mirror of
https://github.com/rustfs/rustfs.git
synced 2026-07-26 16:28:15 +00:00
Zhengchao An
4310b55238
Scheduled workflow failures previously went unnoticed (15 consecutive red weekly s3-tests sweeps, silent perf nightly failures). Add a reusable composite action that opens a tracking issue titled "[scheduled-failure] <workflow name>" — or appends a comment to the existing open one (dedupe key = workflow name) — with the run URL, run attempt, and failed job names, labeled "infrastructure". Wire it into the scheduled paths of e2e-s3tests, mint, fuzz (nightly) and performance-ab via a final alert-on-failure job gated by "always() && github.event_name == 'schedule' && contains(needs.*.result, 'failure')", with issues:write scoped to that job only. e2e-s3tests and mint previously had no permissions key; they now get workflow-level contents:read, reducing every other job's token. Add a dispatch-only drill workflow that forces a job failure and runs the action through the exact consumer wiring, for end-to-end verification. The ci-7 e2e nightly does not exist yet; it is recorded as a pending consumer in the action README. Refs: rustfs/backlog#1149 (ci-8), rustfs/backlog#1155
239 lines
10 KiB
YAML
239 lines
10 KiB
YAML
# Copyright 2024 RustFS Team
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
|
|
# Warp A/B budget gate for the hotpath series (rustfs/backlog#935 HP-14, item 4).
|
|
#
|
|
# Two entry points, honestly scoped:
|
|
# * schedule (nightly, on main): post-merge detection — catches a regression
|
|
# within 24h of landing, not before merge.
|
|
# * pull_request labeled `perf-ab`: opt-in pre-merge gate for a specific PR.
|
|
# The `perf-deliberate-tradeoff` label runs the gate with --allow-regression so
|
|
# a deliberate correctness cost (e.g. the #4221 fsync durability fix) is
|
|
# recorded but does not block (rustfs/backlog#935 correction 1).
|
|
|
|
name: Performance A/B
|
|
|
|
on:
|
|
schedule:
|
|
- cron: "0 6 * * *" # 06:00 UTC nightly, against main
|
|
workflow_dispatch:
|
|
inputs:
|
|
duration:
|
|
description: "warp duration per round (short by default to fit the double-build budget)"
|
|
required: false
|
|
default: "12s"
|
|
type: string
|
|
allow_regression:
|
|
description: "Pass the gate despite a FAIL (deliberate tradeoff)"
|
|
required: false
|
|
default: false
|
|
type: boolean
|
|
pull_request:
|
|
types: [labeled, synchronize, reopened]
|
|
|
|
permissions:
|
|
contents: read
|
|
pull-requests: write
|
|
|
|
# Per-PR: a new push cancels the previous (up to 90-minute) A/B run instead of
|
|
# stacking them. Nightly schedule and manual dispatch get a unique group and
|
|
# always run to completion.
|
|
concurrency:
|
|
group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.run_id }}
|
|
cancel-in-progress: ${{ github.event_name == 'pull_request' }}
|
|
|
|
env:
|
|
CARGO_TERM_COLOR: always
|
|
RUST_BACKTRACE: 1
|
|
|
|
jobs:
|
|
warp-ab:
|
|
name: Warp A/B budget gate
|
|
# Opt-in on PRs: only run when the `perf-ab` label is present, and for
|
|
# `labeled` events only when the label being added is `perf-ab` itself —
|
|
# adding an unrelated label to an opted-in PR must not re-run the gate.
|
|
# Always run on schedule / manual dispatch.
|
|
if: >-
|
|
github.event_name != 'pull_request' ||
|
|
(contains(github.event.pull_request.labels.*.name, 'perf-ab') &&
|
|
(github.event.action != 'labeled' || github.event.label.name == 'perf-ab'))
