ci(viewerjs): run browser suites with workers and shards

Frontend coverage runs as three shards (PM_TEST_WORKERS=3 each) that upload their raw V8 files as coverage-raw-N; a merge job downloads them, fails unless all three arrived with raw files and no clashing names, then runs coverage:merge. Firefox and WebKit page workflows run as two shards each with three workers. The required viewerjs context keeps its name and now needs the shards, the merge and the browser shards, failing unless every one succeeded.
2026-10-21 19:41:54 -07:00
parent 3ebf5c48cf
commit 21a2cc0932
3 changed files with 317 additions and 30 deletions
@@ -16,9 +16,13 @@ concurrency:
  group: ${{ github.workflow }}-${{ github.event_name == 'pull_request' && github.ref || github.run_id }}
  cancel-in-progress: ${{ github.event_name == 'pull_request' }}

+# Timeouts are the measured job time plus about 50%, so a hung run stops early.
+# Before sharding (main 2cecfcf, one worker): frontend coverage 32m10s, page workflows firefox 18m59s,
+# webkit 19m26s. Sharded with 3 workers per job: estimates pending the first CI run (coverage shard ~10m,
+# merge ~5m, workflow shard ~8m). Re-measure when a job passes its estimate.
 jobs:
  frontend-coverage:
-    name: frontend coverage (chromium and touch)
+    name: frontend coverage (shard ${{ matrix.shard }}/3)
    runs-on: ubuntu-latest
    # Layout comparisons depend on the fonts each browser falls back to, so browser jobs run in the
    # same pinned Playwright image as local runs (tag = @playwright/test in tools/vendor/package-lock.json;
@@ -26,12 +30,15 @@ jobs:
    container:
      image: mcr.microsoft.com/playwright:v1.64.1-noble
      options: --user 1001
-    # This job runs every page workflow twice (chromium, then touch) on one worker with V8 coverage on, so it
-    # takes about twice a single-browser job. Measured 2026-10-20: whole job 18m26s-24m57s (main 5ded3cf
-    # 22m15s; PR head 6359999 was cancelled at the old 25-minute limit while still passing), coverage step
-    # alone 20m55s-22m17s+, against ~12-15 minutes for the firefox/webkit jobs. 40 minutes leaves headroom
-    # for suite growth while still stopping a hung run; re-measure if a run passes 30 minutes.
-    timeout-minutes: 40
+    timeout-minutes: 15
+    # Public-repo ubuntu-latest runners have 4 vCPUs: three Playwright workers, each with its own test
+    # server, leave one CPU for the servers and the runner.
+    env:
+      PM_TEST_WORKERS: 3
+    strategy:
+      fail-fast: false
+      matrix:
+        shard: [1, 2, 3]
    steps:
      - uses: actions/checkout@v7
      # The image's own Python 3.12 and Node 24: setup-python/setup-node install the runner's toolcache
@@ -51,23 +58,92 @@ jobs:
          echo "$venv/bin" >> "$GITHUB_PATH"
      - run: python --version && node --version && node --version | grep -q '^v24\.'
      - run: npm ci --prefix tools/vendor --ignore-scripts
-      - run: npm run --prefix tools/vendor check
-      - run: npm run --prefix tools/vendor test
-      - name: Frontend unit, viewer, workflow, and coverage checks
-        run: npm run --prefix tools/vendor test:coverage
-      - name: Upload frontend coverage and Chromium traces
+      # Shard 1 also runs the node units and the viewer suite, so the vendor pins and the tooling tests
+      # run on the lightest shard instead.
+      - if: matrix.shard == 3
+        run: npm run --prefix tools/vendor check
+      - if: matrix.shard == 3
+        run: npm run --prefix tools/vendor test
+      - name: Page workflows with coverage, shard ${{ matrix.shard }}/3
+        run: npm run --prefix tools/vendor test:coverage:shard -- ${{ matrix.shard }}/3
+      - name: Upload raw coverage
+        uses: actions/upload-artifact@v7
+        with:
+          name: coverage-raw-${{ matrix.shard }}
+          path: coverage/js/raw/
+          if-no-files-found: error
+          retention-days: 3
+      - name: Upload Chromium and touch traces
+        if: always()
+        uses: actions/upload-artifact@v7
+        with:
+          name: frontend-traces-shard-${{ matrix.shard }}
+          path: tools/vendor/test-results/
+          retention-days: 14
+
+  frontend-coverage-merge:
+    name: frontend coverage (merge)
+    needs: frontend-coverage
+    runs-on: ubuntu-latest
+    # Same image as the shards: the raw files name sources by the container's workspace path.
+    container:
+      image: mcr.microsoft.com/playwright:v1.64.1-noble
+      options: --user 1001
+    timeout-minutes: 8
+    steps:
+      - uses: actions/checkout@v7
+      - run: node --version && node --version | grep -q '^v24\.'
+      - run: npm ci --prefix tools/vendor --ignore-scripts
+      # Each artifact lands in its own coverage-raw-N directory, so the next step can count them.
+      - uses: actions/download-artifact@v8
+        with:
+          pattern: coverage-raw-*
+          path: ${{ runner.temp }}/coverage-raw
+      # coverage:merge only checks that raw files exist; merging two of three shards would report
+      # partial coverage, so a missing or empty shard artifact fails here.
+      - name: Verify every shard's raw coverage arrived
+        shell: bash
+        env:
+          STAGED_RAW: ${{ runner.temp }}/coverage-raw
+          EXPECTED_SHARDS: 3
+        run: |
+          found=0
+          for shard in $(seq 1 "$EXPECTED_SHARDS"); do
+            directory="$STAGED_RAW/coverage-raw-$shard"
+            count=0
+            if [ -d "$directory" ]; then count=$(find "$directory" -maxdepth 1 -type f -name '*.json' | wc -l); fi
+            echo "coverage-raw-$shard: $count raw files"
+            if [ "$count" -gt 0 ]; then found=$((found + 1)); fi
+          done
+          echo "shard artifacts with raw coverage: $found of $EXPECTED_SHARDS"
+          if [ "$found" -ne "$EXPECTED_SHARDS" ]; then
+            echo "::error::Expected raw coverage from $EXPECTED_SHARDS shards, got $found of $EXPECTED_SHARDS"
+            exit 1
+          fi
+          staged=$(find "$STAGED_RAW" -mindepth 2 -maxdepth 2 -type f -name '*.json' | wc -l)
+          mkdir -p coverage/js/raw
+          # cp -n never overwrites; a clash shows up as fewer merged files than staged ones.
+          find "$STAGED_RAW" -mindepth 2 -maxdepth 2 -type f -name '*.json' -exec cp -n -t coverage/js/raw {} + || true
+          merged=$(find coverage/js/raw -maxdepth 1 -type f -name '*.json' | wc -l)
+          if [ "$merged" -ne "$staged" ]; then
+            echo "::error::Shards wrote clashing raw file names: $staged staged, $merged merged"
+            exit 1
+          fi
+          echo "merged $merged raw files"
+      - name: Frontend coverage report and baseline check
+        run: npm run --prefix tools/vendor coverage:merge
+      - name: Upload frontend coverage report
        if: always()
        uses: actions/upload-artifact@v7
        with:
          name: frontend-test-reports
          path: |
-            tools/vendor/test-results/
            coverage/js/
            !coverage/js/raw/**
          retention-days: 14

