ci: bound every job's runtime and stop pasting inputs into shell (#5537)

Three hardening changes with no effect on what any workflow produces. Declare timeout-minutes on the 25 jobs that lacked it. GitHub's default is 360 minutes, and this repository has a history of runners stalling intermittently (#5394) plus a measured 9m57s plain `git checkout` under node-level I/O contention, so one wedged job could hold a runner for six hours out of a pool of roughly 15-21. Budgets follow what the jobs actually do: 10 minutes for echo-only and guard-script jobs, 30 for anything calling the GitHub API, uploading release assets or pushing over the network. scripts/security/check_job_timeouts.sh keeps it that way, checking only jobs that declare runs-on so reusable-workflow callers are not flagged. Pass workflow inputs and workflow_run fields through env instead of `${{ }}` interpolation in run blocks. A git ref name may contain `$(...)` — any string without a space is a legal tag — and interpolation pastes it into the script where bash evaluates it. The worst instance was helm-package's final commit message: it is built from the triggering tag name inside the job that holds the cross-repository push token with rustfs/helm already checked out. Also converted in build.yml, docker.yml and performance-ab.yml; the last is currently disabled, but a disabled workflow can be re-enabled. Not touched: helm-package's `contains(head_branch, '.')` tag test, since GitHub expressions have no regex and this repository's tags carry no `v` prefix, so rewriting the condition would change which builds publish a chart. Give audit.yml a scheduled-failure alert and run it daily. A scheduled cargo-deny failure usually means the dependency tree just matched a newly published RustSec advisory — the most important signal this workflow produces, and until now it was visible only to whoever happened to open the Actions tab. coverage.yml and e2e-replication-nightly.yml already use this ci-8 mechanism. The cron moves from weekly to daily so a new advisory against an unchanged tree surfaces within a day instead of seven; the check list is untouched, since splitting it into a light daily run and a weekly full run would create runs where sources, bans and licenses go unverified. Refs: rustfs/backlog#1598, rustfs/backlog#1602
2026-08-01 19:12:14 +00:00 · 2026-08-01 11:25:26 +08:00
parent b965bd6eef
commit e2b2bdcc34
14 changed files with 173 additions and 15 deletions
@@ -37,6 +37,7 @@ jobs:
    name: Cancel Closed PR Runs
    if: github.event_name == 'pull_request' && github.event.action == 'closed'
    runs-on: ubuntu-latest
+    timeout-minutes: 10
    steps:
      - name: Explain cancellation run
        run: echo "PR closed; this run only cancels older runs in the same concurrency group."
@@ -45,6 +46,7 @@ jobs:
    name: Architecture Migration Rules
    if: github.event_name != 'pull_request' || github.event.action != 'closed'
    runs-on: ubuntu-latest
+    timeout-minutes: 10
    steps:
      - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7

@@ -39,7 +39,12 @@ on:
      - 'scripts/security/check_preview_release_workflow.sh'
      - 'scripts/security/check_workflow_pins.sh'
  schedule:
-    - cron: '0 3 * * 0' # Weekly on Sunday 03:00 UTC (staggered after the midnight ci/build crons)
+    # Daily, not weekly. This schedule exists to catch RustSec advisories
+    # published against an unchanged dependency tree; at weekly cadence a new
+    # advisory could sit unnoticed for seven days. The check list is unchanged —
+    # splitting it into a light daily advisories-only run and a weekly full run
+    # would create runs where sources/bans/licenses go unverified.
+    - cron: '0 3 * * *' # Daily 03:00 UTC (staggered after the midnight ci/build crons)
  workflow_dispatch:

 permissions:
@@ -59,6 +64,7 @@ jobs:
    name: Cancel Closed PR Runs
    if: github.event_name == 'pull_request' && github.event.action == 'closed'
    runs-on: ubuntu-latest
+    timeout-minutes: 10
    steps:
      - name: Explain cancellation run
        run: echo "PR closed; this run only cancels older runs in the same concurrency group."
@@ -120,12 +126,16 @@ jobs:
      - name: Check setup cache-save-if is explicit
        run: ./scripts/security/check_cache_save_if.sh

