emcc only runs Binaryen at link -O2+ (link.py: should_run_binaryen_optimizer returns OPT_LEVEL >= 2) and we link at -O1, so the shipped module had never seen wasm-opt at all — it kept its entire 19.56 MB name section, ~20% of the editor (-sJSPI sets ASYNCIFY=2, which suppresses wasm-ld's --strip-debug, leaving wasm-opt as the only thing that would drop it). Step 8.2 runs it post-link and in-container, so CI's cached compile phase covers it and the host post-process stays pure-host. Default -O2, picked by measuring every level on the same module: -O0 already captures 27% of the raw win (it is mostly the name section), -O2 costs 23 s and gives the best frame rate, and -O3/-O4/-Os/-Oz cost 48-132 s for at most 1.5% more brotli — -O4 is not even smaller than -O3. Targets that already link -O2/-Oz (occ_service, kicad_tools) are skipped by testing for the target_features section, which emcc strips whenever it ran the optimizer itself, so there is no hard-coded target list to drift. Feature flags come from the module's own target_features section and so cannot diverge from the link. The perf specs reported requestAnimationFrame ticks as "FPS". That is not a frame rate: rAF fires on the compositor's schedule whether or not the GAL redrew, and it read 120/s on a board where the renderer completed zero frames in six seconds. measureInteractionFps now counts completed GAL frames — runs of draws to the default framebuffer, exactly one per frame in every AA mode — and drives a pure middle-drag pan after a zoom-to-fit. Mixing wheel zoom into the drive made the result depend on where the wheel left the view: +-20% across identical repeats, against +-2% for pan alone. The report gains a GAL fps column with a regression flag on the 1x number; rAF is kept so historical runs stay comparable. CI has no GPU, so its number is a software-rasteriser redraw rate — a regression signal, not a user-facing frame rate. Method and measurements in the bench report. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_016X9eh1s5sTx1o9Em9KBuwR
193 lines
8.7 KiB
TypeScript
193 lines
8.7 KiB
TypeScript
/**
|
||
* Renders the track-only runtime-perf block for the CI-on-main Discord comment.
|
||
*
|
||
* The perf e2e (tests/kicad/{eeschema,pcbnew}-perf.spec.ts) already writes
|
||
* test-results/perf-{app}.json — schema { app, when, loadMs, openMs, fps:[{throttle,fps,galFps}] }.
|
||
* We read those, fetch the PREVIOUS successful main run's perf via `gh run
|
||
* download` (so we can show a Δ without committing a baseline — stays
|
||
* no-write-back), and format an aligned monospace table (Discord doesn't render
|
||
* markdown tables, so it goes in a ``` code block).
|
||
*
|
||
* Track-only: nothing here gates the build. A regression past REGRESSION_PCT on
|
||
* the stable metrics (loadMs/openMs) is only flagged (a `*`), never failed. Both
|
||
* FPS columns are measured on CI's software rasteriser (ANGLE over Mesa llvmpipe,
|
||
* under Xvfb — there is no GPU on the runner), so they are a regression signal
|
||
* only and never a user-facing frame rate.
|
||
*
|
||
* CLI (from tests/):
|
||
* tsx tools/screenshots/perf-report.ts [--results DIR] [--prev DIR] [--repo owner/repo]
|
||
*/
|
||
import * as fs from 'fs';
|
||
import * as os from 'os';
|
||
import * as path from 'path';
|
||
import { execFileSync } from 'child_process';
|
||
import { RESULTS_DIR } from './config';
|
||
|
||
export const PERF_APPS = ['eeschema', 'pcbnew'] as const;
|
||
const REGRESSION_PCT = 10; // stable-metric regression past this is flagged with `*`
|
||
const CI_WORKFLOW = 'ci-ubicloud.yml';
|
||
|
||
/** `fps` is the legacy rAF tick count; `galFps` is the real frame rate. */
|
||
export type Fps = { throttle: number; fps: number; galFps?: number };
|
||
export type PerfData = { app: string; when?: string; loadMs: number; openMs: number; fps: Fps[] };
|
||
|
||
export function readPerf(dir: string): Map<string, PerfData> {
|
||
const out = new Map<string, PerfData>();
|
||
for (const app of PERF_APPS) {
|
||
const p = path.join(dir, `perf-${app}.json`);
|
||
if (!fs.existsSync(p)) continue;
|
||
try {
|
||
out.set(app, JSON.parse(fs.readFileSync(p, 'utf8')) as PerfData);
|
||
} catch (e) {
|
||
console.warn(`[perf] could not parse ${p}: ${(e as Error).message}`);
|
||
}
|
||
}
|
||
return out;
|
||
}
|
||
|
||
/**
|
||
* Best-effort fetch of the previous successful main CI run's perf JSONs into a
|
||
* temp dir. Returns the dir, or null if gh is unavailable / no prior run.
