2025-12-15 11:47:50 +01:00
|
|
|
import { test, expect, tryLoadApp } from './utils/fixtures';
|
e2e/CI: dual-engine suites, per-engine screenshots, SwiftShader retired, prod web suite, CI-coverage gate
Squash of experiment/ff-big-modules vs main.
Big-module routing removed: native-EH shrank kicad_editor below
SpiderMonkey's x86-64 code budget (runs 29355049705/29356152413 green on
stock Firefox), so BIG_MODULE_SPECS routing and the baseline-only-JIT
crutch are gone — kicad-firefox and kicad-chromium both run the full
suite, with the module compiled the way real users' browsers compile it.
Per-engine screenshots end to end: stableShot/shotPath write
test-results/<engine>/<name>.png; baselines move to
baseline-screenshots/{chromium,firefox}/ and the whole tools/screenshots
pipeline (compare/promote/manifest/spec-map/changelog/Discord) keys on
<engine>/<name>. Previously Firefox and Chromium renders of one spec
overwrote each other and Firefox renders were never actually gated.
Seeded from CI run 29421380806 (92 new firefox baselines, +24 chromium
web-suite shots); manifest generated from the baseline tree.
One merged playwright.config.ts (kicad/asyncify/coroutine/perf as
projects); ~25 dead npm scripts dropped. The web suite is gated in CI for
the first time ever (4 rotted specs fixed, 5 broken lib-bridge specs
triaged as fixme in docs/features/web-e2e-rot/); cheap lint step after
npm ci; last 26 blind-sleep violations fixed.
SwiftShader retired: CI Chromium renders WebGL on ANGLE → Mesa llvmpipe
(--use-gl=angle --use-angle=gl --ignore-gpu-blocklist; the blocklist flag
is mandatory — llvmpipe is blocklisted and WebGL is silently unavailable
without it) in BOTH configs. Under WORKERS=4 congestion SwiftShader
transiently failed the first post-board-load draw and the recovery
cascade ended in a silent permanent Cairo fallback — that engine flip was
the "~1.2% changedRatio both directions" occ-export baseline flake.
Validated 160/160 across two 80-repeat rigs; full analysis in
docs/features/wx-parity-bugs/occ-export-context-eviction.md. Chromium
baselines shift slightly on llvmpipe — promote once from the first green
run. Deflakes the new coverage exposed: presence baselines settle before
capture; presence fixtures declare current file formats; perf gets its
own outputDir so CI evidence survives; occ-export settles the board paint
before the export dialog; menu-item waits (waitForRenderedByLabel before
clickMenuItem) in 4 specs + the TESTING.md rule.
Web suite runs the PROD build, in parallel: webServer becomes backend
`start` + the standalone's e2e:preview (build-preview.mjs: link-wasm →
stash the public/wasm symlink aside during vite build, build-demo.mjs's
move — then vite preview as the persistent server). The wasm middleware
serves /wasm/* in preview and emits COOP/COEP/CORP itself (a pthread
worker script's own response must carry COEP or Chrome kills it with
ERR_BLOCKED_BY_RESPONSE). VITE_* flags bake at build time;
VITE_ALLOW_USER_OVERRIDE joins turbo globalEnv. fullyParallel + default
workers: 5.2m → 1.4m. Determinism fixes the parallel run exposed:
shared-page specs become serial groups; locks.spec grabs alice's exact
item via the new kicadCollabTestSelectByUuid hook (cross-tab "first
footprint" order is not a ysync invariant); quit specs poll page.url()
(quit supersedes its own navigation — NS_BINDING_ABORTED on Firefox).
Suite: 51 passed / 12 skipped / 0 failed in 1.6m.
CI-coverage gate (lint:ci-coverage): every tests/**/*.spec.ts must be
reachable from the npm scripts the workflows invoke — scraped from
.github/workflows/, resolved through package.json, coverage asked from
playwright --list itself. Rules: uncovered-spec + orphan-project (with a
documented LOCAL_ONLY_PROJECTS allowlist). Gating next to
lint:determinism; 138 spec files / 13 projects accounted for.