+      - name: Check every job declares a timeout
+        run: ./scripts/security/check_job_timeouts.sh
+
      - name: Check preview release workflow policy
        run: ./scripts/security/check_preview_release_workflow.sh

  dependency-review:
    name: Dependency Review
    runs-on: ubuntu-latest
+    timeout-minutes: 30
    if: github.event_name == 'pull_request' && github.event.action != 'closed'
    permissions:
      contents: read
@@ -145,3 +155,26 @@ jobs:
          # conscious re-review of the license/provenance claim (backlog#1181).
          allow-dependencies-licenses: pkg:cargo/rustfs-uring@0.1.0
          comment-summary-in-pr: always
+
+  alert-on-failure:
+    name: Alert on scheduled failure
+    # dependency-review is deliberately excluded: it only runs on pull_request,
+    # so it can never contribute a failure to a scheduled run.
+    needs: [cargo-deny, workflow-pin-report]
+    # A scheduled cargo-deny failure usually means the dependency tree just
+    # matched a newly published advisory — the single most important signal this
+    # workflow produces, and until now it was only visible to whoever happened to
+    # open the Actions tab. Same ci-8 mechanism coverage.yml and
+    # e2e-replication-nightly.yml already use.
+    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 }}
@@ -83,6 +83,7 @@ jobs:
  build-check:
    name: Build Strategy Check
    runs-on: ubuntu-latest
+    timeout-minutes: 30
    outputs:
      should_build: ${{ steps.check.outputs.should_build }}
      build_type: ${{ steps.check.outputs.build_type }}
@@ -164,6 +165,7 @@ jobs:
    name: Prepare Platform Matrix
    needs: build-check
    runs-on: ubuntu-latest
+    timeout-minutes: 30
    outputs:
      matrix: ${{ steps.select.outputs.matrix }}
      selected: ${{ steps.select.outputs.selected }}
@@ -171,10 +173,14 @@ jobs:
      - name: Select target platforms
        id: select
        shell: bash
+        env:
+          # via env, not interpolation: a dispatch input is free-form text and
+          # would otherwise be pasted into the script for bash to evaluate.
+          RAW_PLATFORMS: ${{ github.event_name == 'workflow_dispatch' && github.event.inputs.platforms || 'all' }}
        run: |
          set -euo pipefail

