bench: JSPI vs asyncify A/B — harness + results
Adds pcbnew-large-perf.spec.ts (PERF_LARGE-gated: repeated cold loads, vme-wren/jetson opens, rAF + distinct-glcanvas-frame FPS under throttle, wasm/JS heap checkpoints), fetchIntoMemfs + openAndWait/sampleMemory/ measureFpsDetailed perf-utils, dual 9.99+10.0 config seeding in pcbnew.html so foreign-branch builds boot wizard-free, and the full benchmark report + raw data under docs/features/async/migration-evidence/. Headlines: wasm 94 vs 113 MB raw (18.6 vs 36.7 MB gzip), post-link tail 1.6 s/49 MB vs 63 s/6.1 GB per build, cold load −40 %, 27.7 MB board open −45 %, real redraws +68 % at 4× throttle, boot heap −31 %. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_016X9eh1s5sTx1o9Em9KBuwR
This commit is contained in:
Viktor Vaczi
parent
9c475a804e
commit
da299ed6f9
12 changed files with 707 additions and 11 deletions
1
.gitignore
vendored
1
.gitignore
vendored
|
|
@ -40,6 +40,7 @@ wxwidgets-clean/
|
|||
/tests/node_modules/
|
||||
/tests/playwright-report/
|
||||
/tests/test-results/
|
||||
/tests/bench-results/
|
||||
/tests/pw-artifacts/
|
||||
/tests/.test-port
|
||||
/test-results/
|
||||
|
|
|
|||
|
|
@ -216,6 +216,10 @@ same-origin serving works. Not fixed in the cleanup — tracked here.
|
|||
|
||||
## 10. Migration evidence
|
||||
|
||||
- **A/B benchmark vs the asyncify build** (2026-08-14): build time / build
|
||||
memory / bundle size / load / open / FPS / heap —
|
||||
[`migration-evidence/jspi-vs-asyncify-bench-2026-08.md`](migration-evidence/jspi-vs-asyncify-bench-2026-08.md)
|
||||
(raw data in `migration-evidence/bench-data-2026-08/`).
|
||||
- **Workflow results**: `migration-evidence/wf-result-11.json` /
|
||||
`wf-result-12.json` (the durable spike output; the rest of the
|
||||
`.jspi-assets/` spike tree was scratch and is gone — its ignore rule came
|
||||
|
|
|
|||
|
|
@ -0,0 +1,6 @@
|
|||
A-S1a,175,0,19584995328
|
||||
A-S1b,427,0,22525415424
|
||||
A-S2a,165,0,21735530496
|
||||
A-S2b,248,0,23429591040
|
||||
A-compileonly,91,0,23662247936
|
||||
A-S3,819,0,23760617472
|
||||
|
|
|
@ -0,0 +1,6 @@
|
|||
B-S1a,379,0,20131172352
|
||||
B-S1b,154,0,20515237888
|
||||
B-S2a,122,0,20695916544
|
||||
B-S2b,95,0,20612022272
|
||||
B-S3,26,2,4479885312
|
||||
B-S3,305,0,20694478848
|
||||
|
|
|
@ -0,0 +1,66 @@
|
|||
{
|
||||
"jspi": {
|
||||
"kicad_editor.wasm": {
|
||||
"raw": 98664038,
|
||||
"gzip": 19469712,
|
||||
"brotli": 14173019
|
||||
},
|
||||
"kicad_editor.js": {
|
||||
"raw": 474692,
|
||||
"gzip": 116955,
|
||||
"brotli": 106125
|
||||
},
|
||||
"wx.js": {
|
||||
"raw": 74281,
|
||||
"gzip": 17356,
|
||||
"brotli": 16439
|
||||
},
|
||||
"wx-dom.js": {
|
||||
"raw": 63269,
|
||||
"gzip": 16857,
|
||||
"brotli": 15848
|
||||
},
|
||||
"images.tar.gz": {
|
||||
"raw": 5370904,
|
||||
"gzip": 5372562,
|
||||
"brotli": 5114985
|
||||
},
|
||||
"TOTAL": {
|
||||
"raw": 104647184,
|
||||
"gzip": 24993442,
|
||||
"brotli": 19426416
|
||||
}
|
||||
},
|
||||
"asyncify": {
|
||||
"kicad_editor.wasm": {
|
||||
"raw": 118557371,
|
||||
"gzip": 38473650,
|
||||
"brotli": 25666194
|
||||
},
|
||||
"kicad_editor.js": {
|
||||
"raw": 472325,
|
||||
"gzip": 116872,
|
||||
"brotli": 105662
|
||||
},
|
||||
"wx.js": {
|
||||
"raw": 74281,
|
||||
"gzip": 17356,
|
||||
"brotli": 16439
|
||||
},
|
||||
"wx-dom.js": {
|
||||
"raw": 63041,
|
||||
"gzip": 16773,
|
||||
"brotli": 15765
|
||||
},
|
||||
"images.tar.gz": {
|
||||
"raw": 5370145,
|
||||
"gzip": 5371803,
|
||||
"brotli": 5160999
|
||||
},
|
||||
"TOTAL": {
|
||||
"raw": 124537163,
|
||||
"gzip": 43996454,
|
||||
"brotli": 30965059
|
||||
}
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,20 @@
|
|||
{"arm":"asyncify","sha256":"6dab493196d060d7","when":"2026-08-14T09:46:53.665Z","section":"load","run":1,"loadMs":2629,"wasmFetch":{"durationMs":1053,"transferSize":32139352},"bootMem":{"wasmHeapBytes":556793856,"jsHeapBytes":27600000}}
|
||||
{"arm":"asyncify","sha256":"6dab493196d060d7","when":"2026-08-14T09:46:56.364Z","section":"load","run":2,"loadMs":2610,"wasmFetch":{"durationMs":961,"transferSize":32139352},"bootMem":{"wasmHeapBytes":556793856,"jsHeapBytes":27600000}}
|
||||
{"arm":"asyncify","sha256":"6dab493196d060d7","when":"2026-08-14T09:46:59.036Z","section":"load","run":3,"loadMs":2576,"wasmFetch":{"durationMs":989,"transferSize":32139352},"bootMem":{"wasmHeapBytes":556793856,"jsHeapBytes":27600000}}
|
||||
{"arm":"asyncify","sha256":"6dab493196d060d7","when":"2026-08-14T09:47:01.667Z","section":"load","run":4,"loadMs":2526,"wasmFetch":{"durationMs":987,"transferSize":32139352},"bootMem":{"wasmHeapBytes":556793856,"jsHeapBytes":27600000}}
|
||||
{"arm":"asyncify","sha256":"6dab493196d060d7","when":"2026-08-14T09:47:04.272Z","section":"load","run":5,"loadMs":2521,"wasmFetch":{"durationMs":997,"transferSize":32139352},"bootMem":{"wasmHeapBytes":556793856,"jsHeapBytes":27600000}}
|
||||
{"arm":"asyncify","sha256":"6dab493196d060d7","when":"2026-08-14T09:47:06.873Z","section":"load-cdp-sanity","loadMs":2514}
|
||||
{"arm":"asyncify","sha256":"6dab493196d060d7","when":"2026-08-14T09:47:09.937Z","section":"open-demo","run":1,"openMs":467,"postOpenMem":{"wasmHeapBytes":556793856,"jsHeapBytes":33100000}}
|
||||
{"arm":"asyncify","sha256":"6dab493196d060d7","when":"2026-08-14T09:47:12.982Z","section":"open-demo","run":2,"openMs":468,"postOpenMem":{"wasmHeapBytes":556793856,"jsHeapBytes":33100000}}
|
||||
{"arm":"asyncify","sha256":"6dab493196d060d7","when":"2026-08-14T09:47:16.025Z","section":"open-demo","run":3,"openMs":467,"postOpenMem":{"wasmHeapBytes":556793856,"jsHeapBytes":33100000}}
|
||||
{"arm":"asyncify","sha256":"6dab493196d060d7","when":"2026-08-14T09:47:25.126Z","section":"open-vme","run":1,"bytes":29032252,"openMs":6465,"openPeakHeap":962330624,"postOpenMem":{"wasmHeapBytes":962330624,"jsHeapBytes":56800000}}
|
||||
{"arm":"asyncify","sha256":"6dab493196d060d7","when":"2026-08-14T09:47:34.418Z","section":"open-vme","run":2,"bytes":29032252,"openMs":6582,"openPeakHeap":962330624,"postOpenMem":{"wasmHeapBytes":962330624,"jsHeapBytes":56800000}}
|
||||
{"arm":"asyncify","sha256":"6dab493196d060d7","when":"2026-08-14T09:47:43.512Z","section":"open-vme","run":3,"bytes":29032252,"openMs":6398,"openPeakHeap":1182793728,"postOpenMem":{"wasmHeapBytes":1182793728,"jsHeapBytes":56800000}}
|
||||
{"arm":"asyncify","sha256":"6dab493196d060d7","when":"2026-08-14T09:47:58.746Z","section":"fps-vme","throttle":1,"rep":1,"rafFps":44.5,"distinctFps":7.8}
|
||||
{"arm":"asyncify","sha256":"6dab493196d060d7","when":"2026-08-14T09:48:04.925Z","section":"fps-vme","throttle":1,"rep":2,"rafFps":49.1,"distinctFps":7.8}
|
||||
{"arm":"asyncify","sha256":"6dab493196d060d7","when":"2026-08-14T09:48:10.980Z","section":"fps-vme","throttle":4,"rep":1,"rafFps":32.4,"distinctFps":3}
|
||||
{"arm":"asyncify","sha256":"6dab493196d060d7","when":"2026-08-14T09:48:17.030Z","section":"fps-vme","throttle":4,"rep":2,"rafFps":37.6,"distinctFps":3.1}
|
||||
{"arm":"asyncify","sha256":"6dab493196d060d7","when":"2026-08-14T09:48:23.361Z","section":"fps-vme","throttle":6,"rep":1,"rafFps":39.9,"distinctFps":4.1}
|
||||
{"arm":"asyncify","sha256":"6dab493196d060d7","when":"2026-08-14T09:48:29.439Z","section":"fps-vme","throttle":6,"rep":2,"rafFps":34.3,"distinctFps":2.8}
|
||||
{"arm":"asyncify","sha256":"6dab493196d060d7","when":"2026-08-14T09:48:29.442Z","section":"fps-vme-postmem","postFpsMem":{"wasmHeapBytes":962330624,"jsHeapBytes":60300000}}
|
||||
{"arm":"asyncify","sha256":"6dab493196d060d7","when":"2026-08-14T09:48:46.855Z","section":"open-jetson","bytes":84806775,"outcome":"loaded","openMs":14584,"openPeakHeap":1904214016,"postOpenMem":{"wasmHeapBytes":1904214016,"jsHeapBytes":116000000}}
|
||||
|
|
@ -0,0 +1,27 @@
|
|||
{"arm":"jspi","sha256":"6f03e62d6d5619c3","when":"2026-08-14T09:43:04.217Z","section":"load","run":1,"loadMs":1841,"wasmFetch":{"durationMs":692,"transferSize":17051037},"bootMem":{"wasmHeapBytes":386662400,"jsHeapBytes":27600000}}
|
||||
{"arm":"jspi","sha256":"6f03e62d6d5619c3","when":"2026-08-14T09:43:05.422Z","section":"load","run":2,"loadMs":1117,"wasmFetch":{"durationMs":554,"transferSize":17051037},"bootMem":{"wasmHeapBytes":268435456,"jsHeapBytes":29400000}}
|
||||
{"arm":"jspi","sha256":"6f03e62d6d5619c3","when":"2026-08-14T09:43:07.469Z","section":"load","run":3,"loadMs":1547,"wasmFetch":{"durationMs":573,"transferSize":17051037},"bootMem":{"wasmHeapBytes":386662400,"jsHeapBytes":27600000}}
|
||||
{"arm":"jspi","sha256":"6f03e62d6d5619c3","when":"2026-08-14T09:43:09.081Z","section":"load","run":4,"loadMs":1123,"wasmFetch":{"durationMs":574,"transferSize":17051037},"bootMem":{"wasmHeapBytes":386662400,"jsHeapBytes":24500000}}
|
||||
{"arm":"jspi","sha256":"6f03e62d6d5619c3","when":"2026-08-14T09:43:10.697Z","section":"load","run":5,"loadMs":1538,"wasmFetch":{"durationMs":571,"transferSize":17051037},"bootMem":{"wasmHeapBytes":386662400,"jsHeapBytes":26000000}}
|
||||
{"arm":"jspi","sha256":"6f03e62d6d5619c3","when":"2026-08-14T09:43:11.887Z","section":"load-cdp-sanity","loadMs":1117}
|
||||
{"arm":"jspi","sha256":"6f03e62d6d5619c3","when":"2026-08-14T09:43:14.226Z","section":"open-demo","run":1,"openMs":698,"postOpenMem":{"wasmHeapBytes":386662400,"jsHeapBytes":31200000}}
|
||||
{"arm":"jspi","sha256":"6f03e62d6d5619c3","when":"2026-08-14T09:43:16.208Z","section":"open-demo","run":2,"openMs":693,"postOpenMem":{"wasmHeapBytes":386662400,"jsHeapBytes":31200000}}
|
||||
{"arm":"jspi","sha256":"6f03e62d6d5619c3","when":"2026-08-14T09:43:18.164Z","section":"open-demo","run":3,"openMs":358,"postOpenMem":{"wasmHeapBytes":386662400,"jsHeapBytes":31200000}}
|
||||
{"arm":"jspi","sha256":"6f03e62d6d5619c3","when":"2026-08-14T09:43:23.447Z","section":"open-vme","run":1,"bytes":29032252,"openMs":3551,"openPeakHeap":801898496,"postOpenMem":{"wasmHeapBytes":801898496,"jsHeapBytes":56800000}}
|
||||
{"arm":"jspi","sha256":"6f03e62d6d5619c3","when":"2026-08-14T09:43:28.639Z","section":"open-vme","run":2,"bytes":29032252,"openMs":3538,"openPeakHeap":801898496,"postOpenMem":{"wasmHeapBytes":801898496,"jsHeapBytes":60300000}}