|
||
* `currentSha` is skipped so a re-run doesn't diff against itself.
|
||
*/
|
||
export function fetchPreviousPerf(repo: string | undefined, currentSha: string | undefined): string | null {
|
||
try {
|
||
const gh = (args: string[]) =>
|
||
execFileSync('gh', args, { encoding: 'utf8', stdio: ['ignore', 'pipe', 'ignore'] });
|
||
const repoArgs = repo ? ['--repo', repo] : [];
|
||
const runs = JSON.parse(
|
||
gh([
|
||
'run', 'list', '--workflow', CI_WORKFLOW, '--branch', 'main', '--status', 'success',
|
||
'--limit', '15', '--json', 'databaseId,headSha', ...repoArgs,
|
||
])
|
||
) as Array<{ databaseId: number; headSha: string }>;
|
||
const prev = runs.find((r) => r.headSha !== currentSha);
|
||
if (!prev) return null;
|
||
const tmp = fs.mkdtempSync(path.join(os.tmpdir(), 'perf-prev-'));
|
||
// Artifact is named ubicloud-e2e-<run_id>; -D extracts it under tmp/<artifact>/...
|
||
gh(['run', 'download', String(prev.databaseId), '-D', tmp, ...repoArgs]);
|
||
// Find the dir that actually holds the perf-*.json (artifact nests test-results/).
|
||
const hit = findPerfDir(tmp);
|
||
return hit;
|
||
} catch {
|
||
return null;
|
||
}
|
||
}
|
||
|
||
function findPerfDir(root: string): string | null {
|
||
const stack = [root];
|
||
while (stack.length) {
|
||
const dir = stack.pop()!;
|
||
let entries: fs.Dirent[];
|
||
try {
|
||
entries = fs.readdirSync(dir, { withFileTypes: true });
|
||
} catch {
|
||
continue;
|
||
}
|
||
if (entries.some((e) => e.isFile() && /^perf-\w+\.json$/.test(e.name))) return dir;
|
||
for (const e of entries) if (e.isDirectory()) stack.push(path.join(dir, e.name));
|
||
}
|
||
return null;
|
||
}
|
||
|
||
function pct(cur: number, prev: number): number {
|
||
return prev === 0 ? 0 : ((cur - prev) / prev) * 100;
|
||
}
|
||
|
||
/** Format a stable-metric value with a Δ vs previous (lower is better). */
|
||
function fmtMetric(cur: number, prev?: number): string {
|
||
if (prev === undefined) return `${cur}`;
|
||
const p = pct(cur, prev);
|
||
const arrow = p < 0 ? '▼' : p > 0 ? '▲' : '·';
|
||
const flag = p > REGRESSION_PCT ? '*' : ''; // regression (slower) beyond threshold
|
||
return `${cur} ${arrow}${Math.abs(p).toFixed(0)}%${flag}`;
|
||
}
|
||
|
||
/**
|
||
* GAL fps with a Δ vs the previous main run, flagged on REGRESSION.
|
||
*
|
||
* Higher is better here, so the sign convention is inverted relative to
|
||
* fmtMetric: a DROP past the threshold gets the `*`. Only the 1x-throttle
|
||
* number drives the flag — it is the one that repeats within ~2% (pan-only
|
||
* drive, zoom-to-fit before each measurement), so it is safe to act on.