-          selected="${{ github.event_name == 'workflow_dispatch' && github.event.inputs.platforms || 'all' }}"
+          selected="$RAW_PLATFORMS"
          selected="$(echo "${selected}" | tr -d '[:space:]')"
          if [[ -z "${selected}" ]]; then
            selected="all"
@@ -710,9 +716,14 @@ jobs:
    needs: [ build-check, build-rustfs ]
    if: always() && needs.build-check.outputs.should_build == 'true'
    runs-on: ubuntu-latest
+    timeout-minutes: 10
    steps:
      - name: Build completion summary
        shell: bash
+        env:
+          # dispatch input via env: free-form text must not be pasted into the
+          # script for bash to evaluate.
+          INPUT_BUILD_DOCKER: ${{ github.event.inputs.build_docker }}
        run: |
          BUILD_TYPE="${{ needs.build-check.outputs.build_type }}"
          VERSION="${{ needs.build-check.outputs.version }}"
@@ -754,7 +765,7 @@ jobs:
          echo "🐳 Docker Images:"
          if [[ "$BUILD_TYPE" == "preview" ]]; then
            echo "⏭️  Preview tags do not publish Docker images"
-          elif [[ "${{ github.event.inputs.build_docker }}" == "false" ]]; then
+          elif [[ "$INPUT_BUILD_DOCKER" == "false" ]]; then
            echo "⏭️  Docker image build was skipped (binary only build)"
          elif [[ "$BUILD_STATUS" == "success" ]]; then
            echo "🔄 Docker images will be built and pushed automatically via workflow_run event"
@@ -768,6 +779,7 @@ jobs:
    needs: [ build-check, build-rustfs ]
    if: startsWith(github.ref, 'refs/tags/') && (needs.build-check.outputs.build_type == 'preview' || needs.build-check.outputs.build_type == 'release' || needs.build-check.outputs.build_type == 'prerelease')
    runs-on: ubuntu-latest
+    timeout-minutes: 30
    permissions:
      contents: write
    outputs:
@@ -827,6 +839,7 @@ jobs:
    needs: [ build-check, build-rustfs, create-release ]
    if: startsWith(github.ref, 'refs/tags/') && (needs.build-check.outputs.build_type == 'preview' || needs.build-check.outputs.build_type == 'release' || needs.build-check.outputs.build_type == 'prerelease')
    runs-on: ubuntu-latest
+    timeout-minutes: 30
    permissions:
      contents: write
      actions: read
@@ -918,6 +931,7 @@ jobs:
    needs: [ build-check, publish-release ]
    if: startsWith(github.ref, 'refs/tags/') && (needs.build-check.outputs.build_type == 'release' || needs.build-check.outputs.build_type == 'prerelease')
    runs-on: ubuntu-latest
+    timeout-minutes: 30
    steps:
      - name: Update latest.json
        env:
@@ -977,6 +991,7 @@ jobs:
    needs: [ build-check, create-release, upload-release-assets ]
    if: startsWith(github.ref, 'refs/tags/') && (needs.build-check.outputs.build_type == 'preview' || needs.build-check.outputs.build_type == 'release' || needs.build-check.outputs.build_type == 'prerelease')
    runs-on: ubuntu-latest
+    timeout-minutes: 30
    permissions:
      contents: write
    steps:
@@ -81,6 +81,7 @@ jobs:
    name: Cancel Closed PR Runs
    if: github.event_name == 'pull_request' && github.event.action == 'closed'
    runs-on: ubuntu-latest
+    timeout-minutes: 10
    steps:
      - name: Explain cancellation run
        run: echo "PR closed; this run only cancels older runs in the same concurrency group."
@@ -89,6 +90,7 @@ jobs:
    name: Typos
    if: github.event_name != 'pull_request' || github.event.action != 'closed'
    runs-on: ubuntu-latest
+    timeout-minutes: 10
    steps:
      - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7
      - name: Typos check with custom config file
@@ -37,6 +37,7 @@ jobs:
    name: Cancel Closed PR Runs
    if: github.event_name == 'pull_request_target' && github.event.action == 'closed'
    runs-on: ubuntu-latest
+    timeout-minutes: 10
    steps:
      - name: Explain cancellation run
        run: echo "PR closed; this run only cancels older runs in the same concurrency group."
@@ -44,6 +45,7 @@ jobs:
  cla:
    if: ${{ (github.event_name != 'issue_comment' || github.event.issue.pull_request) && (github.event_name != 'pull_request_target' || github.event.action != 'closed') }}
    runs-on: ubuntu-latest
+    timeout-minutes: 30
    steps:
      - name: Report CLA result for merge queue
        if: github.event_name == 'merge_group'
@@ -85,6 +85,7 @@ jobs:
       github.event.workflow_run.head_branch != 'main' &&
       !contains(github.event.workflow_run.head_branch, '-preview'))
    runs-on: ubuntu-latest
+    timeout-minutes: 30
    outputs:
      should_build: ${{ steps.check.outputs.should_build }}
      should_push: ${{ steps.check.outputs.should_push }}
@@ -102,6 +103,12 @@ jobs:

      - name: Check build conditions
        id: check
+        env:
+          # dispatch inputs via env, not `${{ }}` interpolation: they are
+          # free-form strings and would otherwise be evaluated by bash.
+          INPUT_VERSION: ${{ github.event.inputs.version }}
+          INPUT_PUSH_IMAGES: ${{ github.event.inputs.push_images }}
+          INPUT_FORCE_REBUILD: ${{ github.event.inputs.force_rebuild }}
        run: |
          should_build=false
          should_push=false
@@ -202,9 +209,9 @@ jobs:

          elif [[ "${{ github.event_name }}" == "workflow_dispatch" ]]; then
            # Manual trigger
-            input_version="${{ github.event.inputs.version }}"
+            input_version="$INPUT_VERSION"
            version="${input_version}"
-            should_push="${{ github.event.inputs.push_images }}"
+            should_push="$INPUT_PUSH_IMAGES"
            should_build=true