|
|
runs-on: sm-standard-2
|
|
# Phase-0 stopgap: the baseline+candidate release double-build alone is
|
|
# ~65min on this runner, so 90min left no room for a real full-matrix
|
|
# measurement (the earlier nightly runs only ever failed *before*
|
|
# measuring). 120min gives the 24-cell short matrix headroom until perf-3
|
|
# caches the baseline binary and restores a tighter budget.
|
|
timeout-minutes: 120
|
|
steps:
|
|
- name: Checkout repository
|
|
uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7
|
|
with:
|
|
fetch-depth: 0 # baseline is built from origin/main
|
|
|
|
- name: Setup Rust environment
|
|
uses: ./.github/actions/setup
|
|
with:
|
|
rust-version: stable
|
|
cache-shared-key: warp-ab-${{ hashFiles('**/Cargo.lock') }}
|
|
cache-save-if: ${{ github.ref == 'refs/heads/main' }}
|
|
github-token: ${{ secrets.GITHUB_TOKEN }}
|
|
|
|
- name: Install warp
|
|
run: |
|
|
set -euo pipefail
|
|
WARP_VERSION="1.0.0"
|
|
curl -fsSL "https://github.com/minio/warp/releases/download/v${WARP_VERSION}/warp_Linux_x86_64.tar.gz" \
|
|
| sudo tar -xz -C /usr/local/bin warp
|
|
warp --version
|
|
|
|
- name: Decide exemption
|
|
id: exempt
|
|
run: |
|
|
allow="false"
|
|
if [[ "${{ github.event_name }}" == "pull_request" ]] \
|
|
&& ${{ contains(github.event.pull_request.labels.*.name, 'perf-deliberate-tradeoff') }}; then
|
|
allow="true"
|
|
fi
|
|
if [[ "${{ github.event.inputs.allow_regression }}" == "true" ]]; then
|
|
allow="true"
|
|
fi
|
|
echo "allow_regression=$allow" >> "$GITHUB_OUTPUT"
|
|
|
|
- name: Run warp A/B and gate
|
|
id: ab
|
|
run: |
|
|
set -euo pipefail
|
|
# Budget note: the baseline+candidate release double-build (~65 min,
|
|
# cached away later by perf-3) dominates the 90-min job, so the
|
|
# measurement runs a short warp matrix — duration/rounds/cooldown are
|
|
# kept small to fit all 24 cells (6 workloads x 2 phases x 2 drive-sync)
|
|
# under budget rather than dropping cells. --health-timeout 180 outlasts
|
|
# the server's own 120s startup-readiness budget, which is what the
|
|
# rig's previous 60s health poll undershot (the first two nightly
|
|
# failures). perf-6 will recalibrate these once the pipeline is green.
|
|
duration="${{ github.event.inputs.duration || '12s' }}"
|
|
args=(--baseline-ref origin/main
|
|
--duration "$duration" --rounds 2 --cooldown 5 --health-timeout 180)
|
|
if [[ "${{ steps.exempt.outputs.allow_regression }}" == "true" ]]; then
|
|
args+=(--allow-regression --exemption-reason "labeled perf-deliberate-tradeoff / dispatch override")
|
|
fi
|
|
# Do not let a gate FAIL abort the job here; capture status and surface
|
|
# it after the PR comment is posted.
|
|
set +e
|
|
bash scripts/run_hotpath_warp_ab.sh "${args[@]}"
|
|
echo "status=$?" >> "$GITHUB_OUTPUT"
|
|
set -e
|
|
# Locate the newest run dir + gate.md for the summary/comment/artifact
|
|
# steps. On a startup failure there is no gate.md, but the run dir still
|
|
# holds server-logs/ for diagnosis.
|
|
# Run dirs are UTC-timestamp names (no special chars); ls is safe here.
|
|
# shellcheck disable=SC2012
|
|
run_dir="$(ls -td target/hotpath-ab/*/ 2>/dev/null | head -n1 || true)"
|
|
echo "run_dir=${run_dir%/}" >> "$GITHUB_OUTPUT"
|
|
# shellcheck disable=SC2012
|
|
gate_md="$(ls -t target/hotpath-ab/*/gate.md 2>/dev/null | head -n1 || true)"
|
|
echo "gate_md=$gate_md" >> "$GITHUB_OUTPUT"
|
|
|
|
- name: Upload A/B results
|
|
if: always()
|
|
uses: actions/upload-artifact@b7c566a772e6b6bfb58ed0dc250532a479d7789f # v6
|
|
with:
|
|
name: hotpath-warp-ab-${{ github.run_number }}
|
|
# Includes per-cell median_summary.csv / baseline_compare.csv, gate.md,
|
|
# and server-logs/ (rustfs.log + startup env per phase) so a failed run
|
|
# is diagnosable. Short retention: this is churny nightly debug data.
|
|
path: target/hotpath-ab/
|
|
if-no-files-found: warn
|
|
retention-days: 14
|
|
|
|
- name: Write gate summary
|
|
if: always()
|
|
run: |
|
|
set -euo pipefail
|
|
status="${{ steps.ab.outputs.status }}"
|
|
gate_md="${{ steps.ab.outputs.gate_md }}"
|
|
run_dir="${{ steps.ab.outputs.run_dir }}"
|
|
{
|
|
echo "## Hotpath warp A/B — run ${{ github.run_number }}"
|
|
echo
|
|
if [[ "$status" == "0" ]]; then
|
|
echo "Rig/gate exit: \`0\` (pass or warn)."
|
|
else
|
|
echo "Rig/gate exit: \`${status:-unknown}\` — **FAILED**."
|
|
fi
|
|
echo
|
|
if [[ -n "$gate_md" && -f "$gate_md" ]]; then
|
|
cat "$gate_md"
|
|
else
|
|
echo "No \`gate.md\` produced — the rig failed **before** the gate"
|
|
echo "(most likely server startup / health). Failing phase(s) below;"
|
|
echo "full logs in the \`hotpath-warp-ab-${{ github.run_number }}\` artifact."
|
|
if [[ -n "$run_dir" && -d "$run_dir/server-logs" ]]; then
|
|
for f in "$run_dir"/server-logs/*.log; do
|
|
[[ -f "$f" ]] || continue
|
|
echo
|
|
echo "<details><summary>$(basename "$f")</summary>"
|
|
echo
|
|
echo '```'
|
|
tail -n 30 "$f"
|
|
echo '```'
|
|
echo "</details>"
|
|
done
|
|
fi
|
|
fi
|
|
} >> "$GITHUB_STEP_SUMMARY"
|
|
|
|
- name: Comment gate result on PR
|
|
if: always() && github.event_name == 'pull_request' && steps.ab.outputs.gate_md != ''
|
|
env:
|
|
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
|
|
run: |
|
|
gh pr comment "${{ github.event.pull_request.number }}" --body-file "${{ steps.ab.outputs.gate_md }}"
|
|
|
|
# TODO(ci-8/perf-2): scheduled/dispatch failures are currently silent. Once
|
|
# ci-8 lands the .github/actions/schedule-failure-issue composite action,
|
|
# perf-2 adds a step here guarded by
|
|
# if: failure() && github.event_name != 'pull_request'
|
|
# that calls it (label perf-nightly-failure, append to an existing open
|
|
# issue) instead of hand-rolling gh CLI dedup. Do not implement it here.
|
|
|
|
- name: Enforce gate
|
|
if: always()
|
|
run: |
|
|
status="${{ steps.ab.outputs.status }}"
|
|
if [[ "$status" != "0" ]]; then
|
|
echo "::error::warp A/B budget gate failed (exit $status). See the step summary / PR comment / gate.md artifact." >&2
|
|
exit "$status"
|
|
fi
|
|
echo "warp A/B budget gate passed."
|
|
|
|
alert-on-failure:
|
|
name: Alert on scheduled failure
|
|
needs: [warp-ab]
|
|
# `always()` is required: without it this job is skipped when a needed
|
|
# job fails. Alerts only for scheduled (nightly) runs (backlog#1149
|
|
# ci-8); PR and manual dispatch failures are already watched by a human.
|
|
if: always() && github.event_name == 'schedule' && contains(needs.*.result, 'failure')
|
|
runs-on: ubuntu-latest
|
|
timeout-minutes: 10
|
|
permissions:
|
|
contents: read
|
|
issues: write
|
|
steps:
|
|
- uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7
|
|
- name: Open or update failure-tracking issue
|
|
uses: ./.github/actions/schedule-failure-issue
|
|
with:
|
|
github-token: ${{ secrets.GITHUB_TOKEN }}
|