static_assert(kilobytes(2) == 2048, "kilobytes(2) == 2048");
static_assert(megabytes(3) == 3145728, "megabytes(3) == 3145728");
} // namespace xrpl
#endif

View File

@@ -1,4 +1,5 @@
#pragma once
#ifndef XRPL_COMPRESSIONALGORITHMS_H_INCLUDED
#define XRPL_COMPRESSIONALGORITHMS_H_INCLUDED
#include <xrpl/basics/contract.h>
@@ -132,3 +133,5 @@ lz4Decompress(InputStream& in, std::size_t inSize, std::uint8_t* decompressed, s
} // namespace compression_algorithms
} // namespace xrpl
#endif // XRPL_COMPRESSIONALGORITHMS_H_INCLUDED

View File

@@ -1,4 +1,5 @@
#pragma once
#ifndef XRPL_BASICS_COUNTEDOBJECT_H_INCLUDED
#define XRPL_BASICS_COUNTEDOBJECT_H_INCLUDED
#include <xrpl/beast/type_name.h>
@@ -133,3 +134,5 @@ public:
};
} // namespace xrpl
#endif

View File

@@ -1,4 +1,5 @@
#pragma once
#ifndef XRPL_BASICS_DECAYINGSAMPLE_H_INCLUDED
#define XRPL_BASICS_DECAYINGSAMPLE_H_INCLUDED
#include <chrono>
#include <cmath>
@@ -129,3 +130,5 @@ private:
};
} // namespace xrpl
#endif

View File

@@ -1,4 +1,5 @@
#pragma once
#ifndef XRPL_BASICS_EXPECTED_H_INCLUDED
#define XRPL_BASICS_EXPECTED_H_INCLUDED
#include <xrpl/basics/contract.h>
@@ -228,3 +229,5 @@ public:
};
} // namespace xrpl
#endif // XRPL_BASICS_EXPECTED_H_INCLUDED

View File

@@ -1,4 +1,5 @@
#pragma once
#ifndef XRPL_BASICS_FILEUTILITIES_H_INCLUDED
#define XRPL_BASICS_FILEUTILITIES_H_INCLUDED
#include <boost/filesystem.hpp>
#include <boost/system/error_code.hpp>
@@ -17,3 +18,5 @@ void
writeFileContents(boost::system::error_code& ec, boost::filesystem::path const& destPath, std::string const& contents);
} // namespace xrpl
#endif

View File

@@ -1,4 +1,5 @@
#pragma once
#ifndef XRPL_BASICS_INTRUSIVEPOINTER_H_INCLUDED
#define XRPL_BASICS_INTRUSIVEPOINTER_H_INCLUDED
#include <concepts>
#include <cstdint>
@@ -484,3 +485,4 @@ dynamic_pointer_cast(TT const& v)
}
} // namespace intr_ptr
} // namespace xrpl
#endif

View File

@@ -1,4 +1,5 @@
#pragma once
#ifndef XRPL_BASICS_INTRUSIVEPOINTER_IPP_INCLUDED
#define XRPL_BASICS_INTRUSIVEPOINTER_IPP_INCLUDED
#include <xrpl/basics/IntrusivePointer.h>
#include <xrpl/basics/IntrusiveRefCounts.h>
@@ -702,3 +703,4 @@ SharedWeakUnion<T>::unsafeReleaseNoStore()
}
} // namespace xrpl
#endif

View File

@@ -1,4 +1,5 @@
#pragma once
#ifndef XRPL_BASICS_INTRUSIVEREFCOUNTS_H_INCLUDED
#define XRPL_BASICS_INTRUSIVEREFCOUNTS_H_INCLUDED
#include <xrpl/beast/utility/instrumentation.h>
@@ -460,3 +461,4 @@ partialDestructorFinished(T** o)
//------------------------------------------------------------------------------
} // namespace xrpl
#endif

View File

@@ -1,4 +1,5 @@
#pragma once
#ifndef XRPL_BASICS_KEYCACHE_H
#define XRPL_BASICS_KEYCACHE_H
#include <xrpl/basics/TaggedCache.h>
#include <xrpl/basics/base_uint.h>
@@ -8,3 +9,5 @@ namespace xrpl {
using KeyCache = TaggedCache<uint256, int, true>;
} // namespace xrpl
#endif // XRPL_BASICS_KEYCACHE_H

View File

@@ -1,4 +1,5 @@
#pragma once
#ifndef XRPL_BASICS_LOCALVALUE_H_INCLUDED
#define XRPL_BASICS_LOCALVALUE_H_INCLUDED
#include <boost/thread/tss.hpp>
@@ -106,3 +107,5 @@ LocalValue<T>::operator*()
lvs->values.emplace(this, std::make_unique<detail::LocalValues::Value<T>>(t_)).first->second->get());
}
} // namespace xrpl
#endif

View File

@@ -1,4 +1,5 @@
#pragma once
#ifndef XRPL_BASICS_LOG_H_INCLUDED
#define XRPL_BASICS_LOG_H_INCLUDED
#include <xrpl/basics/UnorderedContainers.h>
#include <xrpl/beast/utility/Journal.h>
@@ -257,3 +258,5 @@ beast::Journal
debugLog();
} // namespace xrpl
#endif

View File

@@ -1,4 +1,5 @@
#pragma once
#ifndef XRPL_BASICS_MATHUTILITIES_H_INCLUDED
#define XRPL_BASICS_MATHUTILITIES_H_INCLUDED
#include <algorithm>
#include <cassert>
@@ -44,3 +45,5 @@ static_assert(calculatePercent(50'000'001, 100'000'000) == 51);
static_assert(calculatePercent(99'999'999, 100'000'000) == 100);
} // namespace xrpl
#endif

View File

@@ -1,4 +1,5 @@
#pragma once
#ifndef XRPL_BASICS_NUMBER_H_INCLUDED
#define XRPL_BASICS_NUMBER_H_INCLUDED
#include <xrpl/beast/utility/instrumentation.h>
@@ -818,3 +819,5 @@ public:
};
} // namespace xrpl
#endif // XRPL_BASICS_NUMBER_H_INCLUDED

View File

@@ -1,4 +1,5 @@
#pragma once
#ifndef XRPL_BASICS_RANGESET_H_INCLUDED
#define XRPL_BASICS_RANGESET_H_INCLUDED
#include <xrpl/beast/core/LexicalCast.h>
@@ -172,3 +173,5 @@ prevMissing(RangeSet<T> const& rs, T t, T minVal = 0)
}
} // namespace xrpl
#endif

View File

@@ -1,4 +1,5 @@
#pragma once
#ifndef XRPL_BASICS_RESOLVER_H_INCLUDED
#define XRPL_BASICS_RESOLVER_H_INCLUDED
#include <xrpl/beast/net/IPEndpoint.h>
@@ -44,3 +45,5 @@ public:
};
} // namespace xrpl
#endif

View File

@@ -1,4 +1,5 @@
#pragma once
#ifndef XRPL_BASICS_RESOLVERASIO_H_INCLUDED
#define XRPL_BASICS_RESOLVERASIO_H_INCLUDED
#include <xrpl/basics/Resolver.h>
#include <xrpl/beast/utility/Journal.h>
@@ -17,3 +18,5 @@ public:
};
} // namespace xrpl
#endif

View File

@@ -1,4 +1,5 @@
#pragma once
#ifndef XRPL_BASICS_SHAMAP_HASH_H_INCLUDED
#define XRPL_BASICS_SHAMAP_HASH_H_INCLUDED
#include <xrpl/basics/base_uint.h>
#include <xrpl/basics/partitioned_unordered_map.h>
@@ -97,3 +98,5 @@ extract(SHAMapHash const& key)
}
} // namespace xrpl
#endif // XRPL_BASICS_SHAMAP_HASH_H_INCLUDED

View File

@@ -1,4 +1,5 @@
#pragma once
#ifndef XRPL_BASICS_SHAREDWEAKCACHEPOINTER_H_INCLUDED
#define XRPL_BASICS_SHAREDWEAKCACHEPOINTER_H_INCLUDED
#include <memory>
#include <variant>
@@ -112,3 +113,4 @@ private:
std::variant<std::shared_ptr<T>, std::weak_ptr<T>> combo_;
};
} // namespace xrpl
#endif

View File

@@ -1,4 +1,5 @@
#pragma once
#ifndef XRPL_BASICS_SHAREDWEAKCACHEPOINTER_IPP_INCLUDED
#define XRPL_BASICS_SHAREDWEAKCACHEPOINTER_IPP_INCLUDED
#include <xrpl/basics/SharedWeakCachePointer.h>
@@ -163,3 +164,4 @@ SharedWeakCachePointer<T>::convertToWeak()
return false;
}
} // namespace xrpl
#endif

View File

@@ -1,6 +1,7 @@
// Copyright (c) 2022, Nikolaos D. Bougalis <nikb@bougalis.net>
#pragma once
#ifndef XRPL_BASICS_SLABALLOCATOR_H_INCLUDED
#define XRPL_BASICS_SLABALLOCATOR_H_INCLUDED
#include <xrpl/basics/ByteUtilities.h>
#include <xrpl/beast/type_name.h>
@@ -385,3 +386,5 @@ public:
};
} // namespace xrpl
#endif // XRPL_BASICS_SLABALLOCATOR_H_INCLUDED

View File

@@ -1,4 +1,5 @@
#pragma once
#ifndef XRPL_BASICS_SLICE_H_INCLUDED
#define XRPL_BASICS_SLICE_H_INCLUDED
#include <xrpl/basics/contract.h>
#include <xrpl/basics/strHex.h>
@@ -230,3 +231,5 @@ makeSlice(std::basic_string<char, Traits, Alloc> const& s)
}
} // namespace xrpl
#endif

View File

@@ -1,4 +1,5 @@
#pragma once
#ifndef XRPL_BASICS_STRINGUTILITIES_H_INCLUDED
#define XRPL_BASICS_STRINGUTILITIES_H_INCLUDED
#include <xrpl/basics/Blob.h>
#include <xrpl/basics/strHex.h>
@@ -131,3 +132,5 @@ bool
isProperlyFormedTomlDomain(std::string_view domain);
} // namespace xrpl
#endif

View File

@@ -1,4 +1,5 @@
#pragma once
#ifndef XRPL_BASICS_TAGGEDCACHE_H_INCLUDED
#define XRPL_BASICS_TAGGEDCACHE_H_INCLUDED
#include <xrpl/basics/IntrusivePointer.h>
#include <xrpl/basics/Log.h>
@@ -297,3 +298,5 @@ private:
};
} // namespace xrpl
#endif

View File

@@ -1,4 +1,5 @@
#pragma once
#ifndef XRPL_BASICS_TAGGEDCACHE_IPP_INCLUDED
#define XRPL_BASICS_TAGGEDCACHE_IPP_INCLUDED
#include <xrpl/basics/IntrusivePointer.ipp>
#include <xrpl/basics/TaggedCache.h>
@@ -783,3 +784,5 @@ TaggedCache<Key, T, IsKeyCache, SharedWeakUnionPointer, SharedPointerType, Hash,
}
} // namespace xrpl
#endif

View File

@@ -1,4 +1,5 @@
#pragma once
#ifndef XRPL_BASICS_TOSTRING_H_INCLUDED
#define XRPL_BASICS_TOSTRING_H_INCLUDED
#include <string>
#include <type_traits>
@@ -43,3 +44,5 @@ to_string(char const* s)
}
} // namespace xrpl
#endif

View File

@@ -1,4 +1,5 @@
#pragma once
#ifndef XRPL_BASICS_UNORDEREDCONTAINERS_H_INCLUDED
#define XRPL_BASICS_UNORDEREDCONTAINERS_H_INCLUDED
#include <xrpl/basics/hardened_hash.h>
#include <xrpl/basics/partitioned_unordered_map.h>
@@ -98,3 +99,5 @@ template <
using hardened_hash_multiset = std::unordered_multiset<Value, Hash, Pred, Allocator>;
} // namespace xrpl
#endif

View File

@@ -1,4 +1,5 @@
#pragma once
#ifndef XRPL_BASICS_UPTIMETIMER_H_INCLUDED
#define XRPL_BASICS_UPTIMETIMER_H_INCLUDED
#include <atomic>
#include <chrono>
@@ -45,3 +46,5 @@ private:
};
} // namespace xrpl
#endif

View File

@@ -1,4 +1,5 @@
#pragma once
#ifndef XRPL_ALGORITHM_H_INCLUDED
#define XRPL_ALGORITHM_H_INCLUDED
#include <utility>
@@ -89,3 +90,5 @@ remove_if_intersect_or_match(FwdIter1 first1, FwdIter1 last1, InputIter2 first2,
}
} // namespace xrpl
#endif

View File

@@ -32,7 +32,8 @@
*/
#pragma once
#ifndef XRPL_BASICS_BASE64_H_INCLUDED
#define XRPL_BASICS_BASE64_H_INCLUDED
#include <cstdint>
#include <string>
@@ -52,3 +53,5 @@ std::string
base64_decode(std::string_view data);
} // namespace xrpl
#endif

View File

@@ -3,7 +3,8 @@
// Distributed under the MIT/X11 software license, see the accompanying
// file license.txt or http://www.opensource.org/licenses/mit-license.php.
#pragma once
#ifndef XRPL_BASICS_BASE_UINT_H_INCLUDED
#define XRPL_BASICS_BASE_UINT_H_INCLUDED
#include <xrpl/basics/Expected.h>
#include <xrpl/basics/Slice.h>
@@ -643,3 +644,5 @@ struct is_uniquely_represented<xrpl::base_uint<Bits, Tag>> : public std::true_ty
};
} // namespace beast
#endif

View File

@@ -1,4 +1,5 @@
#pragma once
#ifndef XRPL_BASICS_CHRONO_H_INCLUDED
#define XRPL_BASICS_CHRONO_H_INCLUDED
#include <xrpl/beast/clock/abstract_clock.h>
#include <xrpl/beast/clock/basic_seconds_clock.h>
@@ -98,3 +99,5 @@ stopwatch()
}
} // namespace xrpl
#endif

View File

@@ -1,4 +1,5 @@
#pragma once
#ifndef XRPL_BASICS_COMPARATORS_H_INCLUDED
#define XRPL_BASICS_COMPARATORS_H_INCLUDED
#include <functional>
@@ -52,3 +53,5 @@ using equal_to = std::equal_to<T>;
#endif
} // namespace xrpl
#endif

View File

@@ -1,4 +1,5 @@
#pragma once
#ifndef XRPL_BASICS_CONTRACT_H_INCLUDED
#define XRPL_BASICS_CONTRACT_H_INCLUDED
#include <xrpl/beast/type_name.h>
@@ -47,3 +48,5 @@ Throw(Args&&... args)
LogicError(std::string const& how) noexcept;
} // namespace xrpl
#endif

View File

@@ -1,4 +1,5 @@
#pragma once
#ifndef XRPL_BASICS_HARDENED_HASH_H_INCLUDED
#define XRPL_BASICS_HARDENED_HASH_H_INCLUDED
#include <xrpl/beast/hash/hash_append.h>
#include <xrpl/beast/hash/xxhasher.h>
@@ -92,3 +93,5 @@ public:
};
} // namespace xrpl
#endif

View File

@@ -1,4 +1,5 @@
#pragma once
#ifndef JOIN_H_INCLUDED
#define JOIN_H_INCLUDED
#include <string>
@@ -79,3 +80,5 @@ public:
};
} // namespace xrpl
#endif

View File

@@ -1,4 +1,5 @@
#pragma once
#ifndef XRPL_BASICS_MAKE_SSLCONTEXT_H_INCLUDED
#define XRPL_BASICS_MAKE_SSLCONTEXT_H_INCLUDED
#include <boost/asio/ssl/context.hpp>
@@ -19,3 +20,5 @@ make_SSLContextAuthed(
std::string const& cipherList);
} // namespace xrpl
#endif

View File

@@ -1,4 +1,5 @@
#pragma once
#ifndef XRPL_BASICS_MULDIV_H_INCLUDED
#define XRPL_BASICS_MULDIV_H_INCLUDED
#include <cstdint>
#include <limits>
@@ -21,3 +22,5 @@ std::optional<std::uint64_t>
mulDiv(std::uint64_t value, std::uint64_t mul, std::uint64_t div);
} // namespace xrpl
#endif

View File

@@ -1,4 +1,5 @@
#pragma once
#ifndef XRPL_BASICS_PARTITIONED_UNORDERED_MAP_H
#define XRPL_BASICS_PARTITIONED_UNORDERED_MAP_H
#include <xrpl/beast/hash/uhash.h>
#include <xrpl/beast/utility/instrumentation.h>
@@ -392,3 +393,5 @@ private:
};
} // namespace xrpl
#endif // XRPL_BASICS_PARTITIONED_UNORDERED_MAP_H

View File

@@ -1,4 +1,5 @@
#pragma once
#ifndef XRPL_BASICS_RANDOM_H_INCLUDED
#define XRPL_BASICS_RANDOM_H_INCLUDED
#include <xrpl/beast/utility/instrumentation.h>
#include <xrpl/beast/xor_shift_engine.h>
@@ -173,3 +174,5 @@ rand_bool()
/** @} */
} // namespace xrpl
#endif // XRPL_BASICS_RANDOM_H_INCLUDED

View File

@@ -1,4 +1,5 @@
#pragma once
#ifndef XRPL_UNITY_ROCKSDB_H_INCLUDED
#define XRPL_UNITY_ROCKSDB_H_INCLUDED
#if XRPL_ROCKSDB_AVAILABLE
// #include <rocksdb2/port/port_posix.h>
@@ -27,3 +28,5 @@
#include <rocksdb/write_batch.h>
#endif
#endif