            # Get short SHA
@@ -212,7 +219,7 @@ jobs:

            echo "🎯 Manual Docker build triggered:"
            echo "   📋 Requested version: $input_version"
-            echo "   🔧 Force rebuild: ${{ github.event.inputs.force_rebuild }}"
+            echo "   🔧 Force rebuild: $INPUT_FORCE_REBUILD"
            echo "   🚀 Push images: $should_push"

            case "$input_version" in
@@ -439,6 +446,7 @@ jobs:
    needs: [ build-check, build-docker ]
    if: needs.build-check.outputs.should_build == 'true' && needs.build-check.outputs.should_push == 'true'
    runs-on: ubuntu-latest
+    timeout-minutes: 30
    permissions:
      contents: read
      security-events: write
@@ -493,6 +501,7 @@ jobs:
    needs: [ build-check, build-docker ]
    if: always() && needs.build-check.outputs.should_build == 'true'
    runs-on: ubuntu-latest
+    timeout-minutes: 10
    steps:
      - name: Docker build completion summary
        run: |
@@ -59,6 +59,7 @@ jobs:
    name: Cancel Closed PR Runs
    if: github.event_name == 'pull_request' && github.event.action == 'closed'
    runs-on: ubuntu-latest
+    timeout-minutes: 10
    steps:
      - name: Explain cancellation run
        run: echo "PR closed; this run only cancels older runs in the same concurrency group."
@@ -32,6 +32,7 @@ permissions:
 jobs:
  build-helm-package:
    runs-on: ubuntu-latest
+    timeout-minutes: 30
    if: |
      (github.event_name == 'workflow_dispatch' && !contains(github.event.inputs.version, '-preview')) ||
      (
@@ -50,15 +51,23 @@ jobs:
      - name: Checkout helm chart repo
        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7

+      # Both inputs reach the shell through env rather than `${{ }}`
+      # interpolation. A git ref name may contain `$(...)` — anything without a
+      # space is a legal tag — and interpolation pastes it into the script
+      # verbatim, where bash would run it. Reading "$RAW_INPUT" instead makes it
+      # data.
      - name: Normalize release version
        id: version
+        env:
+          RAW_INPUT: ${{ github.event.inputs.version }}
+          RAW_BRANCH: ${{ github.event.workflow_run.head_branch }}
        run: |
          set -eux

          if [ "${{ github.event_name }}" = "workflow_dispatch" ]; then
-            RAW="${{ github.event.inputs.version }}"
+            RAW="$RAW_INPUT"
          else
-            RAW="${{ github.event.workflow_run.head_branch }}"
+            RAW="$RAW_BRANCH"
          fi

          case "$RAW" in
@@ -73,10 +82,13 @@ jobs:
          ./scripts/helm_chart_version.sh "$RAW_TAG"

      - name: Replace chart version and app version
+        env:
+          CHART_VERSION: ${{ steps.version.outputs.chart_version }}
+          APP_VERSION: ${{ steps.version.outputs.app_version }}
        run: |
          set -eux
-          sed -i -E 's/^version:.*/version: "${{ steps.version.outputs.chart_version }}"/' helm/rustfs/Chart.yaml
-          sed -i -E 's/^appVersion:.*/appVersion: "${{ steps.version.outputs.app_version }}"/' helm/rustfs/Chart.yaml
+          sed -i -E "s/^version:.*/version: \"${CHART_VERSION}\"/" helm/rustfs/Chart.yaml
+          sed -i -E "s/^appVersion:.*/appVersion: \"${APP_VERSION}\"/" helm/rustfs/Chart.yaml