|
||||
{"arm":"jspi","sha256":"6f03e62d6d5619c3","when":"2026-08-14T09:43:33.963Z","section":"open-vme","run":3,"bytes":29032252,"openMs":3635,"openPeakHeap":801898496,"postOpenMem":{"wasmHeapBytes":801898496,"jsHeapBytes":60300000}}
|
||||
{"arm":"jspi","sha256":"6f03e62d6d5619c3","when":"2026-08-14T09:43:45.276Z","section":"fps-vme","throttle":1,"rep":1,"rafFps":51.6,"distinctFps":1.6,"note":"SUPERSEDED - sampler watched #canvas, not glcanvas"}
|
||||
{"arm":"jspi","sha256":"6f03e62d6d5619c3","when":"2026-08-14T09:43:51.293Z","section":"fps-vme","throttle":1,"rep":2,"rafFps":53,"distinctFps":1.8,"note":"SUPERSEDED - sampler watched #canvas, not glcanvas"}
|
||||
{"arm":"jspi","sha256":"6f03e62d6d5619c3","when":"2026-08-14T09:43:57.442Z","section":"fps-vme","throttle":4,"rep":1,"rafFps":36,"distinctFps":0.7,"note":"SUPERSEDED - sampler watched #canvas, not glcanvas"}
|
||||
{"arm":"jspi","sha256":"6f03e62d6d5619c3","when":"2026-08-14T09:44:03.520Z","section":"fps-vme","throttle":4,"rep":2,"rafFps":36.2,"distinctFps":0,"note":"SUPERSEDED - sampler watched #canvas, not glcanvas"}
|
||||
{"arm":"jspi","sha256":"6f03e62d6d5619c3","when":"2026-08-14T09:44:09.587Z","section":"fps-vme","throttle":6,"rep":1,"rafFps":33,"distinctFps":0,"note":"SUPERSEDED - sampler watched #canvas, not glcanvas"}
|
||||
{"arm":"jspi","sha256":"6f03e62d6d5619c3","when":"2026-08-14T09:44:16.055Z","section":"fps-vme","throttle":6,"rep":2,"rafFps":33.7,"distinctFps":0,"note":"SUPERSEDED - sampler watched #canvas, not glcanvas"}
|
||||
{"arm":"jspi","sha256":"6f03e62d6d5619c3","when":"2026-08-14T09:44:16.057Z","section":"fps-vme-postmem","postFpsMem":{"wasmHeapBytes":801898496,"jsHeapBytes":60300000}}
|
||||
{"arm":"jspi","sha256":"6f03e62d6d5619c3","when":"2026-08-14T09:44:26.524Z","section":"open-jetson","bytes":84806775,"outcome":"loaded","openMs":8620,"openPeakHeap":1730805760,"postOpenMem":{"wasmHeapBytes":1730805760,"jsHeapBytes":116000000}}
|
||||
{"arm":"jspi","sha256":"6f03e62d6d5619c3","when":"2026-08-14T09:52:00.000Z","section":"fps-vme","throttle":1,"rep":1,"rafFps":51.9,"distinctFps":9.6,"note":"glcanvas sampler re-run; when approximate (row reconstructed from run log after test-results wipe)"}
|
||||
{"arm":"jspi","sha256":"6f03e62d6d5619c3","when":"2026-08-14T09:52:06.000Z","section":"fps-vme","throttle":1,"rep":2,"rafFps":55.7,"distinctFps":9.2,"note":"glcanvas sampler re-run; when approximate"}
|
||||
{"arm":"jspi","sha256":"6f03e62d6d5619c3","when":"2026-08-14T09:52:12.000Z","section":"fps-vme","throttle":4,"rep":1,"rafFps":39.2,"distinctFps":5.1,"note":"glcanvas sampler re-run; when approximate"}
|
||||
{"arm":"jspi","sha256":"6f03e62d6d5619c3","when":"2026-08-14T09:52:18.000Z","section":"fps-vme","throttle":4,"rep":2,"rafFps":41.4,"distinctFps":5.2,"note":"glcanvas sampler re-run; when approximate"}
|
||||
{"arm":"jspi","sha256":"6f03e62d6d5619c3","when":"2026-08-14T09:52:24.000Z","section":"fps-vme","throttle":6,"rep":1,"rafFps":34.3,"distinctFps":3.3,"note":"glcanvas sampler re-run; when approximate"}
|
||||
{"arm":"jspi","sha256":"6f03e62d6d5619c3","when":"2026-08-14T09:52:30.000Z","section":"fps-vme","throttle":6,"rep":2,"rafFps":41.8,"distinctFps":5.3,"note":"glcanvas sampler re-run; when approximate"}
|
||||
{"arm":"jspi","sha256":"6f03e62d6d5619c3","when":"2026-08-14T09:52:30.100Z","section":"fps-vme-postmem","postFpsMem":{"wasmHeapBytes":801898496,"jsHeapBytes":64000000}}
|
||||
|
|
@ -0,0 +1,199 @@
|
|||
# JSPI vs Asyncify: editor benchmark (2026-08-14)
|
||||
|
||||
A/B benchmark of the `kicad_editor` app built two ways:
|
||||
|
||||
- **Arm A — asyncify**: `pcbjam` @ `29c61b8` (branch `staging`), emscripten **4.0.2**,
|
||||
`-sASYNCIFY=1` + host post-link pipeline (finalize → hoist-cpp-catches →
|
||||
`wasm-opt --asyncify` → `wasm-opt -O1`, Binaryen fork v130).
|
||||
- **Arm B — JSPI**: worktree @ `9c475a8` (branch `experiment/jspi`), emscripten **6.0.6**,
|
||||
`-sJSPI`, single-phase link, no post-link transform (only the ~1 s env-shim patch).
|
||||
|
||||
**Stated confound, up front:** the two arms differ by emscripten major (4.0.2 vs
|
||||
6.0.6) — libc/libc++/linker/JS-glue all moved with it. That skew is inseparable
|
||||
from the backend switch (strict-JSPI needs emscripten 6); every number below is
|
||||
"the shipped asyncify build vs the shipped JSPI build", not a pure
|
||||
suspension-mechanism isolate. What IS matched: same KiCad commit (`4bfed3f1`),
|
||||
wxWidgets 3.3.1, EH flags (`-fwasm-exceptions -sSUPPORT_LONGJMP=wasm
|
||||
-sWASM_LEGACY_EXCEPTIONS=1`), mimalloc, memory config (256 MB initial / 4 GB
|
||||
max), **DEBUG mode on both** (TU `-g -O1`, link `-O1 -g -gseparate-dwarf` — the
|
||||
default), docker caps 10 CPU / 32 GB, `-j 10`, `BINARYEN_CORES=8`,
|
||||
`HOIST_KEEP_NAMES` unset, runs serialized on an idle machine.
|
||||
|
||||
Machine: Apple M4 Max, 16 cores, 64 GB; Docker Desktop VM 12 CPU / 28 GiB;
|
||||
macOS 26.5.2. Raw data: [`bench-data-2026-08/`](bench-data-2026-08/).
|
||||
|
||||
## TL;DR
|
||||
|
||||
| Metric | Asyncify | JSPI | Δ |
|
||||
|---|---|---|---|
|
||||
| Editor wasm, raw | 113.1 MB | 94.1 MB | **−17 %** |
|
||||
| Editor wasm, gzip −9 | 36.7 MB | 18.6 MB | **−49 %** |
|
||||
| Editor wasm, brotli | 24.5 MB | 13.5 MB | **−45 %** |
|
||||
| Post-link tail (per build!) | 63.4 s, 6.1 GB RSS | 1.6 s, 49 MB RSS | **−97 %** |
|
||||
| Clean rebuild (warm ccache) | 165 s | 95 s | **−42 %** |
|
||||
| Cold load (median of 5) | 2 576 ms | 1 538 ms | **−40 %** |
|
||||
| Open vme-wren (27.7 MB board) | 6 465 ms | 3 551 ms | **−45 %** |
|
||||
| Real redraws/s @1× (vme-wren) | 7.8 | 9.4 | **+21 %** |
|
||||
| Real redraws/s @4× throttle | 3.1 | 5.2 | **+68 %** |
|
||||
| Wasm heap after big-board open | 962 MB | 802 MB | **−17 %** |
|
||||
| Jetson 80.9 MB board open | 14.6 s, peak 1.90 GB | 8.6 s, peak 1.73 GB | **−41 %** |
|
||||
|
||||
The asyncify tax was real on every axis: bytes (instrumented code also
|
||||
compresses ~2× worse), build time (a mandatory 6-GB-RSS host pass per link),
|
||||
load (bigger download + more code to tier), compute (slower opens, fewer real
|
||||
frames — the gap *widens* under CPU throttle, the doc-12 signature of
|
||||
per-operation overhead rather than mere size), and memory.
|
||||
|
||||
## 1. Build time
|
||||
|
||||
Scenarios (identical commands both arms, run serially): **S1** no-change
|
||||
rebuild (`./docker/build.sh kicad_editor -j 10` twice, 2nd reported), **S2**
|
||||
clean editor rebuild with warm ccache (`--clean-kicad`, twice), **S3** clean
|
||||
rebuild with `CCACHE_DISABLE=1` (manual `compose exec`, compile cost only).
|
||||
|
||||
Both trees exhibit an **mtime ping-pong** in the wx re-enter (a reconfigure
|
||||
regenerates files the next rsync restores → every other build pays a wx
|
||||
reconfigure). Numbers are therefore given per observed mode; phase splits from
|
||||
the `@KW@` markers.
|
||||
|
||||
| Scenario | Asyncify | JSPI |
|
||||
|---|---|---|
|
||||
| S1 no-change, quiet mode | **175 s** (cfg 40 + link 40 + finalize 4 + **asyncify 58**) | **154 s** (cfg 56 + link 46, tail ≈0) |
|
||||
| S1 no-change, wx-churn mode | 427 s (wx 89 + cfg 132 + compile 124 + tail 63) | 379 s (first run after container recreate) |
|
||||
| S2 clean, warm ccache, quiet | **165 s** (1 819 TU in 29 s + tail 61) | **95 s** (1 819 TU in 26 s) |
|
||||
| S2 clean, wx-churn mode | 248 s | 122 s |
|
||||
| S3 clean, no ccache (kicad only) | **365 s** (cfg 154 + compile 211) | **304 s** (cfg 136 + compile 168) |
|
||||
| Container compile-only, steady | 91 s | — (contained in S2) |
|
||||
|
||||
Reading: the container-side compile is broadly comparable (emscripten 6 is
|
||||
~15-20 % faster on the uncached compile); **the structural difference is the
|
||||
host tail** — asyncify pays 58-63 s *on every single link*, JSPI pays ~1.6 s.
|
||||
In the dev loop that is the difference between a ~2.5-minute and a ~4-minute
|
||||
edit-to-browser cycle (or 7 min when the wx churn mode hits, which the tail
|
||||
compounds).
|
||||
|
||||
Note: A-S3's wall figure included a 453 s wx rebuild triggered by the bench's
|
||||
own `touch` of the wx build Makefile (used to pin the wx skip path) — excluded
|
||||
above; the kicad configure+compile figures are uncontaminated.
|
||||
|
||||
## 2. Build memory
|
||||
|
||||
- **Container peak** (cgroup v2 `memory.peak`, fresh cgroup per run): both arms
|
||||
18–24 GiB across all scenarios — dominated by the `-j 10` compile and the
|
||||
DWARF-heavy `wasm-ld` link, essentially backend-independent.
|
||||
- **Host post-link tail** (`/usr/bin/time -l`):
|
||||
- Asyncify: **63.4 s wall, 307 s user, peak RSS 6.09 GiB**
|
||||
(finalize ≈4 s + hoist+asyncify+`-O1` ≈58 s at `BINARYEN_CORES=8`).
|
||||
Historical logs show 59–154 s and one OOM-killed build (exit 137).
|
||||
- JSPI: **1.6 s wall, peak RSS 49 MB** (node env-shim patch).
|
||||
|
||||
## 3. Bundle size
|
||||
|
||||
Same-day builds, DEBUG mode, complete cold-load set
|
||||
(`kicad_editor.{wasm,js}`, `wx.js`, `wx-dom.js`, `images.tar.gz`):
|
||||
|
||||
| | raw | gzip −9 | brotli |
|
||||
|---|---|---|---|
|
||||
| Asyncify wasm | 118 557 371 B (113.1 MB) | 36.7 MB | 24.5 MB |
|
||||
| JSPI wasm | 98 664 038 B (94.1 MB) | 18.6 MB | 13.5 MB |
|
||||
| Asyncify total set | 118.8 MB | 42.0 MB | 29.5 MB |
|
||||
| JSPI total set | 99.8 MB | 23.8 MB | 18.5 MB |
|
||||
|
||||
The compressed delta (−49 % gzip) is much larger than the raw delta (−17 %):
|
||||
asyncify's spilled-locals/branch-table instrumentation is high-entropy. The
|
||||
over-the-wire cost of a cold editor load roughly **halves** under JSPI.
|
||||
Side note: separate DWARF is 2.27 GB vs 1.91 GB (−16 %); dev-tools-only fetch.
|
||||
|
||||
Other apps (existing artifacts, not rebuilt today): pl_editor −19 %,
|
||||
gerbview −19 %, calculator −26 %, occ_service −1 % (never asyncified),
|
||||
ngspice_service 0 %.
|
||||
|
||||
## 4. Runtime
|
||||
|
||||
One harness for both arms: the jspi tree's Playwright 1.62.1 `perf` project
|
||||
(bundled Chromium, no JSPI-specific launch flags), `tests/kicad/
|
||||
pcbnew-large-perf.spec.ts`, artifact sets swapped in `tests/apps/kicad/` with
|
||||
sha256 recorded per row (jspi `6f03e62d…`, asyncify `6dab4931…`). The harness
|
||||
page seeds KiCad config for both settings versions (9.99 + 10.0) so the
|
||||
asyncify binary boots wizard-free. Local static server serves wasm gzipped
|
||||
(hence `transferSize` ≈ the gzip column above). Headless; per doc-12, headless
|
||||
FPS is a comparative indicator, not an absolute.
|
||||
|
||||
**Cold load** (fresh context ×5, navigation → fully-ready editor):
|
||||
|
||||
| | Asyncify | JSPI |
|
||||
|---|---|---|
|
||||
| loadMs median (range) | 2 576 (2 521–2 629) | 1 538 (1 117–1 841) |
|
||||
| wasm fetch (gzipped wire) | ~990 ms / 32.1 MB | ~570 ms / 17.1 MB |
|
||||
| wasm heap at boot | 556.8 MB | 386.7 MB |
|
||||
|
||||
CDP-attach sanity: loadMs with a CDP session pre-attached fell inside each
|
||||
arm's normal range (2 514 / 1 117 ms) — no tier-down artifact from the
|
||||
throttling channel.