Product fixes kept from the investigations (reachable on real GPUs too):
wx 7799fd1be5 — paint flags clear before dispatch + Invalidate always
propagates; kicad 3dcfea5e45 — SwiftShader pass-boundary flush +
per-instance font texture + first-frame GL-error drain (GAL recovery
recovers instead of falling back to Cairo) + the user-facing eeschema
switch navigates again under __EMSCRIPTEN__ (project-sync's
FaceRegistered gate had rerouted it into the hidden sync player; caught
by the newly-gated web suite).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_018eUxiPApHgGiu9NFyQfhAq
2026-07-17 12:10:40 +02:00
|
|
|
import { shotPath } from './utils/element-tracker';
|
2025-12-15 11:47:50 +01:00
|
|
|
|
|
|
|
|
test.describe('Thread Pool Deadlock Tests', () => {
|
|
|
|
|
|
|
|
|
|
test('Creating hardware_concurrency threads should not deadlock', async ({ page, testLogger }) => {
|
|
|
|
|
// This test replicates KiCad's BS::priority_thread_pool pattern:
|
|
|
|
|
// - Creates hardware_concurrency() threads in the frame constructor
|
|
|
|
|
// - If PTHREAD_POOL_SIZE < hardware_concurrency, this will deadlock because:
|
|
|
|
|
// 1. Threads 1-N use pre-warmed Web Workers
|
|
|
|
|
// 2. Thread N+1 needs new Web Worker (posts to event loop)
|
|
|
|
|
// 3. Main thread busy-waits for thread to start
|
|
|
|
|
// 4. Busy-wait blocks event loop -> Worker message never processed
|
|
|
|
|
// 5. DEADLOCK (timeout)
|
|
|
|
|
|
|
|
|
|
await page.goto('/standalone/threadpool/threadpool_test.html');
|
|
|
|
|
|
|
|
|
|
// If there's a deadlock, tryLoadApp will timeout waiting for canvas
|
|
|
|
|
const loaded = await tryLoadApp(page, 30000);
|
|
|
|
|
|
e2e/CI: dual-engine suites, per-engine screenshots, SwiftShader retired, prod web suite, CI-coverage gate
Squash of experiment/ff-big-modules vs main.
Big-module routing removed: native-EH shrank kicad_editor below
SpiderMonkey's x86-64 code budget (runs 29355049705/29356152413 green on
stock Firefox), so BIG_MODULE_SPECS routing and the baseline-only-JIT
crutch are gone — kicad-firefox and kicad-chromium both run the full
suite, with the module compiled the way real users' browsers compile it.
Per-engine screenshots end to end: stableShot/shotPath write
test-results/<engine>/<name>.png; baselines move to
baseline-screenshots/{chromium,firefox}/ and the whole tools/screenshots
pipeline (compare/promote/manifest/spec-map/changelog/Discord) keys on
<engine>/<name>. Previously Firefox and Chromium renders of one spec
overwrote each other and Firefox renders were never actually gated.
Seeded from CI run 29421380806 (92 new firefox baselines, +24 chromium
web-suite shots); manifest generated from the baseline tree.
One merged playwright.config.ts (kicad/asyncify/coroutine/perf as
projects); ~25 dead npm scripts dropped. The web suite is gated in CI for
the first time ever (4 rotted specs fixed, 5 broken lib-bridge specs
triaged as fixme in docs/features/web-e2e-rot/); cheap lint step after
npm ci; last 26 blind-sleep violations fixed.
SwiftShader retired: CI Chromium renders WebGL on ANGLE → Mesa llvmpipe
(--use-gl=angle --use-angle=gl --ignore-gpu-blocklist; the blocklist flag
is mandatory — llvmpipe is blocklisted and WebGL is silently unavailable
without it) in BOTH configs. Under WORKERS=4 congestion SwiftShader
transiently failed the first post-board-load draw and the recovery
cascade ended in a silent permanent Cairo fallback — that engine flip was
the "~1.2% changedRatio both directions" occ-export baseline flake.
Validated 160/160 across two 80-repeat rigs; full analysis in
docs/features/wx-parity-bugs/occ-export-context-eviction.md. Chromium
baselines shift slightly on llvmpipe — promote once from the first green
run. Deflakes the new coverage exposed: presence baselines settle before
capture; presence fixtures declare current file formats; perf gets its
own outputDir so CI evidence survives; occ-export settles the board paint
before the export dialog; menu-item waits (waitForRenderedByLabel before
clickMenuItem) in 4 specs + the TESTING.md rule.
