ci: 🎡 -o1 & test workers

.github/workflows/ci-ubicloud.yml

@@ -1,5 +1,5 @@
 # The build + e2e CI: full KiCad WASM build (all 6 tools, Binaryen 130, host-side
-# asyncify only — the -O2 pass is skipped via ASYNCIFY_ONLY=1) + wxWidgets e2e
+# asyncify + a lighter wasm-opt -O1 shrink pass via BINARYEN_OPT_LEVEL) + wxWidgets e2e
 # (291 tests) + KiCad e2e (38 tests) on a Ubicloud runner. Runs on pushes to
 # main/ubicloud-ci and on PRs against main.
 # Replaced the ephemeral-Hetzner-VM workflows (ci-full-build.yml / ci.yml,
@@ -38,10 +38,14 @@ jobs:
     env:
       KICAD_LOG_NESTED: "1"
       BINARYEN_VERSION: ${{ inputs.binaryen_version || '130' }}
-      # Skip the heavy wasm-opt -O2 pass (scripts/common/apply-asyncify.sh:124):
-      # stops after the asyncify pass. The full e2e suite below validates that
-      # the non-O2 wasm runs correctly in Chrome/Firefox.
-      ASYNCIFY_ONLY: "1"
+      # Use the lighter wasm-opt -O1 shrink pass instead of -O2
+      # (scripts/common/apply-asyncify.sh). -O1 still runs CoalesceLocals, so the
+      # asyncify-instrumented coroutine functions stay under V8's per-function
+      # locals limit: it produces the same ~187 MB pcbnew.wasm as -O2 and is green
+      # on the load-pcb chromium-ci spec, but is a faster pass. (Skipping the
+      # optimization entirely via ASYNCIFY_ONLY=1 shipped a 336 MB wasm that
+      # crashed headless Chromium — that flag is benchmark-only, not for e2e.)
+      BINARYEN_OPT_LEVEL: "-O1"
       # Stable docker-compose project → deterministic build-cache volume name
       # (kicad-wasm-ci_kicad-build-cache) for the deps cache below.
       COMPOSE_PROJECT_NAME: kicad-wasm-ci
@@ -86,7 +90,7 @@ jobs:
 
       # Same build recipe as ci-full-build.yml: full KiCad WASM build of ALL 6
       # tools, host-side asyncify on Binaryen v130 (BINARYEN_VERSION in env →
-      # get-wasm-opt.sh); the -O2 pass is skipped (ASYNCIFY_ONLY=1 in job env).
+      # get-wasm-opt.sh) + a lighter -O1 shrink pass (BINARYEN_OPT_LEVEL in job env).
       # 'all' = pcbnew eeschema calculator pl_editor symbol_editor gerbview,
       # built in sequence. --build-deps short-circuits on a cache hit.
       - name: Build all KiCad tools WASM with Binaryen ${{ env.BINARYEN_VERSION }}
@@ -117,6 +121,25 @@ jobs:
           docker run --rm -v kicad-wasm-ci_kicad-build-cache:/bw -v "$PWD/deps-cache":/cache \
             alpine sh -c 'cd /bw && tar czf /cache/deps.tar.gz sysroot stamps'
 
+      # Cache the host wxWidgets build (build-wasm/wxwidgets, ~11 min, incremental
+      # but uncached) keyed on the wx submodule SHA + the build script/versions.
+      # On a hit, touch the tree so make treats the restored objects as current
+      # (same SHA ⇒ identical sources), so build-wx-wasm.sh just relinks fast.
+      - name: wx submodule sha
+        id: wxsha
+        run: echo "sha=$(git -C wxwidgets rev-parse HEAD)" >> "$GITHUB_OUTPUT"
+
+      - name: Restore wx build cache
+        id: wx-cache
+        uses: actions/cache@v4
+        with:
+          path: build-wasm/wxwidgets
+          key: wx-${{ runner.os }}-${{ steps.wxsha.outputs.sha }}-${{ hashFiles('scripts/build-wx-wasm.sh','scripts/common/versions.sh') }}
+
+      - name: Mark restored wx objects current
+        if: steps.wx-cache.outputs.cache-hit == 'true'
+        run: find build-wasm/wxwidgets -exec touch {} +
+
       # Host-side wxWidgets build producing the wx test apps for `npm run test`
       # (separate from the in-docker wxWidgets that KiCad links against).
       # Auto-installs emsdk into tools/ on first run.

