mirror of
https://github.com/pnpm/pnpm.git
synced 2026-07-14 01:32:40 -04:00
When resolving with --offline or --prefer-offline, pickPackage loaded a package's metadata from the on-disk cache mirror but never stored it in the in-memory metaCache, so every subsequent resolution of the same package (once per dependent that references it) re-read and re-parsed the full packument from disk. Store the parsed metadata in the in-memory cache on those disk-return paths, so each package's metadata is parsed at most once per command. On a large monorepo this collapses 23,746 metadata loads to 5,124 (66.8 GB of JSON parsed to 8.8 GB) and takes pnpm dedupe --offline from ~140s to ~75s with a byte-identical lockfile. The cache is the existing bounded LRU; online and network paths are untouched. Promotion alone would have made the top-of-function cache hit terminal: a disk-promoted packument that predates a later-requested range would turn a previously-recoverable network fallback into ERR_PNPM_NO_MATCHING_VERSION. Track registry-unverified disk promotions (a WeakSet keyed by object identity in TypeScript; a registry_verified flag carried inside the cache value in pacquet, so meta and state are read atomically) and let a cache hit whose pick fails on such an entry fall through to the regular network-validating flow unless offline. The revalidating fetch stores a verified entry, so each package revalidates at most once. The pre-existing exact-version fast paths on both stacks had the same latent failure mode and are covered by the same marking. Pacquet's PackageMetaCache::set_unverified is a required trait method so custom cache implementations cannot silently inherit the terminal behavior, and the TypeScript PackageMetaCache documents the object-identity contract its WeakSet relies on. Also registry-qualify pacquet's verifier shared-meta-cache reads (read_shared_meta queried bare name keys while the resolver stores registry-qualified ones, so the fast path could never hit), mirroring the TypeScript readSharedMeta lookup order. Add an isolated-linker.fresh-resolve.hot-cache.offline benchmark scenario (install --offline --lockfile-only against a warm mirror, with an untimed online pre-warm pass and per-iteration node_modules + lockfile wipes so the up-to-date short-circuit cannot skip the measured resolution) to guard offline resolution on all Bencher testbeds. Fixing it to measure real work also revived the pnpm benchmark pipeline, silently dead since the pnpm11/ move: bench.sh resolved REPO_ROOT to pnpm11/ where no Cargo.toml exists, the orchestrator probed the pre-move pnpm/dist bundle path, and continue-on-error masked every failure as a green run. The scenario measures this change directly: pnpm@HEAD resolves the fixture offline in 2.41s vs 3.17s for pnpm@main (1.31x), with metadata-mirror reads dropping from 2625 to 1297. --------- Co-authored-by: Zoltan Kochan <z@kochan.io>
212 lines
7.0 KiB
YAML
212 lines
7.0 KiB
YAML
name: Benchmarks
|
|
|
|
on:
|
|
workflow_dispatch:
|
|
inputs:
|
|
pr_number:
|
|
description: 'PR number to benchmark (works with fork PRs too)'
|
|
required: false
|
|
default: ''
|
|
type: string
|
|
runs:
|
|
description: 'Number of benchmark runs per scenario'
|
|
required: false
|
|
default: '10'
|
|
type: string
|
|
warmup:
|
|
description: 'Number of warmup runs before timing'
|
|
required: false
|
|
default: '1'
|
|
type: string
|
|
push:
|
|
# Build Bencher's continuous baseline for the `pnpm` testbed.
|
|
# Every merge to main that touches the TypeScript stack re-runs the
|
|
# bench so PR comparisons have an up-to-date reference; cancel-in-progress
|
|
# stays off below so we never throw away a partial run.
|
|
branches: [main]
|
|
paths:
|
|
- 'pnpm11/**'
|
|
- 'package.json'
|
|
- 'pnpm-workspace.yaml'
|
|
- 'pnpm-lock.yaml'
|
|
- '.github/workflows/benchmark.yml'
|
|
|
|
permissions:
|
|
contents: read
|
|
pull-requests: write
|
|
checks: write
|
|
|
|
# Don't cancel-in-progress — killing a bench mid-run wastes a long
|
|
# CI job and produces no usable data.
|
|
concurrency:
|
|
group: benchmark-${{ inputs.pr_number || github.ref }}
|
|
cancel-in-progress: false
|
|
|
|
jobs:
|
|
benchmark:
|
|
name: Run Benchmarks
|
|
runs-on: ubuntu-latest
|
|
timeout-minutes: 180
|
|
|
|
steps:
|
|
- name: Checkout
|
|
uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
|
|
with:
|
|
fetch-depth: 0
|
|
persist-credentials: false
|
|
|
|
- name: Checkout PR head
|
|
if: inputs.pr_number != ''
|
|
env:
|
|
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
|
|
PR_NUMBER: ${{ inputs.pr_number }}
|
|
run: |
|
|
echo "Fetching PR #$PR_NUMBER head..."
|
|
git fetch origin "refs/pull/${PR_NUMBER}/head:refs/remotes/origin/pr-${PR_NUMBER}"
|
|
git checkout "origin/pr-${PR_NUMBER}"
|
|
echo "Checked out PR #$PR_NUMBER at $(git rev-parse --short HEAD)"
|
|
|
|
- name: Install pnpm and Node
|
|
uses: pnpm/setup@77cf06832101b3ac8c65caaf76a21643936d07a4
|
|
with:
|
|
runtime: node@26.4.0
|
|
|
|
- name: Install Rust Toolchain
|
|
uses: ./.github/actions/rustup
|
|
with:
|
|
shared-key: pnpm-benchmark
|
|
|
|
- name: Install hyperfine
|
|
uses: ./.github/actions/binstall
|
|
with:
|
|
packages: hyperfine@1.18.0
|
|
|
|
- name: Run benchmarks
|
|
id: bench
|
|
run: |
|
|
set -o pipefail
|
|
./pnpm11/benchmarks/bench.sh 2>&1 | tee bench-output.txt
|
|
BENCH_DIR=$(grep "Temp directory kept at:" bench-output.txt | sed 's/Temp directory kept at: //')
|
|
echo "bench_dir=$BENCH_DIR" >> "$GITHUB_OUTPUT"
|
|
env:
|
|
RUNS: ${{ inputs.runs }}
|
|
WARMUP: ${{ inputs.warmup }}
|
|
|
|
- name: Install Bencher CLI
|
|
if: steps.bench.outputs.bench_dir != ''
|
|
uses: bencherdev/bencher@ec56bb69a7f34096002ca3384d10e2f6676b063e # v0.6.7
|
|
|
|
- name: Upload results to Bencher
|
|
if: steps.bench.outputs.bench_dir != ''
|
|
env:
|
|
BENCHER_API_TOKEN: ${{ secrets.BENCHER_API_TOKEN }}
|
|
BENCH_DIR: ${{ steps.bench.outputs.bench_dir }}
|
|
EVENT_NAME: ${{ github.event_name }}
|
|
INPUT_PR_NUMBER: ${{ inputs.pr_number }}
|
|
REF_NAME: ${{ github.ref_name }}
|
|
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
|
|
run: |
|
|
if [ -z "${BENCHER_API_TOKEN:-}" ]; then
|
|
echo "::notice::BENCHER_API_TOKEN not set, skipping Bencher upload"
|
|
exit 0
|
|
fi
|
|
if [ ! -f "$BENCH_DIR/bencher-results.json" ]; then
|
|
echo "::warning::bencher-results.json not found, skipping upload"
|
|
exit 0
|
|
fi
|
|
|
|
# `bencher run --file` takes hyperfine JSON via the
|
|
# shell_hyperfine adapter. Branch policy:
|
|
# - push to main → record into the `main` branch (baseline)
|
|
# - workflow_dispatch with pr_number → record into `pr/<n>`,
|
|
# forked from main at the latest baseline
|
|
# - workflow_dispatch without pr_number → record into the
|
|
# ref's branch name (e.g. a feature branch), forked from main
|
|
args=(
|
|
--project pnpm
|
|
--testbed pnpm
|
|
--adapter shell_hyperfine
|
|
--file "$BENCH_DIR/bencher-results.json"
|
|
--github-actions "$GITHUB_TOKEN"
|
|
)