Web suite runs the PROD build, in parallel: webServer becomes backend
`start` + the standalone's e2e:preview (build-preview.mjs: link-wasm →
stash the public/wasm symlink aside during vite build, build-demo.mjs's
move — then vite preview as the persistent server). The wasm middleware
serves /wasm/* in preview and emits COOP/COEP/CORP itself (a pthread
worker script's own response must carry COEP or Chrome kills it with
ERR_BLOCKED_BY_RESPONSE). VITE_* flags bake at build time;
VITE_ALLOW_USER_OVERRIDE joins turbo globalEnv. fullyParallel + default
workers: 5.2m → 1.4m. Determinism fixes the parallel run exposed:
shared-page specs become serial groups; locks.spec grabs alice's exact
item via the new kicadCollabTestSelectByUuid hook (cross-tab "first
footprint" order is not a ysync invariant); quit specs poll page.url()
(quit supersedes its own navigation — NS_BINDING_ABORTED on Firefox).
Suite: 51 passed / 12 skipped / 0 failed in 1.6m.
CI-coverage gate (lint:ci-coverage): every tests/**/*.spec.ts must be
reachable from the npm scripts the workflows invoke — scraped from
.github/workflows/, resolved through package.json, coverage asked from
playwright --list itself. Rules: uncovered-spec + orphan-project (with a
documented LOCAL_ONLY_PROJECTS allowlist). Gating next to
lint:determinism; 138 spec files / 13 projects accounted for.
Product fixes kept from the investigations (reachable on real GPUs too):
wx 7799fd1be5 — paint flags clear before dispatch + Invalidate always
propagates; kicad 3dcfea5e45 — SwiftShader pass-boundary flush +
per-instance font texture + first-frame GL-error drain (GAL recovery
recovers instead of falling back to Cairo) + the user-facing eeschema
switch navigates again under __EMSCRIPTEN__ (project-sync's
FaceRegistered gate had rerouted it into the hidden sync player; caught
by the newly-gated web suite).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_018eUxiPApHgGiu9NFyQfhAq
2026-07-17 12:10:40 +02:00
|
|
|
await page.screenshot({ path: shotPath(page, 'threadpool-01-loaded.png'), fullPage: true });
|
2025-12-15 11:47:50 +01:00
|
|
|
|
|
|
|
|
// Check for success marker - all threads created and joined
|
|
|
|
|
const success = testLogger.consoleLogs.some(log =>
|
|
|
|
|
log.includes('[THREADPOOL] SUCCESS')
|
|
|
|
|
);
|
|
|
|
|
|
|
|
|
|
expect(loaded, 'App should load without deadlock').toBe(true);
|
|
|
|
|
expect(success, 'All threads should complete successfully').toBe(true);
|
|
|
|
|
expect(testLogger.errors.filter(e => !e.includes('favicon'))).toHaveLength(0);
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
test('Thread creation logs show all threads started', async ({ page, testLogger }) => {
|
|
|
|
|
await page.goto('/standalone/threadpool/threadpool_test.html');
|
|
|
|
|
|
|
|
|
|
const loaded = await tryLoadApp(page, 30000);
|
2026-01-01 20:18:19 +01:00
|
|
|
expect(loaded, 'App should load without deadlock').toBe(true);
|
2025-12-15 11:47:50 +01:00
|
|
|
|
|
|
|
|
// Extract hardware_concurrency from logs
|
|
|
|
|
const hwLog = testLogger.consoleLogs.find(log =>
|
|
|
|
|
log.includes('[THREADPOOL] hardware_concurrency:')
|
|
|
|
|
);
|
2026-01-01 20:18:19 +01:00
|
|
|
expect(hwLog, 'Should find hardware_concurrency log').toBeDefined();
|
2025-12-15 11:47:50 +01:00
|
|
|
|
2026-01-01 20:18:19 +01:00
|
|
|
const match = hwLog!.match(/hardware_concurrency:\s*(\d+)/);
|
|
|
|
|
expect(match, 'Should parse hardware_concurrency value').not.toBeNull();
|
2025-12-15 11:47:50 +01:00
|
|
|
|
2026-01-01 20:18:19 +01:00
|
|
|
const expectedThreads = parseInt(match![1], 10);
|
2025-12-15 11:47:50 +01:00
|
|
|
|
|
|
|
|
// Count "Thread X started" messages
|
|
|
|
|
const threadStartedLogs = testLogger.consoleLogs.filter(log =>
|
|
|
|
|
log.includes('[THREADPOOL] Thread') && log.includes('started')
|
|
|
|
|
);
|
|
|
|
|
|
|
|
|
|
// All threads should have started
|
|
|
|
|
expect(threadStartedLogs.length).toBe(expectedThreads);
|
|
|
|
|
});
|
|
|
|
|
});
|