scripts/common/apply-asyncify.sh

@@ -128,18 +128,30 @@ if [[ "${ASYNCIFY_ONLY:-0}" == "1" ]]; then
     exit 0
 fi
 
+# Post-asyncify shrink pass. Asyncify emits deliberately verbose instrumentation
+# (spills every live local) and relies on the optimizer to coalesce it back down
+# under V8's per-function locals limit — without it, large coroutine-entry
+# functions silently stall (and on newer Chromium hard-crash the renderer while
+# loading a heavy board) in Chrome's V8. See docs/debugging/DEBUG.md §6-7.
+#
+# Level is configurable via BINARYEN_OPT_LEVEL: -O1 already runs CoalesceLocals
+# and is sufficient (measured: same ~187 MB / 64 MB-gzip output as -O2 on pcbnew,
+# validated green on the load-pcb chromium-ci spec — but a lighter, faster pass,
+# which is why CI sets -O1). -O2 stays the default for the more thorough rewrite.
+# Do NOT use -Os/-Oz here: they break the asyncify runtime (Binaryen #4484).
+BINARYEN_OPT_LEVEL="${BINARYEN_OPT_LEVEL:--O2}"
+
 echo ""
-echo "Running wasm-opt -O2 on the asyncified wasm..."
+echo "Running wasm-opt ${BINARYEN_OPT_LEVEL} on the asyncified wasm..."
 echo "  Purpose: shrink asyncify-instrumented functions back under V8's"
 echo "  per-function locals limit (otherwise large coroutine-entry and"
-echo "  similar functions silently stall in Chrome's V8). See docs/debugging/DEBUG.md §7"
-echo "  and memory/bundle-size-asyncify-optimization.md."
-echo "  This pass also takes several minutes and ~10-15 GB RAM."
+echo "  similar functions stall/crash in Chrome's V8). See docs/debugging/DEBUG.md §6-7."
+echo "  This pass takes several minutes and ~10-15 GB RAM."
 echo "  BINARYEN_CORES=${BINARYEN_CORES}"
 echo "  LD_PRELOAD=${WASM_OPT_PRELOAD:-<none>}"
 
-"${PRELOAD_CMD[@]}" "${TIME_CMD[@]}" "${WASM_OPT}" -O2 "${OUTPUT_WASM}" -o "${OUTPUT_WASM}"
+"${PRELOAD_CMD[@]}" "${TIME_CMD[@]}" "${WASM_OPT}" "${BINARYEN_OPT_LEVEL}" "${OUTPUT_WASM}" -o "${OUTPUT_WASM}"
 
 echo ""
-echo "Asyncify + -O2 complete: ${OUTPUT_WASM}"
+echo "Asyncify + ${BINARYEN_OPT_LEVEL} complete: ${OUTPUT_WASM}"
 ls -lh "${OUTPUT_WASM}"

tests/playwright-kicad.config.ts

@@ -97,7 +97,10 @@ export default defineConfig({
   // as playwright.config.ts): the load-pcb post-load clipboard crash that can
   // close the page on Firefox, and the calculator first-run-wizard timing race.
   retries: process.env.CI ? 2 : 1,
-  workers: process.env.CI ? 1 : undefined,
+  // Run parallel workers on CI too (Playwright default ≈ 50% of cores), same as
+  // local — the serial CI run was the dominant wall-clock cost. Cap (e.g. '50%'
+  // or a fixed count) if contention OOMs/flakes; retries:2 covers transient.
+  workers: undefined,
   reporter: 'html',
   timeout: 180000,  // KiCad WASM needs more time to load (3 minutes)
 

tests/playwright.config.ts

@@ -72,7 +72,10 @@ export default defineConfig({
   // 1 local retry absorbs transient `npx serve` connection refusals under heavy
   // parallel load (many workers fetching large WASM bundles at once).
   retries: process.env.CI ? 2 : 1,
-  workers: process.env.CI ? 1 : undefined,
+  // Run parallel workers on CI too (Playwright default ≈ 50% of cores), same as
+  // local — the serial CI run was the dominant wall-clock cost. Cap (e.g. '50%'
+  // or a fixed count) if contention OOMs/flakes; retries:2 covers transient.
+  workers: undefined,
   reporter: 'html',
   timeout: 60000,  // WASM can be slow to load