|
|
# `--start-point-clone-thresholds` so the forked branch inherits
|
|
# the threshold configured on main; `--err` so the workflow fails
|
|
# when a sample breaches the upper boundary. Main pushes skip
|
|
# both — by then the regression has already landed.
|
|
if [ "$EVENT_NAME" = "push" ] || [ "$REF_NAME" = "main" ]; then
|
|
args+=(--branch main)
|
|
elif [ -n "$INPUT_PR_NUMBER" ]; then
|
|
args+=(
|
|
--branch "pr/$INPUT_PR_NUMBER"
|
|
--start-point main
|
|
--start-point-reset
|
|
--start-point-clone-thresholds
|
|
--err
|
|
)
|
|
else
|
|
args+=(
|
|
--branch "$REF_NAME"
|
|
--start-point main
|
|
--start-point-reset
|
|
--start-point-clone-thresholds
|
|
--err
|
|
)
|
|
fi
|
|
bencher run "${args[@]}"
|
|
|
|
- name: Comment on PR
|
|
if: steps.bench.outputs.bench_dir != ''
|
|
env:
|
|
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
|
|
BENCH_DIR: ${{ steps.bench.outputs.bench_dir }}
|
|
INPUT_PR_NUMBER: ${{ inputs.pr_number }}
|
|
REF_NAME: ${{ github.ref_name }}
|
|
RUN_ID: ${{ github.run_id }}
|
|
SERVER_URL: ${{ github.server_url }}
|
|
REPO: ${{ github.repository }}
|
|
RUNS: ${{ inputs.runs }}
|
|
ACTOR: ${{ github.actor }}
|
|
run: |
|
|
RESULTS_FILE="$BENCH_DIR/results.md"
|
|
|
|
if [ ! -f "$RESULTS_FILE" ]; then
|
|
echo "::warning::Results file not found at $RESULTS_FILE"
|
|
exit 0
|
|
fi
|
|
|
|
echo "--- Benchmark Results ---"
|
|
cat "$RESULTS_FILE"
|
|
echo "-------------------------"
|
|
|
|
if [ -n "$INPUT_PR_NUMBER" ]; then
|
|
PR_NUMBER="$INPUT_PR_NUMBER"
|
|
else
|
|
PR_NUMBER=$(gh pr list --head "$REF_NAME" --json number --jq '.[0].number' 2>/dev/null || echo "")
|
|
fi
|
|
|
|
if [ -z "$PR_NUMBER" ]; then
|
|
echo "::notice::No open PR found for branch $REF_NAME. Results printed above."
|
|
exit 0
|
|
fi
|
|
|
|
MARKER="<!-- pnpm-benchmark-results -->"
|
|
{
|
|
echo "$MARKER"
|
|
cat "$RESULTS_FILE"
|
|
echo ""
|
|
echo "_Run [${RUN_ID}](${SERVER_URL}/${REPO}/actions/runs/${RUN_ID}) · ${RUNS} runs per scenario · triggered by @${ACTOR}_"
|
|
} > /tmp/comment-body.md
|
|
|
|
COMMENT_ID=$(gh api "repos/${REPO}/issues/${PR_NUMBER}/comments" \
|
|
--jq "[.[] | select(.body | startswith(\"$MARKER\"))] | .[0].id // empty" 2>/dev/null || echo "")
|
|
|
|
if [ -n "$COMMENT_ID" ]; then
|
|
echo "Updating existing benchmark comment $COMMENT_ID on PR #$PR_NUMBER"
|
|
gh api "repos/${REPO}/issues/comments/${COMMENT_ID}" \
|
|
-X PATCH \
|
|
-F "body=@/tmp/comment-body.md"
|
|
else
|
|
echo "Creating new benchmark comment on PR #$PR_NUMBER"
|
|
gh pr comment "$PR_NUMBER" --body-file /tmp/comment-body.md
|
|
fi
|