View File

@@ -1,4 +1,5 @@
#pragma once
#ifndef XRPL_BASICS_SAFE_CAST_H_INCLUDED
#define XRPL_BASICS_SAFE_CAST_H_INCLUDED
#include <type_traits>
@@ -68,3 +69,5 @@ unsafe_cast(Src s) noexcept
}
} // namespace xrpl
#endif

View File

@@ -1,4 +1,5 @@
#pragma once
#ifndef XRPL_BASICS_SCOPE_H_INCLUDED
#define XRPL_BASICS_SCOPE_H_INCLUDED
#include <xrpl/beast/utility/instrumentation.h>
@@ -219,3 +220,5 @@ template <class Mutex>
scope_unlock(std::unique_lock<Mutex>&) -> scope_unlock<Mutex>;
} // namespace xrpl
#endif

View File

@@ -1,6 +1,7 @@
// Copyright (c) 2022, Nikolaos D. Bougalis <nikb@bougalis.net>
#pragma once
#ifndef XRPL_BASICS_SPINLOCK_H_INCLUDED
#define XRPL_BASICS_SPINLOCK_H_INCLUDED
#include <xrpl/beast/utility/instrumentation.h>
@@ -200,3 +201,5 @@ public:
/** @} */
} // namespace xrpl
#endif

View File

@@ -1,4 +1,5 @@
#pragma once
#ifndef XRPL_BASICS_STRHEX_H_INCLUDED
#define XRPL_BASICS_STRHEX_H_INCLUDED
#include <boost/algorithm/hex.hpp>
#include <boost/endian/conversion.hpp>
@@ -26,3 +27,5 @@ strHex(T const& from)
}
} // namespace xrpl
#endif

View File

@@ -1,6 +1,7 @@
// Copyright (c) 2014, Nikolaos D. Bougalis <nikb@bougalis.net>
#pragma once
#ifndef BEAST_UTILITY_TAGGED_INTEGER_H_INCLUDED
#define BEAST_UTILITY_TAGGED_INTEGER_H_INCLUDED
#include <xrpl/beast/hash/hash_append.h>
@@ -201,3 +202,4 @@ struct is_contiguously_hashable<xrpl::tagged_integer<Int, Tag>, HashAlgorithm>
};
} // namespace beast
#endif

View File

@@ -1,4 +1,5 @@
#pragma once
#ifndef BEAST_ASIO_IO_LATENCY_PROBE_H_INCLUDED
#define BEAST_ASIO_IO_LATENCY_PROBE_H_INCLUDED
#include <xrpl/beast/utility/instrumentation.h>
@@ -225,3 +226,5 @@ private:
};
} // namespace beast
#endif

View File

@@ -1,4 +1,5 @@
#pragma once
#ifndef BEAST_CHRONO_ABSTRACT_CLOCK_H_INCLUDED
#define BEAST_CHRONO_ABSTRACT_CLOCK_H_INCLUDED
namespace beast {
@@ -88,3 +89,5 @@ get_abstract_clock()
}
} // namespace beast
#endif

View File

@@ -1,4 +1,5 @@
#pragma once
#ifndef BEAST_CHRONO_BASIC_SECONDS_CLOCK_H_INCLUDED
#define BEAST_CHRONO_BASIC_SECONDS_CLOCK_H_INCLUDED
#include <chrono>
@@ -32,3 +33,5 @@ public:
};
} // namespace beast
#endif

View File

@@ -1,4 +1,5 @@
#pragma once
#ifndef BEAST_CHRONO_MANUAL_CLOCK_H_INCLUDED
#define BEAST_CHRONO_MANUAL_CLOCK_H_INCLUDED
#include <xrpl/beast/clock/abstract_clock.h>
#include <xrpl/beast/utility/instrumentation.h>
@@ -74,3 +75,5 @@ public:
};
} // namespace beast
#endif

View File

@@ -1,4 +1,5 @@
#pragma once
#ifndef BEAST_CONTAINER_AGED_CONTAINER_H_INCLUDED
#define BEAST_CONTAINER_AGED_CONTAINER_H_INCLUDED
#include <type_traits>
@@ -11,3 +12,5 @@ struct is_aged_container : std::false_type
};
} // namespace beast
#endif

View File

@@ -1,4 +1,5 @@
#pragma once
#ifndef BEAST_CONTAINER_AGED_CONTAINER_UTILITY_H_INCLUDED
#define BEAST_CONTAINER_AGED_CONTAINER_UTILITY_H_INCLUDED
#include <xrpl/beast/container/aged_container.h>
@@ -23,3 +24,5 @@ expire(AgedContainer& c, std::chrono::duration<Rep, Period> const& age)
}
} // namespace beast
#endif

View File

@@ -1,4 +1,5 @@
#pragma once
#ifndef BEAST_CONTAINER_AGED_MAP_H_INCLUDED
#define BEAST_CONTAINER_AGED_MAP_H_INCLUDED
#include <xrpl/beast/container/detail/aged_ordered_container.h>
@@ -17,3 +18,5 @@ template <
using aged_map = detail::aged_ordered_container<false, true, Key, T, Clock, Compare, Allocator>;
}
#endif

View File

@@ -1,4 +1,5 @@
#pragma once
#ifndef BEAST_CONTAINER_AGED_MULTIMAP_H_INCLUDED
#define BEAST_CONTAINER_AGED_MULTIMAP_H_INCLUDED
#include <xrpl/beast/container/detail/aged_ordered_container.h>
@@ -17,3 +18,5 @@ template <
using aged_multimap = detail::aged_ordered_container<true, true, Key, T, Clock, Compare, Allocator>;
}
#endif

View File

@@ -1,4 +1,5 @@
#pragma once
#ifndef BEAST_CONTAINER_AGED_MULTISET_H_INCLUDED
#define BEAST_CONTAINER_AGED_MULTISET_H_INCLUDED
#include <xrpl/beast/container/detail/aged_ordered_container.h>
@@ -16,3 +17,5 @@ template <
using aged_multiset = detail::aged_ordered_container<true, false, Key, void, Clock, Compare, Allocator>;
}
#endif

View File

@@ -1,4 +1,5 @@
#pragma once
#ifndef BEAST_CONTAINER_AGED_SET_H_INCLUDED
#define BEAST_CONTAINER_AGED_SET_H_INCLUDED
#include <xrpl/beast/container/detail/aged_ordered_container.h>
@@ -16,3 +17,5 @@ template <
using aged_set = detail::aged_ordered_container<false, false, Key, void, Clock, Compare, Allocator>;
}
#endif

View File

@@ -1,4 +1,5 @@
#pragma once
#ifndef BEAST_CONTAINER_AGED_UNORDERED_MAP_H_INCLUDED
#define BEAST_CONTAINER_AGED_UNORDERED_MAP_H_INCLUDED
#include <xrpl/beast/container/detail/aged_unordered_container.h>
@@ -18,3 +19,5 @@ template <
using aged_unordered_map = detail::aged_unordered_container<false, true, Key, T, Clock, Hash, KeyEqual, Allocator>;
}
#endif

View File

@@ -1,4 +1,5 @@
#pragma once
#ifndef BEAST_CONTAINER_AGED_UNORDERED_MULTIMAP_H_INCLUDED
#define BEAST_CONTAINER_AGED_UNORDERED_MULTIMAP_H_INCLUDED
#include <xrpl/beast/container/detail/aged_unordered_container.h>
@@ -18,3 +19,5 @@ template <
using aged_unordered_multimap = detail::aged_unordered_container<true, true, Key, T, Clock, Hash, KeyEqual, Allocator>;
}
#endif

View File

@@ -1,4 +1,5 @@
#pragma once
#ifndef BEAST_CONTAINER_AGED_UNORDERED_MULTISET_H_INCLUDED
#define BEAST_CONTAINER_AGED_UNORDERED_MULTISET_H_INCLUDED
#include <xrpl/beast/container/detail/aged_unordered_container.h>
@@ -18,3 +19,5 @@ using aged_unordered_multiset =
detail::aged_unordered_container<true, false, Key, void, Clock, Hash, KeyEqual, Allocator>;
}
#endif

View File

@@ -1,4 +1,5 @@
#pragma once
#ifndef BEAST_CONTAINER_AGED_UNORDERED_SET_H_INCLUDED
#define BEAST_CONTAINER_AGED_UNORDERED_SET_H_INCLUDED
#include <xrpl/beast/container/detail/aged_unordered_container.h>
@@ -17,3 +18,5 @@ template <
using aged_unordered_set = detail::aged_unordered_container<false, false, Key, void, Clock, Hash, KeyEqual, Allocator>;
}
#endif

Some files were not shown because too many files have changed in this diff Show More