  browser-workflows:
-    name: page workflows (${{ matrix.browser }})
+    name: page workflows (${{ matrix.browser }}, shard ${{ matrix.shard }}/2)
    runs-on: ubuntu-latest
    # Layout comparisons depend on the fonts each browser falls back to, so browser jobs run in the
    # same pinned Playwright image as local runs (tag = @playwright/test in tools/vendor/package-lock.json;
@@ -75,11 +151,16 @@ jobs:
    container:
      image: mcr.microsoft.com/playwright:v1.64.1-noble
      options: --user 1001
-    timeout-minutes: 25
+    timeout-minutes: 12
+    # Public-repo ubuntu-latest runners have 4 vCPUs: three Playwright workers, each with its own test
+    # server, leave one CPU for the servers and the runner.
+    env:
+      PM_TEST_WORKERS: 3
    strategy:
      fail-fast: false
      matrix:
        browser: [firefox, webkit]
+        shard: [1, 2]
    steps:
      - uses: actions/checkout@v7
      # The image's own Python 3.12 and Node 24: setup-python/setup-node install the runner's toolcache
@@ -99,21 +180,21 @@ jobs:
          echo "$venv/bin" >> "$GITHUB_PATH"
      - run: python --version && node --version && node --version | grep -q '^v24\.'
      - run: npm ci --prefix tools/vendor --ignore-scripts
-      - name: Page workflows in ${{ matrix.browser }}
-        run: npm run --prefix tools/vendor test:workflows -- --project ${{ matrix.browser }}
+      - name: Page workflows in ${{ matrix.browser }}, shard ${{ matrix.shard }}/2
+        run: npm run --prefix tools/vendor test:workflows -- --project ${{ matrix.browser }} --shard ${{ matrix.shard }}/2
      - name: Upload browser traces
        if: always()
        uses: actions/upload-artifact@v7
        with:
-          name: browser-traces-${{ matrix.browser }}
+          name: browser-traces-${{ matrix.browser }}-shard-${{ matrix.shard }}
          path: tools/vendor/test-results/
          retention-days: 14

  # Branch protection requires the exact context "viewerjs". This job keeps that
-  # name and fails unless every frontend job above succeeded, including when one
-  # was cancelled or skipped.
+  # name and fails unless every frontend job above succeeded (every shard, the
+  # coverage merge and every browser shard), including when one was cancelled or skipped.
  viewerjs:
-    needs: [frontend-coverage, browser-workflows]
+    needs: [frontend-coverage, frontend-coverage-merge, browser-workflows]
    if: always()
    runs-on: ubuntu-latest
    timeout-minutes: 5
@@ -121,8 +202,10 @@ jobs:
      - name: Require every frontend job to succeed
        env:
          COVERAGE_RESULT: ${{ needs.frontend-coverage.result }}
+          MERGE_RESULT: ${{ needs.frontend-coverage-merge.result }}
          WORKFLOWS_RESULT: ${{ needs.browser-workflows.result }}
        run: |
          echo "frontend-coverage: $COVERAGE_RESULT"
+          echo "frontend-coverage-merge: $MERGE_RESULT"
          echo "browser-workflows: $WORKFLOWS_RESULT"
-          test "$COVERAGE_RESULT" = success && test "$WORKFLOWS_RESULT" = success
+          test "$COVERAGE_RESULT" = success && test "$MERGE_RESULT" = success && test "$WORKFLOWS_RESULT" = success