Compare commits

..

14 Commits

Author SHA1 Message Date
Denis Angell
1ac1d40d06 fix: satisfy clang-tidy include-cleaner and brace style in paychan 2026-08-03 12:26:20 -04:00
Denis Angell
fb10515cff Merge remote-tracking branch 'origin/develop' into token-paychan
# Conflicts:
#	include/xrpl/protocol/detail/features.macro
2026-08-03 11:38:43 -04:00
Denis Angell
3c85a0180f refactor: address review nits 2026-08-02 16:05:25 -04:00
Denis Angell
096fa967da fix: repair bad develop merge resolutions 2026-08-02 16:05:22 -04:00
dangell8
1ced7dc8f3 Merge branch 'develop' into token-paychan
Includes post-merge compile fixes (build-verified).
2026-07-17 15:02:03 +00:00
Denis Angell
df1458a136 test: expand token paychan transactor phase coverage 2026-07-13 19:25:43 -04:00
Denis Angell
cdd5ebf4c1 fix: validate paychan asset match in preclaim with tecWRONG_ASSET 2026-07-13 16:33:49 -04:00
Denis Angell
1a9a11fc31 style: remove includes flagged by misc-include-cleaner 2026-07-13 15:28:42 -04:00
Denis Angell
a9430d4778 style: conform doxygen comments to check-doxygen-style hook 2026-07-13 15:11:48 -04:00
Denis Angell
fed5093488 fix: adapt token paychan to develop merge helpers and sponsor reserve 2026-07-13 14:59:54 -04:00
Denis Angell
6c74fc1a7d Merge branch 'develop' into token-paychan 2026-07-13 14:05:56 -04:00
dangell8
939f8b1a49 Merge develop into token-paychan 2026-07-11 04:27:08 +00:00
Denis Angell
1f8c462c42 feat: XLS-93d Token-Enabled Payment Channels 2026-07-10 12:14:12 -04:00
Denis Angell
47df026dcc refactor: Move escrow lock/unlock helpers to EscrowHelpers.h 2026-07-10 11:55:13 -04:00
719 changed files with 32156 additions and 45067 deletions

View File

@@ -85,8 +85,6 @@ CheckOptions:
readability-braces-around-statements.ShortStatementLines: 2
readability-identifier-naming.MacroDefinitionCase: UPPER_CASE
readability-identifier-naming.NamespaceCase: lower_case
readability-identifier-naming.InlineNamespaceCase: lower_case
readability-identifier-naming.ClassCase: CamelCase
readability-identifier-naming.StructCase: CamelCase
readability-identifier-naming.UnionCase: CamelCase

View File

@@ -1,32 +1,10 @@
codecov:
require_ci_to_pass: true
# The C++ and Rust uploads land minutes apart; without this gate Codecov
# publishes a near-zero total from whichever one arrives first.
notify:
after_n_builds: 2
wait_for_ci: true
comment:
behavior: default
layout: reach,diff,flags,tree,reach
show_carryforward_flags: true
after_n_builds: 2
# C++ and Rust coverage upload from independent workflows under the `cpp` and
# `rust` flags; carryforward keeps one language's total when only the other reran.
flag_management:
default_rules:
carryforward: true
individual_flags:
- name: cpp
carryforward: true
paths:
- include/
- src/
- name: rust
carryforward: true
paths:
- crates/
show_carryforward_flags: false
coverage:
range: "70..85"

View File

@@ -7,7 +7,6 @@ ignorePaths:
- cmake/**
- LICENSE.md
- .clang-tidy
- nix/check-tools/*.txt # generated, and full of Nix store hashes
language: en
allowCompoundWords: true # TODO (#6334)
ignoreRandomStrings: true
@@ -68,9 +67,7 @@ words:
- Btrfs
- Buildx
- canonicality
- CGNAT
- canonicalised
- cctools
- changespq
- checkme
- choco
@@ -112,7 +109,6 @@ words:
- disablerepo
- distro
- doxyfile
- dsymutil
- dxrpl
- elgamal
- enabled
@@ -129,8 +125,6 @@ words:
- fsanitize
- funclets
- Gamal
- gantt
- Gantt
- gcov
- gcovr
- ghead
@@ -138,7 +132,6 @@ words:
- godexsoft
- gpgcheck
- gpgkey
- Hinnant
- hotwallet
- hwaddress
- hwrap
@@ -172,18 +165,17 @@ words:
- llection
- LOCALGOOD
- logwstream
- Lombrozo
- lresolv
- lseq
- lsmf
- ltype
- mathbunnyru
- mcmodel
- MEMORYSTATUSEX
- MPTAMM
- MPTDEX
- Merkle
- misprediction
- missingok
- MPTAMM
- mptbalance
- MPTDEX
- mptflags
@@ -209,7 +201,6 @@ words:
- nftokens
- nftpage
- nikb
- Nikolaos
- nixfmt
- nixos
- nixpkgs
@@ -218,7 +209,6 @@ words:
- nonxrp
- noreplace
- noripple
- nostd
- nostdinc
- notifempty
- nudb
@@ -227,8 +217,6 @@ words:
- Nyffenegger
- onlatest
- ostr
- otelc
- otool
- oxalica
- pargs
- partitioner
@@ -258,15 +246,11 @@ words:
- Raphson
- rcflags
- replayer
- repodata
- repomd
- rerandomize
- rerandomization
- rerandomized
- rerandomizes
- rerere
- retargeted
- retargets
- retriable
- RIPD
- ripdtop
@@ -302,7 +286,6 @@ words:
- sles
- soci
- socidb
- Sonatype
- sponsee
- sponsees
- SRPMS
@@ -322,14 +305,12 @@ words:
- summands
- superpeer
- superpeers
- Swatinem
- takergets
- takerpays
- ters
- TMEndpointv2
- toolchain
- tparam
- traceql
- trixie
- tx
- txid
@@ -337,7 +318,6 @@ words:
- txjson
- txn
- txns
- txqueue
- txs
- ubsan
- UBSAN
@@ -380,16 +360,12 @@ words:
- wthread
- xbridge
- xchain
- xcrun
- ximinez
- XMACRO
- xored
- xrpkuwait
- xrpl
- xrpld
- xrplf
- xxhash
- xxhasher
- xychart
- zpages
- zstdio
- CGNAT

6
.envrc
View File

@@ -1,7 +1 @@
watch_file nix/*.nix
# The dev shell derivation includes all of conan/ (see nix/devshell.nix), so any
# change in there has to invalidate direnv's cached environment.
watch_dir conan
use flake

View File

@@ -0,0 +1,44 @@
name: Generate build version number
description: "Generate build version number."
outputs:
version:
description: "The generated build version number."
value: ${{ steps.version.outputs.version }}
runs:
using: composite
steps:
# When a tag is pushed, the version is used as-is.
- name: Generate version for tag event
if: ${{ startsWith(github.ref, 'refs/tags/') }}
shell: bash
env:
VERSION: ${{ github.ref_name }}
run: echo "VERSION=${VERSION}" >>"${GITHUB_ENV}"
# When a tag is not pushed, then the version (e.g. 1.2.3-b0) is extracted
# from the BuildInfo.cpp file and the shortened commit hash appended to it.
# We use a plus sign instead of a hyphen because Conan recipe versions do
# not support two hyphens.
- name: Generate version for non-tag event
if: ${{ !startsWith(github.ref, 'refs/tags/') }}
shell: bash
run: |
echo 'Extracting version from BuildInfo.cpp.'
VERSION="$(cat src/libxrpl/protocol/BuildInfo.cpp | grep "versionString =" | awk -F '"' '{print $2}')"
if [[ -z "${VERSION}" ]]; then
echo 'Unable to extract version from BuildInfo.cpp.'
exit 1
fi
echo 'Appending shortened commit hash to version.'
SHA='${{ github.sha }}'
VERSION="${VERSION}+${SHA:0:7}"
echo "VERSION=${VERSION}" >>"${GITHUB_ENV}"
- name: Output version
id: version
shell: bash
run: echo "version=${VERSION}" >>"${GITHUB_OUTPUT}"

View File

@@ -1,90 +0,0 @@
name: Release info
description: "Derive the version, release channel and package release number for this build."
outputs:
version:
description: "The build version number."
value: ${{ steps.version.outputs.version }}
channel:
description: "The release channel this build belongs to."
value: ${{ steps.channel.outputs.channel }}
pkg_release:
description: "The package release number: 1 for a tag, the run number otherwise."
value: ${{ steps.pkg_release.outputs.pkg_release }}
runs:
using: composite
steps:
# A tag names its own version. Anything else takes it from BuildInfo.cpp and
# appends the commit hash as build metadata, joined with a plus sign because a
# Conan version cannot contain two hyphens.
- name: Determine version
id: version
shell: bash
env:
IS_TAG: ${{ startsWith(github.ref, 'refs/tags/') }}
REF_NAME: ${{ github.ref_name }}
SHA: ${{ github.sha }}
run: |
if [[ "${IS_TAG}" == "true" ]]; then
version="${REF_NAME}"
else
version="$(awk -F'"' '/versionString =/ { print $2 }' src/libxrpl/protocol/BuildInfo.cpp)"
if [[ -z "${version}" ]]; then
echo "Unable to read versionString from BuildInfo.cpp." >&2
exit 1
fi
version="${version}+${SHA:0:7}"
fi
echo "version=${version}" | tee -a "${GITHUB_OUTPUT}"
# Only a tag says how mature a build is: a push is a develop build whatever
# its version, and a non-public codebase keeps its packages to itself.
- name: Determine release channel
id: channel
shell: bash
env:
IS_TAG: ${{ startsWith(github.ref, 'refs/tags/') }}
REF_NAME: ${{ github.ref_name }}
VISIBILITY: ${{ github.event.repository.visibility }}
run: |
pre_release=""
if [[ "${REF_NAME}" == *-* ]]; then
pre_release="${REF_NAME#*-}"
fi
if [[ "${VISIBILITY}" != "public" ]]; then
channel=private
elif [[ "${IS_TAG}" != "true" ]]; then
channel=develop
elif [[ -z "${pre_release}" ]]; then
channel=stable
elif [[ "${pre_release}" =~ ^rc[0-9]+(\+.*)?$ ]]; then
channel=unstable
elif [[ "${pre_release}" =~ ^b(0|[1-9][0-9]*)(\+.*)?$ ]]; then
channel=experimental
else
echo "Unsupported pre-release in tag '${REF_NAME}'. Use bN or rcN." >&2
exit 1
fi
echo "channel=${channel}" | tee -a "${GITHUB_OUTPUT}"
# A tag is packaged once, so its release number is fixed at 1. Develop builds
# repeat the same version, so the run number is what makes each push an
# upgrade rather than a reinstall.
- name: Determine package release
id: pkg_release
shell: bash
env:
IS_TAG: ${{ startsWith(github.ref, 'refs/tags/') }}
RUN_NUMBER: ${{ github.run_number }}
run: |
if [[ "${IS_TAG}" == "true" ]]; then
pkg_release=1
else
pkg_release="${RUN_NUMBER}"
fi
echo "pkg_release=${pkg_release}" | tee -a "${GITHUB_OUTPUT}"

View File

@@ -1,69 +0,0 @@
name: Setup Nix environment
description: "Build the flake's CI environment and put its tools on PATH."
# The environment from nix/ci-env.nix, the same one the Linux CI images bake in
# (see nix/docker). Exported onto PATH rather than entered with `nix develop`:
# the composite actions below run plain `bash` and would escape a dev shell.
runs:
using: composite
steps:
- name: Build the CI environment
id: build
shell: bash
env:
# --out-link doubles as a GC root for the length of the job.
OUT_LINK: ${{ runner.temp }}/xrpld-ci-env
run: |
# --extra-experimental-features: flakes may not be on in the runner's nix.conf.
nix --extra-experimental-features "nix-command flakes" \
build .#default --out-link "${OUT_LINK}" --print-build-logs
echo "path=$(readlink -f "${OUT_LINK}")" >>"${GITHUB_OUTPUT}"
- name: Export the environment
shell: bash
env:
ENV_PATH: ${{ steps.build.outputs.path }}
run: |
echo "${ENV_PATH}/bin" >>"${GITHUB_PATH}"
# Already KEY=VALUE per line. See `darwinEnv` in nix/ci-env.nix.
ENV_FILE="${ENV_PATH}/share/xrpld-ci-env/env"
if [ -f "${ENV_FILE}" ]; then
cat "${ENV_FILE}" >>"${GITHUB_ENV}"
fi
# XrplSanity.cmake otherwise rejects a Nix compiler as one that leaked.
echo "XRPL_DEVSHELL=ci-env" >>"${GITHUB_ENV}"
# Unlike the Linux nix images, macOS needs no SSL_CERT_FILE: it has its
# own trust store, and pinning would break TLS to hosts relying on it.
# Workspace-local, so `cleanup-workspace` clears it, but not the
# `.conan2` prepare-runner hands the system toolchain: that Conan is a
# different version, and the two would migrate each other's cache.
echo "CONAN_HOME=${{ github.workspace }}/.conan2-nix" >>"${GITHUB_ENV}"
# Config, profiles and remote, exactly as the dev shell sets them up on
# entry; the `setup-conan` action is skipped for this toolchain.
- name: Setup Conan
shell: bash
run: ./conan/init.sh
# `Check tools` runs later but swallows failures; a bad export would just
# build with the system toolchain.
- name: Verify the toolchain resolves into the Nix store
shell: bash
run: |
for tool in clang clang++ cmake ninja conan; do
path="$(command -v "${tool}" || true)"
echo "${tool} -> ${path:-<not found>}"
case "${path}" in
/nix/store/*) ;;
*)
echo "::error::${tool} does not resolve into the Nix store"
exit 1
;;
esac
done

View File

@@ -4,7 +4,7 @@ updates:
directories:
- /
- .github/actions/build-deps/
- .github/actions/release-info/
- .github/actions/generate-version/
- .github/actions/set-compiler-env/
- .github/actions/setup-conan/
schedule:
@@ -19,19 +19,3 @@ updates:
github-actions:
patterns:
- "*"
- package-ecosystem: cargo
directory: /crates
schedule:
interval: weekly
day: monday
time: "04:00"
timezone: Etc/GMT
commit-message:
prefix: "chore: [DEPENDABOT] "
target-branch: develop
open-pull-requests-limit: 10
groups:
rust-dependencies:
patterns:
- "*"

View File

@@ -49,7 +49,7 @@ ${SED_COMMAND} -i -E 's@ripple/xrpld@XRPLF/rippled@g' BUILD.md
${SED_COMMAND} -i -E 's@XRPLF/xrpld@XRPLF/rippled@g' BUILD.md
${SED_COMMAND} -i -E 's@xrpld \(`xrpld`\)@xrpld@g' BUILD.md
${SED_COMMAND} -i -E 's@XRPLF/xrpld@XRPLF/rippled@g' CONTRIBUTING.md
${SED_COMMAND} -i -E 's@XRPLF/xrpld@XRPLF/rippled@g' docs/install.md
${SED_COMMAND} -i -E 's@XRPLF/xrpld@XRPLF/rippled@g' docs/build/install.md
popd
echo "Processing complete."

View File

@@ -77,8 +77,8 @@ ${SED_COMMAND} -i 's/Ripple integrators/XRPL developers/' README.md
${SED_COMMAND} -i 's/sanitizer-configuration-for-rippled/sanitizer-configuration-for-xrpld/' docs/build/sanitizers.md
${SED_COMMAND} -i 's/rippled/xrpld/g' .github/scripts/levelization/README.md
${SED_COMMAND} -i 's/rippled/xrpld/g' .github/scripts/strategy-matrix/generate.py
${SED_COMMAND} -i 's@/rippled@/xrpld@g' docs/install.md
${SED_COMMAND} -i 's@github.com/XRPLF/xrpld@github.com/XRPLF/rippled@g' docs/install.md
${SED_COMMAND} -i 's@/rippled@/xrpld@g' docs/build/install.md
${SED_COMMAND} -i 's@github.com/XRPLF/xrpld@github.com/XRPLF/rippled@g' docs/build/install.md
${SED_COMMAND} -i 's/rippled/xrpld/g' docs/Doxyfile
${SED_COMMAND} -i 's/ripple_basics/basics/' include/xrpl/basics/CountedObject.h
${SED_COMMAND} -i 's/<ripple/<xrpl/' include/xrpl/protocol/AccountID.h

View File

@@ -7,13 +7,7 @@ from pathlib import Path
THIS_DIR = Path(__file__).parent.resolve()
_BASE_CMAKE_ARGS = [
"-Dtests=ON",
"-Dwerr=ON",
"-Dxrpld=ON",
"-Dwextra=ON",
"-Drust=ON",
]
_BASE_CMAKE_ARGS = ["-Dtests=ON", "-Dwerr=ON", "-Dxrpld=ON", "-Dwextra=ON"]
# Maps sanitizer names (as used in cmake) to short config-name suffixes.
_SANITIZER_SUFFIX: dict[str, str] = {
@@ -39,10 +33,6 @@ def get_cmake_args(build_type: str, extra_args: str) -> str:
# Every config must declare 'minimal'. Minimal configs form the reduced matrix
# built for pull requests by default; the full matrix adds the rest. Packaging
# configs declare it too, but packaging is gated in the workflow, not by it.
#
# Configs may also opt into 'benchmark' to smoke-run the benchmarks. Note that
# the flag applies to every entry a config expands into, so only set it on
# configs that expand to a single combination.
@dataclasses.dataclass
@@ -53,7 +43,6 @@ class LinuxConfig:
build_type: list[str]
arch: list[str]
minimal: bool
benchmark: bool = False # if true, smoke-run the benchmarks after testing
sanitizers: list[str] = dataclasses.field(default_factory=list)
suffix: str = ""
extra_cmake_args: str = ""
@@ -92,11 +81,7 @@ class PlatformConfig:
build_type: list[str]
minimal: bool
build_only: bool = False # if true, skip tests (e.g. macos/Windows Debug)
benchmark: bool = False # if true, smoke-run the benchmarks after testing
extra_cmake_args: str = ""
# "" is the runner's system compiler, "nix" the flake's CI environment.
# macOS only: Linux always builds in a Nix image, Windows has no Nix.
toolchain: str = ""
def __post_init__(self) -> None:
if isinstance(self.build_type, str):
@@ -140,21 +125,18 @@ class MatrixEntry:
cmake_args: str
cmake_target: str
build_only: bool
benchmark: bool
build_type: str
architecture: Architecture
sanitizers: str
image: str = "" # container image; empty for macOS/Windows (runs natively)
compiler: str = "" # compiler name ("gcc" or "clang"); empty for macOS/Windows
toolchain: str = "" # "nix" for the flake's CI environment; see PlatformConfig
@dataclasses.dataclass
class PackagingEntry:
"""One entry in the generated packaging strategy matrix."""
xrpld_artifact_name: str
validator_keys_artifact_name: str
artifact_name: str
image: str
distro: str # e.g. "debian" or "rhel"; drives package-format-specific steps
@@ -211,7 +193,6 @@ def expand_linux_matrix(linux: LinuxFile, minimal: bool) -> list[MatrixEntry]:
cmake_args=get_cmake_args(build_type, cfg.extra_cmake_args),
cmake_target="all",
build_only=False,
benchmark=cfg.benchmark,
build_type=build_type,
architecture=arch_info,
sanitizers=sanitizer,
@@ -225,23 +206,18 @@ def expand_linux_matrix(linux: LinuxFile, minimal: bool) -> list[MatrixEntry]:
def expand_linux_packaging(linux: LinuxFile) -> list[PackagingEntry]:
"""Generate the packaging matrix from a LinuxFile's package_configs section.
Packaging uses vanilla distro images (debian:bookworm, almalinux:9) instead of
Packaging uses vanilla distro images (debian:bookworm, ubi9, …) instead of
the nix-based build images, because deb/rpm tooling (debhelper, rpm-build)
is taken from the distro's archive rather than from nixpkgs. Each config
entry carries its own 'image'.
The artifact names must match what the build job uploads: one artifact per
binary, each named after the build config.
"""
entries = []
for distro, configs in linux.package_configs.items():
for cfg in configs:
for compiler, build_type in itertools.product(cfg.compiler, cfg.build_type):
config_name = f"{distro}-{compiler}-{build_type.lower()}-amd64"
entries.append(
PackagingEntry(
xrpld_artifact_name=f"xrpld-{config_name}",
validator_keys_artifact_name=f"validator-keys-{config_name}",
artifact_name=f"xrpld-{distro}-{compiler}-{build_type.lower()}-amd64",
image=cfg.image,
distro=distro,
)
@@ -263,20 +239,15 @@ def expand_platform_matrix(pf: PlatformFile, minimal: bool) -> list[MatrixEntry]
if minimal and not cfg.minimal:
continue
for build_type in cfg.build_type:
name = f"{platform_name}-{arch}-{build_type.lower()}"
if cfg.toolchain:
name += f"-{cfg.toolchain}"
entries.append(
MatrixEntry(
config_name=name,
config_name=f"{platform_name}-{arch}-{build_type.lower()}",
cmake_args=get_cmake_args(build_type, cfg.extra_cmake_args),
cmake_target="install" if is_windows else "all",
build_only=cfg.build_only,
benchmark=cfg.benchmark,
build_type=build_type,
architecture=Architecture(platform=pf.platform, runner=pf.runner),
sanitizers="",
toolchain=cfg.toolchain,
)
)
return entries

View File

@@ -1,5 +1,5 @@
{
"image_tag": "sha-a0074f8",
"image_tag": "sha-fecfc0c",
"configs": {
"ubuntu": [
{
@@ -14,8 +14,7 @@
"compiler": ["clang"],
"build_type": ["Release"],
"arch": ["amd64"],
"minimal": true,
"benchmark": true
"minimal": true
},
{
@@ -70,8 +69,7 @@
"compiler": ["gcc"],
"build_type": ["Release"],
"arch": ["amd64"],
"minimal": false,
"extra_cmake_args": "-Dvalidator_keys=ON"
"minimal": false
}
],
@@ -80,8 +78,7 @@
"compiler": ["gcc"],
"build_type": ["Release"],
"arch": ["amd64"],
"minimal": false,
"extra_cmake_args": "-Dvalidator_keys=ON"
"minimal": false
}
]
},
@@ -92,7 +89,7 @@
"build_type": ["Release"],
"arch": ["amd64"],
"minimal": false,
"image": "ghcr.io/xrplf/xrpld/packaging-debian:sha-a6983f8"
"image": "ghcr.io/xrplf/xrpld/packaging-debian:sha-577d745"
}
],
@@ -102,7 +99,7 @@
"build_type": ["Release"],
"arch": ["amd64"],
"minimal": false,
"image": "ghcr.io/xrplf/xrpld/packaging-rhel:sha-a6983f8"
"image": "ghcr.io/xrplf/xrpld/packaging-rhel:sha-577d745"
}
]
}

View File

@@ -12,19 +12,6 @@
"extra_cmake_args": "-DCMAKE_POLICY_VERSION_MINIMUM=3.5",
"build_only": true,
"minimal": false
},
{
"build_type": "Release",
"extra_cmake_args": "-DCMAKE_POLICY_VERSION_MINIMUM=3.5",
"toolchain": "nix",
"minimal": false
},
{
"build_type": "Debug",
"extra_cmake_args": "-DCMAKE_POLICY_VERSION_MINIMUM=3.5",
"toolchain": "nix",
"build_only": true,
"minimal": false
}
]
}

View File

@@ -36,9 +36,8 @@ jobs:
distro:
- name: debian
base_image: debian:bookworm
# AlmaLinux rather than UBI9, which does not ship rpm-sign.
- name: rhel
base_image: almalinux:9
base_image: registry.access.redhat.com/ubi9/ubi:latest
uses: XRPLF/actions/.github/workflows/build-multiarch-image.yml@9e7e4e80af9e684c116b38369add8eea64451f32
with:
image_name: xrpld/packaging-${{ matrix.distro.name }}

View File

@@ -1,80 +0,0 @@
name: Cargo audit
on:
schedule:
# 06:32 UTC every Monday.
- cron: "32 6 * * 1"
push:
branches:
- "develop"
- "release/*"
paths:
- "crates/**/Cargo.toml"
- "crates/Cargo.lock"
- ".github/workflows/cargo-audit.yml"
pull_request:
paths:
- "crates/**/Cargo.toml"
- "crates/Cargo.lock"
- ".github/workflows/cargo-audit.yml"
workflow_dispatch:
concurrency:
group: ${{ github.workflow }}-${{ github.ref }}
cancel-in-progress: true
defaults:
run:
shell: bash
working-directory: crates
permissions:
contents: read
jobs:
audit:
runs-on: ubuntu-latest
container: ghcr.io/xrplf/xrpld/nix-ubuntu:sha-a0074f8
permissions:
contents: read
# Needed to open an issue on scheduled failures.
issues: write
steps:
- name: Checkout repository
uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- name: Run cargo audit
id: audit
continue-on-error: true
run: |
set -o pipefail
cargo audit | tee /tmp/cargo-audit.txt
- name: Prepare issue body
if: ${{ steps.audit.outcome != 'success' && github.event_name == 'schedule' }}
run: |
{
echo "## \`cargo audit\` found advisories"
echo
echo '```'
cat /tmp/cargo-audit.txt
echo '```'
echo
echo "---"
echo "*This issue was automatically created by the cargo-audit workflow.*"
} >/tmp/cargo-audit-issue.md
- name: Create issue
if: ${{ steps.audit.outcome != 'success' && github.event_name == 'schedule' }}
uses: XRPLF/actions/create-issue@2b8bc36af85b88bca0dd7bfac2e2dc05f94ad712
with:
title: "cargo audit found vulnerabilities"
body_file: /tmp/cargo-audit-issue.md
labels: "Bug,Security"
- name: Fail if advisories were found
if: ${{ steps.audit.outcome != 'success' }}
run: |
echo "cargo audit found advisories!"
cat /tmp/cargo-audit.txt
exit 1

View File

@@ -79,7 +79,7 @@ jobs:
uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- name: Prepare runner
uses: XRPLF/actions/prepare-runner@51af40f99ea91a08c3528ddf16d98132dcc7e63c
uses: XRPLF/actions/prepare-runner@c00c22ada3bd6bcda48fcb0d62fbbab49fec8a0f
with:
enable_ccache: false

View File

@@ -77,28 +77,23 @@ jobs:
# Keep the paths below in sync with those in `on-trigger.yml`.
.github/actions/build-deps/**
.github/actions/release-info/**
.github/actions/generate-version/**
.github/actions/setup-conan/**
.github/actions/setup-nix-env/**
.github/scripts/strategy-matrix/**
.github/workflows/reusable-build-test-config.yml
.github/workflows/reusable-build-test.yml
.github/workflows/reusable-check-autogen.yml
.github/workflows/reusable-clang-tidy.yml
.github/workflows/reusable-package.yml
.github/workflows/reusable-rust.yml
.github/workflows/reusable-strategy-matrix.yml
.github/workflows/reusable-test.yml
.github/workflows/reusable-upload-recipe.yml
.clang-tidy
.codecov.yml
bin/check-nix-store-refs.sh
bin/check-tools.sh
bin/default-loader-path.sh
cfg/**
cmake/**
conan/**
crates/**
external/**
include/**
src/**
@@ -106,9 +101,6 @@ jobs:
CMakeLists.txt
conanfile.py
conan.lock
flake.lock
flake.nix
nix/**
LICENSE.md
package/**
README.md
@@ -134,11 +126,6 @@ jobs:
outputs:
go: ${{ steps.go.outputs.go == 'true' }}
check-autogen:
needs: should-run
if: ${{ needs.should-run.outputs.go == 'true' }}
uses: ./.github/workflows/reusable-check-autogen.yml
check-levelization:
needs: should-run
if: ${{ needs.should-run.outputs.go == 'true' }}
@@ -175,13 +162,6 @@ jobs:
secrets:
CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
rust:
needs: should-run
if: ${{ needs.should-run.outputs.go == 'true' }}
uses: ./.github/workflows/reusable-rust.yml
secrets:
CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
package:
needs: [should-run, build-test]
# Packaging consumes the debian/rhel release binaries, which are only built
@@ -220,12 +200,10 @@ jobs:
passed:
if: failure() || cancelled()
needs:
- check-autogen
- check-levelization
- check-rename
- clang-tidy
- build-test
- rust
- package
- upload-recipe
- notify-clio

View File

@@ -1,9 +1,5 @@
# When a versioned tag is pushed, this workflow:
#
# - uploads the libxrpl recipe to the Conan remote
# - builds and tests the release binaries
# - builds the DEB and RPM packages
# - publishes those packages to the XRPLF package repositories
# This workflow uploads the libxrpl recipe to the Conan remote and builds
# release packages when a versioned tag is pushed.
name: Tag
on:
@@ -28,7 +24,7 @@ jobs:
remote_password: ${{ secrets.NEXUS_REMOTE_PASSWORD }}
build-test:
if: ${{ github.repository_owner == 'XRPLF' }}
if: ${{ github.repository == 'XRPLF/rippled' }}
uses: ./.github/workflows/reusable-build-test.yml
strategy:
fail-fast: true
@@ -41,12 +37,6 @@ jobs:
CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
package:
if: ${{ github.repository_owner == 'XRPLF' }}
if: ${{ github.repository == 'XRPLF/rippled' }}
needs: build-test
uses: ./.github/workflows/reusable-package.yml
with:
publish: true
secrets:
remote_username: ${{ secrets.NEXUS_REMOTE_USERNAME }}
remote_password: ${{ secrets.NEXUS_REMOTE_PASSWORD }}
signing_key: ${{ secrets.NEXUS_PACKAGES_PRIVATE_KEY }}

View File

@@ -15,28 +15,23 @@ on:
# Keep the paths below in sync with those in `on-pr.yml`.
- ".github/actions/build-deps/**"
- ".github/actions/release-info/**"
- ".github/actions/generate-version/**"
- ".github/actions/setup-conan/**"
- ".github/actions/setup-nix-env/**"
- ".github/scripts/strategy-matrix/**"
- ".github/workflows/reusable-build-test-config.yml"
- ".github/workflows/reusable-build-test.yml"
- ".github/workflows/reusable-check-autogen.yml"
- ".github/workflows/reusable-clang-tidy.yml"
- ".github/workflows/reusable-package.yml"
- ".github/workflows/reusable-rust.yml"
- ".github/workflows/reusable-strategy-matrix.yml"
- ".github/workflows/reusable-test.yml"
- ".github/workflows/reusable-upload-recipe.yml"
- ".clang-tidy"
- ".codecov.yml"
- "bin/check-nix-store-refs.sh"
- "bin/check-tools.sh"
- "bin/default-loader-path.sh"
- "cfg/**"
- "cmake/**"
- "conan/**"
- "crates/**"
- "external/**"
- "include/**"
- "src/**"
@@ -44,9 +39,6 @@ on:
- "CMakeLists.txt"
- "conanfile.py"
- "conan.lock"
- "flake.lock"
- "flake.nix"
- "nix/**"
- "LICENSE.md"
- "package/**"
- "README.md"
@@ -75,9 +67,6 @@ defaults:
shell: bash
jobs:
check-autogen:
uses: ./.github/workflows/reusable-check-autogen.yml
clang-tidy:
uses: ./.github/workflows/reusable-clang-tidy.yml
permissions:
@@ -103,11 +92,6 @@ jobs:
secrets:
CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
rust:
uses: ./.github/workflows/reusable-rust.yml
secrets:
CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
upload-recipe:
needs: build-test
# Only run when pushing to the develop branch.
@@ -120,11 +104,3 @@ jobs:
package:
needs: build-test
uses: ./.github/workflows/reusable-package.yml
with:
# Packages are built on every trigger; only develop pushes in XRPLF/rippled
# publish them, matching upload-recipe above.
publish: ${{ github.repository == 'XRPLF/rippled' && github.event_name == 'push' && github.ref == 'refs/heads/develop' }}
secrets:
remote_username: ${{ secrets.NEXUS_REMOTE_USERNAME }}
remote_password: ${{ secrets.NEXUS_REMOTE_PASSWORD }}
signing_key: ${{ secrets.NEXUS_PACKAGES_PRIVATE_KEY }}

View File

@@ -41,13 +41,13 @@ env:
jobs:
build:
runs-on: ubuntu-latest
container: ghcr.io/xrplf/xrpld/nix-ubuntu:sha-a0074f8
container: ghcr.io/xrplf/xrpld/nix-ubuntu:sha-fecfc0c
steps:
- name: Checkout repository
uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- name: Prepare runner
uses: XRPLF/actions/prepare-runner@51af40f99ea91a08c3528ddf16d98132dcc7e63c
uses: XRPLF/actions/prepare-runner@c00c22ada3bd6bcda48fcb0d62fbbab49fec8a0f
with:
enable_ccache: false

View File

@@ -3,12 +3,6 @@ name: Build and test configuration
on:
workflow_call:
inputs:
benchmark:
description: "Whether to smoke-run the benchmarks after testing."
required: false
type: boolean
default: false
build_only:
description: 'Whether to only build or to build and test the code ("true", "false").'
required: true
@@ -69,12 +63,6 @@ on:
type: string
default: ""
toolchain:
description: 'Where the toolchain comes from ("nix" to build the flake CI environment on the runner, empty for the system one). macOS only: Linux always builds in a Nix image, and Nix has no Windows support.'
required: false
type: string
default: ""
secrets:
CODECOV_TOKEN:
description: "The Codecov token to use for uploading coverage reports."
@@ -112,14 +100,10 @@ jobs:
# header files are copied into separate directories by CMake, which will
# otherwise result in cache misses.
CCACHE_SLOPPINESS: include_file_ctime,include_file_mtime
# Determine if coverage, voidstar and validator-keys should be enabled.
# Determine if coverage and voidstar should be enabled.
COVERAGE_ENABLED: ${{ contains(inputs.cmake_args, '-Dcoverage=ON') }}
VOIDSTAR_ENABLED: ${{ contains(inputs.cmake_args, '-Dvoidstar=ON') }}
VALIDATOR_KEYS_ENABLED: ${{ contains(inputs.cmake_args, '-Dvalidator_keys=ON') }}
SANITIZERS_ENABLED: ${{ inputs.sanitizers != '' }}
# The binaries reusable-package.yml consumes. A private repository skips
# them except on a tag push, which is what produces its release packages.
PACKAGING_ARTIFACTS_ENABLED: ${{ github.event.repository.visibility == 'public' || startsWith(github.ref, 'refs/tags/') }}
steps:
- name: Cleanup workspace (macOS and Windows)
if: ${{ runner.os == 'macOS' || runner.os == 'Windows' }}
@@ -129,15 +113,10 @@ jobs:
uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- name: Prepare runner
uses: XRPLF/actions/prepare-runner@51af40f99ea91a08c3528ddf16d98132dcc7e63c
uses: XRPLF/actions/prepare-runner@c00c22ada3bd6bcda48fcb0d62fbbab49fec8a0f
with:
enable_ccache: ${{ inputs.ccache_enabled }}
# Before any step that uses a build tool, composite actions included.
- name: Setup Nix environment
if: ${{ inputs.toolchain == 'nix' }}
uses: ./.github/actions/setup-nix-env
- name: Set ccache log file
if: ${{ inputs.ccache_enabled && runner.debug == '1' }}
run: echo "CCACHE_LOGFILE=${{ runner.temp }}/ccache.log" >>"${GITHUB_ENV}"
@@ -162,22 +141,7 @@ jobs:
with:
compiler: ${{ inputs.compiler }}
- name: Use cargo artifacts cache
uses: Swatinem/rust-cache@6323deb102c322ba6fcbdcafc7e3dddab59af2b6 # v2.9.2
with:
cache-directories: ${{ env.BUILD_DIR }}/corrosion
key: ${{ inputs.config_name }}
save-if: ${{ github.ref == 'refs/heads/develop' || startsWith(github.ref, 'refs/heads/release') }}
# two workspaces here because build artifacts are located in 2 places:
# - crates/target when cargo is called directly
# - build/cargo when cargo is called by cmake
workspaces: |
crates
crates -> ${{ runner.os == 'Windows' && format('../{0}/x64/{1}/cargo', env.BUILD_DIR, inputs.build_type) || format('../{0}/cargo', env.BUILD_DIR) }}
# `setup-nix-env` already did this for the Nix toolchain.
- name: Setup Conan
if: ${{ inputs.toolchain != 'nix' }}
env:
SANITIZERS: ${{ inputs.sanitizers }}
uses: ./.github/actions/setup-conan
@@ -206,9 +170,9 @@ jobs:
..
# Export the sanitizer options before any instrumented binary runs. The
# build step below invokes instrumented dependency tools (protoc, grpc),
# so setting UBSAN_OPTIONS here lets the UBSan suppression list silence
# their diagnostics too, not just at test time.
# protocol code-gen and build steps below invoke instrumented dependency
# tools (protoc, grpc), so setting UBSAN_OPTIONS here lets the UBSan
# suppression list silence their diagnostics too, not just at test time.
# GITHUB_WORKSPACE (not the github.workspace context) is used so the path
# resolves correctly inside the container job.
- name: Set sanitizer options
@@ -226,6 +190,32 @@ jobs:
echo "UBSAN_OPTIONS=include=${SUPP}/runtime-ubsan-options.txt:suppressions=${SUPP}/ubsan.supp" >>${GITHUB_ENV}
echo "LSAN_OPTIONS=include=${SUPP}/runtime-lsan-options.txt:suppressions=${SUPP}/lsan.supp" >>${GITHUB_ENV}
- name: Check protocol autogen files are up-to-date
working-directory: ${{ env.BUILD_DIR }}
env:
MESSAGE: |
The generated protocol wrapper classes are out of date.
This typically happens when the macro files or generator scripts
have changed but the generated files were not regenerated.
To fix this:
1. Run: cmake --build . --target setup_code_gen
2. Run: cmake --build . --target code_gen
3. Commit and push the regenerated files
run: |
set -e
cmake --build . --target setup_code_gen
cmake --build . --target code_gen
DIFF=$(git -C .. status --porcelain -- include/xrpl/protocol_autogen src/tests/libxrpl/protocol_autogen)
if [ -n "${DIFF}" ]; then
echo "::error::Generated protocol files are out of date"
git -C .. diff -- include/xrpl/protocol_autogen src/tests/libxrpl/protocol_autogen
echo "${MESSAGE}"
exit 1
fi
- name: Build the binary
working-directory: ${{ env.BUILD_DIR }}
env:
@@ -241,24 +231,6 @@ jobs:
--target "${CMAKE_TARGET}" \
2>&1 | tee "${GITHUB_WORKSPACE}/build.log"
# Nothing may reference the store, so whole trees are checked - the Conan
# cache included, since what it holds is what gets uploaded and reused.
- name: Check the build output for Nix store references (Nix toolchain)
if: ${{ inputs.toolchain == 'nix' }}
run: ./bin/check-nix-store-refs.sh "${BUILD_DIR}"
- name: Check the Conan cache for Nix store references (Nix toolchain)
if: ${{ inputs.toolchain == 'nix' }}
run: ./bin/check-nix-store-refs.sh "${CONAN_HOME}"
# Only what PatchNixBinary.cmake retargets: the toolchain in the Linux
# images always references the store. Same condition it uses.
- name: Check for Nix store references (Linux)
if: ${{ runner.os == 'Linux' && env.SANITIZERS_ENABLED == 'false' }}
run: |
./bin/check-nix-store-refs.sh "${BUILD_DIR}/xrpld"
./bin/check-nix-store-refs.sh "${BUILD_DIR}/xrpl_tests"
- name: Show ccache statistics
if: ${{ inputs.ccache_enabled }}
run: |
@@ -269,7 +241,7 @@ jobs:
fi
- name: Upload the binary (Linux)
if: ${{ env.PACKAGING_ARTIFACTS_ENABLED == 'true' && runner.os == 'Linux' }}
if: ${{ github.event.repository.visibility == 'public' && runner.os == 'Linux' }}
uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
with:
name: xrpld-${{ inputs.config_name }}
@@ -277,22 +249,6 @@ jobs:
retention-days: 3
if-no-files-found: error
- name: Run the validator-keys tests
if: ${{ env.VALIDATOR_KEYS_ENABLED == 'true' }}
working-directory: ${{ env.BUILD_DIR }}
run: ./validator-keys --unittest
- name: Upload the validator-keys binary
if: ${{ env.PACKAGING_ARTIFACTS_ENABLED == 'true' && env.VALIDATOR_KEYS_ENABLED == 'true' }}
uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
with:
name: validator-keys-${{ inputs.config_name }}
path: |
${{ env.BUILD_DIR }}/validator-keys
${{ env.BUILD_DIR }}/validator-keys-LICENSE
retention-days: 3
if-no-files-found: error
- name: Upload the test binary (Linux)
if: ${{ github.event.repository.visibility == 'public' && runner.os == 'Linux' }}
uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
@@ -370,21 +326,13 @@ jobs:
LD_PRELOAD="$PRELOAD" ./xrpld --unittest --unittest-jobs "${BUILD_NPROC}" 2>&1 | tee "${GITHUB_WORKSPACE}/unittest.log"
- name: Run Rust tests
if: ${{ !inputs.build_only }}
working-directory: crates
run: cargo nextest run --workspace --all-features --locked --no-tests=warn
# Smoke-run every benchmark module with a single repetition to confirm the
# benchmarks still build and execute. This is a correctness check, not a
# performance measurement, so there is nothing to gain from repeating it
# across configurations: it is opted into by a single config in the
# strategy matrix (see the 'benchmark' flag in the JSON files), which
# keeps it off instrumented builds (sanitizers/coverage/voidstar), where
# it would be slow and meaningless, off Debug builds, where it is much
# slower, and off Windows, where the `install` target does not build them.
# performance measurement, so it is skipped for instrumented builds
# (sanitizers/coverage/voidstar), where it would be slow and meaningless,
# and on Windows, where the `install` target does not build them.
- name: Run the benchmarks
if: ${{ inputs.benchmark }}
if: ${{ !inputs.build_only && runner.os != 'Windows' && env.SANITIZERS_ENABLED == 'false' && env.COVERAGE_ENABLED != 'true' && env.VOIDSTAR_ENABLED != 'true' }}
working-directory: ${{ env.BUILD_DIR }}
run: |
rc=0
@@ -439,14 +387,13 @@ jobs:
--target coverage
- name: Upload coverage report
if: ${{ github.repository_owner == 'XRPLF' && !inputs.build_only && env.COVERAGE_ENABLED == 'true' }}
if: ${{ github.repository == 'XRPLF/rippled' && !inputs.build_only && env.COVERAGE_ENABLED == 'true' }}
uses: codecov/codecov-action@fb8b3582c8e4def4969c97caa2f19720cb33a72f # v7.0.0
with:
disable_search: true
disable_telem: true
fail_ci_if_error: true
files: ${{ env.BUILD_DIR }}/coverage.xml
flags: cpp
plugins: noop
token: ${{ secrets.CODECOV_TOKEN }}
verbose: true

View File

@@ -40,7 +40,6 @@ jobs:
fail-fast: ${{ github.event_name == 'merge_group' }}
matrix: ${{ fromJson(needs.generate-matrix.outputs.matrix) }}
with:
benchmark: ${{ matrix.benchmark }}
build_only: ${{ matrix.build_only }}
build_type: ${{ matrix.build_type }}
ccache_enabled: ${{ inputs.ccache_enabled }}
@@ -51,6 +50,5 @@ jobs:
config_name: ${{ matrix.config_name }}
sanitizers: ${{ matrix.sanitizers }}
compiler: ${{ matrix.compiler || '' }}
toolchain: ${{ matrix.toolchain || '' }}
secrets:
CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}

View File

@@ -1,76 +0,0 @@
# This workflow checks that the generated protocol wrapper classes are
# up-to-date with the macro files and generator scripts they are produced from,
# see more info in include/xrpl/protocol_autogen/README.md.
name: Check autogen
# This workflow can only be triggered by other workflows.
on: workflow_call
concurrency:
group: ${{ github.workflow }}-${{ github.ref }}-autogen
cancel-in-progress: true
defaults:
run:
shell: bash
env:
BUILD_DIR: build/codegen
jobs:
autogen:
runs-on: ubuntu-latest
steps:
- name: Checkout repository
uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- name: Set up Python
uses: actions/setup-python@5fda3b95a4ea91299a34e894583c3862153e4b97 # v7.0.0
with:
python-version: "3.13"
# Code generation is pure Python, so the standalone project below offers
# the same targets as the main build without needing its dependencies or
# a compiler, which keeps this job down to a few seconds.
- name: Configure CMake
run: cmake -S cmake/codegen -B "${BUILD_DIR}"
- name: Install code generation dependencies
run: cmake --build "${BUILD_DIR}" --target setup_code_gen
- name: Generate code
run: cmake --build "${BUILD_DIR}" --target code_gen
- name: Check for differences
env:
MESSAGE: |
The generated protocol wrapper classes are out of date.
This typically happens when the macro files or generator scripts
have changed but the generated files were not regenerated.
Run the following from the repository root, then commit and push
the regenerated files. This needs neither the dependencies nor a
compiler. See include/xrpl/protocol_autogen/README.md for more info.
cmake -S cmake/codegen -B build/codegen
cmake --build build/codegen --target setup_code_gen
cmake --build build/codegen --target code_gen
In an already configured build directory, the 'setup_code_gen' and
'code_gen' targets do the same thing.
run: |
# Record untracked files in the index without staging their contents,
# so that classes generated for a newly added transaction or ledger
# entry type show up in the diff below rather than silently as an
# empty one.
git add --intent-to-add .
DIFF=$(git status --porcelain)
if [ -n "${DIFF}" ]; then
# Print the differences to give the contributor a hint about what to
# expect when running code generation on their own machine.
git diff
echo "${MESSAGE}"
exit 1
fi

View File

@@ -34,7 +34,7 @@ jobs:
needs: [determine-files]
if: ${{ needs.determine-files.outputs.cpp_changed_files != '' || needs.determine-files.outputs.need_full_run == 'true' }}
runs-on: ["self-hosted", "Linux", "X64", "heavy"]
container: "ghcr.io/xrplf/xrpld/nix-debian:sha-a0074f8"
container: "ghcr.io/xrplf/xrpld/nix-debian:sha-fecfc0c"
permissions:
contents: read
issues: write
@@ -43,7 +43,7 @@ jobs:
uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- name: Prepare runner
uses: XRPLF/actions/prepare-runner@51af40f99ea91a08c3528ddf16d98132dcc7e63c
uses: XRPLF/actions/prepare-runner@c00c22ada3bd6bcda48fcb0d62fbbab49fec8a0f
with:
enable_ccache: false
@@ -59,13 +59,6 @@ jobs:
with:
compiler: ${{ env.COMPILER }}
- name: Use cargo artifacts cache
uses: Swatinem/rust-cache@6323deb102c322ba6fcbdcafc7e3dddab59af2b6 # v2.9.2
with:
cache-directories: ${{ env.BUILD_DIR }}/corrosion
save-if: ${{ github.ref == 'refs/heads/develop' || startsWith(github.ref, 'refs/heads/release') }}
workspaces: crates -> ../${{ env.BUILD_DIR }}/cargo
- name: Setup Conan
uses: ./.github/actions/setup-conan
@@ -87,13 +80,13 @@ jobs:
-Dwerr=ON \
-Dxrpld=ON \
-Dverify_headers=ON \
-Drust=ON \
..
- name: Build clang-tidy prerequisites
# clang-tidy needs headers generated from proto files
- name: Build libxrpl.libpb
working-directory: ${{ env.BUILD_DIR }}
run: |
ninja -j ${{ steps.nproc.outputs.nproc }} tidy_prerequisites
ninja -j ${{ steps.nproc.outputs.nproc }} xrpl.libpb
- name: Run clang tidy
id: run_clang_tidy

View File

@@ -1,37 +1,17 @@
# Build Linux packages from the pre-built xrpld and validator-keys artifacts:
#
# - one job per distro, taken from "package_configs" in linux.json
# - each job runs in that distro's container, which is what decides DEB or RPM
# - with 'publish: true' a job also uploads what it built
# (see package/publish_pkg.sh)
#
# Only linux/amd64 is supported; the runner is hardcoded in the job below.
# Build Linux packages (DEB and RPM) from pre-built binary artifacts.
# Discovers which configurations to package from linux.json (configs in
# "package_configs") and fans out one job per distro. Only linux/amd64 is
# supported; the runner is hardcoded in the job below.
name: Package
on:
workflow_call:
inputs:
publish:
description: "Whether to publish the packages after building them."
required: false
type: boolean
default: false
nexus_url:
description: "The base URL of the Nexus instance hosting the deb and rpm repositories."
pkg_release:
description: "Package release number. Increment when repackaging the same executable."
required: false
type: string
default: https://packages.xrplf.org
secrets:
remote_username:
description: "The username of a Nexus account with write access to the repositories."
required: false
remote_password:
description: "The password or token for that Nexus account."
required: false
signing_key:
description: "Armoured PGP private key used to sign the RPMs. Required when publishing."
required: false
default: "1"
defaults:
run:
@@ -61,11 +41,11 @@ jobs:
package:
needs: [generate-matrix]
if: ${{ github.event.repository.visibility == 'public' || startsWith(github.ref, 'refs/tags/') }}
if: ${{ github.event.repository.visibility == 'public' }}
strategy:
fail-fast: false
matrix: ${{ fromJson(needs.generate-matrix.outputs.matrix) }}
name: "${{ matrix.xrpld_artifact_name }}"
name: "${{ matrix.artifact_name }}"
permissions:
contents: read
runs-on: ["self-hosted", "Linux", "X64", "heavy"]
@@ -76,54 +56,26 @@ jobs:
- name: Checkout repository
uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- name: Download pre-built xrpld binary
- name: Download pre-built binary
uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
with:
name: ${{ matrix.xrpld_artifact_name }}
name: ${{ matrix.artifact_name }}
path: ${{ env.BUILD_DIR }}
- name: Download pre-built validator-keys binary
uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8.0.1
with:
name: ${{ matrix.validator_keys_artifact_name }}
path: ${{ env.BUILD_DIR }}
- name: Make binaries executable
run: chmod +x "${BUILD_DIR}/xrpld" "${BUILD_DIR}/validator-keys"
- name: Determine release info
id: release_info
uses: ./.github/actions/release-info
- name: Make binary executable
run: chmod +x "${BUILD_DIR}/xrpld"
- name: Build package
env:
PKG_RELEASE: ${{ steps.release_info.outputs.pkg_release }}
PKG_CHANNEL: ${{ steps.release_info.outputs.channel }}
PKG_RELEASE: ${{ inputs.pkg_release }}
run: ./package/build_pkg.sh
# Before the upload, so the artifact and the published package are the
# same bytes. DEBs are not signed, so the key is never set on that job.
- name: Sign RPM
if: ${{ inputs.publish && matrix.distro == 'rhel' }}
env:
PKG_SIGNING_KEY: ${{ secrets.signing_key }}
run: ./package/sign_rpm.sh "${BUILD_DIR}"
- name: Upload package artifact
uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
with:
name: ${{ matrix.xrpld_artifact_name }}-pkg
name: ${{ matrix.artifact_name }}-pkg
path: |
${{ env.BUILD_DIR }}/debbuild/*.deb
${{ env.BUILD_DIR }}/debbuild/*.ddeb
${{ env.BUILD_DIR }}/rpmbuild/RPMS/**/*.rpm
if-no-files-found: error
- name: Publish package
if: ${{ inputs.publish }}
env:
CHANNEL: ${{ steps.release_info.outputs.channel }}
NEXUS_URL: ${{ inputs.nexus_url }}
NEXUS_USERNAME: ${{ secrets.remote_username }}
NEXUS_PASSWORD: ${{ secrets.remote_password }}
run: ./package/publish_pkg.sh "${CHANNEL}" "${BUILD_DIR}"

View File

@@ -1,86 +0,0 @@
# Clippy, coverage and documentation for the Rust crates in crates/. Each runs
# as an independent job on a GitHub-hosted runner, but inside the same container
# image used to build the crates in the C++/Corrosion path, so the toolchain
# (and therefore the lints, coverage instrumentation and the cargo cache) matches
# what production builds use.
#
# Rust unit tests are deliberately NOT run here. They run as part of the C++
# build (reusable-build-test-config.yml), which already compiles the crates on a
# self-hosted runner, so there is no need to provision a toolchain again.
name: Rust
on:
workflow_call:
secrets:
CODECOV_TOKEN:
description: "The Codecov token to use for uploading coverage reports."
required: true
defaults:
run:
shell: bash
working-directory: crates
permissions:
contents: read
jobs:
clippy:
runs-on: ubuntu-latest
container: ghcr.io/xrplf/xrpld/nix-ubuntu:sha-a0074f8
steps:
- name: Checkout repository
uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- name: Use cargo artifacts cache
uses: Swatinem/rust-cache@6323deb102c322ba6fcbdcafc7e3dddab59af2b6 # v2.9.2
with:
workspaces: crates
- name: Run clippy
run: cargo clippy --workspace --all-targets --all-features --locked -- -D warnings
coverage:
runs-on: ubuntu-latest
container: ghcr.io/xrplf/xrpld/nix-ubuntu:sha-a0074f8
steps:
- name: Checkout repository
uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- name: Use cargo artifacts cache
uses: Swatinem/rust-cache@6323deb102c322ba6fcbdcafc7e3dddab59af2b6 # v2.9.2
with:
workspaces: crates
- name: Generate coverage report
run: cargo llvm-cov nextest --workspace --all-features --locked --no-tests=warn --lcov --output-path lcov.info
- name: Upload coverage report
if: ${{ github.repository == 'XRPLF/rippled' }}
uses: codecov/codecov-action@fb8b3582c8e4def4969c97caa2f19720cb33a72f # v7.0.0
with:
disable_search: true
disable_telem: true
fail_ci_if_error: true
files: crates/lcov.info
flags: rust
plugins: noop
token: ${{ secrets.CODECOV_TOKEN }}
verbose: true
doc:
runs-on: ubuntu-latest
container: ghcr.io/xrplf/xrpld/nix-ubuntu:sha-a0074f8
steps:
- name: Checkout repository
uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- name: Use cargo artifacts cache
uses: Swatinem/rust-cache@6323deb102c322ba6fcbdcafc7e3dddab59af2b6 # v2.9.2
with:
workspaces: crates
- name: Build documentation
env:
RUSTDOCFLAGS: "-D warnings"
run: cargo doc --workspace --no-deps --all-features --locked

View File

@@ -40,7 +40,7 @@ defaults:
jobs:
upload:
runs-on: ubuntu-latest
container: ghcr.io/xrplf/xrpld/nix-ubuntu:sha-a0074f8
container: ghcr.io/xrplf/xrpld/nix-ubuntu:sha-fecfc0c
env:
REMOTE_NAME: ${{ inputs.remote_name }}
CONAN_LOGIN_USERNAME_XRPLF: ${{ secrets.remote_username }}
@@ -49,9 +49,9 @@ jobs:
- name: Checkout repository
uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v7.0.1
- name: Determine release info
id: release_info
uses: ./.github/actions/release-info
- name: Generate build version number
id: version
uses: ./.github/actions/generate-version
- name: Set up Conan
uses: ./.github/actions/setup-conan
@@ -64,8 +64,8 @@ jobs:
- name: Upload Conan recipe (version)
run: |
conan export . --version=${{ steps.release_info.outputs.version }}
conan upload --confirm --check --remote="${REMOTE_NAME}" xrpl/${{ steps.release_info.outputs.version }}
conan export . --version=${{ steps.version.outputs.version }}
conan upload --confirm --check --remote="${REMOTE_NAME}" xrpl/${{ steps.version.outputs.version }}
# When this workflow is triggered by a push event, it will always be when merging into the
# 'develop' branch, see on-trigger.yml.
@@ -92,4 +92,4 @@ jobs:
conan upload --confirm --check --remote="${REMOTE_NAME}" xrpl/release
outputs:
ref: xrpl/${{ steps.release_info.outputs.version }}
ref: xrpl/${{ steps.version.outputs.version }}

View File

@@ -72,11 +72,6 @@ jobs:
with:
enable_ccache: false
# Before any step that uses a build tool, composite actions included.
- name: Setup Nix environment
if: ${{ matrix.toolchain == 'nix' }}
uses: ./.github/actions/setup-nix-env
- name: Print build environment
uses: XRPLF/actions/print-build-env@59dec886e4afb05a1724443af08baccbc045b574
@@ -92,9 +87,7 @@ jobs:
with:
compiler: ${{ matrix.compiler }}
# `setup-nix-env` already did this for the Nix toolchain.
- name: Setup Conan
if: ${{ matrix.toolchain != 'nix' }}
env:
SANITIZERS: ${{ matrix.sanitizers }}
uses: ./.github/actions/setup-conan
@@ -113,10 +106,6 @@ jobs:
log_verbosity: ${{ runner.os == 'Windows' && 'quiet' || 'verbose' }}
sanitizers: ${{ matrix.sanitizers }}
- name: Check the Conan cache for Nix store references (Nix toolchain)
if: ${{ matrix.toolchain == 'nix' }}
run: ./bin/check-nix-store-refs.sh "${CONAN_HOME}"
- name: Log into Conan remote
if: ${{ github.repository == 'XRPLF/rippled' && (github.event_name == 'push' || github.event_name == 'workflow_dispatch') }}
run: conan remote login "${CONAN_REMOTE_NAME}" "${{ secrets.NEXUS_REMOTE_USERNAME }}" --password "${{ secrets.NEXUS_REMOTE_PASSWORD }}"

3
.gitignore vendored
View File

@@ -89,6 +89,3 @@ target/
# clangd cache
/.cache
# Rust build directory
crates/target

View File

@@ -62,15 +62,6 @@ repos:
types_or: [c++, c, proto]
exclude: ^include/xrpl/protocol_autogen/(transactions|ledger_entries)/
- repo: local
hooks:
- id: cargo-fmt
name: cargo fmt
entry: cargo fmt --manifest-path crates/Cargo.toml --all
language: system
types: [rust]
pass_filenames: false # rustfmt formats the whole workspace
- repo: https://github.com/BlankSpruce/gersemi-pre-commit
rev: e98930bdc210d3387007f9252d8c1694ea7e410f # frozen: 0.27.7
hooks:

View File

@@ -42,7 +42,6 @@ This section contains changes targeting a future version.
### Bugfixes
- `get_aggregate_price`: Duplicate entries in the `oracles` request array are now ignored. [#6586](https://github.com/XRPLF/rippled/pull/6586)
- Peer Crawler: The `port` field in `overlay.active[]` now consistently returns an integer instead of a string for outbound peers. [#6318](https://github.com/XRPLF/rippled/pull/6318)
- `ping`: The `ip` field is no longer returned as an empty string for proxied connections without a forwarded-for header. It is now omitted, consistent with the behavior for identified connections. [#6730](https://github.com/XRPLF/rippled/pull/6730)
- gRPC `GetLedgerDiff`: Fixed error message that incorrectly said "base ledger not validated" when the desired ledger was not validated. [#6730](https://github.com/XRPLF/rippled/pull/6730)
@@ -54,8 +53,6 @@ This section contains changes targeting a future version.
- `submit`: The `fail_hard` field now returns an error if the value is not a boolean. [#6529](https://github.com/XRPLF/rippled/pull/6529)
- `subscribe`: The `taker` field in the `books` array now returns `actMalformed` instead of `badIssuer` if the value is not a valid account. [#6529](https://github.com/XRPLF/rippled/pull/6529)
- Fixed a bug in `Forwarded` HTTP header parsing where the extracted IP address could be incorrect when no comma or semicolon delimiter follows the address. This could cause the server to misidentify a client's IP address when operating behind a reverse proxy. [#6529](https://github.com/XRPLF/rippled/pull/6529)
- `gateway_balances`: The `account` and `ident` fields now return an `invalidParams` error if the value is not a string, instead of an `internal` error. [#7655](https://github.com/XRPLF/rippled/pull/7655)
- `account_lines`: The `peer` field now returns an error if the value is not a string. [#7728](https://github.com/XRPLF/rippled/pull/7728)
## XRP Ledger server version 3.1.0

125
BUILD.md
View File

@@ -4,14 +4,34 @@
## Minimum Requirements
For the hardware needed to run a node, see
[System Requirements](https://xrpl.org/system-requirements.html).
See [System Requirements](https://xrpl.org/system-requirements.html).
For the software needed to build xrpld, see the
[environment setup guide](./docs/build/environment.md).
Building xrpld generally requires Git, Python, Conan, CMake, and a C++
compiler.
- [Python](https://www.python.org/downloads/)
- [Conan](https://conan.io/downloads.html)
- [CMake](https://cmake.org/download/)
You can verify that the required tools are installed and runnable with:
```bash
./bin/check-tools.sh
```
`xrpld` is written in the C++23 dialect. The [tested compiler versions][cpp23-support] are:
| Compiler | Version |
| ----------- | --------------- |
| GCC | 15.2 |
| Clang | 22 |
| Apple Clang | 21 |
| MSVC | 19.44[^windows] |
## Operating Systems
Please see the [environment setup guide](./docs/build/environment.md) for detailed instructions for all platforms.
### Linux
The Ubuntu Linux distribution has received the highest level of quality
@@ -22,13 +42,12 @@ Our Linux CI tooling is distro-independent and uses a Nix-based environment, so
### macOS
Many `xrpld` engineers use macOS for development.
The minimum supported version is macOS 15 (Sequoia).
CI testing is done in macOS 26 (Tahoe), but the build defaults `CMAKE_OSX_DEPLOYMENT_TARGET` to 15.
### Windows
Windows is used by some engineers for development only, and is not recommended
for production use.
Windows is used by some engineers for development only.
[^windows]: Windows is not recommended for production use.
## Steps
@@ -53,25 +72,37 @@ releases](https://github.com/XRPLF/rippled/releases).
### Set Up Conan
Once your [development environment](./docs/build/environment.md) is ready, set
Conan up for this repository:
After you have a [C++ development environment](./docs/build/environment.md) ready with Git, Python,
Conan, CMake, and a C++ compiler, you may need to set up your Conan profile.
These instructions assume a basic familiarity with Conan and CMake. If you are
unfamiliar with Conan, then please read [this crash course](./docs/build/conan.md) or the official
[Getting Started][conan-getting-started] walkthrough.
#### Profiles
We recommend that you install our Conan profiles:
```bash
./conan/init.sh
conan config install conan/profiles/ -tf $(conan config home)/profiles/
```
That installs our [`global.conf`](./conan/global.conf), our Conan
[profiles](./conan/profiles), and the `xrplf` remote that hosts some of our
dependencies. It honours `CONAN_HOME` and never deletes an existing Conan home,
so it is safe to re-run — it only overwrites the files it manages.
You can check your Conan profile by running:
> [!TIP]
> In the [Nix development shell](./docs/build/nix.md#conan-configuration) this is
> already done for you: the script runs on entry.
```bash
conan profile show
```
You can inspect the resulting profile with `conan profile show`. If it is not
suitable for your environment, create a custom profile and pass it to Conan — see
[Advanced Conan configuration](./docs/build/advanced_conan.md).
If the default profile is not suitable for your environment, you can create a custom profile and pass it to Conan.
More information on customizing Conan can be found in the [Advanced Conan configuration](./docs/build/advanced_conan.md).
#### Add xrplf remote
Run the following command to add the `xrplf` remote, which hosts some of our dependencies:
```bash
conan remote add --index 0 --force xrplf https://conan.xrplf.org/repository/conan/
```
### Set Up Ccache
@@ -214,17 +245,7 @@ cmake --build . --target setup_code_gen # create venv and install dependencies
cmake --build . --target code_gen # regenerate code
```
The same targets are also available as a standalone project, which does not
need the dependencies to be configured first:
```
cmake -S cmake/codegen -B build/codegen
cmake --build build/codegen --target setup_code_gen
cmake --build build/codegen --target code_gen
```
The regenerated files should be committed alongside your changes. CI verifies
that they are up-to-date.
The regenerated files should be committed alongside your changes.
## Coverage report
@@ -236,14 +257,10 @@ which is only enabled when the `coverage` option is set, e.g. with
Prerequisites for the coverage report:
- [gcovr tool][gcovr] (can be installed e.g. with [pip][python-pip])
- `gcov` for GCC or `llvm-cov` for Clang, usually installed with the compiler
- `gcov` for GCC (installed with the compiler by default) or
- `llvm-cov` for Clang (installed with the compiler by default)
- `Debug` build type
> [!NOTE]
> Clang coverage is not available in the [Nix development shell](./docs/build/nix.md#building-xrpld-in-the-nix-shell):
> its `clang` shells do not ship `llvm-cov`. Use a `gcc` shell instead (`.#gcc`,
> or `.#gcc-plain` on Linux), which provides a `gcov` matching its compiler.
A coverage report is created when the following steps are completed, in order:
1. `xrpld` binary built with instrumentation data, enabled by the `coverage`
@@ -304,7 +321,6 @@ See [Sanitizers docs](./docs/build/sanitizers.md) for more details.
| ---------------- | ------------- | ----------------------------------------------------------------------------- |
| `assert` | OFF | Force enabling assertions. |
| `coverage` | OFF | Prepare the coverage report. |
| `rust` | OFF | Build the Rust crates and the C++ code that depends on them. |
| `tests` | OFF | Build tests. |
| `unity` | OFF | Configure a unity build. |
| `verify_headers` | ON | Make the `verify-headers` target available to compile each header on its own. |
@@ -317,30 +333,6 @@ 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.
### Rust crates
The Rust crates in `crates/` are only part of the build when `rust` is ON. With
`-Drust=OFF` (the default) the `crates` directory is not added to the build, no
cxxbridge bindings are generated, and the C++ tests that exercise the Rust
interop are not compiled — so no Rust toolchain is needed. CI builds always pass
`-Drust=ON`.
With `-Drust=ON` you need one extra dependency: a Rust toolchain (`cargo`,
`rustc`) matching the channel pinned in
[`rust-toolchain.toml`](./rust-toolchain.toml), which compiles the crates and
generates the cxxbridge bindings. It is provided by the
[Nix development shell](./docs/build/nix.md), so `-Drust=ON` works there without
any extra setup; otherwise install it as described in
[Rust](./docs/build/environment.md#rust).
The crates also have their own Rust unit tests. Those are run with `cargo` and
need only the Rust toolchain, independently of CMake and of the `rust` option
(CI runs them with `cargo nextest`):
```bash
cargo test --manifest-path crates/Cargo.toml --workspace
```
### Verifying headers
The regular build only compiles `.cpp` files, so a header is only ever checked
@@ -385,14 +377,10 @@ After any updates or changes to dependencies, you may need to do the following:
4. [Regenerate lockfile](./docs/build/advanced_conan.md#conan-lockfile).
5. Re-run [conan install](#build-and-test).
If you are using the Nix development shell, whether prebuilt Conan binaries apply
depends on your platform — see
[Prebuilt packages](./docs/build/nix.md#prebuilt-packages).
#### ERROR: Package not resolved
If you're seeing an error like `ERROR: Package 'snappy/1.1.10' not resolved: Unable to find 'snappy/1.1.10#968fef506ff261592ec30c574d4a7809%1756234314.246' in remotes.`,
please [set Conan up](#set-up-conan) so the `xrplf` remote is configured, or re-run `conan export` for [patched recipes](./docs/build/advanced_conan.md#patched-recipes).
please [add `xrplf` remote](#add-xrplf-remote) or re-run `conan export` for [patched recipes](./docs/build/advanced_conan.md#patched-recipes).
### `protobuf/port_def.inc` file not found
@@ -412,6 +400,7 @@ For example, if you want to build Debug:
1. For conan install, pass `--settings build_type=Debug`
2. For cmake, pass `-DCMAKE_BUILD_TYPE=Debug`
[cpp23-support]: https://en.cppreference.com/w/cpp/compiler_support/23
[conan-getting-started]: https://docs.conan.io/en/latest/getting_started.html
[unity-build]: https://en.wikipedia.org/wiki/Unity_build
[gcovr]: https://gcovr.com/en/stable/getting-started.html

View File

@@ -13,23 +13,6 @@ if(DEFINED CMAKE_MODULE_PATH)
endif()
list(APPEND CMAKE_MODULE_PATH "${CMAKE_CURRENT_SOURCE_DIR}/cmake")
# Must be set before project() because project() consumes it when configuring the compiler and SDK.
# A user-provided -DCMAKE_OSX_DEPLOYMENT_TARGET still takes precedence.
#
# CMAKE_SYSTEM_NAME can't be used before project(), so CMAKE_HOST_SYSTEM_NAME is used instead.
#
# When CMAKE_OSX_DEPLOYMENT_TARGET is bumped to >=26.0, FastFloat dependency won't be needed anymore
if(
CMAKE_HOST_SYSTEM_NAME STREQUAL "Darwin"
AND NOT DEFINED CMAKE_OSX_DEPLOYMENT_TARGET
)
set(CMAKE_OSX_DEPLOYMENT_TARGET
"15.0"
CACHE STRING
"Minimum macOS deployment version"
)
endif()
project(xrpl)
set(CMAKE_CXX_EXTENSIONS OFF)
set(CMAKE_CXX_STANDARD 23)
@@ -104,7 +87,6 @@ include(deps/Boost)
add_subdirectory(external/antithesis-sdk)
find_package(date REQUIRED)
find_package(ed25519 REQUIRED)
find_package(FastFloat REQUIRED)
find_package(gRPC REQUIRED)
find_package(LibArchive REQUIRED)
find_package(lz4 REQUIRED)
@@ -120,7 +102,6 @@ target_link_libraries(
xrpl_libs
INTERFACE
ed25519::ed25519
FastFloat::fast_float
lz4::lz4
mpt-crypto::mpt-crypto
OpenSSL::Crypto
@@ -158,19 +139,11 @@ if(coverage)
include(XrplCov)
endif()
add_custom_target(tidy_prerequisites)
if(rust)
add_subdirectory(crates)
endif()
include(XrplCore)
include(XrplProtocolAutogen)
include(XrplInstall)
include(XrplValidatorKeys)
# Must come after XrplValidatorKeys: the 'package' target depends on the
# validator-keys target existing.
include(XrplPackaging)
include(XrplValidatorKeys)
if(tests)
include(CTest)

View File

@@ -225,9 +225,8 @@ environment, so you don't need to install most of the individual tools
yourself. The version of each hook sourced from an external repository
(`clang-format`, `gersemi`, etc.) is pinned in that file, so running the hooks
locally uses exactly the same versions as CI. A few `local` hooks — most notably
`clang-tidy` and `cargo fmt` — run tools from your own environment; see
[Installing clang-tidy](#installing-clang-tidy) and
[Rust](./docs/build/environment.md#rust) for how to get those.
`clang-tidy` — run tools from your own environment; see
[Installing clang-tidy](#installing-clang-tidy) for how to get those.
To get started, install `pre-commit` and enable the git hook scripts:
@@ -256,7 +255,6 @@ The hooks configured in this repository include, among others:
- `clang-tidy` — C++ static analysis (see [Clang-tidy](#clang-tidy)); opt in with `TIDY=1`
- `fix-include-style`, `fix-pragma-once`, `check-doxygen-style` — C++ hygiene
- `gersemi` — CMake formatting
- `cargo fmt` — Rust formatting for the crates in `crates/`
- `prettier`, `black`, `shfmt` — formatting for JavaScript/JSON/Markdown, Python, and shell
- `cspell` — spell checking
@@ -321,11 +319,7 @@ See the [environment setup guide](./docs/build/environment.md#clang-tidy) for ho
### Running clang-tidy locally
Before running clang-tidy, you must generate the files it depends on (protobuf headers, and, when the project is configured with `-Drust=ON`, the cxxbridge headers from the Rust crates). Configure the project as described in [`BUILD.md`](./BUILD.md), then build the `tidy_prerequisites` target, which generates all of them:
```bash
cmake --build build --target tidy_prerequisites
```
Before running clang-tidy, you must build the project to generate required files (particularly protobuf headers). Refer to [`BUILD.md`](./BUILD.md) for build instructions.
#### Via pre-commit (recommended)
@@ -362,46 +356,6 @@ run-clang-tidy -p build -quiet -fix -format -allow-no-checks src tests
`-format` reformats the fixed code with [`.clang-format`](./.clang-format); without it the fixes are inserted in LLVM style and the `clang-format` hook rewrites them afterwards.
## Telemetry span attribute naming
OpenTelemetry span attribute keys follow these rules so they stay consistent
across the code, the OTel collector, Tempo, Grafana dashboards, and docs. The
constants in the `*SpanNames.h` headers are the single source of truth; every
other layer must match them. A CI check enforces this end to end.
1. Per-span unique attribute: bare field name — allowed when the field is
recorded by a single span/workflow, so the span name already supplies the
domain (e.g. `command`, `local`, `version` on `rpc.command` / `tx.process`).
2. Shared attribute (same concept on more than one span): ONE key, reused
verbatim on every span that records it — the span name tells the occurrences
apart, so no per-emitter prefix is added. Pick the name by the field's
meaning: a property of a domain object keeps that object's bare field name
(`ledger_hash`, `ledger_seq`, `tx_hash`, `peer_id`, `full_validation`); a
field already qualified by a sub-kind keeps that qualifier on every emitter
(`proposal_trusted` on both `consensus.proposal.receive` and
`peer.proposal.receive`; `validation_trusted` likewise). Define it once in
the base `SpanNames.h` `namespace attr` block and re-export (`using`) it from
each domain header, so all emitters share the exact string.
3. Collision qualifier: `<domain>_<field>` — only when a bare name would collide
with a DIFFERENT concept in the shared spanmetrics label space, or with the
OTel-reserved `status` key (e.g. `rpc_status`, `grpc_status`,
`consensus_phase`, `consensus_round`). This disambiguates distinct concepts
that share a word; it is NOT used to tag the same concept with the workflow
that emitted it — that is rule 2 (one shared name).
4. Resource attribute: dotted `xrpl.<subsystem>.<field>` — reserved ONLY for
process/network identity set once at startup (`xrpl.network.id`,
`xrpl.network.type`). Never use the dotted `xrpl.` form for span attributes.
5. Span names use `<subsystem>[.<component>]` (dotted). Only attribute _keys_
follow rules 14.
Standard OpenTelemetry semantic-convention keys keep their canonical dotted
form (e.g. `service.*` resource attributes, `http.*` span attributes); the
"no dotted form" rule above applies to xrpl-custom keys, not to OTel-standard
conventions.
Always reference the `*SpanNames.h` constants — never pass string literals as
attribute keys or values to `setAttribute`/`addEvent`.
## Contracts and instrumentation
We are using [Antithesis](https://antithesis.com/) for continuous fuzzing,

View File

@@ -1,565 +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.
---
## Actors and Actions at a Glance
### Actors
| Who (Plain English) | Technical Term |
| ---------------------------------------------- | --------------- |
| A single unit of work being tracked | Span |
| The complete journey of a request | Trace |
| Data that links spans across services | Trace Context |
| Code that creates spans and propagates context | Instrumentation |
| Service that receives and processes traces | Collector |
| Storage and visualization system | Backend (Tempo) |
| Decision logic for which traces to keep | Sampler |
### Actions
| What Happens (Plain English) | Technical Term |
| --------------------------------------- | ----------------------- |
| Start tracking a new operation | Create a Span |
| Connect a child operation to its parent | Set `parent_span_id` |
| Group all related operations together | Share a `trace_id` |
| Pass tracking data between services | Context Propagation |
| Decide whether to record a trace | Sampling (Head or Tail) |
| Send completed traces to storage | Export (OTLP) |
---
## 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` | Identifies the trace | `event123` |
| `span_id` | Unique identifier | `span456` |
| `parent_span_id` | Parent span (if any) | `p_span123` |
| `name` | Operation name | `rpc.submit` |
| `start_time` | When work began (local time) | `2024-01-15T10:30:00Z` |
| `end_time` | When work completed (local time) | `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
```
**Reading the diagram:**
- **tx.submit (blue, root)**: The top-level span representing the entire transaction submission; all other spans are its descendants.
- **tx.validate, tx.relay, tx.apply (green)**: Direct children of tx.submit, representing the three main stages -- validation, relay to peers, and application to the ledger.
- **ledger.update (red)**: A grandchild span nested under tx.apply, representing the actual ledger state mutation triggered by applying the transaction.
- **Arrows (parent to child)**: Each arrow indicates a parent-child span relationship where the parent's completion depends on the child finishing.
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 │ │▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓│
```
---
## Span Relationships
Spans don't always form simple parent-child trees. Distributed tracing defines several relationship types to capture different causal patterns:
### 1. Parent-Child (ChildOf)
The default relationship. The parent span **depends on** or **contains** the child span. The child runs within the scope of the parent.
```
tx.submit (parent)
├── tx.validate (child) ← parent waits for this
├── tx.relay (child) ← parent waits for this
└── tx.apply (child) ← parent waits for this
```
**When to use:** Synchronous calls, nested operations, any case where the parent's completion depends on the child.
### 2. Follows-From
A causal relationship where the first span **triggers** the second, but does **not wait** for it. The originator fires and moves on.
```
Time →
tx.receive [=======]
↓ triggers (follows-from)
tx.relay [===========] ← runs independently
```
**When to use:** Asynchronous jobs, queued work, fire-and-forget patterns. For example, a node receives a transaction and queues it for relay — the relay span _follows from_ the receive span but the receiver doesn't wait for relaying to complete.
> **OpenTracing** defined `FollowsFrom` as a first-class reference type alongside `ChildOf`.
> **OpenTelemetry** represents this using **Span Links** with descriptive attributes instead (see below).
### 3. Span Links (Cross-Trace and Non-Hierarchical)
Links connect spans that are **causally related but not in a parent-child hierarchy**. Unlike parent-child, links can cross trace boundaries.
```
Trace A Trace B
────── ──────
batch.schedule batch.execute
├─ item.enqueue (span X) ┌──► process.item
├─ item.enqueue (span Y) ───┤ (links to X, Y, Z)
├─ item.enqueue (span Z) └──►
```
**Use cases:**
| Pattern | Description |
| -------------------- | --------------------------------------------------------------------------- |
| **Batch processing** | A batch span links back to all individual spans that contributed to it |
| **Fan-in** | An aggregation span links to the multiple producer spans it merges |
| **Fan-out** | Multiple downstream spans link back to the single span that triggered them |
| **Async handoff** | A deferred job links back to the request that queued it (follows-from) |
| **Cross-trace** | Correlating spans across independent traces (e.g., retries, related events) |
**Link structure:** Each link carries the target span's context plus optional attributes:
```
Link {
trace_id: <target trace>
span_id: <target span>
attributes: { "link.description": "triggered by batch scheduler" }
}
```
### Relationship Summary
```mermaid
flowchart LR
subgraph parent_child["Parent-Child"]
direction TB
P["Parent"] --> C["Child"]
end
subgraph follows_from["Follows-From"]
direction TB
A["Span A"] -.->|triggers| B["Span B"]
end
subgraph links["Span Links"]
direction TB
X["Span X\n(Trace 1)"] -.-|link| Y["Span Y\n(Trace 2)"]
end
parent_child ~~~ follows_from ~~~ links
style P fill:#0d47a1,stroke:#082f6a,color:#ffffff
style C fill:#1b5e20,stroke:#0d3d14,color:#ffffff
style A fill:#0d47a1,stroke:#082f6a,color:#ffffff
style B fill:#bf360c,stroke:#8c2809,color:#ffffff
style X fill:#4a148c,stroke:#38006b,color:#ffffff
style Y fill:#4a148c,stroke:#38006b,color:#ffffff
```
| Relationship | Same Trace? | Dependency? | OTel Mechanism |
| ---------------- | ----------- | -------------------------- | ----------------- |
| **Parent-Child** | Yes | Parent depends on child | `parent_span_id` |
| **Follows-From** | Usually | Causal but no dependency | Link + attributes |
| **Span Link** | Either | Correlation, no dependency | Link + attributes |
---
## Trace ID Generation
A `trace_id` is a 128-bit (16-byte) identifier that groups all spans belonging to one logical operation. How it's generated determines how easily you can find and correlate traces later.
### General Approaches
#### 1. Random (W3C Default)
Generate a random 128-bit ID when a trace starts. Standard approach for most services.
```
trace_id = random_128_bits()
```
| Pros | Cons |
| --------------------------- | --------------------------------------------- |
| Simple, standard | No natural correlation to domain events |
| Guaranteed unique per trace | If propagation is lost, trace is broken |
| Works with all OTel tooling | "Find trace for TX abc" requires index lookup |
#### 2. Deterministic (Derived from Domain Data)
Compute the trace_id from a hash of a natural identifier. Every node independently derives the **same** trace_id for the same event.
```
trace_id = SHA-256(domain_identifier)[0:16] // truncate to 128 bits
```
| Pros | Cons |
| --------------------------------------------------- | ---------------------------------------------------------- |
| Propagation-resilient — same ID computed everywhere | Same event processed twice (retry) shares trace_id |
| Natural search — domain ID maps directly to trace | Non-standard (tooling assumes random) |
| No coordination needed between nodes | 256→128 bit truncation (collision risk negligible at ~2⁶⁴) |
#### 3. Hybrid (Deterministic Prefix + Random Suffix)
First 8 bytes derived from domain data, last 8 bytes random.
```
trace_id = SHA-256(domain_identifier)[0:8] || random_64_bits()
```
| Pros | Cons |
| ------------------------------------------- | ---------------------------------------- |
| Prefix search: "find all traces for TX abc" | Must propagate to maintain full trace_id |
| Unique per processing instance | More complex generation logic |
| Retries get distinct trace_ids | Partial correlation only (prefix match) |
### XRPL Workflow Analysis
XRPL has a unique advantage: its core workflows produce **globally unique 256-bit hashes** that are known on every node. This makes deterministic trace_id generation practical in ways most systems can't achieve.
#### Natural Identifiers by Workflow
| Workflow | Natural Identifier | Size | Known at Start? | Same on All Nodes? |
| ------------------- | --------------------------------- | ---------- | ----------------------------- | -------------------------------- |
| **Transaction** | Transaction hash (`tid_`) | 256-bit | Yes — computed before signing | Yes — hash of canonical tx data |
| **Consensus round** | Previous ledger hash + ledger seq | 256+32 bit | Yes — known when round opens | Yes — all validators agree |
| **Validation** | Ledger hash being validated | 256-bit | Yes — from consensus result | Yes — same closed ledger |
| **Ledger catch-up** | Target ledger hash | 256-bit | Yes — we know what to fetch | Yes — identifies ledger globally |
#### Where These Identifiers Live in Code
```
Transaction: STTx::getTransactionID() → uint256 tid_
TMTransaction::rawTransaction → recompute hash from bytes
Consensus: ConsensusProposal::prevLedger_ → uint256 (previous ledger hash)
ConsensusProposal::position_ → uint256 (TxSet hash)
LedgerHeader::seq → uint32_t (ledger sequence)
Validation: STValidation::getLedgerHash() → uint256
STValidation::getNodeID() → NodeID (160-bit)
Ledger fetch: InboundLedger constructor → uint256 hash, uint32_t seq
TMGetLedger::ledgerHash → bytes (uint256)
```
### Recommended Strategy: Workflow-Scoped Deterministic
Each workflow type derives its trace_id from its natural domain identifier:
```
Transaction trace: trace_id = SHA-256("tx" || tx_hash)[0:16]
Consensus trace: trace_id = SHA-256("cons" || prev_ledger_hash || ledger_seq)[0:16]
Ledger catch-up: trace_id = SHA-256("fetch" || target_ledger_hash)[0:16]
```
The string prefix (`"tx"`, `"cons"`, `"fetch"`) prevents collisions between workflows that might share underlying hashes.
**Why this works for XRPL:**
1. **Propagation-resilient** — Even if a P2P message drops trace context, every node independently computes the same trace_id from the same tx_hash or ledger_hash. Spans still correlate.
2. **Zero-cost search** — "Show me the trace for transaction ABC" becomes a direct lookup: compute `SHA-256("tx" || ABC)[0:16]` and query. No secondary index needed.
3. **Cross-workflow linking via Span Links** — A consensus trace links to individual transaction traces. A validation span links to the consensus trace. This connects the full picture without forcing everything into one giant trace.
### Cross-Workflow Correlation
Each workflow gets its own trace. Span Links tie them together:
```mermaid
flowchart TB
subgraph tx_trace["Transaction Trace"]
direction LR
Tn["trace_id = f(tx_hash)"]:::note --> T1["tx.receive"] --> T2["tx.validate"] --> T3["tx.relay"]
end
subgraph cons_trace["Consensus Trace"]
direction LR
Cn["trace_id = f(prev_ledger, seq)"]:::note --> C1["cons.open"] --> C2["cons.propose"] --> C3["cons.accept"]
end
subgraph val_trace["Validation"]
direction LR
Vn["spans within consensus trace"]:::note --> V1["val.create"] --> V2["val.broadcast"]
end
subgraph fetch_trace["Catch-Up Trace"]
direction LR
Fn["trace_id = f(ledger_hash)"]:::note --> F1["fetch.request"] --> F2["fetch.receive"] --> F3["fetch.apply"]
end
C1 -.-|"span link\n(tx traces)"| T3
C3 --> V1
F1 -.-|"span link\n(target ledger)"| C3
classDef note fill:none,stroke:#888,stroke-dasharray:5 5,color:#333,font-style:italic
style T1 fill:#0d47a1,stroke:#082f6a,color:#ffffff
style T2 fill:#0d47a1,stroke:#082f6a,color:#ffffff
style T3 fill:#0d47a1,stroke:#082f6a,color:#ffffff
style C1 fill:#1b5e20,stroke:#0d3d14,color:#ffffff
style C2 fill:#1b5e20,stroke:#0d3d14,color:#ffffff
style C3 fill:#1b5e20,stroke:#0d3d14,color:#ffffff
style V1 fill:#bf360c,stroke:#8c2809,color:#ffffff
style V2 fill:#bf360c,stroke:#8c2809,color:#ffffff
style F1 fill:#4a148c,stroke:#38006b,color:#ffffff
style F2 fill:#4a148c,stroke:#38006b,color:#ffffff
style F3 fill:#4a148c,stroke:#38006b,color:#ffffff
```
**Reading the diagram:**
- **Transaction Trace (blue)**: An independent trace whose `trace_id` is deterministically derived from the transaction hash. Contains receive, validate, and relay spans.
- **Consensus Trace (green)**: An independent trace whose `trace_id` is derived from the previous ledger hash and sequence number. Covers the open, propose, and accept phases.
- **Validation (red)**: Validation spans live within the consensus trace (not a separate trace). They are created after the accept phase completes.
- **Catch-Up Trace (purple)**: An independent trace for ledger acquisition, derived from the target ledger hash. Used when a node is behind and fetching missing ledgers.
- **Dotted arrows (span links)**: Cross-trace correlations. Consensus links to transaction traces it included; catch-up links to the consensus trace that produced the target ledger.
- **Solid arrow (C3 to V1)**: A parent-child relationship -- validation spans are direct children of the consensus accept span within the same trace.
**How a query flows:**
```
"Why was TX abc slow?"
1. Compute trace_id = SHA-256("tx" || abc)[0:16]
2. Find transaction trace → see it was included in consensus round N
3. Follow span link → consensus trace for round N
4. See which phase was slow (propose? accept?)
5. If a node was catching up, follow link → catch-up trace
```
### Trade-offs to Consider
| Concern | Mitigation |
| ----------------------------- | ----------------------------------------------------------------------------------------------------------------------------- |
| **Retries get same trace_id** | Add `attempt` attribute to root span; spans have unique span_ids and timestamps |
| **256→128 bit truncation** | Birthday-bound collision at ~2⁶⁴ operations — negligible for XRPL's throughput |
| **Non-standard generation** | OTel spec allows any 16-byte non-zero value; tooling works on the hex string |
| **Hash computation cost** | SHA-256 is ~0.3μs per call; XRPL already computes these hashes for other purposes |
| **Late-binding identifiers** | Ledger hash isn't known until after consensus — validation spans use ledger_seq as fallback, then link to the consensus trace |
---
## Distributed Traces Across Nodes
In distributed systems like xrpld, 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
```
**Reading the diagram:**
- **Client**: The external entity that submits a transaction. It does not carry trace context -- the trace originates at the first node.
- **Node A**: The entry point that creates a new trace (trace_id: abc123) and the root span `tx.receive`. It relays the transaction to peers with trace context attached.
- **Node B and Node C**: Peer nodes that receive the relayed transaction along with the propagated trace context. Each creates a child span under Node A's span, preserving the same `trace_id`.
- **Arrows with trace context**: The relay messages carry `trace_id` and `parent_span_id`, allowing each downstream node to link its spans back to the originating span on Node A.
---
## Context Propagation
For traces to work across nodes, **trace context must be propagated** in messages.
### What's in the Context (~26 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` | 1 byte | Sampling decision (bit 0 = sampled; bits 1-7 reserved) |
| `trace_state` | variable | Optional vendor-specific data (typically omitted) |
### 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: 00-4bf92f3577b34da6a3ce929d0e0e4736-00f067aa0ba902b7-01
│ │ │ │
│ │ │ └── Flags (sampled)
│ │ └── Parent span ID (16 hex)
│ └── Trace ID (32 hex)
└── Version
```
### Protocol Buffers (xrpld P2P messages)
xrpld P2P messages such as `TMTransaction` carry the trace context in two added byte fields alongside the existing payload: `trace_parent` holds the W3C traceparent (`trace_id`, `span_id`, and `trace_flags`), and `trace_state` holds the optional W3C tracestate. Together they propagate the trace across the P2P boundary so a receiving node can attach its spans to the sender's span.
---
## Sampling
Not every trace needs to be recorded. **Sampling** reduces overhead:
### Head Sampling (at trace start)
```
Request arrives → Random N% chance → Record or skip entire trace
```
- ✅ Low overhead
- ❌ May miss interesting traces
> **xrpld note**: xrpld intentionally fixes head sampling at 100% (sample
> everything) and does not expose a configurable ratio. A per-node ratio
> would let different nodes make divergent keep/drop decisions for the same
> distributed trace, producing broken/partial traces. xrpld uses a
> `ParentBased` sampler so spans with a remote parent honor the upstream
> decision. Volume reduction is delegated to collector-side tail sampling.
### 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 xrpld
| 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 |
| **Parent-Child** | Span relationship where the parent depends on the child |
| **Follows-From** | Causal relationship where originator doesn't wait for the result |
| **Span Link** | Non-hierarchical connection between spans, possibly across traces |
| **Deterministic ID** | Trace ID derived from domain data (e.g., tx_hash) instead of random |
| **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 (Tempo) |
| **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

@@ -1,467 +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 xrpld Architecture Overview
> **WS** = WebSocket | **UNL** = Unique Node List | **TxQ** = Transaction Queue | **StatsD** = Statistics Daemon
The xrpld node software consists of several interconnected components that need instrumentation for distributed tracing:
```mermaid
flowchart TB
subgraph xrpld["xrpld Node"]
subgraph services["Core Services"]
RPC["RPC Server<br/>(HTTP/WS/gRPC)"]
Overlay["Overlay<br/>(P2P Network)"]
Consensus["Consensus<br/>(RCLConsensus)"]
ValidatorList["ValidatorList<br/>(UNL Mgmt)"]
end
JobQueue["JobQueue<br/>(Thread Pool)"]
subgraph processing["Processing Layer"]
NetworkOPs["NetworkOPs<br/>(Tx Processing)"]
LedgerMaster["LedgerMaster<br/>(Ledger Mgmt)"]
NodeStore["NodeStore<br/>(Database)"]
InboundLedgers["InboundLedgers<br/>(Ledger Sync)"]
end
subgraph appservices["Application Services"]
PathFind["PathFinding<br/>(Payment Paths)"]
TxQ["TxQ<br/>(Fee Escalation)"]
LoadMgr["LoadManager<br/>(Fee/Load)"]
end
subgraph observability["Existing Observability"]
PerfLog["PerfLog<br/>(JSON)"]
Insight["Insight<br/>(StatsD)"]
Logging["Logging<br/>(Journal)"]
end
services --> JobQueue
JobQueue --> processing
JobQueue --> appservices
end
style xrpld fill:#424242,stroke:#212121,color:#ffffff
style services fill:#1565c0,stroke:#0d47a1,color:#ffffff
style processing fill:#2e7d32,stroke:#1b5e20,color:#ffffff
style appservices fill:#6a1b9a,stroke:#4a148c,color:#ffffff
style observability fill:#e65100,stroke:#bf360c,color:#ffffff
```
**Reading the diagram:**
- **Core Services (blue)**: The entry points into xrpld -- RPC Server handles client requests, Overlay manages peer-to-peer networking, Consensus drives agreement, and ValidatorList manages trusted validators.
- **JobQueue (center)**: The asynchronous thread pool that decouples Core Services from the Processing and Application layers. All work flows through it.
- **Processing Layer (green)**: Core business logic -- NetworkOPs processes transactions, LedgerMaster manages ledger state, NodeStore handles persistence, and InboundLedgers synchronizes missing data.
- **Application Services (purple)**: Higher-level features -- PathFinding computes payment routes, TxQ manages fee-based queuing, and LoadManager tracks server load.
- **Existing Observability (orange)**: The current monitoring stack (PerfLog, Insight, Journal logging) that OpenTelemetry will complement, not replace.
- **Arrows (Services to JobQueue to layers)**: Work originates at Core Services, is enqueued onto the JobQueue, and dispatched to Processing or Application layers for execution.
---
## 1.1.1 Actors and Actions
### Actors
| Who (Plain English) | Technical Term |
| ----------------------------------------- | -------------------------- |
| Network node running XRPL software | xrpld node |
| External client submitting requests | RPC Client |
| Network neighbor sharing data | Peer (PeerImp) |
| Request handler for client queries | RPC Server (ServerHandler) |
| Command executor for specific RPC methods | RPCHandler |
| Agreement process between nodes | Consensus (RCLConsensus) |
| Transaction processing coordinator | NetworkOPs |
| Background task scheduler | JobQueue |
| Ledger state manager | LedgerMaster |
| Payment route calculator | PathFinding (Pathfinder) |
| Transaction waiting room | TxQ (Transaction Queue) |
| Fee adjustment system | LoadManager |
| Trusted validator list manager | ValidatorList |
| Protocol upgrade tracker | AmendmentTable |
| Ledger state hash tree | SHAMap |
| Persistent key-value storage | NodeStore |
### Actions
| What Happens (Plain English) | Technical Term |
| ---------------------------------------------- | ---------------------- |
| Client sends a request to a node | `rpc.request` |
| Node executes a specific RPC command | `rpc.command.*` |
| Node receives a transaction from a peer | `tx.receive` |
| Node checks if a transaction is valid | `tx.validate` |
| Node forwards a transaction to neighbors | `tx.relay` |
| Nodes agree on which transactions to include | `consensus.round` |
| Consensus progresses through phases | `consensus.phase.*` |
| Node builds a new confirmed ledger | `ledger.build` |
| Node fetches missing ledger data from peers | `ledger.acquire` |
| Node computes payment routes | `pathfind.compute` |
| Node queues a transaction for later processing | `txq.enqueue` |
| Node increases fees due to high load | `fee.escalate` |
| Node fetches the latest trusted validator list | `validator.list.fetch` |
| Node votes on a protocol amendment | `amendment.vote` |
| Node synchronizes state tree data | `shamap.sync` |
---
## 1.2 Key Components for Instrumentation
> **TxQ** = Transaction Queue | **UNL** = Unique Node List
| 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 |
| **PathFinding** | `src/xrpld/app/paths/` | Payment path computation | Path latency, cache hits |
| **TxQ** | `src/xrpld/app/misc/TxQ.cpp` | Transaction queue/fees | Queue depth, eviction rates |
| **LoadManager** | `src/xrpld/app/main/LoadManager.cpp` | Fee escalation/load | Fee levels, load factors |
| **InboundLedgers** | `src/xrpld/app/ledger/InboundLedgers.cpp` | Ledger acquisition | Sync time, peer reliability |
| **ValidatorList** | `src/xrpld/app/misc/ValidatorList.cpp` | UNL management | List freshness, fetch failures |
| **AmendmentTable** | `src/xrpld/app/misc/AmendmentTable.cpp` | Protocol amendments | Voting status, activation events |
| **SHAMap** | `src/xrpld/shamap/` | State hash tree | Sync speed, missing nodes |
---
## 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)
```
**Reading the diagram:**
- **Client**: The external entity that submits a transaction to Peer A. It has no trace context -- the trace starts at the first node.
- **Peer A (Receive)**: The entry node that creates the root span `tx.receive`, runs HashRouter deduplication to avoid processing duplicates, and creates a child `tx.validate` span.
- **Peer A to Peer B arrow**: The relay message carries trace context (trace_id + parent span_id), enabling Peer B to create a linked span under the same trace.
- **Peer B (Relay)**: Receives the transaction and trace context, creates a `tx.receive` span linked to Peer A's trace, then relays onward.
- **Peer C (Validate)**: Final hop in this example. Creates a linked `tx.receive` span and runs `tx.process` to fully process the transaction.
- **Blue rectangles**: Highlight the span boundaries on each node, showing where instrumentation creates and closes spans.
### 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/>ledger_seq = 12345678<br/>consensus_mode = proposing<br/>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
```
**Reading the diagram:**
- **consensus.round (orange, root span)**: The top-level span encompassing the entire consensus round, with attributes like ledger sequence, mode, and proposer count.
- **consensus.phase.open (blue)**: The first phase where the node waits (~3s) to collect incoming transactions before proposing.
- **consensus.phase.establish (green)**: The negotiation phase where validators exchange proposals, resolve disputes, and converge on a transaction set. Child spans track each proposal received/sent and each dispute resolved.
- **consensus.phase.accept (pink)**: The final phase where the agreed transaction set is applied, a new ledger is built, and the ledger is validated. Child spans cover `ledger.build` and `ledger.validate`.
- **Arrows (open to establish to accept)**: The sequential flow through the three consensus phases. Each phase must complete before the next begins.
---
## 1.5 RPC Request Flow
> **WS** = WebSocket
RPC requests support W3C Trace Context headers for distributed tracing across services:
```mermaid
flowchart TB
subgraph request["rpc.request (root span)"]
http["HTTP Request — POST /<br/>traceparent:<br/>00-abc123...-def456...-01"]
attrs["Attributes:<br/>http.method = POST<br/>net.peer.ip = 192.168.1.100<br/>command = submit"]
subgraph enqueue["jobqueue.enqueue"]
job_attr["job_type = jtCLIENT_RPC"]
end
subgraph command["rpc.command.submit"]
cmd_attrs["version = 2<br/>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
```
**Reading the diagram:**
- **rpc.request (green, root span)**: The outermost span representing the full RPC request lifecycle, from HTTP receipt to response. Carries the W3C `traceparent` header for distributed tracing.
- **HTTP Request node**: Shows the incoming POST request with its `traceparent` header and extracted attributes (method, peer IP, command name).
- **jobqueue.enqueue (blue)**: The span covering the asynchronous handoff from the RPC thread to the JobQueue worker thread. The trace context is preserved across this async boundary.
- **rpc.command.submit (orange)**: The span for the actual command execution, with child spans for deserialization, local validation, and network submission.
- **Response node**: The final output with HTTP status and total duration, marking the end of the root span.
- **Arrows (top to bottom)**: The sequential processing pipeline -- receive request, extract attributes, enqueue job, execute command, return response.
---
## 1.6 Key Trace Points
> **TxQ** = Transaction Queue
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 |
| **PathFinding** | `pathfind.request` | `PathRequest.cpp` | `doUpdate()` | High |
| **PathFinding** | `pathfind.compute` | `Pathfinder.cpp` | `findPaths()` | High |
| **TxQ** | `txq.enqueue` | `TxQ.cpp` | `apply()` | High |
| **TxQ** | `txq.apply` | `TxQ.cpp` | `processClosedLedger()` | High |
| **Fee** | `fee.escalate` | `LoadManager.cpp` | `raiseLocalFee()` | Medium |
| **Ledger** | `ledger.replay` | `LedgerReplayer.h` | `replay()` | Medium |
| **Ledger** | `ledger.delta` | `LedgerDeltaAcquire.h` | `processData()` | Medium |
| **Validator** | `validator.list.fetch` | `ValidatorList.cpp` | `verify()` | Medium |
| **Validator** | `validator.manifest` | `Manifest.cpp` | `applyManifest()` | Low |
| **Amendment** | `amendment.vote` | `AmendmentTable.cpp` | `doVoting()` | Low |
| **SHAMap** | `shamap.sync` | `SHAMap.cpp` | `fetchRoot()` | Medium |
---
## 1.7 Instrumentation Priority
> **TxQ** = Transaction Queue
```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: [0.2, 0.92]
Transaction Tracing: [0.55, 0.88]
Consensus Tracing: [0.78, 0.82]
PathFinding: [0.38, 0.75]
TxQ and Fees: [0.25, 0.65]
Ledger Sync: [0.62, 0.58]
Peer Message Tracing: [0.35, 0.25]
JobQueue Tracing: [0.2, 0.48]
Validator Mgmt: [0.48, 0.42]
Amendment Tracking: [0.15, 0.32]
SHAMap Operations: [0.72, 0.45]
```
---
## 1.8 Observable Outcomes
> **TxQ** = Transaction Queue | **UNL** = Unique Node List
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="xrpld" && tx_hash="ABC123..."}` |
| **Cross-Node Propagation** | Transaction path across multiple xrpld nodes with timing | `{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 | `{command="account_info"}` |
| **Ledger Acquisition** | Peer-to-peer ledger data requests and responses | `{span.name="ledger.acquire"}` |
| **PathFinding Latency** | Path computation time and cache effectiveness for payment RPCs | `{span.name="pathfind.compute"}` |
| **TxQ Behavior** | Queue depth, eviction patterns, fee escalation during congestion | `{span.name=~"txq.*"}` |
| **Ledger Sync** | Full acquisition timeline including delta and transaction fetches | `{span.name=~"ledger.acquire.*"}` |
| **Validator Health** | UNL fetch success, manifest updates, stale list detection | `{span.name=~"validator.*"}` |
### 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 |
| **PathFinding Latency** | Path computation time per currency pair | Heatmap by currency |
| **TxQ Depth** | Queued transactions over time | Time series with thresholds |
| **Fee Escalation Level** | Current fee multiplier | Gauge with alert thresholds |
| **Ledger Sync Duration** | Time to acquire missing ledgers | Histogram |
### 1.8.3 Concrete Dashboard Examples
**Transaction Trace View (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, 2.4, 2.8, 3.2, 3.8, 4.3, 4.5, 5.0, 4.7, 4.0, 3.2, 2.6, 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 |
| **Path Computation Slow** | pathfind.compute span shows high latency; cache miss rate in attributes | Warm the RippleLineCache, check order book depth |
| **TxQ Full** | txq.enqueue spans show evictions; fee.escalate spans increasing | Monitor fee levels, alert operators |
| **Ledger Sync Stalled** | ledger.acquire spans timing out; peer reliability attributes show issues | Check peer connectivity, add trusted peers |
| **UNL Stale** | validator.list.fetch spans failing; last_update attribute aging | Verify validator site URLs, check DNS |
### 1.8.5 Developer Debugging Workflow
1. **Find Transaction**: Query by `tx_hash` to get full trace
2. **Identify Bottleneck**: Look at span durations to find slowest component
3. **Check Attributes**: Review `validity`, `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

@@ -1,568 +0,0 @@
# Design Decisions
> **Parent Document**: [OpenTelemetryPlan.md](./OpenTelemetryPlan.md)
> **Related**: [Architecture Analysis](./01-architecture-analysis.md)
---
## 2.1 OpenTelemetry Components
> **OTLP** = OpenTelemetry Protocol
### 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_http_exporter` | OTLP/HTTP export | Yes (shipped in Phase 1b) |
| `opentelemetry-cpp::otlp_grpc_exporter` | OTLP/gRPC export | Future (not yet wired up) |
### 2.1.2 Instrumentation Strategy
**Manual Instrumentation** (recommended):
| Approach | Pros | Cons |
| ---------- | --------------------------------------------------------------- | ------------------------------------------------------- |
| **Manual** | Precise control, optimized placement, xrpld-specific attributes | More development effort |
| **Auto** | Less code, automatic coverage | Less control, potential overhead, limited customization |
---
## 2.2 Exporter Configuration
> **OTLP** = OpenTelemetry Protocol
```mermaid
flowchart TB
subgraph nodes["xrpld Nodes"]
node1["xrpld<br/>Node 1"]
node2["xrpld<br/>Node 2"]
node3["xrpld<br/>Node 3"]
end
collector["OpenTelemetry<br/>Collector<br/>(sidecar or standalone)"]
subgraph backends["Observability Backends"]
tempo["Tempo"]
elastic["Elastic<br/>APM"]
end
node1 -->|"OTLP/HTTP<br/>:4318"| collector
node2 -->|"OTLP/HTTP<br/>:4318"| collector
node3 -->|"OTLP/HTTP<br/>:4318"| collector
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
```
**Reading the diagram:**
- **xrpld Nodes (blue)**: The source of telemetry data. Each xrpld node exports spans via OTLP/HTTP on port 4318 (the only exporter shipped in Phase 1b).
- **OpenTelemetry Collector (red)**: The central aggregation point that receives spans from all nodes. Can run as a sidecar (per-node) or standalone (shared). Handles batching, filtering, and routing.
- **Observability Backends (green)**: The storage and visualization destinations. Tempo is the recommended backend for both development and production, and Elastic APM is an alternative. The Collector routes to one or more backends.
- **Arrows (nodes to collector to backends)**: The data pipeline -- spans flow from nodes to the Collector over HTTP, then the Collector fans out to the configured backends.
### 2.2.1 OTLP/HTTP (Shipped in Phase 1b)
OTLP/HTTP is the only exporter wired up in Phase 1b. It is configured via
`OtlpHttpExporterOptions` with the collector traces endpoint
(`http://localhost:4318/v1/traces` by default) and a JSON content type
(binary protobuf is also available).
### 2.2.2 OTLP/gRPC (Future Work — Planned Upgrade)
OTLP/gRPC is planned as a future upgrade from the HTTP exporter. The gRPC
transport offers lower per-span overhead and tighter back-pressure semantics
than HTTP/JSON, making it attractive for production deployments once the HTTP
path is validated in earlier phases.
Required to land this upgrade:
1. Add `opentelemetry-cpp::otlp_grpc_exporter` to the Conan recipe (the
dependency already exists but is not linked in Phase 1b builds).
2. Extend `TelemetryConfig.cpp` to parse an `exporter` key (`otlp_http`
default, `otlp_grpc` opt-in) and a gRPC endpoint override.
3. In `Telemetry::start()` branch on the parsed exporter type and construct
either `OtlpHttpExporterFactory::Create(httpOpts)` or
`OtlpGrpcExporterFactory::Create(grpcOpts)` accordingly.
4. Update the runbook and dashboards to document the alternate port and TLS
settings.
When wired up, the gRPC path will use `OtlpGrpcExporterOptions` configured with
the collector endpoint (host on port 4317), TLS credentials enabled, and a CA
certificate path.
Until that work lands, `OtlpGrpcExporterOptions` is **not** used by any code
path in Phase 1b through Phase 5.
---
## 2.3 Span Naming Conventions
> **TxQ** = Transaction Queue | **UNL** = Unique Node List | **WS** = WebSocket
### 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
| Span name | Description |
| ------------------------------ | --------------------------------------- |
| `tx.receive` | Transaction received from network |
| `tx.validate` | Transaction signature/format validation |
| `tx.process` | Full transaction processing |
| `tx.relay` | Transaction relay to peers |
| `tx.apply` | Apply transaction to ledger |
| `consensus.round` | Complete consensus round |
| `consensus.phase.open` | Open phase - collecting transactions |
| `consensus.phase.establish` | Establish phase - reaching agreement |
| `consensus.phase.accept` | Accept phase - applying consensus |
| `consensus.proposal.receive` | Receive peer proposal |
| `consensus.proposal.send` | Send our proposal |
| `consensus.validation.receive` | Receive peer validation |
| `consensus.validation.send` | Send our validation |
| `rpc.request` | HTTP/WebSocket request handling |
| `rpc.command.*` | Specific RPC command (dynamic) |
| `peer.connect` | Peer connection establishment |
| `peer.disconnect` | Peer disconnection |
| `peer.message.send` | Send protocol message |
| `peer.message.receive` | Receive protocol message |
| `ledger.acquire` | Ledger acquisition from network |
| `ledger.build` | Build new ledger |
| `ledger.validate` | Ledger validation |
| `ledger.close` | Close ledger |
| `ledger.replay` | Ledger replay executed |
| `ledger.delta` | Delta-based ledger acquired |
| `pathfind.request` | Path request initiated |
| `pathfind.compute` | Path computation executed |
| `txq.enqueue` | Transaction queued |
| `txq.apply` | Queued transaction applied |
| `fee.escalate` | Fee escalation triggered |
| `validator.list.fetch` | UNL list fetched |
| `validator.manifest` | Manifest update processed |
| `amendment.vote` | Amendment voting executed |
| `shamap.sync` | State tree synchronization |
| `job.enqueue` | Job added to queue |
| `job.execute` | Job execution |
### 2.3.3 Attribute Naming Conventions
Span **names** follow §2.3.1 (dotted `<component>.<operation>`). Span
**attribute keys** follow the rules below. The constants in the `*SpanNames.h`
headers are the single source of truth; the collector, Tempo, the Grafana
dashboards, and the runbook all consume these exact keys, so every layer must
agree with the code. A CI check enforces this end to end.
1. **Per-span unique attribute** → bare field name, allowed when the field is
recorded by a single span/workflow so the span name already supplies the
domain (e.g. `command`, `version`, `local` on `rpc.command`).
2. **Shared attribute (same concept on more than one span)** → ONE key, reused
verbatim on every span that records it; the span name tells the occurrences
apart, so no per-emitter prefix is added. Name it by the field's meaning: a
property of a domain object keeps that object's bare field name (`ledger_hash`,
`ledger_seq`, `tx_hash`, `peer_id`, `full_validation`); a field already
qualified by a sub-kind keeps that qualifier on every emitter (`proposal_trusted`
on both `consensus.proposal.receive` and `peer.proposal.receive`;
`validation_trusted` likewise). Defined once in the base `SpanNames.h`
`namespace attr` block and re-exported (`using`) by each domain header.
3. **Collision qualifier**`<domain>_<field>`, only when a bare name would
collide with a DIFFERENT concept in the shared spanmetrics label space or with
the OTel-reserved `status` key (e.g. `rpc_status`, `grpc_status`,
`consensus_phase`, `consensus_round`, `consensus_mode`). This disambiguates
distinct concepts that share a word; it is NOT used to tag the same concept
with its emitting workflow — that is rule 2 (one shared name).
4. **Resource attribute** → dotted `xrpl.<subsystem>.<field>`, reserved ONLY
for process/network identity set once at startup (`xrpl.network.id`,
`xrpl.network.type`). Span attributes are never dotted in the `xrpl.` form —
it blurs the resource/span scope boundary and parses awkwardly in TraceQL.
5. **Span names** use `<subsystem>[.<component>]` (dotted, per §2.3.1). Only
attribute _keys_ follow rules 14.
Standard OpenTelemetry semantic-convention keys keep their canonical dotted
form (e.g. `service.*` resource attributes, `http.*` span attributes); the
"no dotted form" rule applies to xrpl-custom keys only.
The same rules are recorded in `CONTRIBUTING.md` (the permanent home, since
`OpenTelemetryPlan/` is removed once the rollout completes). The attribute
examples in §2.4 below follow these rules.
---
## 2.4 Attribute Schema
> **TxQ** = Transaction Queue | **UNL** = Unique Node List | **OTLP** = OpenTelemetry Protocol
### 2.4.1 Resource Attributes (Set Once at Startup)
Resource attributes identify the process and are set once at startup. They use
the standard OpenTelemetry semantic conventions plus custom dotted `xrpl.*`
keys (the dotted form is reserved for resource scope per §2.3.3).
| Key | Type / value | Description |
| --------------------- | ------------------------------------------------------- | ------------------------------ |
| `service.name` | `"xrpld"` | Standard `SERVICE_NAME` |
| `service.version` | `build_info::getVersionString()` | Standard `SERVICE_VERSION` |
| `service.instance.id` | node public key (base58) | Standard `SERVICE_INSTANCE_ID` |
| `xrpl.network.id` | network id (e.g. 0 for mainnet) | Network identifier |
| `xrpl.network.type` | `"mainnet"` \| `"testnet"` \| `"devnet"` \| `"unknown"` | Network kind |
| `xrpl.node.type` | `"validator"` \| `"stock"` \| `"reporting"` | Node role |
| `xrpl.node.cluster` | cluster name | Cluster name, if clustered |
### 2.4.2 Span Attributes by Category
> Span attribute keys use the underscore form from §2.3.3 (shared/qualified
> keys are `<domain>_<field>`; per-span unique keys are bare). The dotted form
> is reserved for the resource attributes in §2.4.1 above. This catalog lists
> the planned attribute set by category; the exact emitted key for each
> implemented span is defined by the `*SpanNames.h` constants, which are the
> single source of truth where the two differ.
#### Transaction Attributes
| Key | Type | Description |
| -------------- | ------ | ------------------------------------- |
| `tx_hash` | string | Transaction hash (hex) |
| `tx_type` | string | `"Payment"`, `"OfferCreate"`, etc. |
| `tx_account` | string | Source account (redacted in prod) |
| `tx_sequence` | int64 | Account sequence number |
| `tx_fee` | int64 | Fee in drops |
| `tx_result` | string | `"tesSUCCESS"`, `"tecPATH_DRY"`, etc. |
| `ledger_index` | int64 | Ledger containing transaction |
| `relay_count` | int64 | Peers the transaction was relayed to |
| `suppressed` | bool | `true` when HashRouter dropped a dup |
#### Consensus Attributes
| Key | Type | Description |
| -------------------- | ------- | ----------------------------------- |
| `consensus_round` | int64 | Round number |
| `consensus_phase` | string | `"open"`, `"establish"`, `"accept"` |
| `consensus_mode` | string | `"proposing"`, `"observing"`, etc. |
| `proposers` | int64 | Number of proposers |
| `prev_ledger_prefix` | string | Previous ledger hash prefix |
| `ledger_seq` | int64 | Ledger sequence |
| `tx_count` | int64 | Transactions in consensus set |
| `round_time_ms` | float64 | Round duration |
#### RPC Attributes
| Key | Type | Description |
| ------------- | ------- | ----------------------------------------------------------------------------- |
| `command` | string | Command name (per-span unique on `rpc.command`) |
| `version` | int64 | API version |
| `rpc_role` | string | `"admin"` or `"user"` (qualified — `role` is generic) |
| `params` | string | Sanitized parameters (optional) |
| `rpc_status` | string | Response status: `success` \| `error` (qualified — `status` is OTel-reserved) |
| `duration_ms` | float64 | Request duration in milliseconds |
#### Peer & Message Attributes
| Key | Type | Description |
| -------------------- | ------- | -------------------------- |
| `peer_id` | string | Peer public key (base58) |
| `peer_address` | string | IP:port |
| `peer_latency_ms` | float64 | Measured latency |
| `peer_cluster` | string | Cluster name if clustered |
| `message_type` | string | Protocol message type name |
| `message_size_bytes` | int64 | Message size |
| `message_compressed` | bool | Whether compressed |
#### Ledger & Job Attributes
| Key | Type | Description |
| ----------------- | ------- | --------------------- |
| `ledger_hash` | string | Ledger hash |
| `ledger_index` | int64 | Ledger sequence/index |
| `close_time` | int64 | Close time (epoch) |
| `ledger_tx_count` | int64 | Transaction count |
| `job_type` | string | Job type name |
| `job_queue_ms` | float64 | Time spent in queue |
| `job_worker` | int64 | Worker thread ID |
#### PathFinding Attributes
| Key | Type | Description |
| -------------------------- | ------ | ------------------------- |
| `pathfind_source_currency` | string | Source currency code |
| `pathfind_dest_currency` | string | Destination currency code |
| `pathfind_path_count` | int64 | Number of paths found |
| `pathfind_cache_hit` | bool | RippleLineCache hit |
#### TxQ Attributes
| Key | Type | Description |
| --------------------- | ------ | --------------------------- |
| `txq_queue_depth` | int64 | Current queue depth |
| `txq_fee_level` | int64 | Fee level of transaction |
| `txq_eviction_reason` | string | Why transaction was evicted |
#### Fee Attributes
| Key | Type | Description |
| ---------------------- | ----- | ------------------------- |
| `fee_load_factor` | int64 | Current load factor |
| `fee_escalation_level` | int64 | Fee escalation multiplier |
#### Validator Attributes
| Key | Type | Description |
| ------------------------ | ----- | ------------------------- |
| `validator_list_size` | int64 | UNL size |
| `validator_list_age_sec` | int64 | Seconds since last update |
#### Amendment Attributes
| Key | Type | Description |
| ------------------ | ------ | -------------------------------------- |
| `amendment_name` | string | Amendment name |
| `amendment_status` | string | `"enabled"`, `"vetoed"`, `"supported"` |
#### SHAMap Attributes
| Key | Type | Description |
| ---------------------- | ------- | --------------------------------------------- |
| `shamap_type` | string | `"transaction"`, `"state"`, `"account_state"` |
| `shamap_missing_nodes` | int64 | Number of missing nodes during sync |
| `shamap_duration_ms` | float64 | Sync duration |
### 2.4.3 Data Collection Summary
The following table summarizes what data is collected by category:
| Category | Attributes Collected | Purpose |
| --------------- | ------------------------------------------------------------------------------------------------- | ---------------------------- |
| **Transaction** | `tx_hash`, `tx_type`, `tx_result`, `tx_fee`, `ledger_index` | Trace transaction lifecycle |
| **Consensus** | `consensus_round`, `consensus_phase`, `consensus_mode`, `proposers`, `round_time_ms` | Analyze consensus timing |
| **RPC** | `command`, `version`, `rpc_status`, `duration_ms` | Monitor RPC performance |
| **Peer** | `peer_id` (public key), `peer_latency_ms`, `message_type`, `message_size_bytes` | Network topology analysis |
| **Ledger** | `ledger_hash`, `ledger_index`, `close_time`, `ledger_tx_count` | Ledger progression tracking |
| **Job** | `job_type`, `job_queue_ms`, `job_worker` | JobQueue performance |
| **PathFinding** | `pathfind_source_currency`, `pathfind_dest_currency`, `pathfind_path_count`, `pathfind_cache_hit` | Payment path analysis |
| **TxQ** | `txq_queue_depth`, `txq_fee_level`, `txq_eviction_reason` | Queue depth and fee tracking |
| **Fee** | `fee_load_factor`, `fee_escalation_level` | Fee escalation monitoring |
| **Validator** | `validator_list_size`, `validator_list_age_sec` | UNL health monitoring |
| **Amendment** | `amendment_name`, `amendment_status` | Protocol upgrade tracking |
| **SHAMap** | `shamap_type`, `shamap_missing_nodes`, `shamap_duration_ms` | State tree sync performance |
### 2.4.4 Privacy & Sensitive Data Policy
> **PII** = Personally Identifiable Information
OpenTelemetry instrumentation is designed to collect **operational metadata only**, never sensitive content.
#### Data NOT Collected
The following data is explicitly **excluded** from telemetry collection:
| Excluded Data | Reason |
| ----------------------- | ----------------------------------------- |
| **Private Keys** | Never exposed; not relevant to tracing |
| **Account Balances** | Financial data; privacy sensitive |
| **Transaction Amounts** | Financial data; privacy sensitive |
| **Raw TX Payloads** | May contain sensitive memo/data fields |
| **Personal Data** | No PII collected |
| **IP Addresses** | Configurable; excluded by default in prod |
#### Privacy Protection Mechanisms
| Mechanism | Description |
| ----------------------------- | --------------------------------------------------------------------------------------------------------------------------------------- |
| **Account Hashing** | `tx_account` is hashed at collector level before storage |
| **Configurable Redaction** | Sensitive fields can be excluded via `[telemetry]` config section |
| **Collector Tail Sampling** | xrpld head sampling is fixed at 1.0 (every span emitted); the collector retains ~10% of non-error traces, reducing stored data exposure |
| **Local Control** | Node operators have full control over what gets exported |
| **No Raw Payloads** | Transaction content is never recorded, only metadata (hash, type, result) |
| **Collector-Level Filtering** | Additional redaction/hashing can be configured at OTel Collector |
#### Collector-Level Data Protection
The OpenTelemetry Collector can be configured (via an `attributes` processor)
to hash or redact sensitive attributes before export — for example, hashing
`tx_account`, deleting `peer_address` to drop IP addresses, and deleting
`params` to redact request parameters.
#### Configuration Options for Privacy
In `xrpld.cfg`, operators control data collection granularity through the
`[telemetry]` section. Besides `enabled`, per-component toggles
(`trace_transactions`, `trace_consensus`, `trace_rpc`, `trace_peer` — the last
often disabled due to high volume) select which spans are emitted, and
redaction flags (`redact_account` to hash account addresses, `redact_peer_address`
to remove peer IP addresses) control SDK-level redaction before export.
> **Note**: The `redact_account` configuration in `xrpld.cfg` controls SDK-level redaction before export, while collector-level filtering (see [Collector-Level Data Protection](#collector-level-data-protection) above) provides an additional defense-in-depth layer. Both can operate independently.
> **Key Principle**: Telemetry collects **operational metadata** (timing, counts, hashes) — never **sensitive content** (keys, balances, amounts, raw payloads).
---
## 2.5 Context Propagation Design
> **WS** = WebSocket
### 2.5.1 Propagation Boundaries
```mermaid
flowchart TB
subgraph http["HTTP/WebSocket (RPC)"]
w3c["W3C Trace Context Headers:<br/>traceparent:<br/>00-trace_id-span_id-flags<br/>tracestate: xrpld=..."]
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/> otel::context::Context<br/> 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
```
**Reading the diagram:**
- **HTTP/WebSocket - RPC (blue)**: For client-facing RPC requests, trace context is propagated using the W3C `traceparent` header. This is the standard approach and works with any OTel-compatible client.
- **Protocol Buffers - P2P (green)**: For peer-to-peer messages between xrpld nodes, trace context is embedded as a protobuf `TraceContext` message carrying trace_id, span_id, flags, and optional trace_state.
- **JobQueue - Internal Async (red)**: For asynchronous work within a single node, the OTel context is captured when a job is created and restored when the job executes on a worker thread. This bridges the async gap so spans remain linked.
---
## 2.6 Integration with Existing Observability
> **OTLP** = OpenTelemetry Protocol | **WS** = WebSocket
### 2.6.1 Existing Frameworks Comparison
xrpld 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
A PerfLog entry is a JSON object with fields such as `time`, `method`,
`duration_us`, and `result`.
#### 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
In xrpld, Beast Insight is used through `increment` (counters), `gauge`
(point-in-time values), and `timing` (durations) calls.
#### 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
A span is created via `startSpan` (e.g. `"tx.relay"`), annotated with
attributes such as `tx_hash` and `peer_id`, and is automatically linked to its
parent through the active 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 xrpld["xrpld 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 xrpld fill:#212121,stroke:#0a0a0a,color:#ffffff
style grafana fill:#bf360c,stroke:#8c2809,color:#ffffff
```
**Reading the diagram:**
- **xrpld Process (dark gray)**: The single xrpld node running all three observability frameworks side by side. Each framework operates independently with no interference.
- **PerfLog to perf.log**: PerfLog writes JSON-formatted event logs to a local file. Grafana can ingest these via Loki or a file-based datasource.
- **Beast Insight to StatsD Server**: Insight sends aggregated metrics (counters, gauges) over UDP to a StatsD server. Grafana reads from StatsD-compatible backends like Graphite or Prometheus (via StatsD exporter).
- **OpenTelemetry to OTLP Collector**: OTel exports spans over OTLP/HTTP to a Collector, which then forwards to a trace backend (Tempo). (OTLP/gRPC is future work — §2.2.2.)
- **Grafana (red, unified UI)**: All three data streams converge in Grafana, enabling operators to correlate logs, metrics, and traces in a single dashboard.
### 2.6.5 Correlation with PerfLog
Trace IDs can be correlated with existing PerfLog entries for comprehensive
debugging. The design is for `RPCHandler.cpp` to start an `rpc.command.<method>`
span alongside the existing PerfLog `rpcStart`/`rpcFinish`/`rpcError` calls,
extract the span's `trace_id` (when valid), and eventually stamp it onto the
PerfLog entry (a planned `setTraceId` hook) so logs and traces share a key. The
span status is set to OK on success or to error (recording the exception) on
failure.
---
_Previous: [Architecture Analysis](./01-architecture-analysis.md)_ | _Next: [Implementation Strategy](./03-implementation-strategy.md)_ | _Back to: [Overview](./OpenTelemetryPlan.md)_

View File

@@ -1,415 +0,0 @@
# Implementation Strategy
> **Parent Document**: [OpenTelemetryPlan.md](./OpenTelemetryPlan.md)
> **Related**: [Configuration Reference](./05-configuration-reference.md)
---
## 3.1 Directory Structure
The telemetry implementation follows xrpld'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
> **OTLP** = OpenTelemetry Protocol
| Metric | Overhead | Notes |
| ------------- | ---------- | ------------------------------------------------ |
| CPU | 1-3% | Of per-transaction CPU cost (~200μs baseline) |
| Memory | ~10 MB | SDK statics + batch buffer + worker thread stack |
| 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
> **Note on hardware assumptions**: The costs below are based on the official OTel C++ SDK CI benchmarks
> (969 runs on GitHub Actions 2-core shared runners). On production server hardware (3+ GHz Xeon),
> expect costs at the **lower end** of each range (~30-50% improvement over CI hardware).
| Operation | Time (ns) | Frequency | Impact |
| --------------------- | --------- | ---------------------- | ---------- |
| Span creation | 500-1000 | 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 | 100-200 | 0-2 per span | Low |
| Context injection | 150-250 | Per outgoing message | Low |
| Context extraction | 100-180 | Per incoming message | Low |
| GetCurrent context | 10-20 | Thread-local access | Negligible |
**Source**: Span creation based on OTel C++ SDK `BM_SpanCreation` benchmark (AlwaysOnSampler +
SimpleSpanProcessor + InMemoryExporter), median ~1,000 ns on CI hardware. AddEvent includes
timestamp read + string copy + vector push + mutex acquisition. Context injection/extraction
confirmed by `BM_SpanCreationWithScope` benchmark delta (~160 ns).
### 3.4.2 Transaction Processing Overhead
<div align="center">
```mermaid
%%{init: {'pie': {'textPosition': 0.75}}}%%
pie showData
"tx.receive (1400ns)" : 1400
"tx.validate (1200ns)" : 1200
"tx.relay (1200ns)" : 1200
"Context inject (200ns)" : 200
```
**Transaction Tracing Overhead (~4.0μs total)**
</div>
**Overhead percentage**: 4.0 μs / 200 μs (avg tx processing) = **~2.0%**
> **Breakdown**: Each span (tx.receive, tx.validate, tx.relay) costs ~1,000 ns for creation plus
> ~200-400 ns for 3-5 attribute sets. Context injection is ~200 ns (confirmed by benchmarks).
> On production hardware, expect ~2.6 μs total (~1.3% overhead) due to faster span creation (~500-600 ns).
### 3.4.3 Consensus Round Overhead
| Operation | Count | Cost (ns) | Total |
| ---------------------- | ----- | --------- | ---------- |
| consensus.round span | 1 | ~1200 | ~1.2 μs |
| consensus.phase spans | 3 | ~1100 | ~3.3 μs |
| proposal.receive spans | ~20 | ~1100 | ~22 μs |
| proposal.send spans | ~3 | ~1100 | ~3.3 μs |
| Context operations | ~30 | ~200 | ~6 μs |
| **TOTAL** | | | **~36 μs** |
> **Why higher**: Each span costs ~1,000 ns creation + ~100-200 ns for 1-2 attributes, totaling ~1,100-1,200 ns.
> Context operations remain ~200 ns (confirmed by benchmarks). On production hardware, expect ~24 μs total.
**Overhead percentage**: 36 μs / 3s (typical round) = **~0.001%** (negligible)
### 3.4.4 RPC Request Overhead
| Operation | Cost (ns) |
| ---------------- | ------------ |
| rpc.request span | ~1200 |
| rpc.command span | ~1100 |
| Context extract | ~250 |
| Context inject | ~200 |
| **TOTAL** | **~2.75 μs** |
> **Why higher**: Each span costs ~1,000 ns creation + ~100-200 ns for attributes (command name,
> version, role). Context extract/inject costs are confirmed by OTel C++ benchmarks.
- Fast RPC (1ms): 2.75 μs / 1ms = **~0.275%**
- Slow RPC (100ms): 2.75 μs / 100ms = **~0.003%**
---
## 3.5 Memory Overhead Analysis
> **OTLP** = OpenTelemetry Protocol
### 3.5.1 Static Memory
| Component | Size | Allocated |
| ------------------------------------ | ----------- | ---------- |
| TracerProvider singleton | ~64 KB | At startup |
| BatchSpanProcessor (circular buffer) | ~16 KB | At startup |
| BatchSpanProcessor (worker thread) | ~8 MB | At startup |
| OTLP/HTTP exporter (client init) | ~64 KB | At startup |
| Propagator registry | ~8 KB | At startup |
| **Total static** | **~8.1 MB** | |
> **Why higher than earlier estimate**: The BatchSpanProcessor's circular buffer itself is only ~16 KB
> (2049 x 8-byte `AtomicUniquePtr` entries), but it spawns a dedicated worker thread whose default
> stack size on Linux is ~8 MB. The OTLP/HTTP exporter allocates a small client and TLS
> initialization buffer. The worker thread stack dominates the static footprint.
### 3.5.2 Dynamic Memory
| Component | Size per unit | Max units | Peak |
| -------------------- | -------------- | ---------- | --------------- |
| Active span | ~500-800 bytes | 1000 | ~500-800 KB |
| Queued span (export) | ~500 bytes | 2048 | ~1 MB |
| Attribute storage | ~80 bytes | 5 per span | Included |
| Context storage | ~64 bytes | Per thread | ~6.4 KB |
| **Total dynamic** | | | **~1.5-1.8 MB** |
> **Why active spans are larger**: An active `Span` object includes the wrapper (~88 bytes: shared_ptr,
> mutex, unique_ptr to Recordable) plus `SpanData` (~250 bytes: SpanContext, timestamps, name, status,
> empty containers) plus attribute storage (~200-500 bytes for 3-5 string attributes in a `std::map`).
> Source: `sdk/src/trace/span.h` and `sdk/include/opentelemetry/sdk/trace/span_data.h`.
> Queued spans release the wrapper, keeping only `SpanData` + attributes (~500 bytes).
### 3.5.3 Memory Growth Characteristics
```mermaid
---
config:
xyChart:
width: 700
height: 400
---
xychart-beta
title "Memory Usage vs Span Rate (bounded by queue limit)"
x-axis "Spans/second" [0, 200, 400, 600, 800, 1000]
y-axis "Memory (MB)" 0 --> 12
line [8.5, 9.2, 9.6, 9.9, 10.0, 10.0]
```
**Notes**:
- Memory increases with span rate but **plateaus at queue capacity** (default 2048 spans)
- Batch export prevents unbounded growth
- At queue limit, oldest spans are dropped (not blocked)
- Maximum memory is bounded: ~8.3 MB static (dominated by worker thread stack) + 2048 queued spans x ~500 bytes (~1 MB) + active spans (~0.8 MB) ≈ **~10 MB ceiling**
- The worker thread stack (~8 MB) is virtual memory; actual RSS depends on stack usage (typically much less)
> **Measured outcome**: A perf-iac comparison (telemetry compiled-in + enabled vs compiled-out,
> 9 nodes — validators and client-handlers — under sustained payment load) recorded **no measurable
> RSS increase over the telemetry-off baseline** (~15 GiB mean / ~1819 GiB peak on both sides),
> with no OOM, no swap, and no leak across the run. The ~10 MB ceiling above is therefore a
> provisioning safety margin (dominated by virtual thread-stack address space), not an expected
> resident-memory increase. Steady-state cost shows up as throughput (~34% at head sampling 1.0),
> not memory.
### 3.5.4 Performance Data Sources
The overhead estimates in Sections 3.3-3.5 are derived from the following sources:
| Source | What it covers | URL |
| ------------------------------------------------ | ----------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------ |
| OTel C++ SDK CI benchmarks (969 runs) | Span creation, context activation, sampler overhead | [Benchmark Dashboard](https://open-telemetry.github.io/opentelemetry-cpp/benchmarks/) |
| `api/test/trace/span_benchmark.cc` | API-level span creation (~22 ns no-op) | [Source](https://github.com/open-telemetry/opentelemetry-cpp/blob/main/api/test/trace/span_benchmark.cc) |
| `sdk/test/trace/sampler_benchmark.cc` | SDK span creation with samplers (~1,000 ns AlwaysOn) | [Source](https://github.com/open-telemetry/opentelemetry-cpp/blob/main/sdk/test/trace/sampler_benchmark.cc) |
| `sdk/include/.../span_data.h` | SpanData memory layout (~250 bytes base) | [Source](https://github.com/open-telemetry/opentelemetry-cpp/blob/main/sdk/include/opentelemetry/sdk/trace/span_data.h) |
| `sdk/src/trace/span.h` | Span wrapper memory layout (~88 bytes) | [Source](https://github.com/open-telemetry/opentelemetry-cpp/blob/main/sdk/src/trace/span.h) |
| `sdk/include/.../batch_span_processor_options.h` | Default queue size (2048), batch size (512) | [Source](https://github.com/open-telemetry/opentelemetry-cpp/blob/main/sdk/include/opentelemetry/sdk/trace/batch_span_processor_options.h) |
| `sdk/include/.../circular_buffer.h` | CircularBuffer implementation (AtomicUniquePtr array) | [Source](https://github.com/open-telemetry/opentelemetry-cpp/blob/main/sdk/include/opentelemetry/sdk/common/circular_buffer.h) |
| OTLP proto definition | Serialized span size estimation | [Proto](https://github.com/open-telemetry/opentelemetry-proto/blob/main/opentelemetry/proto/trace/v1/trace.proto) |
---
## 3.6 Network Overhead Analysis
### 3.6.1 Export Bandwidth
> **Bytes per span**: Estimates use ~500 bytes/span (conservative upper bound). OTLP protobuf analysis
> shows a typical span with 3-5 string attributes serializes to ~200-300 bytes raw; with gzip
> compression (~60-70% of raw) and batching (amortized headers), ~350 bytes/span is more realistic.
> The table uses the conservative estimate for capacity planning.
| 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 | 25 bytes | ~100 | ~2.5 KB/s |
| TMProposeSet | 25 bytes | ~10 | ~250 B/s |
| TMValidation | 25 bytes | ~50 | ~1.25 KB/s |
| **Total P2P overhead** | | | **~4 KB/s** |
---
## 3.7 Optimization Strategies
### 3.7.1 Sampling Strategies
#### Tail Sampling
```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
Instrumentation is gated on two levels. A compile-time feature flag (`XRPL_ENABLE_TELEMETRY`) reduces the trace macros to no-ops when telemetry is built out, so disabled builds carry zero cost. At runtime, per-component guards (e.g. `shouldTracePeer()`) skip span creation for components whose tracing is turned off, incurring no overhead beyond a single boolean check.
---
## 3.8 Links to Detailed Documentation
- **[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
> **TxQ** = Transaction Queue
This section provides a detailed assessment of how intrusive the OpenTelemetry integration is to the existing xrpld codebase.
### 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, 0.55]
Transaction Relay: [0.55, 0.85]
Consensus Tracing: [0.75, 0.92]
Peer Message Tracing: [0.85, 0.35]
JobQueue Context: [0.3, 0.42]
Ledger Acquisition: [0.48, 0.65]
PathFinding: [0.38, 0.72]
TxQ and Fees: [0.25, 0.62]
Validator Mgmt: [0.15, 0.35]
```
**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** | Minimal | Read-only instrumentation; no modification to consensus or transaction data flow |
| **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):** Instrumenting an RPC handler adds roughly 3-4 lines: one macro to start the span and one or two `setAttribute` calls (command name, status). The span ends automatically via RAII, so the existing control flow — process the request, send the result — is untouched.
**Consensus Instrumentation (Medium Intrusiveness):** Consensus is slightly more intrusive because child spans in later phase transitions need the round's context. Beyond the span-start and attribute macros, this requires storing the active context in a new member variable (`currentRoundContext_`) at round start. The existing round logic itself remains unchanged.
---
_Previous: [Design Decisions](./02-design-decisions.md)_ | _Next: [Configuration Reference](./05-configuration-reference.md)_ | _Back to: [Overview](./OpenTelemetryPlan.md)_

View File

@@ -1,265 +0,0 @@
# Configuration Reference
> **Parent Document**: [OpenTelemetryPlan.md](./OpenTelemetryPlan.md)
> **Related**: [Implementation Phases](./06-implementation-phases.md)
---
## 5.1 xrpld Configuration
> **OTLP** = OpenTelemetry Protocol | **TxQ** = Transaction Queue
### 5.1.1 Configuration File Section
The authoritative `[telemetry]` example lives in `cfg/xrpld-example.cfg`. Telemetry is disabled by default (`enabled=0`); enabling it turns on distributed tracing for transaction flow, consensus, and RPC calls, with traces exported to an OpenTelemetry Collector over OTLP. Head sampling is intentionally fixed at 1.0 (sample everything) and is not configurable — per-node head-sampling would produce broken/partial distributed traces, so volume reduction is delegated to the collector's tail sampling (see Section 7.4.2). The full option reference follows.
### 5.1.2 Configuration Options Summary
| Option | Type | Default | Description |
| --------------------- | ------ | --------------------------------- | ---------------------------------------------------- |
| `enabled` | bool | `false` | Enable/disable telemetry |
| `endpoint` | string | `http://localhost:4318/v1/traces` | OTLP/HTTP collector endpoint |
| `use_tls` | bool | `false` | Enable TLS for exporter connection |
| `tls_ca_cert` | string | `""` | Path to CA certificate file |
| `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 | `true` | Enable peer message tracing (high volume) |
| `trace_ledger` | bool | `true` | Enable ledger tracing |
| `service_name` | string | `"xrpld"` | Service name (`service.name`) for traces and metrics |
| `service_instance_id` | string | `<node_pubkey>` | Instance identifier |
**Planned (not yet implemented)**: the following options appear in the design
documents but are not parsed by `TelemetryConfig.cpp` in Phase 1b and later
phases. They will be added as the corresponding subsystems are instrumented:
| Option | Planned Phase | Purpose |
| -------------------------- | ------------- | ----------------------------------------------------------------------- |
| `exporter` | Future | Select between OTLP/HTTP and OTLP/gRPC |
| `trace_pathfind` | Phase 2 | Path computation tracing toggle |
| `trace_txq` | Phase 3 | Transaction queue tracing toggle |
| `trace_validator` | Future | Validator list / manifest update tracing |
| `trace_amendment` | Future | Amendment voting tracing |
| `consensus_trace_strategy` | Phase 4 | Trace ID strategy for consensus rounds (`deterministic` \| `attribute`) |
---
## 5.2 Configuration Parser
> **TxQ** = Transaction Queue
The parser `setup_Telemetry()` in `src/libxrpl/telemetry/TelemetryConfig.cpp` reads the `[telemetry]` `Section` and populates a `Telemetry::Setup` struct, applying the defaults listed in Section 5.1.2 via `section.value_or(...)`. It derives `serviceInstanceId` from the node public key when not overridden, selects the exporter endpoint default by exporter type, and leaves the sampling ratio at its fixed 1.0 default (not read from config — see Section 7.4.2).
---
## 5.3 Application Integration
### 5.3.1 ApplicationImp Changes
> **Deferred identity**: The node public key (`nodeIdentity_`) is not
> available during `ApplicationImp`'s member initializer list — it is
> resolved later in `setup()`. The `Telemetry` object is therefore
> constructed with an empty `serviceInstanceId` and patched via
> `setServiceInstanceId()` once `setup()` has called `getNodeIdentity()`.
`ApplicationImp` (in `src/xrpld/app/main/Application.cpp`) owns a `std::unique_ptr<telemetry::Telemetry> telemetry_`. It is built in the member initializer list via `make_Telemetry(setup_Telemetry(...))` with an empty `serviceInstanceId`, then patched in `setup()` by calling `setServiceInstanceId()` with the Base58 node public key (unless the user supplied a custom `service_instance_id`). `start()` and `run()` forward to `telemetry_->start()` / `telemetry_->stop()`, and `getTelemetry()` returns the owned instance.
### 5.3.2 ServiceRegistry Interface Addition
`include/xrpl/core/ServiceRegistry.h` gains a pure-virtual `telemetry::Telemetry& getTelemetry()` (with a forward declaration of `telemetry::Telemetry`), giving every component a uniform accessor for the tracing subsystem.
> **Note:** `Application` extends `ServiceRegistry`, so `getTelemetry()` is
> available on both. Components that hold a `ServiceRegistry&` (e.g.
> `NetworkOPsImp`) call `registry_.get().getTelemetry()`. Components that
> still hold an `Application&` (e.g. `ServerHandler`, `PeerImp`,
> `RCLConsensusAdaptor`) call `app_.getTelemetry()` directly.
---
## 5.4 CMake Integration
> **OTLP** = OpenTelemetry Protocol
### 5.4.1 Find OpenTelemetry Module
A `cmake/FindOpenTelemetry.cmake` module locates the OpenTelemetry C++ SDK. It first tries `find_package(opentelemetry-cpp CONFIG)`, aliasing the imported targets `OpenTelemetry::api`, `OpenTelemetry::sdk`, and `OpenTelemetry::otlp_grpc_exporter`, and falls back to `pkg-config` when no CMake config package is present.
### 5.4.2 CMakeLists.txt Changes
The top-level `CMakeLists.txt` adds an `XRPL_ENABLE_TELEMETRY` option (default `OFF`). When enabled, it runs `find_package(OpenTelemetry REQUIRED)`, defines the `XRPL_ENABLE_TELEMETRY` compile flag, and builds the `xrpl_telemetry` library from the real telemetry sources linked against the OpenTelemetry targets; when disabled, it builds the same target from a no-op `NullTelemetry.cpp` so call sites compile unchanged.
---
## 5.5 OpenTelemetry Collector Configuration
> **OTLP** = OpenTelemetry Protocol | **APM** = Application Performance Monitoring
The authoritative collector config lives in the repo at `docker/telemetry/otel-collector-config.yaml` (with Tempo backend config in `docker/telemetry/tempo.yaml`). The sections below summarize the development and production shapes of that pipeline.
### 5.5.1 Development Configuration
The development collector enables an OTLP receiver on both gRPC (`0.0.0.0:4317`) and HTTP (`0.0.0.0:4318`), a single `batch` processor (1s timeout, batch size 100), and two exporters: a `logging` exporter for console debugging and `otlp/tempo` (insecure) for trace visualization. The single `traces` pipeline wires receiver → batch → both exporters.
### 5.5.2 Production Configuration
The production collector adds TLS on the OTLP gRPC receiver and a richer processor chain: a `memory_limiter` (OOM guard), `batch` (5s timeout, size 512), `tail_sampling`, and an `attributes` processor that hashes sensitive fields (e.g. `tx_account`) and stamps `deployment.environment`. Tail sampling keeps all `ERROR` traces, slow consensus rounds (>5s) and slow RPC requests (>1s), and probabilistically samples the remainder at 10%. Exporters target Grafana Tempo (TLS) and Elastic APM; `health_check` and `zpages` extensions are enabled for operability.
---
## 5.6 Docker Compose Development Environment
> **OTLP** = OpenTelemetry Protocol
The authoritative development stack lives in the repo at `docker/telemetry/docker-compose.yml`. It brings up four services on a shared `xrpld-telemetry` network: an `otel-collector` (otel/opentelemetry-collector-contrib) exposing OTLP gRPC `4317`, OTLP HTTP `4318`, and health check `13133`; `tempo` for trace storage/visualization; `grafana` with provisioned datasources and dashboards (anonymous admin enabled); and an optional `prometheus` for metric correlation.
---
## 5.7 Configuration Architecture
> **OTLP** = OpenTelemetry Protocol
```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
```
**Reading the diagram:**
- **Configuration Sources**: `xrpld.cfg` provides runtime settings (endpoint, per-component trace toggles) while the CMake flag controls whether telemetry is compiled in at all. Head sampling is fixed at 1.0 and is not a config option; volume reduction happens via tail sampling in the collector.
- **Initialization**: `setup_Telemetry()` parses config values, then `make_Telemetry()` constructs the provider, processor, and exporter objects.
- **Runtime Components**: The `TracerProvider` creates spans, the `BatchProcessor` buffers them, and the `OTLP Exporter` serializes and sends them over the wire.
- **OTLP arrow to Collector**: Trace data leaves the xrpld process via OTLP/HTTP and enters the external Collector pipeline. (OTLP/gRPC is future work — see design decisions §2.2.2.)
- **Collector Pipeline**: `Receivers` ingest OTLP data, `Processors` apply sampling/filtering/enrichment, and `Exporters` forward traces to storage backends (Tempo, etc.).
---
## 5.8 Grafana Integration
> **APM** = Application Performance Monitoring
Step-by-step instructions for integrating xrpld traces with Grafana.
### 5.8.1 Data Source Configuration
#### Tempo (Recommended)
A Tempo datasource (`grafana/provisioning/datasources/tempo.yaml`, provisioned from `docker/telemetry/grafana/`) points at `http://tempo:3200` and enables `tracesToLogs` (linking to Loki on `service.name`/`tx_hash` and mapping `trace_id``traceID`), `serviceMap` against Prometheus, the node graph, and Loki search.
#### Elastic APM
Alternatively, an Elasticsearch datasource (`grafana/provisioning/datasources/elastic-apm.yaml`) of type `elasticsearch` points at `http://elasticsearch:9200` against the `apm-*` index, using `@timestamp` as the time field and mapping the log message/level fields.
### 5.8.2 Dashboard Provisioning
A dashboard provider (`grafana/provisioning/dashboards/dashboards.yaml`) loads the `xrpld` dashboard folder from disk (`/var/lib/grafana/dashboards/rippled`), polling for changes every 30s with deletion disabled.
### 5.8.3 Example Dashboard: RPC Performance
An example `xrpld RPC Performance` dashboard (uid `xrpld-rpc-performance`) sourced from Tempo via TraceQL provides four panels: RPC latency by command (heatmap), RPC error rate by command (timeseries), the top 10 slowest RPC commands by average duration (table), and a recent-traces table.
### 5.8.4 Example Dashboard: Transaction Tracing
An example `xrpld Transaction Tracing` dashboard (uid `xrpld-tx-tracing`) over Tempo provides three panels: transaction throughput (`tx.receive` rate, stat), cross-node relay count (average `span.relay_count` on `tx.relay`, timeseries), and a table of transaction validation errors (`tx.validate` with `status.code=error`).
### 5.8.5 TraceQL Query Examples
Common queries for xrpld traces:
```
# Find all traces for a specific transaction hash
{resource.service.name="xrpld" && span.tx_hash="ABC123..."}
# Find slow RPC commands (>100ms)
{resource.service.name="xrpld" && name=~"rpc.command.*"} | duration > 100ms
# Find consensus rounds taking >5 seconds
{resource.service.name="xrpld" && name="consensus.round"} | duration > 5s
# Find failed transactions with error details
{resource.service.name="xrpld" && name="tx.validate" && status.code=error}
# Find transactions relayed to many peers
{resource.service.name="xrpld" && name="tx.relay"} | span.relay_count > 10
# Compare latency across nodes
{resource.service.name="xrpld" && 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**
Configure a Promtail scrape job (`promtail-config.yaml`) that tails `/var/log/rippled/perf*.log`, parses each JSON line, and promotes `trace_id`, `ledger_seq`, and `tx_hash` to Loki labels.
**Step 2: Add trace_id to PerfLog entries**
Modify PerfLog so its JSON output includes a `trace_id` field whenever a valid span is active: fetch the current span from the OpenTelemetry runtime context, and if its context is valid, render the trace ID as a 32-character lowercase hex string into the log entry.
**Step 3: Configure Grafana trace-to-logs link**
In the Tempo datasource, set the `tracesToLogs` derived field to link to Loki on the `trace_id` and `tx_hash` tags, with `filterByTraceID: true`.
### 5.8.7 Correlation with Insight/StatsD Metrics
To correlate traces with existing Beast Insight metrics:
**Step 1: Export Insight metrics to Prometheus**
Add a Prometheus scrape job (`prometheus.yaml`) named `xrpld-statsd` targeting the StatsD exporter at `statsd-exporter:9102`.
**Step 2: Add exemplars to metrics**
The OpenTelemetry SDK automatically adds exemplars (trace IDs) to metrics when using the Prometheus exporter, linking metric spikes to specific traces.
**Step 3: Configure Grafana metric-to-trace link**
In the Prometheus datasource, set `exemplarTraceIdDestinations` to map the `trace_id` exemplar to the Tempo datasource.
**Step 4: Dashboard panel with exemplars**
Add a timeseries panel over Prometheus (e.g. `histogram_quantile(0.99, rate(xrpld_rpc_duration_seconds_bucket[5m]))`) with `exemplar: true` enabled.
This allows clicking on metric data points to jump directly to the related trace.
---
_Previous: [Implementation Strategy](./03-implementation-strategy.md)_ | _Next: [Implementation Phases](./06-implementation-phases.md)_ | _Back to: [Overview](./OpenTelemetryPlan.md)_

View File

@@ -1,575 +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
> **TxQ** = Transaction Queue
```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
Buffer & Integration :p1e, after p1d, 2d
section Phase 2
RPC Tracing :p2, after p1, 2w
HTTP Context Extraction :p2a, after p1, 2d
RPC Handler Instrumentation :p2b, after p2a, 4d
PathFinding Instrumentation :p2f, after p2b, 2d
TxQ Instrumentation :p2g, after p2f, 2d
WebSocket Support :p2c, after p2g, 2d
Integration Tests :p2d, after p2c, 2d
Buffer & Review :p2e, after p2d, 4d
section Phase 3
Transaction Tracing :p3, after p2, 2w
Protocol Buffer Extension :p3a, after p2, 2d
PeerImp Instrumentation :p3b, after p3a, 3d
Fee Escalation Instrumentation :p3f, after p3b, 2d
Relay Context Propagation :p3c, after p3f, 3d
Multi-node Tests :p3d, after p3c, 2d
Buffer & Review :p3e, after p3d, 4d
section Phase 4
Consensus Tracing :p4, after p3, 2w
Consensus Round Spans :p4a, after p3, 3d
Proposal Handling :p4b, after p4a, 3d
Validator List & Manifest Tracing :p4f, after p4b, 2d
Amendment Voting Tracing :p4g, after p4f, 2d
SHAMap Sync Tracing :p4h, after p4g, 2d
Validation Tests :p4c, after p4h, 4d
Buffer & Review :p4e, after p4c, 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 |
| ---- | ----------------------------------------------------- |
| 1.1 | Add OpenTelemetry C++ SDK to Conan/CMake |
| 1.2 | Implement `Telemetry` interface and factory |
| 1.3 | Implement `SpanGuard` RAII wrapper |
| 1.4 | Implement configuration parser |
| 1.5 | Integrate into `ApplicationImp` |
| 1.6 | Add conditional compilation (`XRPL_ENABLE_TELEMETRY`) |
| 1.7 | Create `NullTelemetry` no-op implementation |
| 1.8 | Unit tests for core infrastructure |
### 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)
> **TxQ** = Transaction Queue
**Objective**: Complete tracing for all RPC operations
### Tasks
| Task | Description |
| ---- | -------------------------------------------------------------------------- |
| 2.1 | Implement W3C Trace Context HTTP header extraction |
| 2.2 | Instrument `ServerHandler::onRequest()` |
| 2.3 | Instrument `RPCHandler::doCommand()` |
| 2.4 | Add RPC-specific attributes |
| 2.5 | Instrument WebSocket handler |
| 2.6 | PathFinding instrumentation (`pathfind.request`, `pathfind.compute` spans) |
| 2.7 | TxQ instrumentation (`txq.enqueue`, `txq.apply` spans) |
| 2.8 | Integration tests for RPC tracing |
| 2.9 | Performance benchmarks |
| 2.10 | Documentation |
### 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 |
| ---- | ---------------------------------------------------- |
| 3.1 | Define `TraceContext` Protocol Buffer message |
| 3.2 | Implement protobuf context serialization |
| 3.3 | Instrument `PeerImp::handleTransaction()` |
| 3.4 | Instrument `NetworkOPs::submitTransaction()` |
| 3.5 | Instrument HashRouter integration |
| 3.6 | Fee escalation instrumentation (`fee.escalate` span) |
| 3.7 | Implement relay context propagation |
| 3.8 | Integration tests (multi-node) |
| 3.9 | Performance benchmarks |
### 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 |
| ---- | ---------------------------------------------- |
| 4.1 | Instrument `RCLConsensusAdaptor::startRound()` |
| 4.2 | Instrument phase transitions |
| 4.3 | Instrument proposal handling |
| 4.4 | Instrument validation handling |
| 4.5 | Add consensus-specific attributes |
| 4.6 | Correlate with transaction traces |
| 4.7 | Validator list and manifest tracing |
| 4.8 | Amendment voting tracing |
| 4.9 | SHAMap sync tracing |
| 4.10 | Multi-validator integration tests |
| 4.11 | Performance validation |
### Exit Criteria
- [ ] Complete consensus round traces
- [ ] Phase transitions visible
- [ ] Proposals and validations traced
- [ ] No impact on consensus timing
- [ ] Multi-validator test network validated
### Implementation Status — Phase 4a Plan
Phase 4a (establish-phase gap fill & cross-node correlation) will add:
- **Deterministic trace ID** derived from `previousLedger.id()` so all validators
in the same round share the same `trace_id` (switchable via
`consensus_trace_strategy` config: `"deterministic"` or `"attribute"`).
See [Configuration Reference](./05-configuration-reference.md) for full
configuration options.
- **Round lifecycle spans**: `consensus.round` with round-to-round span links.
- **Establish phase**: `consensus.establish`, `consensus.update_positions` (with
`dispute.resolve` events), `consensus.check` (with threshold tracking).
- **Mode changes**: `consensus.mode_change` spans.
- **Validation**: `consensus.validation.send` with span link to round span
(thread-safe cross-thread access via `roundSpanContext_` snapshot).
- **Separation of concerns**: telemetry extracted to private helpers
(`startRoundTracing`, `createValidationSpan`, `startEstablishTracing`,
`updateEstablishTracing`, `endEstablishTracing`).
The `Phase4_taskList.md` spec document is introduced in the Phase 2 PR (#6424)
and will contain the full task breakdown and implementation notes.
---
## 6.6 Phase 5: Documentation & Deployment (Week 9)
**Objective**: Production readiness
### Tasks
| Task | Description |
| ---- | ----------------------------- |
| 5.1 | Operator runbook |
| 5.2 | Grafana dashboards |
| 5.3 | Alert definitions |
| 5.4 | Collector deployment examples |
| 5.5 | Developer documentation |
| 5.6 | Training materials |
| 5.7 | Final integration testing |
---
## 6.7 Risk Assessment
```mermaid
quadrantChart
title Risk Assessment Matrix
x-axis Low Impact --> High Impact
y-axis Low Likelihood --> High Likelihood
quadrant-1 Mitigate Immediately
quadrant-2 Plan Mitigation
quadrant-3 Accept Risk
quadrant-4 Monitor Closely
SDK Compat: [0.2, 0.18]
Protocol Chg: [0.75, 0.72]
Perf Overhead: [0.58, 0.42]
Context Prop: [0.4, 0.55]
Memory Leaks: [0.85, 0.25]
```
### 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 transaction code paths (independent of sampling ratio) | Sampling verification |
| CPU overhead | <3% | Benchmark tests |
| Memory overhead | <10 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 Quick Wins and Crawl-Walk-Run Strategy
> **TxQ** = Transaction Queue
This section outlines a prioritized approach to maximize ROI with minimal initial investment.
### 6.9.1 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[PathFinding + TxQ Tracing] ~~~ c4[Single Node]
end
subgraph walk["🚶 WALK (Week 3-5)"]
direction LR
w1[Transaction Tracing] ~~~ w2[Fee Escalation Tracing] ~~~ w3[Cross-Node Context] ~~~ w4[Basic Dashboards]
end
subgraph run["🏃 RUN (Week 6-9)"]
direction LR
r1[Consensus Tracing] ~~~ r2[Validator, Amendment,<br/>SHAMap Tracing] ~~~ r3[Full Correlation] ~~~ r4[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 c4 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 w4 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
style r4 fill:#0d47a1,stroke:#082f6a,color:#fff
```
</div>
**Reading the diagram:**
- **CRAWL (Weeks 1-2)**: Minimal investment -- set up the SDK, instrument RPC and PathFinding/TxQ handlers, and verify on a single node. Delivers immediate latency visibility.
- **WALK (Weeks 3-5)**: Expand to transaction lifecycle tracing, fee escalation, cross-node context propagation, and basic Grafana dashboards. This is where distributed tracing starts working.
- **RUN (Weeks 6-9)**: Full consensus instrumentation, validator/amendment/SHAMap tracing, end-to-end correlation, and production deployment with sampling and alerting.
- **Arrows (crawl → walk → run)**: Each phase builds on the prior one; you cannot skip ahead because later phases depend on infrastructure established earlier.
### 6.9.2 Quick Wins (Immediate Value)
| Quick Win | Value | When to Deploy |
| ------------------------------ | ------ | -------------- |
| **RPC Command Tracing** | High | Week 2 |
| **RPC Latency Histograms** | High | Week 2 |
| **Error Rate Dashboard** | Medium | Week 2 |
| **Transaction Submit Tracing** | High | Week 3 |
| **Consensus Round Duration** | Medium | Week 6 |
### 6.9.3 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
- PathFinding and TxQ tracing (directly impacts RPC latency)
- 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
- PathFinding and TxQ are RPC-adjacent and directly affect latency
- Immediate value for debugging client issues
- No cross-node complexity
- Single file modification to existing code
### 6.9.4 WALK Phase (Weeks 3-5)
**Goal**: Add transaction lifecycle tracing across nodes.
**What You Get**:
- End-to-end transaction traces from submit to relay
- Fee escalation tracing within the transaction pipeline
- 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)
- Fee escalation is integral to the transaction processing pipeline
- Moderate complexity (requires context propagation)
- High value for debugging transaction issues
### 6.9.5 RUN Phase (Weeks 6-9)
**Goal**: Full observability including consensus.
**What You Get**:
- Complete consensus round visibility
- Phase transition timing
- Validator proposal tracking
- Validator list and manifest tracing
- Amendment voting tracing
- SHAMap sync tracing
- Full end-to-end traces (client → RPC → TX → consensus → ledger)
**Code Changes**: ~100 lines across 3 consensus files, plus validator/amendment/SHAMap modules
**Why Do This Last**:
- Highest complexity (consensus is critical path)
- Validator, amendment, and SHAMap components are lower priority
- Requires thorough testing
- Lower relative value (consensus issues are rarer)
### 6.9.6 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, 0.92]
TX Submit Trace: [0.3, 0.78]
TX Relay Trace: [0.5, 0.88]
Consensus Trace: [0.72, 0.72]
Peer Msg Trace: [0.85, 0.3]
Ledger Acquire: [0.55, 0.52]
```
---
## 6.10 Definition of Done
> **TxQ** = Transaction Queue | **HA** = High Availability
Clear, measurable criteria for each phase.
### 6.10.1 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 Tempo |
| 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.
### 6.10.2 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 Tempo for all commands, dashboard shows latency distribution.
### 6.10.3 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.
### 6.10.4 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.
### 6.10.5 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.
### 6.10.6 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 |
---
## 6.11 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 Tempo 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
```
**Reading the diagram:**
- **Week 1 (tasks 1-2)**: Foundation work -- integrate the OpenTelemetry SDK via Conan/CMake and build the `Telemetry` interface with `SpanGuard` and config parsing.
- **Week 2 (tasks 3-4)**: First observable output -- instrument `ServerHandler` for RPC tracing and stand up Tempo so developers can see traces immediately.
- **Weeks 3-5 (tasks 5-10)**: Transaction lifecycle -- add submit tracing, build the first Grafana dashboard, extend protobuf for cross-node context, instrument `PeerImp` relay, then validate with multi-node integration tests and performance benchmarks.
- **Weeks 6-8 (tasks 11-12)**: Consensus deep-dive -- instrument consensus rounds and phases, then run full integration testing across all instrumented paths.
- **Week 9 (tasks 13-14)**: Go-live -- deploy to production with sampling/alerting configured, and deliver documentation and operator training.
- **Arrow chain (t1 ... t14)**: Strict sequential dependency; each task's output is a prerequisite for the next.
---
_Previous: [Configuration Reference](./05-configuration-reference.md)_ | _Next: [Observability Backends](./07-observability-backends.md)_ | _Back to: [Overview](./OpenTelemetryPlan.md)_

View File

@@ -1,407 +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
> **OTLP** = OpenTelemetry Protocol
| Backend | Pros | Cons | Use Case |
| ---------- | ----------------------------------- | ---------------------- | ------------------- |
| **Tempo** | Cost-effective, Grafana integration | Requires Grafana stack | Local dev, CI, Prod |
| **Zipkin** | Simple, lightweight | Basic features | Quick prototyping |
### Quick Start with Tempo
```bash
# Start Tempo with OTLP support
docker run -d --name tempo \
-p 3200:3200 \
-p 4317:4317 \
-p 4318:4318 \
grafana/tempo:2.6.1
```
---
## 7.2 Production Backends
> **APM** = Application Performance Monitoring
| Backend | Pros | Cons | Use Case |
| ----------------- | ----------------------------------------- | ---------------------- | --------------------------- |
| **Grafana Tempo** | Cost-effective, Grafana integration | Requires Grafana stack | 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
```
**Reading the diagram:**
- **Budget Constraints? (Yes)**: Leads to open-source options. If you already run Grafana or Elastic, pick the matching backend; otherwise default to Grafana Tempo.
- **Budget Constraints? (No) → Prefer SaaS?**: If you want a managed service, choose between Datadog (enterprise support) and Honeycomb (developer-focused). If not, fall back to open-source.
- **Terminal nodes (Tempo / Elastic / Honeycomb / Datadog)**: Each represents a concrete backend choice, all of which feed into the same final step.
- **Configure Collector**: Regardless of backend, you always finish by configuring the OTel Collector to export to your chosen destination.
---
## 7.3 Recommended Production Architecture
> **OTLP** = OpenTelemetry Protocol | **APM** = Application Performance Monitoring | **HA** = High Availability
```mermaid
flowchart TB
subgraph validators["Validator Nodes"]
v1[xrpld<br/>Validator 1]
v2[xrpld<br/>Validator 2]
end
subgraph stock["Stock Nodes"]
s1[xrpld<br/>Stock 1]
s2[xrpld<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
%% Note: simplified single-collector-per-DC topology shown for clarity
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
```
**Reading the diagram:**
- **Validator / Stock Nodes**: All xrpld nodes emit trace data via OTLP. Validators and stock nodes are grouped separately because they may reside in different network zones.
- **Collector Cluster (DC1, DC2)**: Regional collectors receive OTLP from nodes in their datacenter, apply processing (sampling, enrichment), and fan out to multiple backends. Enrichment includes deployment-tier tagging: each collector stamps `deployment.environment` and (as a fallback) `xrpl.network.type` so one Grafana stack can filter data from many collectors by tier.
- **Storage Backends**: Tempo and Elastic provide queryable trace storage; S3/GCS Archive provides long-term cold storage for compliance or post-incident analysis.
- **Grafana Dashboards**: The single visualization layer that queries both Tempo and Elastic, giving operators a unified view of all traces.
- **Data flow direction**: Nodes → Collectors → Storage → Grafana. Each arrow represents a network hop; minimizing collector-to-backend hops reduces latency.
> **Note**: Production deployments should use multiple collector instances behind a load balancer for high availability. The diagram shows a simplified single-collector topology for clarity.
---
## 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 xrpld 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[Node-level head sampling<br/>fixed at 100%<br/>not configurable]
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
```
**Reading the diagram:**
- **Head Sampling (Node)**: xrpld pins head sampling at 100% (sample everything) and does not expose a configurable ratio. This is intentional: a per-node ratio would let different nodes make divergent keep/drop decisions for the same distributed trace, producing broken/partial traces. xrpld uses a `ParentBased` sampler so spans inheriting a remote parent honor the upstream decision. Volume reduction is delegated to the collector's tail sampling.
- **Tail Sampling (Collector)**: The second filter -- the collector inspects completed traces and applies rules: keep all errors, keep anything slower than 5 seconds, and keep 10% of the remainder.
- **Arrow head → tail**: All head-sampled traces flow to the collector, where tail sampling further reduces volume while preserving the most valuable data.
- **Final Traces**: The output after both sampling stages; this is what gets stored and queried. The two-stage approach balances cost with debuggability.
### 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 xrpld observability.
### 7.6.1 Consensus Health Dashboard
A Tempo-backed dashboard (uid `xrpld-consensus-health`) with four panels, all driven by TraceQL:
- **Consensus Round Duration** (timeseries, ms): average `consensus.round` span duration per node instance, with yellow/red thresholds at 4s/5s.
- **Phase Duration Breakdown** (barchart): average duration of `consensus.phase.*` spans grouped by span name.
- **Proposers per Round** (stat): average of the `span.proposers` attribute on `consensus.round` spans.
- **Recent Slow Rounds (>5s)** (table): `consensus.round` spans filtered to `duration > 5s`.
Each panel's TraceQL query is described inline in its bullet above.
### 7.6.2 Node Overview Dashboard
A Tempo-backed dashboard (uid `xrpld-node-overview`) with four panels:
- **Active Nodes** (stat): count of distinct `resource.service.instance.id` values seen for the `xrpld` service.
- **Total Transactions (1h)** (stat): count of `tx.receive` spans.
- **Error Rate** (gauge, percent): ratio of `status.code=error` spans to all spans, with yellow/red thresholds at 1%/5%.
- **Service Map** (nodeGraph): Tempo-generated service dependency graph.
### 7.6.3 Alert Rules
Grafana provisions three TraceQL-based alert rules (group `xrpld-tracing-alerts`, evaluated every 1m) against the Tempo datasource:
- **Consensus Round Slow** (warning, `for: 5m`): fires when average `consensus.round` duration exceeds 5s.
```
{resource.service.name="xrpld" && name="consensus.round"} | avg(duration) > 5s
```
- **RPC Error Rate Spike** (critical, `for: 2m`): fires when the error rate across `rpc.command.*` spans exceeds 5%. Error _rate_ is a ratio, so it must divide the error-span rate by the total-span rate — a single TraceQL `rate()` returns spans/second, not a percentage, and would fire on traffic volume alone. This uses span metrics emitted by the collector's `spanmetrics` connector (Prometheus datasource), not a TraceQL query:
```
sum(rate(traces_spanmetrics_calls_total{service_name="xrpld", span_name=~"rpc.command.*", status_code="STATUS_CODE_ERROR"}[5m]))
/
sum(rate(traces_spanmetrics_calls_total{service_name="xrpld", span_name=~"rpc.command.*"}[5m]))
> 0.05
```
- **Transaction Throughput Drop** (warning, `for: 10m`): fires when the `tx.receive` span rate falls below 10/s.
```
{resource.service.name="xrpld" && name="tx.receive"} | rate() < 10
```
> **Note**: The Consensus Round Slow and Transaction Throughput Drop rules use TraceQL aggregates (`avg(duration)`, `rate()`), which require Tempo 2.3+ with TraceQL metrics enabled. Verify aggregate query support in your Tempo version before provisioning. The RPC Error Rate Spike rule instead queries Prometheus span metrics (collector `spanmetrics` connector), so it needs that connector enabled in the collector pipeline.
---
## 7.7 PerfLog and Insight Correlation
> **OTLP** = OpenTelemetry Protocol
How to correlate OpenTelemetry traces with existing xrpld observability.
### 7.7.1 Correlation Architecture
```mermaid
flowchart TB
subgraph xrpld["xrpld 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 xrpld 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
```
**Reading the diagram:**
- **xrpld Node (three sources)**: A single node emits three independent data streams -- OpenTelemetry spans, PerfLog JSON logs, and Beast Insight StatsD metrics.
- **Data Collection layer**: Each stream has its own collector -- OTel Collector for spans, Promtail/Fluentd for logs, and a StatsD exporter for metrics. They operate independently.
- **Storage layer (Tempo, Loki, Prometheus)**: Each data type lands in a purpose-built store optimized for its query patterns (trace search, log grep, metric aggregation).
- **Grafana Correlation Panel**: The key integration point -- Grafana queries all three stores and links them via shared fields (`trace_id`, `tx_hash`, `ledger_seq`), enabling a single-pane debugging experience.
### 7.7.2 Correlation Fields
| Source | Field | Link To | Purpose |
| ----------- | ------------------- | ------------- | -------------------------- |
| **Trace** | `trace_id` | Logs | Find log entries for trace |
| **Trace** | `tx_hash` | Logs, Metrics | Find TX-related data |
| **Trace** | `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="xrpld" && span.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="xrpld"} |= "4bf92f3577b34da6a3ce929d0e0e4736"
```
**Step 4: Check Insight metrics for the time window**
```
# In Grafana with Prometheus
rate(xrpld_tx_applied_total[1m])
@ timestamp_from_trace
```
### 7.7.4 Unified Dashboard Example
A single dashboard (uid `xrpld-unified`) that ties traces, metrics, and logs together across the Tempo, Prometheus, and Loki datasources:
- **Transaction Latency (Traces)** (timeseries, Tempo): `histogram_over_time(duration)` of `tx.receive` spans.
- **Transaction Rate (Metrics)** (timeseries, Prometheus): `rate(xrpld_tx_received_total[5m])` per instance, with a data link that opens the matching `tx.receive` traces in Tempo.
- **Recent Logs** (logs, Loki): `{job="xrpld"} | json`.
- **Trace Search** (table, Tempo): all `xrpld` traces, with per-row data links on `traceID` that jump to the trace in Tempo and to the correlated logs in Loki (`{job="xrpld"} |= "<traceID>"`).
The cross-datasource data links are what make this a single-pane debugging view; the correlation fields they rely on are listed in section 7.7.2.
---
_Previous: [Implementation Phases](./06-implementation-phases.md)_ | _Next: [Appendix](./08-appendix.md)_ | _Back to: [Overview](./OpenTelemetryPlan.md)_