      - name: Set up Helm
        uses: azure/setup-helm@b9e51907a09c216f16ebe8536097933489208112 # v4.3.0
@@ -101,6 +113,7 @@ jobs:

  publish-helm-package:
    runs-on: ubuntu-latest
+    timeout-minutes: 30
    needs: [ build-helm-package ]
    if: needs.build-helm-package.result == 'success'

@@ -123,11 +136,19 @@ jobs:
      - name: Generate index
        run: helm repo index . --url https://charts.rustfs.com

+      # app_version is derived from the triggering tag name, and this job holds
+      # the cross-repository push token with rustfs/helm already checked out —
+      # the worst place in the repo to paste an attacker-influenced string into
+      # a shell line. Passed through env so bash treats it as data.
      - name: Push helm package and index file
+        env:
+          GIT_USERNAME: ${{ secrets.USERNAME }}
+          GIT_EMAIL: ${{ secrets.EMAIL_ADDRESS }}
+          APP_VERSION: ${{ needs.build-helm-package.outputs.app_version }}
        run: |
          set -eux
-          git config --global user.name "${{ secrets.USERNAME }}"
-          git config --global user.email "${{ secrets.EMAIL_ADDRESS }}"
+          git config --global user.name "${GIT_USERNAME}"
+          git config --global user.email "${GIT_EMAIL}"
          git add .
-          git commit -m "Update rustfs helm package with ${{ needs.build-helm-package.outputs.app_version }}." || echo "No changes to commit"
+          git commit -m "Update rustfs helm package with ${APP_VERSION}." || echo "No changes to commit"
          git push origin main
@@ -26,6 +26,7 @@ permissions:
 jobs:
  build:
    runs-on: ubuntu-latest
+    timeout-minutes: 10
    steps:
      - uses: usthe/issues-translate-action@b41f55ddc81d7d54bd542a4f289fe28ec081898e # v2.7
        with:
@@ -46,6 +46,7 @@ jobs:
    name: Cancel Closed PR Runs
    if: github.event_name == 'pull_request' && github.event.action == 'closed'
    runs-on: ubuntu-latest
+    timeout-minutes: 10
    steps:
      - name: Explain cancellation run
        run: echo "PR closed; this run only cancels older runs in the same concurrency group."
@@ -162,13 +162,15 @@ jobs:

      - name: Decide exemption
        id: exempt
+        env:
+          INPUT_ALLOW_REGRESSION: ${{ github.event.inputs.allow_regression }}
        run: |
          allow="false"
          if [[ "${{ 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
+          if [[ "$INPUT_ALLOW_REGRESSION" == "true" ]]; then
            allow="true"
          fi
          echo "allow_regression=$allow" >> "$GITHUB_OUTPUT"
@@ -224,6 +226,8 @@ jobs:

      - name: Run warp A/B and gate
        id: ab
+        env:
+          INPUT_DURATION: ${{ github.event.inputs.duration }}
        run: |
          set -euo pipefail
          # Budget note: with perf-3's cached baseline the nightly does no source
@@ -234,7 +238,7 @@ jobs:
          # budget, which the rig's previous 60s health poll undershot (the first
          # two nightly failures). perf-6 recalibrates these once the noise study
          # lands.
-          duration="${{ github.event.inputs.duration || '12s' }}"
+          duration="${INPUT_DURATION:-12s}"
          baseline_sha="${{ steps.commits.outputs.baseline_sha }}"
          candidate_sha="${{ steps.commits.outputs.candidate_sha }}"
          baseline_hit="${{ steps.baseline_cache.outputs.cache-hit }}"
@@ -20,6 +20,7 @@ on:
 jobs:
  stale:
    runs-on: ubuntu-latest
+    timeout-minutes: 30
    steps:
      - uses: actions/stale@5bef64f19d7facfb25b37b414482c7164d639639 # v9
        with:
@@ -15,6 +15,7 @@ concurrency:
 jobs:
  update:
    runs-on: ubuntu-latest
+    timeout-minutes: 10
    steps:
      - uses: overtrue/repo-visuals-action@72f34d24769ff5d341956da2f23952594ef2f1e2 # v1.3.0
        with: