Files
reth/.github/workflows/bench.yml
Alexey Shekhirin b49cadb346 ci(bench): rename main/branch to baseline/feature, add ref args (#22284)
Co-authored-by: Georgios Konstantopoulos <me@gakonst.com>
Co-authored-by: Amp <amp@ampcode.com>
2026-02-17 23:00:01 +00:00

472 lines
19 KiB
YAML

# Runs benchmarks.
#
# The reth-bench job replays real blocks via the Engine API against a reth node
# backed by a local snapshot managed with schelk.
#
# It runs the baseline binary and the feature (candidate) binary on the
# same block range (snapshot recovered between runs) to compare performance.
on:
# TODO: Disabled temporarily for https://github.com/CodSpeedHQ/runner/issues/55
# merge_group:
push:
branches: [main]
issue_comment:
types: [created, edited]
workflow_dispatch:
inputs:
blocks:
description: "Number of blocks to benchmark"
required: false
default: "50"
type: string
env:
CARGO_TERM_COLOR: always
BASELINE: base
SEED: reth
RUSTC_WRAPPER: "sccache"
name: bench
permissions:
contents: write
pull-requests: write
concurrency:
group: bench-${{ github.workflow }}-${{ github.head_ref || github.run_id }}
cancel-in-progress: true
jobs:
codspeed:
if: github.event_name != 'issue_comment'
runs-on: depot-ubuntu-latest
strategy:
matrix:
partition: [1, 2]
total_partitions: [2]
include:
- partition: 1
crates: "-p reth-primitives -p reth-trie-common -p reth-trie-sparse"
- partition: 2
crates: "-p reth-trie"
name: codspeed (${{ matrix.partition }}/${{ matrix.total_partitions }})
steps:
- uses: actions/checkout@v6
with:
submodules: true
ref: ${{ github.event_name == 'issue_comment' && format('refs/pull/{0}/merge', github.event.issue.number) || '' }}
- uses: rui314/setup-mold@v1
- uses: dtolnay/rust-toolchain@stable
- uses: mozilla-actions/sccache-action@v0.0.9
- uses: Swatinem/rust-cache@v2
with:
cache-on-failure: true
- name: Install cargo-codspeed
uses: taiki-e/install-action@v2
with:
tool: cargo-codspeed
- name: Build the benchmark target(s)
run: cargo codspeed build --profile profiling --features test-utils ${{ matrix.crates }}
- name: Run the benchmarks
uses: CodSpeedHQ/action@v4
with:
run: cargo codspeed run ${{ matrix.crates }}
mode: instrumentation
token: ${{ secrets.CODSPEED_TOKEN }}
reth-bench:
if: github.event_name == 'issue_comment' && github.event.issue.pull_request && startsWith(github.event.comment.body, 'derek bench')
name: reth-bench
runs-on: [self-hosted, Linux, X64]
timeout-minutes: 120
env:
BENCH_RPC_URL: https://ethereum.reth.rs/rpc
SCHELK_MOUNT: /reth-bench
steps:
- name: Check org membership
uses: actions/github-script@v7
with:
github-token: ${{ secrets.GITHUB_TOKEN }}
script: |
const user = context.payload.comment.user.login;
try {
const { status } = await github.rest.orgs.checkMembershipForUser({
org: 'paradigmxyz',
username: user,
});
if (status !== 204 && status !== 302) {
core.setFailed(`@${user} is not a member of paradigmxyz`);
}
} catch (e) {
core.setFailed(`@${user} is not a member of paradigmxyz`);
}
- name: Parse arguments
id: args
uses: actions/github-script@v7
with:
script: |
const body = context.payload.comment.body.trim();
const intArgs = new Set(['blocks', 'warmup']);
const refArgs = new Set(['baseline', 'feature']);
const defaults = { blocks: '500', warmup: '100', baseline: '', feature: '' };
const unknown = [];
const invalid = [];
const args = body.replace(/^derek bench\s*/, '');
for (const part of args.split(/\s+/).filter(Boolean)) {
const eq = part.indexOf('=');
if (eq === -1) {
unknown.push(part);
continue;
}
const key = part.slice(0, eq);
const value = part.slice(eq + 1);
if (intArgs.has(key)) {
if (!/^\d+$/.test(value)) {
invalid.push(`\`${key}=${value}\` (must be a positive integer)`);
} else {
defaults[key] = value;
}
} else if (refArgs.has(key)) {
if (!value) {
invalid.push(`\`${key}=\` (must be a git ref)`);
} else {
defaults[key] = value;
}
} else {
unknown.push(key);
}
}
const errors = [];
if (unknown.length) errors.push(`Unknown argument(s): \`${unknown.join('`, `')}\``);
if (invalid.length) errors.push(`Invalid value(s): ${invalid.join(', ')}`);
if (errors.length) {
const msg = `❌ **Invalid bench command**\n\n${errors.join('\n')}\n\n**Usage:** \`derek bench [blocks=N] [warmup=N] [baseline=REF] [feature=REF]\``;
await github.rest.issues.createComment({
owner: context.repo.owner,
repo: context.repo.repo,
issue_number: context.issue.number,
body: msg,
});
core.setFailed(msg);
return;
}
core.setOutput('blocks', defaults.blocks);
core.setOutput('warmup', defaults.warmup);
core.setOutput('baseline', defaults.baseline);
core.setOutput('feature', defaults.feature);
core.exportVariable('BENCH_BLOCKS', defaults.blocks);
core.exportVariable('BENCH_WARMUP_BLOCKS', defaults.warmup);
- name: Acknowledge request
id: ack
uses: actions/github-script@v7
with:
script: |
await github.rest.reactions.createForIssueComment({
owner: context.repo.owner,
repo: context.repo.repo,
comment_id: context.payload.comment.id,
content: 'eyes',
});
const runUrl = `${context.serverUrl}/${context.repo.owner}/${context.repo.repo}/actions/runs/${context.runId}`;
const blocks = '${{ steps.args.outputs.blocks }}';
const warmup = '${{ steps.args.outputs.warmup }}';
const baseline = '${{ steps.args.outputs.baseline }}' || 'merge-base';
const feature = '${{ steps.args.outputs.feature }}' || 'PR head';
const { data: comment } = await github.rest.issues.createComment({
owner: context.repo.owner,
repo: context.repo.repo,
issue_number: context.issue.number,
body: `🚀 Benchmark started! [View run](${runUrl})\n\n⏳ **Status:** Building binaries...\n\n**Config:** ${blocks} blocks, ${warmup} warmup blocks, baseline: \`${baseline}\`, feature: \`${feature}\``,
});
core.setOutput('comment-id', comment.id);
- uses: actions/checkout@v6
with:
submodules: true
fetch-depth: 0
ref: ${{ format('refs/pull/{0}/merge', github.event.issue.number) }}
- uses: dtolnay/rust-toolchain@stable
- uses: mozilla-actions/sccache-action@v0.0.9
continue-on-error: true
# Verify all required tools are available
- name: Check dependencies
run: |
export PATH="$HOME/.local/bin:$HOME/.cargo/bin:$PATH"
echo "$HOME/.local/bin" >> "$GITHUB_PATH"
echo "$HOME/.cargo/bin" >> "$GITHUB_PATH"
missing=()
for cmd in mc schelk cpupower taskset stdbuf python3 curl make uv; do
command -v "$cmd" &>/dev/null || missing+=("$cmd")
done
if [ ${#missing[@]} -gt 0 ]; then
echo "::error::Missing required tools: ${missing[*]}"
exit 1
fi
echo "All dependencies found"
# Build binaries
- name: Resolve PR head branch
id: pr-info
uses: actions/github-script@v7
with:
script: |
const { data: pr } = await github.rest.pulls.get({
owner: context.repo.owner,
repo: context.repo.repo,
pull_number: context.issue.number,
});
core.setOutput('head-ref', pr.head.ref);
core.setOutput('head-sha', pr.head.sha);
- name: Resolve refs
id: refs
run: |
BASELINE_ARG="${{ steps.args.outputs.baseline }}"
FEATURE_ARG="${{ steps.args.outputs.feature }}"
if [ -n "$BASELINE_ARG" ]; then
git fetch origin "$BASELINE_ARG" --quiet 2>/dev/null || true
BASELINE_REF=$(git rev-parse "$BASELINE_ARG" 2>/dev/null || git rev-parse "origin/$BASELINE_ARG" 2>/dev/null)
BASELINE_NAME="$BASELINE_ARG"
else
BASELINE_REF=$(git merge-base HEAD origin/main 2>/dev/null || echo "${{ github.sha }}")
BASELINE_NAME="main"
fi
if [ -n "$FEATURE_ARG" ]; then
git fetch origin "$FEATURE_ARG" --quiet 2>/dev/null || true
FEATURE_REF=$(git rev-parse "$FEATURE_ARG" 2>/dev/null || git rev-parse "origin/$FEATURE_ARG" 2>/dev/null)
FEATURE_NAME="$FEATURE_ARG"
else
FEATURE_REF="${{ steps.pr-info.outputs.head-sha }}"
FEATURE_NAME="${{ steps.pr-info.outputs.head-ref }}"
fi
echo "baseline-ref=$BASELINE_REF" >> "$GITHUB_OUTPUT"
echo "baseline-name=$BASELINE_NAME" >> "$GITHUB_OUTPUT"
echo "feature-ref=$FEATURE_REF" >> "$GITHUB_OUTPUT"
echo "feature-name=$FEATURE_NAME" >> "$GITHUB_OUTPUT"
- name: Fetch or build baseline binaries
run: .github/scripts/bench-reth-build.sh baseline "${{ steps.refs.outputs.baseline-ref }}"
- name: Fetch or build feature binaries
run: .github/scripts/bench-reth-build.sh feature "${{ steps.refs.outputs.feature-ref }}"
# System tuning for reproducible benchmarks
- name: System setup
run: |
sudo cpupower frequency-set -g performance || true
# Disable turbo boost (Intel and AMD paths)
echo 1 | sudo tee /sys/devices/system/cpu/intel_pstate/no_turbo 2>/dev/null || true
echo 0 | sudo tee /sys/devices/system/cpu/cpufreq/boost 2>/dev/null || true
sudo swapoff -a || true
echo 0 | sudo tee /proc/sys/kernel/randomize_va_space || true
# Disable SMT (hyperthreading)
for cpu in /sys/devices/system/cpu/cpu*/topology/thread_siblings_list; do
first=$(cut -d, -f1 < "$cpu" | cut -d- -f1)
current=$(echo "$cpu" | grep -o 'cpu[0-9]*' | grep -o '[0-9]*')
if [ "$current" != "$first" ]; then
echo 0 | sudo tee "/sys/devices/system/cpu/cpu${current}/online" || true
fi
done
echo "Online CPUs: $(nproc)"
# Disable transparent huge pages (compaction causes latency spikes)
for p in /sys/kernel/mm/transparent_hugepage /sys/kernel/mm/transparent_hugepages; do
[ -d "$p" ] && echo never | sudo tee "$p/enabled" && echo never | sudo tee "$p/defrag" && break
done || true
# Prevent deep C-states (avoids wake-up latency jitter)
sudo sh -c 'exec 3<>/dev/cpu_dma_latency; echo -ne "\x00\x00\x00\x00" >&3; sleep infinity' &
# Move all IRQs to core 0 (housekeeping core)
for irq in /proc/irq/*/smp_affinity_list; do
echo 0 | sudo tee "$irq" 2>/dev/null || true
done
# Stop noisy background services
sudo systemctl stop irqbalance cron atd unattended-upgrades snapd 2>/dev/null || true
# Log environment for reproducibility
echo "=== Benchmark environment ==="
uname -r
lscpu | grep -E 'Model name|CPU\(s\)|MHz|NUMA'
cat /sys/devices/system/cpu/cpu0/cpufreq/scaling_governor
cat /sys/devices/system/cpu/cpu0/cpufreq/scaling_cur_freq
cat /sys/kernel/mm/transparent_hugepage/enabled 2>/dev/null || cat /sys/kernel/mm/transparent_hugepages/enabled 2>/dev/null || echo "THP: unknown"
free -h
# Clean up any leftover state
- name: Pre-flight cleanup
run: |
pkill -9 reth || true
mountpoint -q "$SCHELK_MOUNT" && sudo schelk recover -y || true
- name: Update status (running benchmarks)
if: steps.ack.outputs.comment-id
uses: actions/github-script@v7
with:
script: |
const runUrl = `${context.serverUrl}/${context.repo.owner}/${context.repo.repo}/actions/runs/${context.runId}`;
await github.rest.issues.updateComment({
owner: context.repo.owner,
repo: context.repo.repo,
comment_id: ${{ steps.ack.outputs.comment-id || 0 }},
body: `🚀 Benchmark started! [View run](${runUrl})\n\n⏳ **Status:** Running benchmarks (2 runs)...`,
});
- name: "Run benchmark: baseline"
run: taskset -c 0 .github/scripts/bench-reth-run.sh baseline target/profiling-baseline/reth /tmp/bench-results-baseline
- name: "Run benchmark: feature"
run: taskset -c 0 .github/scripts/bench-reth-run.sh feature target/profiling/reth /tmp/bench-results-feature
# Results & charts
- name: Parse results
id: results
if: success()
env:
BASELINE_REF: ${{ steps.refs.outputs.baseline-ref }}
BASELINE_NAME: ${{ steps.refs.outputs.baseline-name }}
FEATURE_NAME: ${{ steps.refs.outputs.feature-name }}
FEATURE_REF: ${{ steps.refs.outputs.feature-ref }}
run: |
git fetch origin "${BASELINE_NAME}" --quiet 2>/dev/null || true
BASELINE_HEAD=$(git rev-parse "origin/${BASELINE_NAME}" 2>/dev/null || echo "")
BEHIND_BASELINE=0
if [ -n "$BASELINE_HEAD" ] && [ "$BASELINE_REF" != "$BASELINE_HEAD" ]; then
BEHIND_BASELINE=$(git rev-list --count "${BASELINE_REF}..${BASELINE_HEAD}" 2>/dev/null || echo "0")
fi
SUMMARY_ARGS="--output-summary /tmp/bench-summary.json"
SUMMARY_ARGS="$SUMMARY_ARGS --output-markdown /tmp/bench-comment.md"
SUMMARY_ARGS="$SUMMARY_ARGS --repo ${{ github.repository }}"
SUMMARY_ARGS="$SUMMARY_ARGS --baseline-ref ${BASELINE_REF}"
SUMMARY_ARGS="$SUMMARY_ARGS --baseline-name ${BASELINE_NAME}"
SUMMARY_ARGS="$SUMMARY_ARGS --feature-name ${FEATURE_NAME}"
SUMMARY_ARGS="$SUMMARY_ARGS --feature-ref ${FEATURE_REF}"
SUMMARY_ARGS="$SUMMARY_ARGS --baseline-csv /tmp/bench-results-baseline/combined_latency.csv"
SUMMARY_ARGS="$SUMMARY_ARGS --feature-csv /tmp/bench-results-feature/combined_latency.csv"
SUMMARY_ARGS="$SUMMARY_ARGS --gas-csv /tmp/bench-results-feature/total_gas.csv"
if [ "$BEHIND_BASELINE" -gt 0 ]; then
SUMMARY_ARGS="$SUMMARY_ARGS --behind-baseline $BEHIND_BASELINE"
fi
# shellcheck disable=SC2086
python3 .github/scripts/bench-reth-summary.py $SUMMARY_ARGS
- name: Generate charts
if: success()
env:
BASELINE_NAME: ${{ steps.refs.outputs.baseline-name }}
FEATURE_NAME: ${{ steps.refs.outputs.feature-name }}
run: |
CHART_ARGS="/tmp/bench-results-feature/combined_latency.csv --output-dir /tmp/bench-charts"
CHART_ARGS="$CHART_ARGS --baseline /tmp/bench-results-baseline/combined_latency.csv"
CHART_ARGS="$CHART_ARGS --baseline-name ${BASELINE_NAME}"
CHART_ARGS="$CHART_ARGS --feature-name ${FEATURE_NAME}"
# shellcheck disable=SC2086
uv run --with matplotlib python3 .github/scripts/bench-reth-charts.py $CHART_ARGS
- name: Upload results
if: success()
uses: actions/upload-artifact@v4
with:
name: bench-reth-results
path: |
/tmp/bench-results-baseline/
/tmp/bench-results-feature/
/tmp/bench-summary.json
/tmp/bench-charts/
- name: Push charts
id: push-charts
if: success()
run: |
PR_NUMBER=${{ github.event.issue.number }}
RUN_ID=${{ github.run_id }}
CHART_DIR="pr/${PR_NUMBER}/${RUN_ID}"
if git fetch origin bench-charts 2>/dev/null; then
git checkout bench-charts
else
git checkout --orphan bench-charts
git rm -rf . 2>/dev/null || true
fi
mkdir -p "${CHART_DIR}"
cp /tmp/bench-charts/*.png "${CHART_DIR}/"
git add "${CHART_DIR}"
git -c user.name="github-actions" -c user.email="github-actions@github.com" \
commit -m "bench charts for PR #${PR_NUMBER} run ${RUN_ID}"
git push origin bench-charts
echo "sha=$(git rev-parse HEAD)" >> "$GITHUB_OUTPUT"
- name: Compare & comment
if: success()
uses: actions/github-script@v7
with:
script: |
const fs = require('fs');
let comment = '';
try {
comment = fs.readFileSync('/tmp/bench-comment.md', 'utf8');
} catch (e) {
comment = '⚠️ Engine benchmark completed but failed to generate comparison.';
}
const sha = '${{ steps.push-charts.outputs.sha }}';
const prNumber = context.issue.number;
const runId = '${{ github.run_id }}';
const baseUrl = `https://raw.githubusercontent.com/${context.repo.owner}/${context.repo.repo}/${sha}/pr/${prNumber}/${runId}`;
const charts = [
{ file: 'latency_throughput.png', label: 'Latency, Throughput & Diff' },
{ file: 'wait_breakdown.png', label: 'Wait Time Breakdown' },
{ file: 'gas_vs_latency.png', label: 'Gas vs Latency' },
];
let chartMarkdown = '\n\n### Charts\n\n';
for (const chart of charts) {
chartMarkdown += `<details><summary>${chart.label}</summary>\n\n`;
chartMarkdown += `![${chart.label}](${baseUrl}/${chart.file})\n\n`;
chartMarkdown += `</details>\n\n`;
}
comment += chartMarkdown;
const requestedBy = '${{ github.event.comment.user.login }}';
const runUrl = `${context.serverUrl}/${context.repo.owner}/${context.repo.repo}/actions/runs/${context.runId}`;
const body = `cc @${requestedBy}\n\n✅ Benchmark complete! [View run](${runUrl})\n\n${comment}`;
const ackCommentId = '${{ steps.ack.outputs.comment-id }}';
if (ackCommentId) {
await github.rest.issues.updateComment({
owner: context.repo.owner,
repo: context.repo.repo,
comment_id: parseInt(ackCommentId),
body,
});
} else {
await github.rest.issues.createComment({
owner: context.repo.owner,
repo: context.repo.repo,
issue_number: context.issue.number,
body,
});
}
- name: Upload node log
if: failure()
uses: actions/upload-artifact@v4
with:
name: reth-node-log
path: |
/tmp/reth-bench-node-baseline.log
/tmp/reth-bench-node-feature.log
- name: Restore system settings
if: always()
run: |
sudo systemctl start irqbalance cron atd 2>/dev/null || true