View File

@@ -1,187 +0,0 @@
# Appendix
> **Parent Document**: [OpenTelemetryPlan.md](./OpenTelemetryPlan.md)
> **Related**: [Observability Backends](./07-observability-backends.md)
---
## 8.1 Glossary
> **OTLP** = OpenTelemetry Protocol | **TxQ** = Transaction Queue
| 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 |
### xrpld-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 xrpld |
| **Beast Insight** | Existing metrics framework in xrpld |
| **PathFinding** | Payment path computation engine for cross-currency payments |
| **TxQ** | Transaction queue managing fee-based prioritization |
| **LoadManager** | Dynamic fee escalation based on network load |
| **SHAMap** | SHA-256 hash-based map (Merkle trie variant) for ledger state |
---
## 8.2 Span Hierarchy Visualization
> **TxQ** = Transaction Queue
```mermaid
flowchart TB
subgraph trace["Trace: Transaction Lifecycle"]
rpc["rpc.request<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
subgraph pathfinding["PathFinding Spans"]
pathfind["pathfind.request"]
pathcomp["pathfind.compute"]
end
consensus["consensus.round"]
apply["tx.apply"]
subgraph txqueue["TxQ Spans"]
txq["txq.enqueue"]
txqApply["txq.apply"]
end
feeCalc["fee.escalate"]
end
subgraph validators["Validator Spans"]
valFetch["validator.list.fetch"]
valManifest["validator.manifest"]
end
rpc --> validate
rpc --> pathfind
pathfind --> pathcomp
validate --> relay
relay --> p1
relay --> p2
relay --> p3
p1 -.->|"context propagation"| consensus
consensus --> apply
apply --> txq
txq --> txqApply
txq --> feeCalc
style trace fill:#0f172a,stroke:#020617,color:#fff
style peers fill:#1e3a8a,stroke:#172554,color:#fff
style pathfinding fill:#134e4a,stroke:#0f766e,color:#fff
style txqueue fill:#064e3b,stroke:#047857,color:#fff
style validators fill:#4c1d95,stroke:#6d28d9,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
style pathfind fill:#0e7490,stroke:#155e75,color:#fff
style pathcomp fill:#0e7490,stroke:#155e75,color:#fff
style txq fill:#047857,stroke:#064e3b,color:#fff
style txqApply fill:#047857,stroke:#064e3b,color:#fff
style feeCalc fill:#047857,stroke:#064e3b,color:#fff
style valFetch fill:#6d28d9,stroke:#4c1d95,color:#fff
style valManifest fill:#6d28d9,stroke:#4c1d95,color:#fff
```
**Reading the diagram:**
- **rpc.request (blue, top)**: The entry point — every traced transaction starts as an RPC call; this root span is the parent of all downstream work.
- **tx.validate and pathfind.request (green/teal, first fork)**: The RPC request fans out into transaction validation and, for cross-currency payments, a PathFinding branch (`pathfind.request` -> `pathfind.compute`).
- **tx.relay -> Peer Spans (teal, middle)**: After validation, the transaction is relayed to peers A, B, and C in parallel; each `peer.send` is a sibling child span showing fan-out across the network.
- **context propagation (dashed arrow)**: The dotted line from `peer.send Peer A` to `consensus.round` represents the trace context crossing a node boundary — the receiving validator picks up the same `trace_id` and continues the trace.
- **consensus.round -> tx.apply -> TxQ Spans (green, lower)**: Once consensus accepts the transaction, it is applied to the ledger; the TxQ spans (`txq.enqueue`, `txq.apply`, `fee.escalate`) capture queue depth and fee escalation behavior.
- **Validator Spans (purple, detached)**: `validator.list.fetch` and `validator.manifest` are independent workflows for UNL management — they run on their own traces and are linked to consensus via Span Links, not parent-child relationships.
---
## 8.3 References
> **OTLP** = OpenTelemetry Protocol
### 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/)
### xrpld Resources
8. [xrpld Source Code](https://github.com/XRPLF/rippled)
9. [XRP Ledger Documentation](https://xrpl.org/docs/)
10. [xrpld Overlay README](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/README.md)
11. [xrpld RPC README](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/rpc/README.md)
12. [xrpld Consensus README](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/consensus/README.md)
---
## 8.4 Version History
| Version | Date | Author | Changes |
| ------- | ---------- | ------ | -------------------------------------------------------------- |
| 1.0 | 2026-02-12 | - | Initial implementation plan |
| 1.1 | 2026-02-13 | - | Refactored into modular documents |
| 1.2 | 2026-03-24 | - | Review fixes: accuracy corrections, cross-document consistency |
---
## 8.5 Document Index
### Plan Documents
| Document | Description |
| ---------------------------------------------------------------- | -------------------------------------------- |
| [OpenTelemetryPlan.md](./OpenTelemetryPlan.md) | Master overview and executive summary |
| [00-tracing-fundamentals.md](./00-tracing-fundamentals.md) | Distributed tracing concepts and OTel primer |
| [01-architecture-analysis.md](./01-architecture-analysis.md) | xrpld 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 |
| [05-configuration-reference.md](./05-configuration-reference.md) | xrpld 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

@@ -1,199 +0,0 @@
# [OpenTelemetry](00-tracing-fundamentals.md) Distributed Tracing Implementation Plan for xrpld
## Executive Summary
> **OTLP** = OpenTelemetry Protocol
This document provides a comprehensive implementation plan for integrating OpenTelemetry distributed tracing into the xrpld 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 | <10 MB | SDK statics + batch buffer + worker thread stack |
| 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 fundamentals["Fundamentals"]
fund["00-tracing-fundamentals.md"]
end
subgraph analysis["Analysis & Design"]
arch["01-architecture-analysis.md"]
design["02-design-decisions.md"]
end
subgraph impl["Implementation"]
strategy["03-implementation-strategy.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 --> fundamentals
overview --> analysis
overview --> impl
overview --> deploy
fund --> arch
arch --> design
design --> strategy
strategy --> config
config --> phases
phases --> backends
backends --> appendix
style overview fill:#1b5e20,stroke:#0d3d14,color:#fff,stroke-width:2px
style fundamentals fill:#00695c,stroke:#004d40,color:#fff
style fund fill:#00695c,stroke:#004d40,color:#fff
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 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 |
| ------- | ---------------------------------------------------------- | ---------------------------------------------------------------------- |
| **0** | [Tracing Fundamentals](./00-tracing-fundamentals.md) | Distributed tracing concepts, span relationships, context propagation |
| **1** | [Architecture Analysis](./01-architecture-analysis.md) | xrpld 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 |
| **5** | [Configuration Reference](./05-configuration-reference.md) | xrpld 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 |
---
## 0. Tracing Fundamentals
This document introduces distributed tracing concepts for readers unfamiliar with the domain. It covers what traces and spans are, how parent-child and follows-from relationships model causality, how context propagates across service boundaries, and how sampling controls data volume. It also maps these concepts to xrpld-specific scenarios like transaction relay and consensus.
➡️ **[Read Tracing Fundamentals](./00-tracing-fundamentals.md)**
---
## 1. Architecture Analysis
> **WS** = WebSocket | **TxQ** = Transaction Queue
The xrpld 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, PathFinding, Transaction Queue (TxQ), fee escalation (LoadManager), ledger acquisition, validator management, 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, ledger building, path computation, transaction queue behavior, fee escalation, and validator health. 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
> **OTLP** = OpenTelemetry Protocol | **CNCF** = Cloud Native Computing Foundation
The OpenTelemetry C++ SDK is selected for its CNCF backing, active development, and native performance characteristics. Traces are exported via OTLP/HTTP to an OpenTelemetry Collector, which provides flexible routing and sampling. OTLP/gRPC is planned future work (see design decisions §2.2.2).
Span naming follows a hierarchical `<component>.<operation>` convention (e.g., `rpc.submit`, `tx.relay`, `consensus.round`). Context propagation uses W3C Trace Context headers for HTTP and embedded Protocol Buffer fields for P2P messages. The implementation coexists with existing PerfLog and Insight observability systems through correlation IDs.
**Data Collection & Privacy**: Telemetry collects only operational metadata (timing, counts, hashes) — never sensitive content (private keys, balances, amounts, raw payloads). Privacy protection includes account hashing, configurable redaction, sampling, and collector-level filtering. Node operators retain full control over telemetry configuration.
➡️ **[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 head sampling fixed at 100% (intentionally not configurable, so trace keep/drop decisions stay coherent across nodes), tail-based sampling at the collector for errors and slow traces to reduce volume, batch export to reduce network overhead, and conditional instrumentation that compiles to no-ops when disabled.
➡️ **[Read full Implementation Strategy](./03-implementation-strategy.md)**
---
## 5. Configuration Reference
> **OTLP** = OpenTelemetry Protocol | **APM** = Application Performance Monitoring
Configuration is handled through the `[telemetry]` section in `xrpld.cfg` with options for enabling/disabling, exporter selection, endpoint configuration, and component-level filtering. Head sampling is fixed at 1.0 (not operator-configurable); volume reduction is done by tail sampling in the collector. CMake integration includes a `XRPL_ENABLE_TELEMETRY` option for compile-time control.
OpenTelemetry Collector configurations are provided for development 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 person-days (2 developers working in parallel)
➡️ **[View full Implementation Phases](./06-implementation-phases.md)**
---
## 7. Observability Backends
> **APM** = Application Performance Monitoring | **GCS** = Google Cloud Storage
Grafana Tempo is recommended for all environments due to 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 xrpld-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 xrpld XRP Ledger node software. For detailed information on any section, follow the links to the corresponding sub-documents._

View File

@@ -54,7 +54,6 @@ Here are some good places to start learning the source code:
| `./docs` | Source documentation files and doxygen config. |
| `./cfg` | Example configuration files. |
| `./src` | Source code. |
| `./crates` | Rust source code. |
Some of the directories under `src` are external repositories included using
git-subtree. See those directories' README files for more details.

View File

@@ -1,111 +0,0 @@
#!/usr/bin/env bash
# Fail if a binary under <path> records a /nix/store path it resolves at run
# time. See docs/build/nix.md#prebuilt-packages for why that matters.
#
# <path> is a file or a directory. macOS: nothing may reference the store, so
# point it at whole trees. Linux: the toolchain always writes the store into
# PT_INTERP and RUNPATH, so only at what cmake/PatchNixBinary.cmake retargets.
#
# Only Mach-O / ELF is inspected. Static archives hold store paths in debug info
# alone; the scripts in a Conan cache are all git hook samples and autotools
# scratch, 36 false positives to 0 real.
#
# Usage: bin/check-nix-store-refs.sh <path>
set -euo pipefail
if [ "$#" -ne 1 ]; then
echo "usage: $0 <path>" >&2
exit 2
fi
if [ ! -e "$1" ]; then
echo "$0: no such path: $1" >&2
exit 2
fi
case "$(uname -s)" in
Darwin)
format=Mach-O
recorded_paths=macho_recorded_paths
tool=otool
;;
Linux)
format=ELF
recorded_paths=elf_recorded_paths
tool=readelf
;;
*)
echo "Unsupported OS - skipping the Nix store reference check."
exit 0
;;
esac
# `pipefail` would catch this too, but only as a bare nonzero exit.
if ! command -v "${tool}" >/dev/null; then
echo "$0: ${tool} not found; cannot inspect binaries" >&2
exit 2
fi
# Both list what the file records. `ldd` would answer what this machine resolves
# now, which is wrong both ways: store paths for a correctly patched binary,
# silence for a store RUNPATH that resolves nowhere.
# `name` covers LC_ID_DYLIB and LC_LOAD*_DYLIB, `path` covers LC_RPATH.
macho_recorded_paths() {
otool -l "$1" | sed -nE 's#^ *(name|path) ([^ ]*).*#\2#p'
}
# RPATH and RUNPATH are colon-separated.
elf_recorded_paths() {
readelf -ldW "$1" |
sed -nE \
-e 's#.*program interpreter: ([^]]*)\].*#\1#p' \
-e 's#.*\((RPATH|RUNPATH|NEEDED)\).*\[([^]]*)\].*#\2#p' |
tr ':' '\n'
}
checked=0
skipped=0
leaked=0
while IFS= read -r file; do
case "$(file -b "${file}" 2>/dev/null)" in
*"${format}"*) ;;
*)
skipped=$((skipped + 1))
continue
;;
esac
checked=$((checked + 1))
# Filter after extracting, or a search path starting elsewhere ($ORIGIN)
# hides the rest. `sed` not `grep`: grep calls "no matches" a failure, and
# the `|| true` that would need masks a broken pipeline too.
refs="$("${recorded_paths}" "${file}" | sed -n '\#^/nix/store/#p' | sort -u)"
if [ -n "${refs}" ]; then
leaked=$((leaked + 1))
echo "::error file=${file}::references the Nix store at run time"
echo "${file}"
echo "${refs}" | sed 's/^/ /'
fi
done < <(find "$1" -type f \( -perm -u+x -o -name '*.dylib' -o -name '*.so*' \))
echo "$1: checked ${checked}, skipped ${skipped}, ${leaked} with Nix store references."
if [ "${leaked}" -ne 0 ]; then
cat >&2 <<'EOF'
Fixes, in order of preference:
- A Conan package built before this check existed: drop it
(`conan remove '<name>/*'`) and rebuild.
- A binary that should have been retargeted to the system loader: check that
cmake/PatchNixBinary.cmake ran for it.
- Link the macOS system library instead of the Nix one - see
libresolvSystemStub in nix/darwin.nix.
- No system library exists (libstdc++): link it statically.
- None of the above: pin the toolchain into the package ID, following
`user.package:libc_version` in conan/profiles/ci.
EOF
exit 1
fi

View File

@@ -15,14 +15,10 @@
# - Windows: the core build tools only (CMake, Conan, Git, Python).
# MSVC is expected to be provided separately and is not checked here.
#
# Some tools (clang-format, clang-tidy, doxygen, gcovr, gh, git-cliff, gpg,
# pre-commit, run-clang-tidy) are present in our Linux CI images and in local
# development setups, but not in the macOS CI environment. They are checked
# everywhere except when running in CI on macOS.
#
# Tools that Nix also exposes under a version-suffixed name (`clang-tidy-22`,
# `g++-15`, ...) are probed under both names: a suffixed name can break while
# the plain one still works (see mkVersionedToolLinks in nix/packages.nix).
# Some tools (clang-format, doxygen, gcovr, gh, git-cliff, gpg, pre-commit,
# run-clang-tidy) are present in our Linux CI images and in local development
# setups, but not in the macOS CI environment. They are checked everywhere
# except when running in CI on macOS.
#
# Environment variables:
# CI if set, skip the tools above when on macOS.
@@ -30,27 +26,14 @@
set -uo pipefail
# Version suffixes of the Nix tool links, tracking nix/packages.nix.
gcc_version=15
llvm_version=22
missing=()
checked=0
# tool_path <name>
# Fully resolved path of a tool, so the snapshots record which derivation
# provides it. Prints nothing when it isn't on PATH.
tool_path() {
local path
path="$(command -v "$1" 2>/dev/null)" || return 0
readlink -f "${path}" 2>/dev/null || printf '%s' "${path}"
}
# check <name> [probe-command...]
# Runs the probe (default: "<name> --version"), capturing both stdout and
# stderr, and prints three lines: the status and name, the first non-blank line
# of the probe output (its version, or the error when it failed), and the tool's
# resolved path. Records <name> as missing if it is not found or exits non-zero.
# stderr, and prints one aligned line: the status, the name, and the first
# non-blank line of the probe output (its version). Records <name> as missing
# if the command is not found or exits non-zero.
check() {
local name="$1"
shift
@@ -60,17 +43,14 @@ check() {
fi
checked=$((checked + 1))
local output version path
path="$(tool_path "${name}")"
local output version
if output="$("${probe[@]}" 2>&1)"; then
printf '%s\n' "${name}"
version="$(printf '%s\n' "${output}" | grep -m1 '[^[:space:]]' || true)"
printf ' [ ok ] %-20s %s\n' "${name}" "${version}"
else
printf ' %s\n' "${name}"
printf ' [MISS] %s\n' "${name}"
missing+=("${name}")
fi
version="$(printf '%s\n' "${output}" | grep -m1 '[^[:space:]]' || true)"
printf ' %s\n' "${version:-(no output)}"
printf ' %s\n' "${path:-(not found)}"
}
case "$(uname -s)" in
@@ -102,9 +82,7 @@ if [ "${os}" = "linux" ] || [ "${os}" = "macos" ]; then
echo "Development tooling:"
check ccache
check clang
check "clang-${llvm_version}"
check clang++
check "clang++-${llvm_version}"
check ClangBuildAnalyzer
check curl
check file
@@ -123,14 +101,7 @@ if [ "${os}" = "linux" ] || [ "${os}" = "macos" ]; then
# setups, but not in the macOS CI environment. So check them everywhere
# except when running in CI on macOS.
if [ "${os}" = "linux" ] || [ -z "${CI:-}" ]; then
check clang-apply-replacements
check "clang-apply-replacements-${llvm_version}"
check clang-format
check "clang-format-${llvm_version}"
# clang-tidy leads --version with the LLVM banner, not the version.
tidy_probe="--version | grep -m1 -oE 'LLVM version [0-9.]+'"
check clang-tidy sh -c "clang-tidy ${tidy_probe}"
check "clang-tidy-${llvm_version}" sh -c "clang-tidy-${llvm_version} ${tidy_probe}"
check dot
check doxygen
check gcovr
@@ -141,7 +112,6 @@ if [ "${os}" = "linux" ] || [ "${os}" = "macos" ]; then
# pre-commit, or its alternative implementation prek
check pre-commit sh -c 'pre-commit --version || prek --version'
check run-clang-tidy run-clang-tidy --help
check "run-clang-tidy-${llvm_version}" "run-clang-tidy-${llvm_version}" --help
fi
fi
@@ -156,7 +126,7 @@ if [ "${os}" = "linux" ] || [ "${os}" = "macos" ]; then
check cargo-audit cargo audit --version
check cargo-llvm-cov cargo llvm-cov --version
check cargo-nextest cargo nextest --version
check clippy-driver
check clippy clippy-driver --version
check rust-analyzer
check rustc
check rustfmt
@@ -168,11 +138,7 @@ if [ "${os}" = "linux" ]; then
echo
echo "GCC toolchain:"
check gcc
check "gcc-${gcc_version}"
check g++
check "g++-${gcc_version}"
check cpp
check "cpp-${gcc_version}"
check gcov
echo
@@ -197,9 +163,9 @@ else
checked=$((checked + 1))
tmp_clone="$(mktemp -d)"
if git clone --depth 1 https://github.com/XRPLF/actions.git "${tmp_clone}/actions" >/dev/null 2>&1; then
printf ' git clone over HTTPS\n'
printf ' [ ok ] git clone over HTTPS\n'
else
printf ' git clone over HTTPS\n'
printf ' [MISS] git clone over HTTPS\n'
missing+=("git-https-clone")
fi
rm -rf "${tmp_clone}"
@@ -207,9 +173,9 @@ fi
echo
if [ "${#missing[@]}" -eq 0 ]; then
echo "All ${checked} checked tools are present and runnable."
echo "All ${checked} checked tools are present and runnable."
else
echo "Missing or non-functional tools (${#missing[@]} of ${checked}):" >&2
echo "Missing or non-functional tools (${#missing[@]} of ${checked}):" >&2
for tool in "${missing[@]}"; do
echo " - ${tool}" >&2
done

View File

@@ -488,17 +488,6 @@
# Must be a number between 100 and 1000, defaults to 250
#
#
# [max_subscriptions_per_connection]
#
# Maximum number of account, real-time account, and account-history
# subscriptions a single client connection may hold at once. Bounds the
# per-connection state torn down when the connection disconnects. Book
# subscriptions are tracked separately and are not counted here.
#
# Defaults to 100000 if not set; large enough for legitimate power users
# such as block explorers.
#
#
# [overlay]
#
# Controls settings related to the peer to peer overlay.
@@ -549,45 +538,6 @@
# only be used for local testing and debugging. Do not disable
# on mainnet.
#
# max_untrusted_count = <number>
#
# The number of manifests the server keeps for validators it does not
# list, and the number it sends and processes in a single peer protocol
# message. Once the server holds this many, a manifest for a new
# unlisted validator is rejected, so peer gossip cannot grow the cache
# without end.
#
# This option can take any value between 50 and 1000, inclusive. If
# the option is not present the server uses its built-in value.
#
# The current default (which is subject to change) is 300.
#
# max_trusted_count = <number>
#
# The number of manifests for listed validators to allow for when
# sizing peer protocol messages. Manifests for listed validators are
# never dropped, whether sending or receiving, because doing so would
# delay a validator key change reaching this server. Set this above the
# number of validators the server lists.
#
# Together the two counts above set the largest manifest message the
# server accepts: bigger messages are discarded without reading them,
# and without penalising the sender. Raising either means the server
# accepts and sends bigger messages than a peer using the defaults, and
# those peers will discard what this server sends. Lowering either below
# what peers send makes this server discard their manifest messages,
# which it does without recording anything.
#
# This option can take any value between 50 and 1000, inclusive. If
# the option is not present the server uses its built-in value.
#
# The current default (which is subject to change) is 300.
#
# NOTE: These two options (max_untrusted_count and max_trusted_count)
# are transitional. They exist to bound manifest-message size and cache
# growth during the network upgrade. They may be removed in a future
# release once the fleet has upgraded, and should not be relied upon as
# stable configuration.
#
# [transaction_queue] EXPERIMENTAL
#

View File

@@ -2,10 +2,9 @@
Patch executables to run in non-Nix environments.
The Nix toolchain links binaries against an ELF interpreter (loader)
that lives in the Nix store, so the resulting binaries don't run elsewhere
(including once installed from the .deb package). `patch_nix_binary` resets
the interpreter to the system default loader and drops the rpath, once the
binary has been linked.
that lives in the Nix store, so the resulting binaries don't run elsewhere.
`patch_nix_binary` adds a POST_BUILD step that resets the interpreter
to the system default loader and drops the rpath.
This runs by default for Nix-toolchain builds (determined by whether the compiler resolves under /nix/store/).
Those builds are where binaries get a Nix-store loader.
@@ -53,38 +52,13 @@ function(patch_nix_binary target)
if(NOT PATCH_NIX_BINARIES)
return()
endif()
set(patch_command
"${PATCHELF_COMMAND}"
--set-interpreter
"${DEFAULT_LOADER_PATH}"
--remove-rpath
"$<TARGET_FILE:${target}>"
add_custom_command(
TARGET ${target}
POST_BUILD
COMMAND
"${PATCHELF_COMMAND}" --set-interpreter "${DEFAULT_LOADER_PATH}"
--remove-rpath "$<TARGET_FILE:${target}>"
COMMENT "Patching ${target}: set default loader, remove rpath"
VERBATIM
)
set(comment "Patching ${target}: set default loader, remove rpath")
# POST_BUILD is the cheap way to do this: it runs only when the binary is
# relinked. It is also only available in the directory that defined the
# target, so for a target from elsewhere (e.g. a FetchContent subproject)
# fall back to a custom target that runs after the binary is linked. That
# one runs on every build, which is harmless because patchelf is idempotent.
get_target_property(target_source_dir ${target} SOURCE_DIR)
if("${target_source_dir}" STREQUAL "${CMAKE_CURRENT_SOURCE_DIR}")
add_custom_command(
TARGET ${target}
POST_BUILD
COMMAND ${patch_command}
COMMENT "${comment}"
VERBATIM
)
else()
add_custom_target(
${target}-patch-nix
ALL
COMMAND ${patch_command}
COMMENT "${comment}"
VERBATIM
)
add_dependencies(${target}-patch-nix ${target})
endif()
endfunction()

View File

@@ -266,50 +266,10 @@ elseif(use_lld)
)
if("${LD_VERSION}" MATCHES "LLD")
target_link_libraries(common INTERFACE -fuse-ld=lld)
# remembered for the linker flag probe below
set(fuse_ld_flag "-fuse-ld=lld")
endif()
unset(LD_VERSION)
endif()
# Linker warnings are errors where we control the toolchain and the dependencies: CI and the Nix dev shell.
# On non-Nix macOS we suppress the deployment target warning: an old Conan profile may not pin os.version.
# Only the new Apple linker understands the flag, so probe the actual linker (lld may be selected above).
if(is_macos OR is_linux)
if(is_ci OR is_nix_compiler)
if(is_macos)
set(fatal_warnings_flag "-Wl,-fatal_warnings")
else()
set(fatal_warnings_flag "-Wl,--fatal-warnings")
endif()
message(
STATUS
"Treating all linker warnings as errors (${fatal_warnings_flag})"
)
target_link_options(common INTERFACE "${fatal_warnings_flag}")
unset(fatal_warnings_flag)
elseif(is_macos)
set(silence_flag "-Wl,-deployment_target_mismatches,suppress")
set(probe_flags ${fuse_ld_flag} "${silence_flag}")
include(CheckLinkerFlag)
check_linker_flag(
CXX
"${probe_flags}"
have_deployment_target_mismatches
)
if(have_deployment_target_mismatches)
message(
STATUS
"Silencing macOS deployment target mismatch warnings (${silence_flag})"
)
target_link_options(common INTERFACE "${silence_flag}")
endif()
unset(probe_flags)
unset(silence_flag)
endif()
endif()
unset(fuse_ld_flag)
if(assert)
foreach(var_ CMAKE_C_FLAGS_RELEASE CMAKE_CXX_FLAGS_RELEASE)
string(REGEX REPLACE "[-/]DNDEBUG" "" ${var_} "${${var_}}")

View File

@@ -51,8 +51,6 @@ target_compile_options(
target_link_libraries(xrpl.libpb PUBLIC protobuf::libprotobuf gRPC::grpc++)
add_dependencies(tidy_prerequisites xrpl.libpb)
# TODO: Clean up the number of library targets later.
add_library(xrpl.imports.main INTERFACE)

View File

@@ -44,7 +44,6 @@ setup_target_for_coverage_gcovr(
EXCLUDE
"src/test"
"src/tests"
"src/benchmarks"
"include/xrpl/beast/test"
"include/xrpl/beast/unit_test"
"${CMAKE_BINARY_DIR}/pb-xrpl.libpb"

View File

@@ -25,19 +25,6 @@ if(NOT (RPMBUILD_EXECUTABLE OR DPKG_BUILDPACKAGE_EXECUTABLE))
return()
endif()
if(NOT TARGET xrpld)
message(STATUS "xrpld=ON is required; 'package' target not available")
return()
endif()
if(NOT TARGET validator-keys)
message(
STATUS
"validator_keys=ON is required; 'package' target not available"
)
return()
endif()
set(package_env
SRC_DIR=${CMAKE_SOURCE_DIR}
BUILD_DIR=${CMAKE_BINARY_DIR}
@@ -50,7 +37,7 @@ add_custom_target(
${CMAKE_COMMAND} -E env ${package_env}
${CMAKE_SOURCE_DIR}/package/build_pkg.sh
WORKING_DIRECTORY ${CMAKE_BINARY_DIR}
DEPENDS xrpld validator-keys
DEPENDS xrpld
COMMENT "Building Linux package (deb/rpm inferred from host tooling)"
VERBATIM
)

View File

@@ -2,22 +2,21 @@
Protocol Autogen - Code generation for protocol wrapper classes
#]===================================================================]
# The repository root, derived from the location of this file rather than from
# the including project, so that the targets below can also be offered on their
# own by cmake/codegen/CMakeLists.txt.
get_filename_component(XRPL_ROOT "${CMAKE_CURRENT_LIST_DIR}/.." ABSOLUTE)
set(CODEGEN_VENV_DIR
"${XRPL_ROOT}/.venv"
"${CMAKE_CURRENT_SOURCE_DIR}/.venv"
CACHE PATH
"Path to a Python virtual environment for code generation. A venv will be created here by setup_code_gen and used to run generation scripts."
)
# Directory paths
set(MACRO_DIR "${XRPL_ROOT}/include/xrpl/protocol/detail")
set(AUTOGEN_HEADER_DIR "${XRPL_ROOT}/include/xrpl/protocol_autogen")
set(AUTOGEN_TEST_DIR "${XRPL_ROOT}/src/tests/libxrpl/protocol_autogen")
set(SCRIPTS_DIR "${XRPL_ROOT}/cmake/scripts/codegen")
set(MACRO_DIR "${CMAKE_CURRENT_SOURCE_DIR}/include/xrpl/protocol/detail")
set(AUTOGEN_HEADER_DIR
"${CMAKE_CURRENT_SOURCE_DIR}/include/xrpl/protocol_autogen"
)
set(AUTOGEN_TEST_DIR
"${CMAKE_CURRENT_SOURCE_DIR}/src/tests/libxrpl/protocol_autogen"
)
set(SCRIPTS_DIR "${CMAKE_CURRENT_SOURCE_DIR}/cmake/scripts/codegen")
# Input macro files
set(TRANSACTIONS_MACRO "${MACRO_DIR}/transactions.macro")
@@ -115,14 +114,14 @@ if(CODEGEN_VENV_DIR)
setup_code_gen
COMMAND ${Python3_EXECUTABLE} -m venv "${CODEGEN_VENV_DIR}"
COMMAND ${CODEGEN_PYTHON} -m pip install -r "${REQUIREMENTS_FILE}"
WORKING_DIRECTORY "${XRPL_ROOT}"
WORKING_DIRECTORY "${CMAKE_CURRENT_SOURCE_DIR}"
COMMENT "Creating venv and installing code generation dependencies..."
)
else()
add_custom_target(
setup_code_gen
COMMAND ${Python3_EXECUTABLE} -m pip install -r "${REQUIREMENTS_FILE}"
WORKING_DIRECTORY "${XRPL_ROOT}"
WORKING_DIRECTORY "${CMAKE_CURRENT_SOURCE_DIR}"
COMMENT "Installing code generation dependencies..."
)
endif()
@@ -140,8 +139,8 @@ add_custom_target(
-DSFIELDS_MACRO=${SFIELDS_MACRO}
-DAUTOGEN_HEADER_DIR=${AUTOGEN_HEADER_DIR}
-DAUTOGEN_TEST_DIR=${AUTOGEN_TEST_DIR} -P
"${CMAKE_CURRENT_LIST_DIR}/XrplProtocolAutogenRun.cmake"
WORKING_DIRECTORY "${XRPL_ROOT}"
"${CMAKE_CURRENT_SOURCE_DIR}/cmake/XrplProtocolAutogenRun.cmake"
WORKING_DIRECTORY "${CMAKE_CURRENT_SOURCE_DIR}"
COMMENT "Running protocol code generation..."
SOURCES ${ALL_INPUT_FILES}
)

View File

@@ -32,11 +32,6 @@ endif()
option(benchmark "Build benchmarks" ON)
# When OFF, the crates directory is not added to the build at all: no Rust
# toolchain is required, no cxxbridge bindings are generated, and the C++ tests
# that consume those bindings are left out of the build tree.
option(rust "Build the Rust crates and the C++ code that depends on them" OFF)
# Enabled by default so every header is compiled on its own as the main file of
# its own compile_commands.json entry - this is what lets clang-tidy (and clangd
# and IDEs) analyse a header's own includes directly. The per-header objects are

View File

@@ -5,39 +5,22 @@ option(
)
if(validator_keys)
# Own the install destination below rather than relying on another module
# having pulled this in first.
include(GNUInstallDirs)
# Pinned to an exact commit, not a branch: the tool ships inside our
# packages, so the same xrpld version must always package the same
# validator-keys. Bump this deliberately.
set(validator_keys_commit "4c0fb75eec9601c711645998c904507e87e910ae")
message(STATUS "Using ValidatorKeys commit: ${validator_keys_commit}")
git_branch(current_branch)
# default to tracking VK master branch unless we are on release
if(NOT (current_branch STREQUAL "release"))
set(current_branch "master")
endif()
message(STATUS "Tracking ValidatorKeys branch: ${current_branch}")
FetchContent_Declare(
validator_keys
GIT_REPOSITORY https://github.com/ripple/validator-keys-tool.git
GIT_TAG "${validator_keys_commit}"
GIT_TAG "${current_branch}"
)
FetchContent_MakeAvailable(validator_keys)
# The tool's own CMakeLists excludes the target from 'all' when it is built
# as a subproject. Undo that, so validator_keys=ON really does build it.
set_target_properties(
validator-keys
PROPERTIES
RUNTIME_OUTPUT_DIRECTORY "${CMAKE_BINARY_DIR}"
EXCLUDE_FROM_ALL OFF
EXCLUDE_FROM_DEFAULT_BUILD OFF
)
# We ship this binary, so like xrpld it must not keep the Nix store's ELF
# loader, or it cannot run on the target distro at all.
patch_nix_binary(validator-keys)
configure_file(
"${validator_keys_SOURCE_DIR}/LICENSE"
"${CMAKE_BINARY_DIR}/validator-keys-LICENSE"
COPYONLY
PROPERTIES RUNTIME_OUTPUT_DIRECTORY "${CMAKE_BINARY_DIR}"
)
install(TARGETS validator-keys RUNTIME DESTINATION ${CMAKE_INSTALL_BINDIR})
endif()

View File

@@ -1,21 +0,0 @@
#[===================================================================[
Protocol Autogen - Standalone project
Exposes the 'setup_code_gen' and 'code_gen' targets on their own, without
configuring the rest of xrpl. Code generation is pure Python, so this needs
neither the dependencies nor a compiler, which makes it usable in CI and by
contributors who only want to regenerate the protocol wrapper classes:
cmake -S cmake/codegen -B build/codegen
cmake --build build/codegen --target setup_code_gen
cmake --build build/codegen --target code_gen
The targets are identical to the ones offered by the top-level build, since
both come from cmake/XrplProtocolAutogen.cmake.
#]===================================================================]
cmake_minimum_required(VERSION 3.16)
project(xrpl_codegen LANGUAGES NONE)
include("${CMAKE_CURRENT_LIST_DIR}/../XrplProtocolAutogen.cmake")

View File

@@ -12,7 +12,7 @@
"protobuf/6.33.5#ff253ead763bd8d9904a52979cd21e81%1782392410.233933",
"openssl/3.6.3#f806de8933e3bf6f01016c6a888cee2e%1783945160.863288",
"nudb/2.0.9#11149c73f8f2baff9a0198fe25971fc7%1782392402.297166",
"mpt-crypto/1.0.2#b313cef0c1a493eb970ad185b2e9bab7%1784285108.866483",
"mpt-crypto/0.4.0-rc4#ffdba12f2332357f0d8b0ae944cfff52%1784138702.932355",
"lz4/1.10.0#982d9b673900f665a1da109e09c17cab%1782392402.164188",
"libiconv/1.17#9923bc6dc6f106646d6967e0039a5ada%1782392792.775744",
"libbacktrace/cci.20210118#a7691bfccd8caaf66309df196790a5a1%1782392402.420732",
@@ -20,10 +20,8 @@
"jemalloc/5.3.1#1fc58d55316041f10fbc1e8a2eae632a%1776700028.228",
"gtest/1.17.0#5224b3b3ff3b4ce1133cbdd27d53ee7d%1782392402.791979",
"grpc/1.81.1#f729f6d75992d20f9c72828e9142d62f%1783945160.094135",
"fast_float/8.2.10#f6f28d6bb22112078e7dbda611caf681%1782494504.298",
"ed25519/2015.03#ae761bdc52730a843f0809bdf6c1b1f6%1782307148.15562",
"date/3.0.4#862e11e80030356b53c2c38599ceb32b%1782392402.538492",
"corrosion/0.6.1#bfa292df0a957bc70a450ff316cd9435%1786119416.131296",
"c-ares/1.34.6#545240bb1c40e2cacd4362d6b8967650%1782392402.681654",
"bzip2/1.0.8#c470882369c2d95c5c77e970c0c7e321%1782392402.296732",
"boost/1.91.0#ea540ca2133d831b560036aa24dece3c%1782392419.475605",
@@ -36,7 +34,7 @@
"protobuf/6.33.5#ff253ead763bd8d9904a52979cd21e81%1782392410.233933",
"nasm/2.16.01#31e26f2ee3c4346ecd347911bd126904%1782395690.33162",
"msys2/cci.latest#d22fe7b2808f5fd34d0a7923ace9c54f%1770657326.649",
"m4/1.4.19#1727f439cf74e83826ec96d0b4904eee%1784541921.659",
"m4/1.4.19#34c4bbc3eeebe98ca6edf2f52d602e7d%1777282960.259",
"cmake/4.3.3#840cf00ea09777e05c2050a50a82c722%1782392418.696091",
"b2/5.4.2#ffd6084a119587e70f11cd45d1a386e2%1782392402.624226",
"automake/1.16.5#b91b7c384c3deaa9d535be02da14d04f%1755524470.56",

View File

@@ -1,21 +0,0 @@
#!/usr/bin/env bash
# Install our Conan configuration, profiles and the xrplf remote into CONAN_HOME.
# Safe to re-run; never deletes the Conan home.
set -euo pipefail
SCRIPT_DIR="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd)"
CONAN_DIR="$(conan config home)"
echo "Installing Conan configuration into ${CONAN_DIR}"
conan config install "${SCRIPT_DIR}/global.conf"
conan config install "${SCRIPT_DIR}/profiles" -tf "${CONAN_DIR}/profiles"
# This script manages these files, so make them read-only - Conan does not
# preserve the source mode. Only the files: the directories must stay writable
# for `conan config install` to replace them.
chmod a-w "${CONAN_DIR}/global.conf"
find "${CONAN_DIR}/profiles" -type f -exec chmod a-w {} +
echo "Adding the xrplf Conan remote"
# --index 0: our patched recipes must win over Conan Center.
conan remote add --index 0 --force xrplf https://conan.xrplf.org/repository/conan/

View File

@@ -1,13 +1,9 @@
{% set os = detect_api.detect_os() %}
{% set arch = detect_api.detect_arch() %}
{% set compiler, version, compiler_exe = detect_api.detect_default_compiler() %}
{% set compiler_version = version %}
{% if os == "Linux" %}
{% set compiler_version = detect_api.default_compiler_version(compiler, version) %}
{% if os == "Macos" %}
{# Minimum macOS the dependencies target. #}
{# Without this, Conan builds each dependency against the (possibly newer) host SDK, so the #}
{# dependency objects target a newer macOS than the binary and the linker warns. #}
{# Keep at or below CMAKE_OSX_DEPLOYMENT_TARGET in CMakeLists.txt. #}
{% set min_macos_version = "15.0" %}
{% endif %}
[settings]
@@ -22,9 +18,6 @@ compiler.runtime=static
{% else %}
compiler.libcxx={{ detect_api.detect_libcxx(compiler, version, compiler_exe) }}
{% endif %}
{% if os == "Macos" %}
os.version={{ min_macos_version }}
{% endif %}
[conf]
{# The Boost recipe builds with b2, which doesn't use Conan's toolchain files. #}
@@ -48,13 +41,3 @@ tools.build:compiler_executables={'c':'{{ cc_exe }}','cpp':'{{ cxx_exe }}'}
{# More info: https://docs.conan.io/2/reference/extensions/binary_compatibility.html #}
user.package:cppstd_version=23
tools.info.package_id:confs+=["user.package:cppstd_version"]
{% if os == "Macos" %}
[buildenv]
{# os.version adds -mmacosx-version-min to compiler command lines, #}
{# but Boost.Context's b2 assembly (.S) rule ignores it, #}
{# so those objects keep the host SDK version and still warn at link time. #}
{# clang's assembler honors this env var regardless, pinning them. #}
{# Scoped to boost/* since it is the only gap. #}
boost/*:MACOSX_DEPLOYMENT_TARGET={{ min_macos_version }}
{% endif %}

View File

@@ -28,9 +28,7 @@ class Xrpl(ConanFile):
}
requires = [
"corrosion/0.6.1",
"ed25519/2015.03",
"fast_float/8.2.10",
"grpc/1.81.1",
"libarchive/3.8.7",
"nudb/2.0.9",
@@ -140,7 +138,7 @@ class Xrpl(ConanFile):
if self.options.jemalloc:
self.requires("jemalloc/5.3.1")
self.requires("lz4/1.10.0", force=True)
self.requires("mpt-crypto/1.0.2", transitive_headers=True)
self.requires("mpt-crypto/0.4.0-rc4", transitive_headers=True)
self.requires("protobuf/6.33.5", force=True)
if self.options.rocksdb:
self.requires("rocksdb/10.5.1")
@@ -213,7 +211,6 @@ class Xrpl(ConanFile):
"boost::thread",
"date::date",
"ed25519::ed25519",
"fast_float::fast_float",
"grpc::grpc++",
"libarchive::libarchive",
"lz4::lz4",

View File

@@ -1,17 +0,0 @@
# The Rust static libraries are linked into C++ targets, so the runtime linkage
# here has to match what the C++ build uses (see cmake/XrplCompiler.cmake).
#
# macOS needs nothing: AppleClang cannot link libgcc/libc++ statically, so the
# C++ build skips those flags on Apple as well.
# Both amd64 and arm64 Linux builds link libgcc statically. This only affects
# links that rustc itself drives (`cargo test` binaries and the like) — the
# `staticlib` crates consumed by CMake are archived, not linked, so rustc
# silently ignores link args for them. Keeping libgcc_s.so.1 off the xrpld link
# line is handled in crates/CMakeLists.txt instead.
[target.'cfg(target_os = "linux")']
rustflags = ["-C", "link-args=-static-libgcc"]
# Windows builds use the static MSVC runtime.
[target.'cfg(windows)']
rustflags = ["-C", "target-feature=+crt-static"]

View File

@@ -1,104 +0,0 @@
find_package(Corrosion REQUIRED)
corrosion_import_crate(MANIFEST_PATH ${CMAKE_CURRENT_SOURCE_DIR}/Cargo.toml)
# The generated C++ lands in the build tree, so put a .clang-tidy next to it to
# keep clang-tidy from analyzing code we don't own.
configure_file(
generated.clang-tidy
"${CMAKE_CURRENT_BINARY_DIR}/.clang-tidy"
COPYONLY
)
add_custom_target(xrpl_crates)
add_dependencies(tidy_prerequisites xrpl_crates)
# On macOS, ld warns `ignoring duplicate libraries` when linking a crate.
# Corrosion is the source of both duplicates it names:
#
# * The crate archive and its cxxbridge archive, because
# `corrosion_add_cxxbridge` makes the two depend on each other, and CMake
# repeats a static library cycle on the link line so single-pass linkers can
# resolve it. (LINK_INTERFACE_MULTIPLICITY can only raise that count.)
# * `-lSystem`, which Corrosion copies from rustc's `native-static-libs` even
# though the compiler driver always links libSystem.
#
# ld needs neither: it resolves the cycle from one copy of each archive and
# links libSystem once. So silence the warning rather than rewrite Corrosion's
# link interface, which the cycle is also part of. The option itself is old —
# Xcode 15 is only where the warning became the default — and the check below
# leaves it out on a linker that does not know it.
if(is_macos)
include(CheckLinkerFlag)
check_linker_flag(
CXX
-Wl,-no_warn_duplicate_libraries
have_no_warn_duplicate_libraries
)
endif()
function(_unlink_libgcc_s crate)
if(NOT (is_linux AND static))
return()
endif()
# Corrosion exposes a crate's staticlib as an imported `<crate>-static`
# target and puts the native libs in its INTERFACE_LINK_LIBRARIES. If either
# of those changes, warn instead of silently letting libgcc_s.so.1 return.
set(imported "${crate}-static")
if(NOT TARGET ${imported})
message(
FATAL_ERROR
"Corrosion did not create the imported target '${imported}', so "
"libgcc_s cannot be removed from the link interface of '${crate}'. "
"xrpld will link libgcc_s.so.1 dynamically. Check where Corrosion "
"${CORROSION_VERSION} now records `native-static-libs`."
)
return()
endif()
get_target_property(libs ${imported} INTERFACE_LINK_LIBRARIES)
if(NOT "gcc_s" IN_LIST libs)
message(
WARNING
"'gcc_s' was not in the link interface of '${imported}' as "
"expected. If the Rust toolchain stopped reporting it this "
"workaround is obsolete and can be deleted; otherwise xrpld may "
"link libgcc_s.so.1 dynamically. Verify with: "
"objdump -p xrpld | grep NEEDED"
)
return()
endif()
list(REMOVE_ITEM libs gcc_s)
set_property(TARGET ${imported} PROPERTY INTERFACE_LINK_LIBRARIES ${libs})
endfunction()
function(add_xrpl_crate name)
cmake_parse_arguments(ARG "" "CRATE" "FILES" ${ARGN})
_unlink_libgcc_s(${ARG_CRATE})
# `cc` picks its runtime flag from `crt-static` alone, so it compiles a
# crate's C++ with `-MT`; Debug needs `-MTd` (to match cmake/XrplCompiler.cmake).
if(is_msvc)
corrosion_set_env_vars(
${ARG_CRATE}
"$<$<CONFIG:Debug>:CXXFLAGS=-MTd>"
)
endif()
corrosion_add_cxxbridge(${name}_cxxbridge CRATE ${ARG_CRATE} FILES
${ARG_FILES}
)
# Generated cxxbridge headers don't exist at configure time; CMake 3.28+
# validates INTERFACE_SOURCES on consuming targets. Clear it to skip the
# existence check — build-time ordering is enforced by the custom commands.
set_target_properties(${name}_cxxbridge PROPERTIES INTERFACE_SOURCES "")
if(have_no_warn_duplicate_libraries)
target_link_options(
${name}_cxxbridge
INTERFACE -Wl,-no_warn_duplicate_libraries
)
endif()
add_dependencies(xrpl_crates ${name}_cxxbridge)
endfunction()
add_xrpl_crate(rs_hello_world CRATE rs_hello_world FILES lib.rs)

301
crates/Cargo.lock generated
View File

@@ -1,301 +0,0 @@
# This file is automatically @generated by Cargo.
# It is not intended for manual editing.
version = 4
[[package]]
name = "anstyle"
version = "1.0.14"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "940b3a0ca603d1eade50a4846a2afffd5ef57a9feac2c0e2ec2e14f9ead76000"
[[package]]
name = "cc"
version = "1.2.61"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d16d90359e986641506914ba71350897565610e87ce0ad9e6f28569db3dd5c6d"
dependencies = [
"find-msvc-tools",
"shlex",
]
[[package]]
name = "clap"
version = "4.6.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "1ddb117e43bbf7dacf0a4190fef4d345b9bad68dfc649cb349e7d17d28428e51"
dependencies = [
"clap_builder",
]
[[package]]
name = "clap_builder"
version = "4.6.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "714a53001bf66416adb0e2ef5ac857140e7dc3a0c48fb28b2f10762fc4b5069f"
dependencies = [
"anstyle",
"clap_lex",
"strsim",
]
[[package]]
name = "clap_lex"
version = "1.1.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c8d4a3bb8b1e0c1050499d1815f5ab16d04f0959b233085fb31653fbfc9d98f9"
[[package]]
name = "codespan-reporting"
version = "0.13.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "af491d569909a7e4dee0ad7db7f5341fef5c614d5b8ec8cf765732aba3cff681"
dependencies = [
"serde",
"termcolor",
"unicode-width",
]
[[package]]
name = "cxx"
version = "1.0.198"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "6fe442a792c7c736eea18b32a7f8a3b63cf8aafabda6760042dc2fdeda456291"
dependencies = [
"cc",
"cxx-build",
"cxxbridge-cmd",
"cxxbridge-flags",
"cxxbridge-macro",
"foldhash",
"link-cplusplus",
]
[[package]]
name = "cxx-build"
version = "1.0.198"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e3184a94384c663718698311a78a51ac00c484c10b4eeac06fb0a068c5f64fa2"
dependencies = [
"cc",
"codespan-reporting",
"indexmap",
"proc-macro2",
"quote",
"scratch",
"syn 3.0.3",
]
[[package]]
name = "cxxbridge-cmd"
version = "1.0.198"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "0148d8fd1199329ddf1d157a5e134e51ceff37c6a7ddd38615c399d81cb05d8d"
dependencies = [
"clap",
"codespan-reporting",
"indexmap",
"proc-macro2",
"quote",
"syn 3.0.3",
]
[[package]]
name = "cxxbridge-flags"
version = "1.0.198"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "52850339faed2eaadd24e286dc1d8268cc6f8a7bd9524d713adc9099566b4c89"
[[package]]
name = "cxxbridge-macro"
version = "1.0.198"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "2c77c856545d886c9bd5215409ebb63b925e262135248b50c79e5a5f194ee47c"
dependencies = [
"indexmap",
"proc-macro2",
"quote",
"syn 3.0.3",
]
[[package]]
name = "equivalent"
version = "1.0.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "877a4ace8713b0bcf2a4e7eec82529c029f1d0619886d18145fea96c3ffe5c0f"
[[package]]
name = "find-msvc-tools"
version = "0.1.9"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "5baebc0774151f905a1a2cc41989300b1e6fbb29aff0ceffa1064fdd3088d582"
[[package]]
name = "foldhash"
version = "0.2.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "77ce24cb58228fbb8aa041425bb1050850ac19177686ea6e0f41a70416f56fdb"
[[package]]
name = "hashbrown"
version = "0.17.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "4f467dd6dccf739c208452f8014c75c18bb8301b050ad1cfb27153803edb0f51"
[[package]]
name = "indexmap"
version = "2.14.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d466e9454f08e4a911e14806c24e16fba1b4c121d1ea474396f396069cf949d9"
dependencies = [
"equivalent",
"hashbrown",
]
[[package]]
name = "link-cplusplus"
version = "1.0.12"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7f78c730aaa7d0b9336a299029ea49f9ee53b0ed06e9202e8cb7db9bae7b8c82"
dependencies = [
"cc",
]
[[package]]
name = "proc-macro2"
version = "1.0.106"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "8fd00f0bb2e90d81d1044c2b32617f68fcb9fa3bb7640c23e9c748e53fb30934"
dependencies = [
"unicode-ident",
]
[[package]]
name = "quote"
version = "1.0.45"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "41f2619966050689382d2b44f664f4bc593e129785a36d6ee376ddf37259b924"
dependencies = [
"proc-macro2",
]
[[package]]
name = "rs-hello_world"
version = "0.1.0"
dependencies = [
"cxx",
]
[[package]]
name = "scratch"
version = "1.0.9"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d68f2ec51b097e4c1a75b681a8bec621909b5e91f15bb7b840c4f2f7b01148b2"
[[package]]
name = "serde"
version = "1.0.228"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9a8e94ea7f378bd32cbbd37198a4a91436180c5bb472411e48b5ec2e2124ae9e"
dependencies = [
"serde_core",
"serde_derive",
]
[[package]]
name = "serde_core"
version = "1.0.228"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "41d385c7d4ca58e59fc732af25c3983b67ac852c1a25000afe1175de458b67ad"
dependencies = [
"serde_derive",
]
[[package]]
name = "serde_derive"
version = "1.0.228"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d540f220d3187173da220f885ab66608367b6574e925011a9353e4badda91d79"
dependencies = [
"proc-macro2",
"quote",
"syn 2.0.117",
]
[[package]]
name = "shlex"
version = "1.3.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "0fda2ff0d084019ba4d7c6f371c95d8fd75ce3524c3cb8fb653a3023f6323e64"
[[package]]
name = "strsim"
version = "0.11.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7da8b5736845d9f2fcb837ea5d9e2628564b3b043a70948a3f0b778838c5fb4f"
[[package]]
name = "syn"
version = "2.0.117"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e665b8803e7b1d2a727f4023456bbbbe74da67099c585258af0ad9c5013b9b99"
dependencies = [
"proc-macro2",
"quote",
"unicode-ident",
]
[[package]]
name = "syn"
version = "3.0.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "53e9bae58849f64dfa4f5d5ae372c8341f7305f82a3868709269343628b659a3"
dependencies = [
"proc-macro2",
"quote",
"unicode-ident",
]
[[package]]
name = "termcolor"
version = "1.4.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "06794f8f6c5c898b3275aebefa6b8a1cb24cd2c6c79397ab15774837a0bc5755"
dependencies = [
"winapi-util",
]
[[package]]
name = "unicode-ident"
version = "1.0.24"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e6e4313cd5fcd3dad5cafa179702e2b244f760991f45397d14d4ebf38247da75"
[[package]]
name = "unicode-width"
version = "0.2.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b4ac048d71ede7ee76d585517add45da530660ef4390e49b098733c6e897f254"
[[package]]
name = "winapi-util"
version = "0.1.11"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c2a7b1c03c876122aa43f3020e6c3c3ee5c05081c9a00739faf7503aeba10d22"
dependencies = [
"windows-sys",
]
[[package]]
name = "windows-link"
version = "0.2.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f0805222e57f7521d6a62e36fa9163bc891acd422f971defe97d64e70d0a4fe5"
[[package]]
name = "windows-sys"
version = "0.61.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ae137229bcbd6cdf0f7b80a31df61766145077ddf49416a728b02cb3921ff3fc"
dependencies = [
"windows-link",
]

View File

@@ -1,15 +0,0 @@
[workspace]
members = ["hello_world"]
resolver = "3"
[workspace.dependencies]
cxx = { version = "1.0.198", features = ["c++20"] }
[workspace.package]
edition = "2024"
[profile.release]
opt-level = 3
overflow-checks = true
lto = true
debug = true

View File

@@ -1,10 +0,0 @@
---
# Neutralizes clang-tidy for the corrosion/cxxbridge-generated C++. Copied into
# the crates build directory by crates/CMakeLists.txt, next to the generated
# sources, so clang-tidy picks it up instead of the top-level configuration.
#
# One check is kept enabled to avoid clang-tidy's "no checks enabled" error.
Checks: "-*,google-readability-todo"
WarningsAsErrors: ""
HeaderFilterRegex: ""
InheritParentConfig: false

View File

@@ -1,10 +0,0 @@
[package]
name = "rs-hello_world"
version = "0.1.0"
edition.workspace = true
[lib]
crate-type = ["staticlib"]
[dependencies]
cxx.workspace = true

View File

@@ -1,10 +0,0 @@
#[cxx::bridge(namespace = "rs::hello_world")]
mod ffi {
extern "Rust" {
fn hello_world() -> String;
}
}
pub fn hello_world() -> String {
"hello_world".to_string()
}

Binary file not shown.

View File

@@ -6,55 +6,22 @@ This document explains how to set one up.
## Tested compiler versions
`xrpld` is built in the **C++23** dialect by default, so your toolchain has to
support it — see [compiler support for C++23][cpp23-support].
The versions currently tested in CI are:
`xrpld` is built in the **C++23** dialect by default.
Make sure your toolchain is recent enough — the compiler versions currently tested in CI are:
| Compiler | Version |
| ----------- | ------------------ |
| GCC | 15.2 |
| Clang | 22 |
| Apple Clang | 21 |
| MSVC | Visual Studio 2026 |
| Compiler | Version |
| ----------- | ------- |
| GCC | 15.2 |
| Clang | 22 |
| Apple Clang | 17 |
| MSVC | 19.44 |
LLVM tools (`clang-tidy` and `clang-format`) are also pinned to version 22.
### Older compilers
Older compilers may fail to build the latest `develop` code: the codebase now
relies on C++23 features and has been adjusted for `clang-tidy`.
If the latest code doesn't build for you, update your build toolchain first.
If updating isn't an option for you, we do accept pull requests that fix builds
on older compilers, as long as the change is small and doesn't make the code
harder to read. What we can't promise is that older compilers will keep working:
only the versions in the table above are tested in CI, and we won't hold back
the use of C++23 features or add invasive workarounds to keep an untested
compiler building. Treat support for anything outside the table as best-effort.
## Required tools
Besides a compiler, building `xrpld` requires:
| Tool | Minimum version |
| ------------------------------------------- | --------------- |
| [Git](https://git-scm.com/downloads) | any recent |
| [Python](https://www.python.org/downloads/) | 3.11 |
| [Conan](https://conan.io/downloads.html) | 2.17 |
| [CMake](https://cmake.org/download/) | 3.16 |
On Linux and macOS, the [Nix development shell](./nix.md) provides all of them
(see below). On Windows they have to be installed manually.
Building with `-Drust=ON` additionally requires a Rust toolchain, see
[Rust](#rust). A default build does not, so it is not in the table above.
Once they are in place, verify that everything is installed and runnable with:
```bash
./bin/check-tools.sh
```
## Linux and macOS
The **recommended way** to get a development environment on Linux and macOS is
@@ -72,15 +39,20 @@ Clang. If you instead opt to use your system-wide Apple Clang (via
below).
See [Using the Nix development shell](./nix.md) for installation and usage
details, including how to select a different compiler and why we recommend Nix
over a hand-maintained environment.
details, including how to select a different compiler.
> [!NOTE]
> Using Nix is not mandatory. Any custom environment (Homebrew packages or
> anything else) will continue to work, but then it is up to you to keep it in
> sync with the environment used in CI. Nix unifies the development environment
> for everyone and synchronizes updates, which is why we recommend it.
### macOS: managing the Apple Clang version
If you use your system-wide Apple Clang on macOS (via `nix develop .#apple-clang`),
the compiler version is whatever your installed Xcode (or Command Line Tools)
provides. The following command should return a version greater than or equal to
the [tested one](#tested-compiler-versions):
the [minimum required](#tested-compiler-versions):
```bash
clang --version
@@ -117,42 +89,23 @@ building xrpld. You may want to install and pin a specific version of Xcode:
Nix is not available on Windows, so the required tools have to be installed
manually:
- [Visual Studio 2026](https://visualstudio.microsoft.com/) with the
- [Visual Studio 2022](https://visualstudio.microsoft.com/) with the
**"Desktop development with C++"** workload — this provides MSVC and the
"x64 Native Tools Command Prompt". CI configures CMake with the
`Visual Studio 18 2026` generator.
"x64 Native Tools Command Prompt".
- [Git for Windows](https://git-scm.com/download/win)
- Python, Conan, and CMake, at the versions listed in
[Required tools](#required-tools).
- a [Rust toolchain](https://rustup.rs) — only needed to build with
`-Drust=ON`, see [Rust](#rust)
- [Python 3.11](https://www.python.org/downloads/), or higher
- [Conan 2.17](https://conan.io/downloads.html), or higher
- [CMake 3.22](https://cmake.org/download/), or higher
## Rust
The repository contains a Rust workspace in [`crates/`](../../crates), whose
crates are exposed to C++ through [cxx](https://cxx.rs) bindings. It is **not**
part of a default build: the CMake `rust` option is OFF by default, and with it
off no Rust toolchain is needed. It is only required when configuring with
`-Drust=ON` (which is what CI does), see [Options](../../BUILD.md#options).
The toolchain (`cargo`, `rustc`) is pinned to the channel in
[`rust-toolchain.toml`](../../rust-toolchain.toml) at the repository root. If
you install Rust with [rustup](https://rustup.rs), that file is picked up
automatically, and `cargo`/`rustc` in the repository will use the pinned
version.
Everything else the Rust build needs on the CMake side comes from Conan along
with the rest of the dependencies, so there is nothing further to install.
> [!NOTE]
> Windows is used for development only and is not recommended for production.
## Clang-tidy
`clang-tidy` is required to run static analysis checks locally (see
[CONTRIBUTING.md](../../CONTRIBUTING.md)). It is not required to build the
project. The version this project uses is listed in
[Tested compiler versions](#tested-compiler-versions).
project. This project currently uses `clang-tidy` version 22.
On Linux and macOS, the [Nix development shell](./nix.md) provides that exact
version out of the box — run it via `run-clang-tidy`. No separate installation
is needed.
[cpp23-support]: https://en.cppreference.com/w/cpp/compiler_support/23
On Linux and macOS, the [Nix development shell](./nix.md) provides `clang-tidy`
22 out of the box — run it via `run-clang-tidy`. No separate installation is
needed.

View File

@@ -1,10 +1,3 @@
# Installing xrpld 3.3.0 and earlier
> [!IMPORTANT]
> These instructions apply to xrpld 3.3.0 and earlier, published to
> repos.ripple.com.
> For later releases see [install.md](./install.md).
This document contains instructions for installing xrpld.
The APT package manager is common on Debian-based Linux distributions like
Ubuntu,
@@ -59,7 +52,7 @@ The default [prefix][1] is typically `/usr/local` on Linux and macOS and
5. Add the appropriate XRPL repository for your operating system version:
echo "deb [signed-by=/usr/local/share/keyrings/ripple-key.gpg] https://repos.ripple.com/repos/rippled-deb focal stable" | \
echo "deb [signed-by=/usr/local/share/keyrings/ripple-key.gpg] https://repos.ripple.com/repos/xrpld-deb focal stable" | \
sudo tee -a /etc/apt/sources.list.d/ripple.list
The above example is appropriate for **Ubuntu 20.04 Focal Fossa**. For other operating systems, replace the word `focal` with one of the following:
@@ -113,8 +106,8 @@ The default [prefix][1] is typically `/usr/local` on Linux and macOS and
enabled=1
gpgcheck=0
repo_gpgcheck=1
baseurl=https://repos.ripple.com/repos/rippled-rpm/stable/
gpgkey=https://repos.ripple.com/repos/rippled-rpm/stable/repodata/repomd.xml.key
baseurl=https://repos.ripple.com/repos/xrpld-rpm/stable/
gpgkey=https://repos.ripple.com/repos/xrpld-rpm/stable/repodata/repomd.xml.key
REPOFILE
_Unstable_
@@ -125,8 +118,8 @@ The default [prefix][1] is typically `/usr/local` on Linux and macOS and
enabled=1
gpgcheck=0
repo_gpgcheck=1
baseurl=https://repos.ripple.com/repos/rippled-rpm/unstable/
gpgkey=https://repos.ripple.com/repos/rippled-rpm/unstable/repodata/repomd.xml.key
baseurl=https://repos.ripple.com/repos/xrpld-rpm/unstable/
gpgkey=https://repos.ripple.com/repos/xrpld-rpm/unstable/repodata/repomd.xml.key
REPOFILE
_Nightly_
@@ -137,8 +130,8 @@ The default [prefix][1] is typically `/usr/local` on Linux and macOS and
enabled=1
gpgcheck=0
repo_gpgcheck=1
baseurl=https://repos.ripple.com/repos/rippled-rpm/nightly/
gpgkey=https://repos.ripple.com/repos/rippled-rpm/nightly/repodata/repomd.xml.key
baseurl=https://repos.ripple.com/repos/xrpld-rpm/nightly/
gpgkey=https://repos.ripple.com/repos/xrpld-rpm/nightly/repodata/repomd.xml.key
REPOFILE
2. Fetch the latest repo updates:

108
docs/build/nix.md vendored
View File

@@ -7,7 +7,7 @@ This guide explains how to use Nix to set up a reproducible development environm
## Benefits of Using Nix
- **Reproducible environment**: Everyone gets the same versions of tools and compilers
- **Matches CI**: The Linux CI runs in Docker images built from this exact Nix environment, and CI builds some macOS configurations in it as well
- **Matches CI**: The Linux CI runs in Docker images built from this exact Nix environment
- **No system pollution**: Dependencies are isolated and don't affect your system packages
- **Consistent compilers**: The GCC and Clang shells use the same versions as CI
- **Quick setup**: Get started with a single command
@@ -68,7 +68,7 @@ A compiler can be chosen by providing its name with the `.#` prefix, e.g. `nix d
On Linux, `.#gcc` and `.#clang` provide the exact toolchain CI uses:
the compiler (pinned in [`nix/packages.nix`](../../nix/packages.nix))
rebuilt against the pinned custom glibc (see [`nix/linux.nix`](../../nix/linux.nix)).
rebuilt against the pinned custom glibc (see [`nix/compilers.nix`](../../nix/compilers.nix)).
Building that toolchain the first time is slow unless it is fetched from a Nix binary cache.
If you don't need the custom glibc, the Linux-only `.#gcc-plain` and `.#clang-plain`
give you the stock nixpkgs compilers of the same versions.
@@ -120,7 +120,7 @@ nix develop -c "$SHELL"
>
> If it doesn't, either adjust your shell configuration so it doesn't override `$PATH`, or use [direnv](#automatic-activation-with-direnv) (below), which loads the environment _after_ your shell config and so takes precedence regardless of the shell you use.
## Building xrpld in the Nix shell
## Building xrpld with Nix
Once inside the Nix development shell, follow the standard [build instructions](../../BUILD.md#steps). The Nix shell provides all necessary tools (CMake, Ninja, Conan, etc.).
@@ -128,100 +128,6 @@ Coverage builds (`-Dcoverage=ON`) work in the `gcc` shell (and `gcc-plain` on Li
each ships a `gcov` matching its compiler, since Nix's cc-wrapper does not expose one.
The `clang` shells do not include `llvm-cov`, so use a `gcc` shell for coverage.
Builds of the Rust crates (`-Drust=ON`) also work out of the box: every shell
provides the Rust toolchain pinned in
[`rust-toolchain.toml`](../../rust-toolchain.toml) (see
[Rust](./environment.md#rust)), plus the `cargo-audit`, `cargo-llvm-cov` and
`cargo-nextest` plugins.
## Conan configuration
The shell runs [`conan/init.sh`](../../conan/init.sh) on entry, so
[Set Up Conan](../../BUILD.md#set-up-conan) is already done for you. It installs
into the shell's own Conan home: `CONAN_HOME=~/.conan2-nix`.
### Prebuilt packages
On **Linux**, the binaries on the `xrplf` remote are built in this same Nix
environment — CI runs in Docker images that bundle the dev shell's toolchain (see
[`nix/docker`](../../nix/docker)) — so `.#gcc` and `.#clang` can reuse them. The
`-plain` shells do not match that toolchain's glibc, so binaries from the remote
are not a reliable match there.
On **macOS**, CI also builds in this Nix environment, in Debug and Release (the
`macos-arm64-*-nix` configurations — Debug because the profile defaults to it).
The Nix build resolves to `compiler=clang`, so it gets its own package IDs,
separate from the Apple Clang ones. The
[dependency upload](../../.github/workflows/upload-conan-deps.yml) publishes them
on pushes to `develop` and on manual runs — its nightly run rebuilds everything
from source but uploads nothing — so once a set has been published `nix develop`
can reuse it instead of compiling every dependency locally. These configurations
run outside the reduced pull-request matrix, so label a PR `Full CI build` when it
touches `flake.lock` or `nix/`.
To compile everything from source, add `--build '*'` to the `conan install`
command.
### Why the nixpkgs revision is not part of the package ID
A Conan package ID records the compiler and its major version, but nothing about
the nixpkgs revision the toolchain came from — and `flake.lock` moves far more
often than the toolchain meaningfully changes, so folding it in would rebuild
every dependency on every bump for nothing.
That is safe as long as no cached artifact resolves a `/nix/store` path at run
time, because store paths change on every update and the old ones disappear with
`nix-collect-garbage`. With the `clang` toolchain macOS CI and the dev shell use,
they do not: it links against `/usr/lib/libc++` and `/usr/lib/libSystem`, and
store paths reach the `.a` files only through debug info, which nothing resolves
at link or run time.
> [!WARNING]
> This does not hold for `nix develop .#gcc` on macOS. There is no system
> libstdc++, so GCC links its own from the store and every binary keeps a
> `/nix/store` reference. That shell is fine for tooling, but it is not a build
> configuration CI covers, and no dependency binaries are published for it.
This is checked rather than assumed.
[`bin/check-nix-store-refs.sh`](../../bin/check-nix-store-refs.sh) takes one file
or directory and fails if a binary under it resolves a store path at run time.
CI runs it over the build output and the Conan cache, and again in the upload job
before anything is published. You can run it yourself:
```bash
bin/check-nix-store-refs.sh build
bin/check-nix-store-refs.sh ~/.conan2-nix
```
It works on Linux too, but asserts something narrower there: the toolchain always
writes the store into `PT_INTERP` and `RUNPATH`, and CI builds inside an image
whose store is fixed for its lifetime, so that is fine. Only the binaries
[`PatchNixBinary.cmake`](../../cmake/PatchNixBinary.cmake) retargets to the
system loader have to be clean, and those are what CI checks:
```bash
bin/check-nix-store-refs.sh build/xrpld
```
### The libresolv stub
This is not hypothetical: `xrpld` used to be caught by it. The c-ares package
tells the linker to pass `-lresolv`, and nixpkgs keeps `libresolv` out of the
macOS SDK and ships it as an ordinary store dylib — so every Nix-built `xrpld`
recorded a `/nix/store/…-libresolv-93/lib/libresolv.9.dylib` load command and
stopped running once that path was collected. Nothing in the link uses a single
symbol from it.
Both environments now put a stub on the linker search path
(`libresolvSystemStub` in [`nix/darwin.nix`](../../nix/darwin.nix)): the
same library with its install name set to `/usr/lib/libresolv.9.dylib`, which is
exactly the load command the Apple Clang build records.
Package IDs did not change, so Conan keeps serving anything built before the
stub landed. If a binary fails to start with `Library not loaded: /nix/store/…`,
see [that entry](./nix_troubleshooting.md#library-not-loaded-nixstore-from-a-binary-that-used-to-work)
in the troubleshooting guide.
## Automatic Activation with direnv
[direnv](https://direnv.net/) or [nix-direnv](https://github.com/nix-community/nix-direnv) can automatically activate the Nix development shell when you enter the repository directory.
@@ -236,6 +142,14 @@ The repository already ships an `.envrc` at its root that activates the Nix flak
> [!NOTE]
> direnv only caches the `.direnv` directory (already listed in `.gitignore`); no other repository files are affected.
## Conan and Prebuilt Packages
Please note that there is no guarantee that binaries from conan cache will work when using nix. If you encounter any errors, please use `--build '*'` to force conan to compile everything from source:
```bash
conan install .. --output-folder . --build '*' --settings build_type=Release
```
## Updating `flake.lock` file
To update `flake.lock` to the latest revision use `nix flake update` command.

View File

@@ -3,78 +3,6 @@
Common issues encountered when using the [Nix development shell](./nix.md), and
how to resolve them.
## `command not found: nix` after a macOS update
If a shell suddenly can't find `nix` at all:
```
$ nix develop
zsh: command not found: nix
```
then Nix is almost certainly still installed — only the shell hook that puts it
on your `PATH` is gone. Confirm that first:
```bash
ls -l /nix/var/nix/profiles/default/bin/nix
```
If that exists, the installation is fine and this is purely a `PATH` problem.
### Why it happens
The installer does not touch your dotfiles. Instead it sources a setup script
from the Nix store by editing **system-wide** rc files:
| Shell | File the installer edits |
| ----- | ------------------------------------- |
| bash | `/etc/bashrc`, `/etc/bash.bashrc` |
| zsh | `/etc/zshrc` |
| fish | `$__fish_sysconf_dir/conf.d/nix.fish` |
macOS manages `/etc/zshrc`, so an OS update can replace it with the vendor copy
and silently drop the Nix block. `/etc/bashrc` and the fish file usually survive,
which is why the breakage often shows up in zsh only. You can verify this by
diffing against the backup the installer left behind:
```bash
diff /etc/zshrc /etc/zshrc.backup-before-nix
```
If they are identical, the Nix snippet was wiped. This is upstream issue
[NixOS/nix#3616](https://github.com/NixOS/nix/issues/3616).
### Fix
To unblock the current shell:
```bash
. /nix/var/nix/profiles/default/etc/profile.d/nix-daemon.sh
```
For a permanent fix, add the snippet to your **user** rc file rather than
restoring `/etc/zshrc` — user dotfiles are not clobbered by OS updates:
```bash
cat >>~/.zshrc <<'EOF'
# Nix
if [ -e '/nix/var/nix/profiles/default/etc/profile.d/nix-daemon.sh' ]; then
. '/nix/var/nix/profiles/default/etc/profile.d/nix-daemon.sh'
fi
# End Nix
EOF
```
The scripts guard against double-sourcing via `__ETC_PROFILE_NIX_SOURCED`, so
this is safe even if a system-wide hook is later restored.
> [!NOTE]
> `/etc/zshrc` and `~/.zshrc` are only read by **interactive** zsh. If the
> snippet is present but `zsh -c '…'`, a script, or an IDE terminal still can't
> find `nix`, that shell is non-interactive — put the snippet in `~/.zshenv`
> instead.
## Git worktrees
If `nix develop` fails with an error like:
@@ -131,91 +59,3 @@ once it picks up that rebuild, then re-run the `grep libgit2` check above to
confirm it reports `1.9.4` or newer.
Until then, prefer the workarounds above.
## `wint_t` / `uint32_t` errors from the Nix libc++ headers
A build that mixes the Nix toolchain with the system SDK fails in libc++ itself,
with errors that look nothing like your code:
```
/nix/store/...-libcxx-.../include/c++/v1/cwchar:136:9: error: target of using declaration conflicts with declaration already in scope
136 | using ::wint_t _LIBCPP_USING_IF_EXISTS;
/Library/Developer/CommandLineTools/SDKs/MacOSX.sdk/usr/include/sys/_types/_wint_t.h:32:25: note: target of using declaration
...
error: use of undeclared identifier 'UINT32_C'
```
The give-away is the second path: Nix's libc++ headers are being combined with
the **Xcode Command Line Tools** SDK instead of the Nix one.
### Why it happens
`SDKROOT` and `DEVELOPER_DIR` are what point the toolchain at the Nix SDK, and
they are not baked into the compiler — a dev shell gets them from the
`apple-sdk` setup hook. CMake, finding neither, asks `xcrun`, which answers with
the system SDK. Nix's `libc++` and Apple's headers then declare the same types
twice.
### Fix
Run the build from inside the dev shell (`nix develop`), or from an environment
that exports both variables. To confirm which SDK a configured build is using:
```bash
grep -o '\-isysroot [^ ]*' build/compile_commands.json | sort -u
```
It should print a `/nix/store/...-apple-sdk-*` path. If it prints
`/Library/Developer/CommandLineTools/...`, re-configure from within the shell —
CMake caches the sysroot, so an existing `build/` directory keeps the wrong one.
## `Library not loaded: /nix/store/…` from a binary that used to work
A binary stops starting after a `nix flake update`, or after
`nix-collect-garbage` removes the paths the previous toolchain used:
```
dyld[57271]: Library not loaded: /nix/store/…-libresolv-93/lib/libresolv.9.dylib
```
[`bin/check-nix-store-refs.sh`](../../bin/check-nix-store-refs.sh) finds the same
thing without having to run anything, and names the file:
```
$ bin/check-nix-store-refs.sh ~/.conan2-nix
::error file=/Users/you/.conan2-nix/p/b/c-area24ded30c388c/p/bin/adig::references the Nix store at run time
/Users/you/.conan2-nix/p/b/c-area24ded30c388c/p/bin/adig
/nix/store/p4lp3xq4imd1qzqh08x8vcq2zfhi7rca-libresolv-93/lib/libresolv.9.dylib
/Users/you/.conan2-nix: checked 135, skipped 2495, 1 with Nix store references.
```
Conan's cache folders are named after a truncated package name plus a hash, so
ask Conan which package the offending one belongs to — pass the folder holding
the hash, not the file itself:
```
$ conan cache ref ~/.conan2-nix/p/b/c-area24ded30c388c
c-ares/1.34.6#545240bb1c40e2cacd4362d6b8967650:dab5992496abe6d219defb7986ecbf367615a5e5#…
```
### Why it happens
The binary records a store path that no longer exists. Nothing we build should:
see [Prebuilt packages](./nix.md#prebuilt-packages) for why, and
`libresolvSystemStub` in [`nix/darwin.nix`](../../nix/darwin.nix) for the one
dependency that needed help to comply.
A Conan package ID does not encode the nixpkgs revision, so a package built
before that stub existed stays in your local cache and keeps being reused. The
dev shell is also what tends to produce one: it is a slightly _less_ isolated
build environment than CI's, because `mkShell` puts every tool's headers and
libraries on the compiler's search path — which is how c-ares found the Nix
`libresolv` in the first place.
### Fix
Drop that package and let Conan refetch or rebuild it:
```bash
conan remove 'c-ares/*'
```

View File

@@ -1,144 +0,0 @@
# Installing xrpld
> [!NOTE]
> These instructions apply to packages published from 2026-08-19 onwards.
> For xrpld 3.3.0 and earlier see [install-legacy.md](./install-legacy.md).
`xrpld` is published as DEB and RPM packages for 64-bit x86 Linux.
Use APT on Debian-based distributions such as Debian and Ubuntu,
and YUM on Red Hat-based distributions such as RHEL, AlmaLinux, and Rocky Linux.
To build from source instead, see [BUILD.md](../BUILD.md).
## Release channels
Packages are published to four channels:
- `stable` - the latest production release
- `unstable` - release candidates
- `experimental` - beta builds
- `develop` - every push to the [`develop` branch](https://github.com/XRPLF/rippled/tree/develop)
See [Publishing packages](../package/README.md#publishing-packages) for how channels are produced.
The instructions below use `stable`.
To follow another channel, replace `stable` with its name
wherever it appears in the repository configuration.
> [!WARNING]
> Channels other than `stable` may be broken at any time.
> Do not use them for production servers.
## Install the xrpld package
### With the APT package manager
1. Install utilities:
```bash
sudo apt update -y
sudo apt install -y apt-transport-https ca-certificates curl gnupg
```
2. Add the XRPL Foundation package-signing key to your list of trusted keys:
```bash
sudo install -d -m 0755 /etc/apt/keyrings
sudo curl -fsS https://packages.xrplf.org/xrplf.asc -o /etc/apt/keyrings/xrplf.asc
```
3. Check the fingerprint of the newly-added key:
```bash
gpg --show-keys /etc/apt/keyrings/xrplf.asc
```
The output should be:
```text
pub rsa4096 2026-08-18 [SC]
B655416741221F780FBCFBC9AA84D41A11D29FA9
uid XRPLF Packages <distribution@xrplf.org>
```
In particular, make sure that the fingerprint matches.
4. Add the repository, using the channel you picked in [Release channels](#release-channels):
```bash
echo "deb [signed-by=/etc/apt/keyrings/xrplf.asc] https://packages.xrplf.org/repository/deb-stable focal main" | \
sudo tee /etc/apt/sources.list.d/xrplf.list
```
5. Fetch the repository:
```bash
sudo apt -y update
```
6. Install the `xrpld` software package:
```bash
sudo apt -y install xrpld
```
### With the YUM package manager
1. Add the XRPL Foundation package-signing key:
```bash
sudo rpm --import https://packages.xrplf.org/xrplf.asc
```
2. Add the repository, using the channel you picked in [Release channels](#release-channels):
```bash
cat << REPOFILE | sudo tee /etc/yum.repos.d/xrplf.repo
[xrplf-stable]
name=XRP Ledger Packages
enabled=1
baseurl=https://packages.xrplf.org/repository/rpm-stable/
gpgcheck=1
repo_gpgcheck=0
gpgkey=https://packages.xrplf.org/xrplf.asc
REPOFILE
```
`gpgcheck=1` verifies each package against the key above.
`repo_gpgcheck` is off because the repository metadata is generated by the server and is not signed.
3. Install the `xrpld` package:
```bash
sudo yum install -y xrpld
```
## The xrpld service
Both package managers install a systemd unit and enable it, so `xrpld` starts on boot.
Check whether it is already running:
```bash
systemctl status xrpld.service
```
The APT packages start it immediately as well; the YUM packages do not, so start it yourself:
```bash
sudo systemctl start xrpld.service
```
### Optional: binding to privileged ports
To serve incoming API requests on port 80 or 443, grant the service the capability to bind them.
You must also update the config file's port settings.
```bash
sudo install -d -m 0755 /etc/systemd/system/xrpld.service.d
sudo tee /etc/systemd/system/xrpld.service.d/privileged-ports.conf >/dev/null <<'EOF'
[Service]
CapabilityBoundingSet=CAP_NET_BIND_SERVICE
AmbientCapabilities=CAP_NET_BIND_SERVICE
EOF
sudo systemctl daemon-reload
sudo systemctl restart xrpld.service
```

24
docs/sample_chart.doc Normal file
View File

@@ -0,0 +1,24 @@
/*!
\page somestatechart Example state diagram
\startuml SomeState "my state diagram"
scale 600 width
[*] -> State1
State1 --> State2 : Succeeded
State1 --> [*] : Aborted
State2 --> State3 : Succeeded
State2 --> [*] : Aborted
state State3 {
state "Accumulate Enough Data\nLong State Name" as long1
long1 : Just a test
[*] --> long1
long1 --> long1 : New Data
long1 --> ProcessData : Enough Data
}
State3 --> State3 : Failed
State3 --> [*] : Succeeded / Save Result
State3 --> [*] : Aborted
\enduml
*/

View File

@@ -1,6 +1,6 @@
#pragma once
#include <filesystem>
#include <boost/filesystem.hpp>
namespace xrpl {
@@ -13,6 +13,6 @@ namespace xrpl {
* @throws runtime_error
*/
void
extractTarLz4(std::filesystem::path const& src, std::filesystem::path const& dst);
extractTarLz4(boost::filesystem::path const& src, boost::filesystem::path const& dst);
} // namespace xrpl

View File

@@ -3,7 +3,6 @@
#include <xrpl/basics/Slice.h>
#include <xrpl/beast/utility/instrumentation.h>
#include <algorithm>
#include <cstdint>
#include <cstring>
#include <memory>
@@ -157,19 +156,6 @@ public:
}
/** @} */
/**
* Set every byte in the buffer to the given value.
*
* The size is unchanged, and this is a no-op on an empty buffer.
*
* @param value the byte to write to every position.
*/
void
fill(std::uint8_t value) noexcept
{
std::fill_n(p_.get(), size_, value);
}
/**
* Reset the buffer.
* All memory is deallocated. The resulting size is 0.
@@ -240,4 +226,10 @@ operator==(Buffer const& lhs, Buffer const& rhs) noexcept
return std::memcmp(lhs.data(), rhs.data(), lhs.size()) == 0;
}
inline bool
operator!=(Buffer const& lhs, Buffer const& rhs) noexcept
{
return !(lhs == rhs);
}
} // namespace xrpl

View File

@@ -1,79 +1,24 @@
#pragma once
#include <boost/filesystem.hpp>
#include <boost/system/error_code.hpp>
#include <cstddef>
#include <filesystem>
#include <optional>
#include <string>
#include <system_error>
namespace xrpl {
std::string
getFileContents(
std::error_code& ec,
std::filesystem::path const& sourcePath,
boost::system::error_code& ec,
boost::filesystem::path const& sourcePath,
std::optional<std::size_t> maxSize = std::nullopt);
void
writeFileContents(
std::error_code& ec,
std::filesystem::path const& destPath,
boost::system::error_code& ec,
boost::filesystem::path const& destPath,
std::string const& contents);
/**
* Generate a unique, non-existing path under @p base whose filename starts with
* @p prefix and ends with a random hex suffix.
*
* Attempts up to @p maxAttempts paths. Throws `std::runtime_error` if a unique
* path cannot be found or if the filesystem returns an error while checking for
* existence.
*/
std::filesystem::path
uniqueRandomPath(
std::filesystem::path const& base,
std::string const& prefix = "",
std::size_t maxAttempts = 100);
/**
* RAII temporary directory.
*
* The directory and all its contents are deleted when
* the instance of `TempDir` is destroyed.
*/
class TempDir
{
std::filesystem::path path_;
public:
#if !GENERATING_DOCS
TempDir(TempDir const&) = delete;
TempDir&
operator=(TempDir const&) = delete;
#endif
/**
* Construct a temporary directory.
*/
TempDir();
/**
* Destroy a temporary directory.
*/
~TempDir();
/**
* Get the native path for the temporary directory.
*/
[[nodiscard]] std::string
path() const;
/**
* Get the native path for a file.
*
* The file does not need to exist.
*/
[[nodiscard]] std::string
file(std::string const& name) const;
};
} // namespace xrpl

View File

@@ -96,6 +96,9 @@ public:
SharedIntrusive&
operator=(SharedIntrusive const& rhs);
bool
operator!=(std::nullptr_t) const;
bool
operator==(std::nullptr_t) const;

View File

@@ -111,6 +111,13 @@ SharedIntrusive<T>::operator=(SharedIntrusive<TT>&& rhs)
return *this;
}
template <class T>
bool
SharedIntrusive<T>::operator!=(std::nullptr_t) const
{
return this->get() != nullptr;
}
template <class T>
bool
SharedIntrusive<T>::operator==(std::nullptr_t) const

View File

@@ -3,8 +3,8 @@
#include <xrpl/beast/utility/Journal.h>
#include <boost/beast/core/string.hpp>
#include <boost/filesystem.hpp>
#include <filesystem>
#include <fstream>
#include <map>
#include <memory>
@@ -84,7 +84,7 @@ private:
* @return `true` if the file was opened.
*/
bool
open(std::filesystem::path const& path);
open(boost::filesystem::path const& path);
/**
* Close and re-open the system file associated with the log
@@ -133,7 +133,7 @@ private:
private:
std::unique_ptr<std::ofstream> stream_;
std::filesystem::path path_;
boost::filesystem::path path_;
};
std::mutex mutable mutex_;
@@ -152,7 +152,7 @@ public:
virtual ~Logs() = default;
bool
open(std::filesystem::path const& pathToLogFile);
open(boost::filesystem::path const& pathToLogFile);
beast::Journal::Sink&
get(std::string const& name);

View File

@@ -304,7 +304,7 @@ concept Integral64 = std::is_same_v<T, std::int64_t> || std::is_same_v<T, std::u
* on-ledger are non-negative. This is due to implementation details of
* several operations which use unsigned arithmetic internally. This is
* sufficient to represent all valid XRP values (where the absolute value
* can not exceed kInitialXRP: 10^17), and MPT values (where the absolute
* can not exceed INITIAL_XRP: 10^17), and MPT values (where the absolute
* value can not exceed maxMPTokenAmount: 2^63-1).
*
* ---- Mantissa Range Switching ----
@@ -449,6 +449,12 @@ public:
x.exponent_ == y.exponent_;
}
friend constexpr bool
operator!=(Number const& x, Number const& y) noexcept
{
return !(x == y);
}
friend constexpr bool
operator<(Number const& l, Number const& r) noexcept
{

View File

@@ -11,7 +11,7 @@ namespace xrpl {
class Resolver
{
public:
using HandlerType = std::function<void(std::string, std::vector<beast::ip::Endpoint>)>;
using HandlerType = std::function<void(std::string, std::vector<beast::IP::Endpoint>)>;
virtual ~Resolver() = 0;

View File

@@ -85,6 +85,12 @@ public:
}
};
inline bool
operator!=(SHAMapHash const& x, SHAMapHash const& y)
{
return !(x == y);
}
template <>
inline std::size_t
extract(SHAMapHash const& key)

View File

@@ -208,6 +208,12 @@ operator==(Slice const& lhs, Slice const& rhs) noexcept
return std::memcmp(lhs.data(), rhs.data(), lhs.size()) == 0;
}
inline bool
operator!=(Slice const& lhs, Slice const& rhs) noexcept
{
return !(lhs == rhs);
}
inline bool
operator<(Slice const& lhs, Slice const& rhs) noexcept
{

View File

@@ -2,6 +2,7 @@
#include <xrpl/basics/Blob.h>
#include <boost/format.hpp>
#include <boost/utility/string_view.hpp>
#include <array>
@@ -124,31 +125,9 @@ struct ParsedUrl
bool
parseUrl(ParsedUrl& pUrl, std::string const& strUrl);
/**
* Remove leading and trailing ASCII whitespace.
*
* Whitespace is the fixed set " \t\n\v\f\r"; the current locale is not
* consulted, so the result depends only on the input.
*
* @param str The string to trim.
* @return @p str without leading or trailing whitespace.
*/
std::string
trimWhitespace(std::string str);
/**
* Fold ASCII upper case letters to lower case.
*
* Only 'A' through 'Z' are remapped; every other byte is left alone and the
* current locale is not consulted, so the result depends only on the input.
*
* @param str The string to fold.
* @return @p str with each ASCII upper case letter replaced by its lower case
* equivalent.
*/
std::string
toLower(std::string str);
std::optional<std::uint64_t>
toUInt64(std::string const& s);

View File

@@ -41,35 +41,6 @@
namespace xrpl {
namespace base64 {
/**
* Returns the maximum number of characters needed to base64-encode @p nBytes bytes.
*
* @param nBytes Number of input bytes.
* @return Size of the encoded string, including padding.
*/
constexpr std::size_t
encodedSize(std::size_t const nBytes)
{
return 4 * ((nBytes + 2) / 3);
}
/**
* Returns the maximum number of bytes a base64 string of @p numChars characters
* decodes to.
*
* @param numChars Number of base64 characters.
* @return Upper bound on the number of decoded bytes.
*/
constexpr std::size_t
decodedSize(std::size_t const numChars)
{
return ((numChars / 4) * 3) + 2;
}
} // namespace base64
std::string
base64Encode(std::uint8_t const* data, std::size_t len);

View File

@@ -116,6 +116,12 @@ public:
{
return lhs.map == rhs.map && lhs.ait == rhs.ait && lhs.mit == rhs.mit;
}
friend bool
operator!=(Iterator const& lhs, Iterator const& rhs)
{
return !(lhs == rhs);
}
};
struct ConstIterator
@@ -183,6 +189,12 @@ public:
{
return lhs.map == rhs.map && lhs.ait == rhs.ait && lhs.mit == rhs.mit;
}
friend bool
operator!=(ConstIterator const& lhs, ConstIterator const& rhs)
{
return !(lhs == rhs);
}
};
private:

View File

@@ -1038,6 +1038,25 @@ public:
Compare,
OtherAllocator> const& other) const;
template <
bool OtherIsMulti,
bool OtherIsMap,
class OtherT,
class OtherDuration,
class OtherAllocator>
bool
operator!=(AgedOrderedContainer<
OtherIsMulti,
OtherIsMap,
Key,
OtherT,
OtherDuration,
Compare,
OtherAllocator> const& other) const
{
return !(this->operator==(other));
}
template <
bool OtherIsMulti,
bool OtherIsMap,

View File

@@ -1340,6 +1340,28 @@ public:
OtherAllocator> const& other) const
requires MaybeMulti;
template <
bool OtherIsMulti,
bool OtherIsMap,
class OtherKey,
class OtherT,
class OtherDuration,
class OtherHash,
class OtherAllocator>
bool
operator!=(AgedUnorderedContainer<
OtherIsMulti,
OtherIsMap,
OtherKey,
OtherT,
OtherDuration,
OtherHash,
KeyEqual,
OtherAllocator> const& other) const
{
return !(this->operator==(other));
}
private:
bool
wouldExceed(size_type additional) const

View File

@@ -82,6 +82,13 @@ public:
return node_ == other.node_;
}
template <typename M>
bool
operator!=(ListIterator<M> const& other) const noexcept
{
return !((*this) == other);
}
reference
operator*() const noexcept
{

View File

@@ -26,7 +26,7 @@ public:
* @param journal Destination for logging output.
*/
static std::shared_ptr<StatsDCollector>
make(ip::Endpoint const& address, std::string const& prefix, Journal journal);
make(IP::Endpoint const& address, std::string const& prefix, Journal journal);
};
} // namespace beast::insight

View File

@@ -15,7 +15,7 @@
//------------------------------------------------------------------------------
namespace beast {
namespace ip {
namespace IP {
using Address = boost::asio::ip::address;
@@ -73,13 +73,13 @@ isPublic(Address const& addr)
return (addr.is_v4()) ? isPublic(addr.to_v4()) : isPublic(addr.to_v6());
}
} // namespace ip
} // namespace IP
//------------------------------------------------------------------------------
template <class Hasher>
void
hash_append(Hasher& h, beast::ip::Address const& addr) noexcept
hash_append(Hasher& h, beast::IP::Address const& addr) noexcept
{
using beast::hash_append;
if (addr.is_v4())
@@ -101,12 +101,12 @@ hash_append(Hasher& h, beast::ip::Address const& addr) noexcept
namespace boost {
template <>
struct hash<::beast::ip::Address>
struct hash<::beast::IP::Address>
{
explicit hash() = default;
std::size_t
operator()(::beast::ip::Address const& addr) const
operator()(::beast::IP::Address const& addr) const
{
return ::beast::Uhash<>{}(addr);
}

View File

@@ -4,7 +4,7 @@
#include <boost/asio.hpp>
namespace beast::ip {
namespace beast::IP {
/**
* Convert to Endpoint.
@@ -32,7 +32,7 @@ toAsioAddress(Endpoint const& endpoint);
boost::asio::ip::tcp::endpoint
toAsioEndpoint(Endpoint const& endpoint);
} // namespace beast::ip
} // namespace beast::IP
namespace beast {
@@ -41,25 +41,25 @@ struct IPAddressConversion
{
explicit IPAddressConversion() = default;
static ip::Endpoint
static IP::Endpoint
fromAsio(boost::asio::ip::address const& address)
{
return ip::fromAsio(address);
return IP::fromAsio(address);
}
static ip::Endpoint
static IP::Endpoint
fromAsio(boost::asio::ip::tcp::endpoint const& endpoint)
{
return ip::fromAsio(endpoint);
return IP::fromAsio(endpoint);
}
static boost::asio::ip::address
toAsioAddress(ip::Endpoint const& address)
toAsioAddress(IP::Endpoint const& address)
{
return ip::toAsioAddress(address);
return IP::toAsioAddress(address);
}
static boost::asio::ip::tcp::endpoint
toAsioEndpoint(ip::Endpoint const& address)
toAsioEndpoint(IP::Endpoint const& address)
{
return ip::toAsioEndpoint(address);
return IP::toAsioEndpoint(address);
}
};

View File

@@ -2,7 +2,7 @@
#include <boost/asio/ip/address_v4.hpp>
namespace beast::ip {
namespace beast::IP {
using AddressV4 = boost::asio::ip::address_v4;
@@ -25,4 +25,4 @@ isPublic(AddressV4 const& addr);
char
getClass(AddressV4 const& address);
} // namespace beast::ip
} // namespace beast::IP

View File

@@ -2,7 +2,7 @@
#include <boost/asio/ip/address_v6.hpp>
namespace beast::ip {
namespace beast::IP {
using AddressV6 = boost::asio::ip::address_v6;
@@ -18,4 +18,4 @@ isPrivate(AddressV6 const& addr);
bool
isPublic(AddressV6 const& addr);
} // namespace beast::ip
} // namespace beast::IP

View File

@@ -13,7 +13,7 @@
#include <optional>
#include <string>
namespace beast::ip {
namespace beast::IP {
using Port = std::uint16_t;
@@ -110,6 +110,12 @@ public:
operator==(Endpoint const& lhs, Endpoint const& rhs);
friend bool
operator<(Endpoint const& lhs, Endpoint const& rhs);
friend bool
operator!=(Endpoint const& lhs, Endpoint const& rhs)
{
return !(lhs == rhs);
}
friend bool
operator>(Endpoint const& lhs, Endpoint const& rhs)
{
@@ -217,7 +223,7 @@ operator<<(OutputStream& os, Endpoint const& endpoint)
std::istream&
operator>>(std::istream& is, Endpoint& endpoint);
} // namespace beast::ip
} // namespace beast::IP
//------------------------------------------------------------------------------
@@ -226,12 +232,12 @@ namespace std {
* std::hash support.
*/
template <>
struct hash<::beast::ip::Endpoint>
struct hash<::beast::IP::Endpoint>
{
hash() = default;
std::size_t
operator()(::beast::ip::Endpoint const& endpoint) const
operator()(::beast::IP::Endpoint const& endpoint) const
{
return ::beast::Uhash<>{}(endpoint);
}
@@ -243,12 +249,12 @@ namespace boost {
* boost::hash support.
*/
template <>
struct hash<::beast::ip::Endpoint>
struct hash<::beast::IP::Endpoint>
{
hash() = default;
std::size_t
operator()(::beast::ip::Endpoint const& endpoint) const
operator()(::beast::IP::Endpoint const& endpoint) const
{
return ::beast::Uhash<>{}(endpoint);
}

View File

@@ -11,7 +11,6 @@
#include <cstddef>
#include <iterator>
#include <string>
#include <string_view>
#include <vector>
namespace beast::rfc2616 {
@@ -187,7 +186,7 @@ splitCommas(FwdIt first, FwdIt last)
template <class Result = std::vector<std::string>>
Result
splitCommas(std::string_view s)
splitCommas(boost::beast::string_view const& s)
{
return splitCommas(s.begin(), s.end());
}
@@ -230,6 +229,12 @@ public:
return other.it_ == it_ && other.end_ == end_ && other.value_.size() == value_.size();
}
bool
operator!=(ListIterator const& other) const
{
return !(*this == other);
}
reference
operator*() const
{

View File

@@ -8,6 +8,7 @@
#include <xrpl/beast/unit_test/runner.h>
#include <xrpl/beast/unit_test/suite_info.h>
#include <boost/lexical_cast.hpp>
#include <boost/optional.hpp>
#include <algorithm>
@@ -187,7 +188,7 @@ Reporter<Unused>::fmtdur(clock_type::duration const& d)
using namespace std::chrono;
auto const ms = duration_cast<milliseconds>(d);
if (ms < seconds{1})
return std::to_string(ms.count()) + "ms";
return boost::lexical_cast<std::string>(ms.count()) + "ms";
std::stringstream ss;
ss << std::fixed << std::setprecision(1) << (ms.count() / 1000.) << "s";
return ss.str();

View File

@@ -6,10 +6,11 @@
#include <xrpl/beast/unit_test/runner.h>
#include <boost/filesystem.hpp>
#include <boost/lexical_cast.hpp>
#include <boost/throw_exception.hpp>
#include <exception>
#include <filesystem>
#include <memory>
#include <ostream>
#include <sstream>
@@ -26,10 +27,10 @@ makeReason(String const& reason, char const* file, int line)
std::string s(reason);
if (!s.empty())
s.append(": ");
namespace fs = std::filesystem;
namespace fs = boost::filesystem;
s.append(fs::path{file}.filename().string());
s.append("(");
s.append(std::to_string(line));
s.append(boost::lexical_cast<std::string>(line));
s.append(")");
return s;
}
@@ -294,20 +295,6 @@ public:
return runner_->arg();
}
protected:
/**
* Lets a suite compose other suites (e.g. an aggregator that reruns a
* group of related suites under its own name) via `SuiteInfo::run`.
*
* @return The runner this suite is executing under.
*/
Runner&
runner() const
{
return *runner_;
}
public:
/**
* DEPRECATED
* @return `true` if the test condition indicates success(a false value)

View File

@@ -0,0 +1,71 @@
#pragma once
#include <boost/filesystem.hpp>
#include <string>
namespace beast {
/**
* RAII temporary directory.
*
* The directory and all its contents are deleted when
* the instance of `temp_dir` is destroyed.
*/
class TempDir
{
boost::filesystem::path path_;
public:
#if !GENERATING_DOCS
TempDir(TempDir const&) = delete;
TempDir&
operator=(TempDir const&) = delete;
#endif
/**
* Construct a temporary directory.
*/
TempDir()
{
auto const dir = boost::filesystem::temp_directory_path();
do
{
path_ = dir / boost::filesystem::unique_path();
} while (boost::filesystem::exists(path_));
boost::filesystem::create_directory(path_);
}
/**
* Destroy a temporary directory.
*/
~TempDir()
{
// use non-throwing calls in the destructor
boost::system::error_code ec;
boost::filesystem::remove_all(path_, ec);
// TODO: warn/notify if ec set ?
}
/**
* Get the native path for the temporary directory
*/
[[nodiscard]] std::string
path() const
{
return path_.string();
}
/**
* Get the native path for the a file.
*
* The file does not need to exist.
*/
[[nodiscard]] std::string
file(std::string const& name) const
{
return (path_ / name).string();
}
};
} // namespace beast

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