|
||||
|
||||
**Board open** (`Module.kicadOpenFile`, ×3 each):
|
||||
|
||||
| Board | Asyncify | JSPI |
|
||||
|---|---|---|
|
||||
| demo (155 KB, 15 fp) | 467 ms | 358–698 ms (par — too small to discriminate) |
|
||||
| vme-wren (27.7 MB, 1 508 fp, 24 858 seg) | **6 465 ms** median, peak heap 962–1 183 MB | **3 551 ms** median, peak heap 802 MB |
|
||||
| jetson-agx-thor (80.9 MB, 1 125 fp) | loaded, **14 584 ms**, peak 1.90 GB | loaded, **8 620 ms**, peak 1.73 GB |
|
||||
|
||||
Neither arm OOMs even on the 80.9 MB board — both stay well under the 4 GB cap.
|
||||
|
||||
**Interaction FPS** on vme-wren (Lissajous pan + wheel zoom, 6 s × 2 reps;
|
||||
`rafFps` = main-thread rAF; `distinctFps` = distinct GAL glcanvas frames at a
|
||||
~30 Hz pixel-hash sampler — the honest "real redraws" number, since rAF keeps
|
||||
vsync-ticking when the GAL skips):
|
||||
|
||||
| Throttle | Asyncify raf / distinct | JSPI raf / distinct |
|
||||
|---|---|---|
|
||||
| 1× | 44.5–49.1 / **7.8** | 51.9–55.7 / **9.2–9.6** |
|
||||
| 4× | 32.4–37.6 / **3.0–3.1** | 39.2–41.4 / **5.1–5.2** |
|
||||
| 6× | 34.3–39.9 / **2.8–4.1** | 34.3–41.8 / **3.3–5.3** |
|
||||
|
||||
The distinct-frame gap grows from +21 % at 1× to +68 % at 4× — the same
|
||||
"advantage widens under throttle" signature doc-12 used to prove lower
|
||||
CPU-per-operation (as opposed to just a smaller module).
|
||||
|
||||
**Memory checkpoints** (wasm linear memory; Chromium `usedJSHeapSize` tracked
|
||||
alongside, differences <10 %): boot 557 vs 387 MB; after vme-wren open 962 vs
|
||||
802 MB; unchanged after the FPS sweep on both arms.
|
||||
|
||||
## 5. Methodology notes & gotchas
|
||||
|
||||
- Asyncify arm reused the warm `kicad-wasm-main` compose volume (62 GB); its
|
||||
branch-default `kicad-wasm-staging` volume is a cold stub — running without
|
||||
`COMPOSE_PROJECT_NAME=kicad-wasm-main` would have benchmarked a multi-hour
|
||||
cold dep build. The other session's tree was verified idle before/after and
|
||||
`git status` byte-identical.
|
||||
- Container `memory.peak` read from a per-run fresh cgroup (`compose stop`
|
||||
between runs, `KICAD_KEEP_CONTAINER=1` so the read happens before teardown),
|
||||
plus a 5 s `docker stats` sampler (CSV in bench-data).
|
||||
- The first S3 attempt died in wx's PCRE `aclocal` regen (manual `compose
|
||||
exec` skips build.sh's rsync, which perturbs the wx reconfigure check); fixed
|
||||
by pre-touching the wx build Makefile — which on arm A then triggered the wx
|
||||
rebuild noted in §1. Symmetric procedure both arms.
|
||||
- The jspi-arm FPS rows in the archived ndjson appear twice: the first pass
|
||||
sampled the static `#canvas` (distinct ≈ 0, marked SUPERSEDED); the glcanvas
|
||||
re-run is authoritative and matches what `perf-utils.measureFpsDetailed` now
|
||||
does. Arm A ran entirely with the fixed sampler.
|
||||
- Playwright clears `tests/test-results/` per invocation — it ate the arm B
|
||||
ndjson during the arm A run (reconstructed from the run logs, two timestamps
|
||||
approximate). The spec now writes to `tests/bench-results/` instead.
|
||||
- The live dev app at :3048 was kept on the JSPI build throughout (its
|
||||
`public/wasm` symlink pointed at a stash during the swap window) and
|
||||
verified serving the JSPI wasm afterwards.
|
||||
|
||||
## 6. Reproduce
|
||||
|
||||
```bash
|
||||
# build side (each arm, serialized; see §1 for scenario commands)
|
||||
KICAD_NO_MONITOR=1 KICAD_KEEP_CONTAINER=1 ./docker/build.sh kicad_editor -j 10
|
||||
|
||||
# runtime side (from tests/, artifacts staged in tests/apps/kicad/)
|
||||
cp kicad/qa/data/pcbnew/vme-wren.kicad_pcb tests/apps/kicad/board/
|
||||
cp kicad/demos/jetson-agx-thor-baseboard/jetson-agx-thor-baseboard.kicad_pcb tests/apps/kicad/board/
|
||||
BENCH_ARM=<arm> PERF_LARGE=1 npx playwright test --project=perf pcbnew-large-perf.spec.ts --workers=1
|
||||
# → tests/bench-results/perf-bench-<arm>.ndjson
|
||||
```
|
||||
|
|
@ -130,23 +130,28 @@
|
|||
|
||||
// Seed a minimal default config before main() so STARTWIZARD finds
|
||||
// NeedsUserInput()==false and the first-run setup wizard never opens —
|
||||
// same as eeschema.html / pl_editor.html.
|
||||
// same as eeschema.html / pl_editor.html. Seeded for BOTH the current
|
||||
// (10.0) and previous (9.99) settings versions: the perf-bench flow
|
||||
// (pcbnew-large-perf.spec.ts) swaps in editor builds from other branches
|
||||
// whose settings version differs, and an unseeded dir would send that
|
||||
// binary into the wizard and skew every load-time number.
|
||||
var seedKicadConfig = function() {
|
||||
var cfgDir = '/home/kicad/.config/kicad/kicad/10.0';
|
||||
FS.mkdirTree(cfgDir);
|
||||
|
||||
var writeIfAbsent = function(path, contents) {
|
||||
try { FS.stat(path); return; } catch (e) { /* absent — seed it */ }
|
||||
FS.writeFile(path, contents);
|
||||
console.log('[KICAD] Seeded ' + path);
|
||||
};
|
||||
|
||||
['9.99', '10.0'].forEach(function(ver) {
|
||||
var cfgDir = '/home/kicad/.config/kicad/kicad/' + ver;
|
||||
FS.mkdirTree(cfgDir);
|
||||
writeIfAbsent(cfgDir + '/kicad_common.json', JSON.stringify({
|
||||
do_not_show_again: { update_check_prompt: true, data_collection_prompt: true }
|
||||
}, null, 2));
|
||||
writeIfAbsent(cfgDir + '/sym-lib-table', '(sym_lib_table\n (version 7)\n)\n');
|
||||
writeIfAbsent(cfgDir + '/fp-lib-table', '(fp_lib_table\n (version 7)\n)\n');
|
||||
writeIfAbsent(cfgDir + '/design-block-lib-table', '(design_block_lib_table\n (version 7)\n)\n');
|
||||
});
|
||||
};
|
||||
|
||||
var Module = {
|
||||
|
|
|
|||
180
tests/kicad/pcbnew-large-perf.spec.ts
Normal file
180
tests/kicad/pcbnew-large-perf.spec.ts
Normal file
|
|
@ -0,0 +1,180 @@
|
|||
import { test, expect } from './fixtures';
|
||||
import * as fs from 'fs';
|
||||
import * as path from 'path';
|
||||
import * as crypto from 'crypto';
|
||||
import {
|
||||
measureLoad,
|
||||
measureOpenRender,
|
||||
openAndWait,
|
||||
measureFpsDetailed,
|
||||
setThrottle,
|
||||
sampleMemory,
|
||||
startHeapPeakSampler,
|
||||
stopHeapPeakSampler,
|
||||
getWasmResourceTiming,
|
||||
} from './utils/perf-utils';
|
||||
import { fetchIntoMemfs } from './utils/fs-inject';
|
||||
import { waitForBoardLoaded } from './utils/board-ready';
|
||||
|
||||
/**
|
||||
* Large-board perf battery (TRACK-ONLY, bench-driven). Extends pcbnew-perf with
|
||||
* the measurements the JSPI-vs-asyncify comparison needs: repeated cold loads,
|
||||
* open+render of a REAL large board (vme-wren: 1508 footprints / 24 858
|
||||
* segments), rAF + distinct-frame FPS under CPU throttle, and wasm-heap /
|
||||
* JS-heap checkpoints. Results append to
|
||||
* tests/test-results/perf-bench-<arm>.ndjson (gitignored), one JSON row per
|
||||
* measurement, each row carrying the sha256 of the wasm actually measured so
|
||||
* A/B artifact swaps can't get misattributed.
|
||||
*
|
||||
* Gated behind PERF_LARGE=1 so the CI perf project (which matches
|
||||
* *-perf.spec.ts) is unaffected. Fixtures are expected in
|
||||
* tests/apps/kicad/board/ (gitignored) — see docs/features/async/
|
||||
* migration-evidence/jspi-vs-asyncify-bench-2026-08.md for the bench flow.
|
||||
*/
|
||||
|
||||
const ARM = process.env.BENCH_ARM || 'current';
|
||||
const LOAD_RUNS = parseInt(process.env.PERF_LOAD_RUNS || '5', 10);
|
||||
const OPEN_RUNS = parseInt(process.env.PERF_OPEN_RUNS || '3', 10);
|
||||
const THROTTLES = (process.env.PERF_THROTTLES || '1,4,6').split(',').map(Number);
|
||||
const FPS_SECS = parseInt(process.env.PERF_FPS_SECS || '6', 10);
|
||||
const FPS_REPS = parseInt(process.env.PERF_FPS_REPS || '2', 10);
|
||||
|
||||
const APPS_KICAD = path.join(__dirname, '..', 'apps', 'kicad');
|
||||
const DEMO = path.join(__dirname, '..', 'fixtures', 'demo', 'demo.kicad_pcb');
|
||||
const VME_URL = '/kicad/board/vme-wren.kicad_pcb';
|
||||
const JETSON_URL = '/kicad/board/jetson-agx-thor-baseboard.kicad_pcb';
|
||||
// NOT under test-results/ — Playwright clears that whole dir at session start,
|
||||
// so an A/B pair of invocations would each wipe the other arm's rows.
|
||||
const RESULTS = path.join(__dirname, '..', 'bench-results', `perf-bench-${ARM}.ndjson`);
|
||||
|
||||
let wasmSha = '';
|
||||
function wasmSha256(): string {
|
||||
if (!wasmSha) {
|
||||
const bytes = fs.readFileSync(path.join(APPS_KICAD, 'kicad_editor.wasm'));
|
||||
wasmSha = crypto.createHash('sha256').update(bytes).digest('hex').slice(0, 16);
|
||||
}
|
||||
return wasmSha;
|
||||
}
|
||||
|
||||
function record(section: string, data: Record<string, unknown>): void {
|
||||
fs.mkdirSync(path.dirname(RESULTS), { recursive: true });
|
||||
const row = { arm: ARM, sha256: wasmSha256(), when: new Date().toISOString(), section, ...data };
|
||||
fs.appendFileSync(RESULTS, JSON.stringify(row) + '\n');
|
||||
// eslint-disable-next-line no-console
|
||||
console.log(`[bench] ${section}: ${JSON.stringify(data)}`);
|
||||
}
|
||||
|
||||
test.describe('pcbnew large-board bench', () => {
|
||||
test.skip(!process.env.PERF_LARGE, 'bench battery — run with PERF_LARGE=1');
|
||||
|
||||
for (let run = 0; run < LOAD_RUNS; run++) {
|
||||
test(`cold load #${run + 1}`, async ({ page }) => {
|
||||
test.setTimeout(300000);
|
||||
const loadMs = await measureLoad(page, '/kicad/pcbnew.html');
|
||||
const wasmFetch = await getWasmResourceTiming(page);
|
||||
const mem = await sampleMemory(page);
|
||||
record('load', { run: run + 1, loadMs, wasmFetch, bootMem: mem });
|
||||
expect(loadMs).toBeGreaterThan(0);
|
||||
});
|
||||
}
|
||||
|
||||
test('cold load with CDP pre-attached (tier-down sanity)', async ({ page }) => {
|
||||
test.setTimeout(300000);
|
||||
const cdp = await page.context().newCDPSession(page);
|
||||
await setThrottle(cdp, 1); // attach + a no-op emulation command, like the FPS path
|
||||
const loadMs = await measureLoad(page, '/kicad/pcbnew.html');
|
||||
record('load-cdp-sanity', { loadMs });
|
||||
expect(loadMs).toBeGreaterThan(0);
|
||||
});
|
||||
|
||||
for (let run = 0; run < OPEN_RUNS; run++) {
|
||||
test(`open demo board #${run + 1}`, async ({ page, testLogger }) => {
|
||||
test.setTimeout(300000);
|
||||
await measureLoad(page, '/kicad/pcbnew.html');
|
||||
const openMs = await measureOpenRender(page, DEMO, 'board', testLogger);
|
||||
const mem = await sampleMemory(page);
|
||||
record('open-demo', { run: run + 1, openMs, postOpenMem: mem });
|
||||
expect(openMs).toBeGreaterThan(0);
|
||||
});
|
||||
}
|
||||
|
||||
for (let run = 0; run < OPEN_RUNS; run++) {
|
||||
test(`open vme-wren (27.7 MB) #${run + 1}`, async ({ page, testLogger }) => {
|
||||
test.setTimeout(600000);
|
||||
await measureLoad(page, '/kicad/pcbnew.html');
|
||||
const bytes = await fetchIntoMemfs(page, VME_URL, '/home/kicad/documents/vme-wren.kicad_pcb');
|
||||
await startHeapPeakSampler(page);
|
||||
const openMs = await openAndWait(
|
||||
page,
|
||||
'/home/kicad/documents/vme-wren.kicad_pcb',
|
||||
'board',
|
||||
testLogger,
|
||||
480000,
|
||||
);
|
||||
const peak = await stopHeapPeakSampler(page);
|
||||
const mem = await sampleMemory(page);
|
||||
record('open-vme', { run: run + 1, bytes, openMs, openPeakHeap: peak, postOpenMem: mem });
|
||||
expect(openMs).toBeGreaterThan(0);
|
||||
});
|
||||
}
|
||||
|
||||
test('FPS on vme-wren across throttles', async ({ page, testLogger }) => {
|
||||
test.setTimeout(900000);
|
||||
await measureLoad(page, '/kicad/pcbnew.html');
|
||||
await fetchIntoMemfs(page, VME_URL, '/home/kicad/documents/vme-wren.kicad_pcb');
|
||||
await openAndWait(page, '/home/kicad/documents/vme-wren.kicad_pcb', 'board', testLogger, 480000);
|
||||
await page.keyboard.press('Escape').catch(() => {}); // eslint-disable-line -- best-effort Escape
|
||||
|
||||
const cdp = await page.context().newCDPSession(page);
|
||||
for (const rate of THROTTLES) {
|
||||
await setThrottle(cdp, rate);
|
||||
for (let rep = 0; rep < FPS_REPS; rep++) {
|
||||
const f = await measureFpsDetailed(page, FPS_SECS);
|
||||
record('fps-vme', { throttle: rate, rep: rep + 1, ...f });
|
||||
expect(f.rafFps).toBeGreaterThan(0);
|
||||
}
|
||||
}
|
||||
await setThrottle(cdp, 1);
|
||||
const mem = await sampleMemory(page);
|
||||
record('fps-vme-postmem', { postFpsMem: mem });
|
||||
});
|
||||
|
||||
test('open jetson-agx-thor (80.9 MB) — outcome, OOM allowed', async ({ page, testLogger }) => {
|
||||
test.setTimeout(900000);
|
||||
await measureLoad(page, '/kicad/pcbnew.html');
|
||||
const bytes = await fetchIntoMemfs(
|
||||
page,
|
||||
JETSON_URL,
|
||||
'/home/kicad/documents/jetson-agx-thor-baseboard.kicad_pcb',
|
||||
);
|
||||
await startHeapPeakSampler(page);
|
||||
const t0 = Date.now();
|
||||
try {
|
||||
await page.evaluate(() => {
|
||||
(window as unknown as { Module: { kicadOpenFile(p: string): unknown } }).Module.kicadOpenFile(
|
||||
'/home/kicad/documents/jetson-agx-thor-baseboard.kicad_pcb',
|
||||
);
|
||||
});
|
||||
await waitForBoardLoaded(page, testLogger, 780000);
|
||||
const peak = await stopHeapPeakSampler(page);
|
||||
const mem = await sampleMemory(page);
|
||||
record('open-jetson', {
|
||||
bytes,
|
||||
outcome: 'loaded',
|
||||
openMs: Date.now() - t0,
|
||||
openPeakHeap: peak,
|
||||
postOpenMem: mem,
|
||||
});
|
||||
} catch (e) {
|
||||
// A 4 GB-cap OOM / abort is a RESULT for this stress tier, not a harness error.
|
||||
const peak = await stopHeapPeakSampler(page).catch(() => -1);
|
||||
record('open-jetson', {
|
||||
bytes,
|
||||
outcome: 'failed',
|
||||
afterMs: Date.now() - t0,
|
||||
openPeakHeap: peak,
|
||||
error: String(e).slice(0, 300),
|
||||
});
|
||||
}
|
||||
});
|
||||
});
|
||||
|
|
@ -42,6 +42,36 @@ export async function injectFileIntoMemfs(
|
|||
);
|
||||
}
|
||||
|
||||
/**
|
||||
* Fetch a same-origin URL inside the page and write it into MEMFS.
|
||||
*
|
||||
* For large fixtures (tens of MB) the base64 round-trip through Playwright's
|
||||
* JSON channel in injectFileIntoMemfs is the bottleneck — an in-page fetch
|
||||
* from the static server (tests/apps is the serve root) keeps the bytes in
|
||||
* the browser. Returns the byte count written.
|
||||
*/
|
||||
export async function fetchIntoMemfs(
|
||||
page: Page,
|
||||
url: string, // e.g. "/kicad/board/vme-wren.kicad_pcb"
|
||||
memfsPath: string,
|
||||
): Promise<number> {
|
||||
const memfsDir = memfsPath.replace(/\/[^/]+$/, '') || '/';
|
||||
return await page.evaluate(
|
||||
async ({ url, memfsDir, memfsPath }) => {
|
||||
const res = await fetch(url);
|
||||
if (!res.ok) throw new Error(`fetchIntoMemfs: ${url} -> HTTP ${res.status}`);
|
||||
const data = new Uint8Array(await res.arrayBuffer());
|
||||
// @ts-expect-error — Emscripten FS lives on window via Module
|
||||
const FS = (window as any).FS;
|
||||
FS.mkdirTree(memfsDir);
|
||||
FS.writeFile(memfsPath, data);
|
||||
console.log(`[KICAD] Fetched ${url} -> ${memfsPath} (${data.length} bytes)`);
|
||||
return data.length;
|
||||
},
|
||||
{ url, memfsDir, memfsPath },
|
||||
);
|
||||
}
|
||||
|
||||
/**
|
||||
* Convenience: read a file from the kicad/ submodule and inject it.
|
||||
*/
|
||||
|
|
|
|||
|
|
@ -64,7 +64,22 @@ export async function measureOpenRender(
|
|||
const ext = kind === 'board' ? 'kicad_pcb' : 'kicad_sch';
|
||||
const memfsPath = `/home/kicad/documents/perf-demo.${ext}`;
|
||||
await injectFileIntoMemfs(page, hostPath, memfsPath);
|
||||
return openAndWait(page, memfsPath, kind, logger, timeout);
|
||||
}
|
||||
|
||||
/**
|
||||
* Open an ALREADY-INJECTED memfs document and wait until loaded+rendered.
|
||||
* Split out of measureOpenRender so large fixtures can arrive via
|
||||
* fetchIntoMemfs (or any other route) and still get the same timed open.
|
||||
*/
|
||||
export async function openAndWait(
|
||||
page: Page,
|
||||
memfsPath: string,
|
||||
kind: 'schematic' | 'board',
|
||||
logger: { consoleLogs: string[]; errors: string[] },
|
||||
timeout = 120000,
|
||||
): Promise<number> {
|
||||
const stem = memfsPath.replace(/^.*\//, '').replace(/\.[^.]+$/, '');
|
||||
const t0 = Date.now();
|
||||
await page.evaluate((p) => {
|
||||
(window as unknown as { Module: KicadModule }).Module.kicadOpenFile(p);
|
||||
|
|
@ -75,13 +90,77 @@ export async function measureOpenRender(
|
|||
} else {
|
||||
const deadline = Date.now() + timeout;
|
||||
while (Date.now() < deadline) {
|
||||
if (/perf-demo/i.test(await page.title())) break;
|
||||
if (new RegExp(stem, 'i').test(await page.title())) break;
|
||||
await page.waitForTimeout(200);
|
||||
}
|
||||
}
|
||||
return Date.now() - t0;
|
||||
}
|
||||
|
||||
export interface MemorySample {
|
||||
/** WebAssembly linear memory size (Module.HEAPU8.byteLength). */
|
||||
wasmHeapBytes: number;
|
||||
/** Chromium-only usedJSHeapSize; 0 elsewhere. */
|
||||
jsHeapBytes: number;
|
||||
}
|
||||
|
||||
/** One-shot memory census — portable across builds (HEAPU8 verified reachable in both). */
|
||||
export async function sampleMemory(page: Page): Promise<MemorySample> {
|
||||
return await page.evaluate(() => {
|
||||
const w = window as unknown as {
|
||||
Module?: { HEAPU8?: { byteLength: number }; wasmMemory?: { buffer: ArrayBuffer } };
|
||||
};
|
||||
const perf = performance as unknown as { memory?: { usedJSHeapSize: number } };
|
||||
return {
|
||||
wasmHeapBytes:
|
||||
w.Module?.wasmMemory?.buffer?.byteLength ?? w.Module?.HEAPU8?.byteLength ?? 0,
|
||||
jsHeapBytes: perf.memory?.usedJSHeapSize ?? 0,
|
||||
};
|
||||
});
|
||||
}
|
||||
|
||||
/**
|
||||
* In-page wasm-heap peak sampler (250 ms). Start before a heavy operation
|
||||
* (board open), stop after — returns the max linear-memory size observed.
|
||||
*/
|
||||
export async function startHeapPeakSampler(page: Page): Promise<void> {
|
||||
await page.evaluate(() => {
|
||||
const w = window as unknown as {
|
||||
Module?: { HEAPU8?: { byteLength: number }; wasmMemory?: { buffer: ArrayBuffer } };
|
||||
__heapPeak?: number;
|
||||
__heapPeakTimer?: number;
|
||||
};
|
||||
if (w.__heapPeakTimer !== undefined) clearInterval(w.__heapPeakTimer);
|
||||
w.__heapPeak = 0;
|
||||
w.__heapPeakTimer = setInterval(() => {
|
||||
const b =
|
||||
w.Module?.wasmMemory?.buffer?.byteLength ?? w.Module?.HEAPU8?.byteLength ?? 0;
|
||||
if (b > (w.__heapPeak ?? 0)) w.__heapPeak = b;
|
||||
}, 250) as unknown as number;
|
||||
});
|
||||
}
|
||||
|
||||
export async function stopHeapPeakSampler(page: Page): Promise<number> {
|
||||
return await page.evaluate(() => {
|
||||
const w = window as unknown as { __heapPeak?: number; __heapPeakTimer?: number };
|
||||
if (w.__heapPeakTimer !== undefined) clearInterval(w.__heapPeakTimer);
|
||||
w.__heapPeakTimer = undefined;
|
||||
return w.__heapPeak ?? 0;
|
||||
});
|
||||
}
|
||||
|
||||
/** Resource-timing attribution for the main wasm fetch (download share of loadMs). */
|
||||
export async function getWasmResourceTiming(
|
||||
page: Page,
|
||||
): Promise<{ durationMs: number; transferSize: number } | null> {
|
||||
return await page.evaluate(() => {
|
||||
const e = performance
|
||||
.getEntriesByType('resource')
|
||||
.find((r) => r.name.includes('kicad_editor.wasm')) as PerformanceResourceTiming | undefined;
|
||||
return e ? { durationMs: Math.round(e.duration), transferSize: e.transferSize } : null;
|
||||
});
|
||||
}
|
||||
|
||||
/** CDP CPU throttling (Chromium only): 1 = none, N = N× slower. */
|
||||
export async function setThrottle(cdp: CDPSession, rate: number): Promise<void> {
|
||||
await cdp.send('Emulation.setCPUThrottlingRate', { rate });
|
||||
|
|
@ -127,6 +206,79 @@ export async function measureFps(page: Page, seconds: number): Promise<number> {
|
|||
return +(frames / (elapsed / 1000)).toFixed(1);
|
||||
}
|
||||
|
||||
/**
|
||||
* measureFps plus a DISTINCT-frame counter: rAF keeps ticking at vsync even
|
||||
* when the GAL skips redraws (draw_panel_gal enforces a min redraw period and
|
||||
* re-arms a timer when it can't keep up), so under load the rAF number can
|
||||
* decouple from real render throughput. Alongside the rAF loop this samples
|
||||
* the largest visible canvas at ~30 Hz (48×48 downscale hash — the
|
||||
* waitForCanvasStable technique; GAL sets preserveDrawingBuffer) and counts
|
||||
* samples whose content changed. distinctFps is capped by the ~30 Hz sample
|
||||
* rate; read it as "real redraws per second, up to 30".
|
||||
*/
|
||||
export async function measureFpsDetailed(
|
||||
page: Page,
|
||||
seconds: number,
|
||||
): Promise<{ rafFps: number; distinctFps: number }> {
|
||||
await page.evaluate(() => {
|
||||
const w = window as unknown as {
|
||||
__dfPrev?: string;
|
||||
__dfCount?: number;
|
||||
__dfSamples?: number;
|
||||
__dfTimer?: number;
|
||||
};
|
||||
if (w.__dfTimer !== undefined) clearInterval(w.__dfTimer);
|
||||
w.__dfPrev = undefined;
|
||||
w.__dfCount = 0;
|
||||
w.__dfSamples = 0;
|
||||
const scratch = document.createElement('canvas');
|
||||
scratch.width = 48;
|
||||
scratch.height = 48;
|
||||
const ctx = scratch.getContext('2d', { willReadFrequently: true })!;
|
||||
w.__dfTimer = setInterval(() => {
|
||||
const canvases = Array.from(document.querySelectorAll('canvas')).filter((c) => {
|
||||
const r = c.getBoundingClientRect();
|
||||
return r.width > 0 && r.height > 0 && c !== scratch;
|
||||
});
|
||||
if (!canvases.length) return;
|
||||
// The GAL draws into a wxGLCanvas (id glcanvas-*), NOT the
|
||||
// full-window emscripten #canvas — sample the GL surface where the
|
||||
// board pixels actually change, falling back to the largest canvas.
|
||||
const gl = canvases.filter((c) => /^glcanvas/.test(c.id));
|
||||
const pool = gl.length ? gl : canvases;
|
||||
const src = pool.reduce((a, b) => {
|
||||
const ra = a.getBoundingClientRect();
|
||||
const rb = b.getBoundingClientRect();
|
||||
return ra.width * ra.height >= rb.width * rb.height ? a : b;
|
||||
});
|
||||
try {
|
||||
ctx.drawImage(src, 0, 0, 48, 48);
|
||||
const d = ctx.getImageData(0, 0, 48, 48).data;
|
||||
let h = 0;
|
||||
for (let i = 0; i < d.length; i += 16) h = ((h << 5) - h + d[i]) | 0;
|
||||
const hs = String(h);
|
||||
w.__dfSamples = (w.__dfSamples ?? 0) + 1;
|
||||
if (w.__dfPrev !== undefined && hs !== w.__dfPrev) w.__dfCount = (w.__dfCount ?? 0) + 1;
|
||||
w.__dfPrev = hs;
|
||||
} catch {
|
||||
/* tainted/zero-size canvas — skip the sample */
|
||||
}
|
||||
}, 33) as unknown as number;
|
||||
});
|
||||
|
||||
const t0 = Date.now();
|
||||
const rafFps = await measureFps(page, seconds);
|
||||
const elapsed = (Date.now() - t0) / 1000;
|
||||
|
||||
const distinct = await page.evaluate(() => {
|
||||
const w = window as unknown as { __dfCount?: number; __dfTimer?: number };
|
||||
if (w.__dfTimer !== undefined) clearInterval(w.__dfTimer);
|
||||
w.__dfTimer = undefined;
|
||||
return w.__dfCount ?? 0;
|
||||
});
|
||||
return { rafFps, distinctFps: +(distinct / elapsed).toFixed(1) };
|
||||
}
|
||||
|
||||
/** Write per-app results to tests/test-results/perf-<app>.json (gitignored, CI-uploaded). */
|
||||
export function recordPerf(app: string, data: Record<string, unknown>): void {
|
||||
fs.mkdirSync(RESULTS_DIR, { recursive: true });
|
||||
|
|
|
|||
Loading…
Reference in a new issue