|
||
* CI has no GPU, so this is a software-rasteriser redraw rate: useful precisely
|
||
* because it is consistent, not because it is the user-facing frame rate.
|
||
*/
|
||
function fmtGalFps(fps: Fps[], prev?: Fps[]): string {
|
||
const triple = fmtFps(fps, 'galFps');
|
||
const cur = fps.find((f) => f.throttle === 1)?.galFps;
|
||
const was = prev?.find((f) => f.throttle === 1)?.galFps;
|
||
if (cur === undefined || was === undefined || was === 0) return triple;
|
||
const p = pct(cur, was); // + = faster than before
|
||
const arrow = p > 0 ? '▲' : p < 0 ? '▼' : '·';
|
||
const flag = -p > REGRESSION_PCT ? '*' : '';
|
||
return `${triple} ${arrow}${Math.abs(p).toFixed(0)}%${flag}`;
|
||
}
|
||
|
||
function fmtFps(fps: Fps[], key: 'fps' | 'galFps' = 'fps'): string {
|
||
return [1, 4, 6].map((t) => {
|
||
const hit = fps.find((f) => f.throttle === t);
|
||
const v = hit?.[key];
|
||
return v === undefined ? '–' : Math.round(v);
|
||
}).join('/');
|
||
}
|
||
|
||
function pad(s: string, n: number): string {
|
||
return s.length >= n ? s : s + ' '.repeat(n - s.length);
|
||
}
|
||
|
||
export type PerfReport = { block: string; regressed: boolean };
|
||
|
||
/** Build the fenced code-block perf table for the Discord comment. */
|
||
export function buildPerfReport(opts: { resultsDir?: string; prevDir?: string | null } = {}): PerfReport {
|
||
const cur = readPerf(opts.resultsDir ?? RESULTS_DIR);
|
||
if (cur.size === 0) return { block: '', regressed: false };
|
||
const prev = opts.prevDir ? readPerf(opts.prevDir) : new Map<string, PerfData>();
|
||
|
||
const headers = ['app', 'loadMs (Δ)', 'openMs (Δ)', 'GAL fps 1/4/6 (Δ@1x)', 'rAF 1/4/6'];
|
||
const rows: string[][] = [];
|
||
let regressed = false;
|
||
for (const app of PERF_APPS) {
|
||
const c = cur.get(app);
|
||
if (!c) continue;
|
||
const p = prev.get(app);
|
||
const loadCell = fmtMetric(c.loadMs, p?.loadMs);
|
||
const openCell = fmtMetric(c.openMs, p?.openMs);
|
||
const galCell = fmtGalFps(c.fps, p?.fps);
|
||
if (loadCell.endsWith('*') || openCell.endsWith('*') || galCell.endsWith('*')) regressed = true;
|
||
rows.push([app, loadCell, openCell, galCell, fmtFps(c.fps, 'fps')]);
|
||
}
|
||
if (rows.length === 0) return { block: '', regressed: false };
|
||
|
||
const widths = headers.map((h, i) => Math.max(h.length, ...rows.map((r) => r[i].length)));
|
||
const line = (cells: string[]) => cells.map((c, i) => pad(c, widths[i])).join(' ');
|
||
const body = [line(headers), rows.map((r) => line(r)).join('\n')].join('\n');
|
||
const footnote = `${prev.size ? 'Δ vs previous main run. ' : 'no prior main run for Δ. '}` +
|
||
`* = >${REGRESSION_PCT}% slower (track-only, non-gating). ` +
|
||
`GAL fps = completed GAL frames on CI's software rasteriser (llvmpipe) — a regression signal, ` +
|
||
`NOT user-facing frame rate; its Δ/* are computed on the 1x number. rAF is the legacy tick count, ` +
|
||
`kept for continuity: it ticks on the compositor's schedule whether or not anything rendered, so ` +
|
||
`it can read 120 while the renderer is stalled.`;
|
||
return { block: '**Runtime perf** (eeschema + pcbnew)\n```\n' + body + '\n```\n' + footnote, regressed };
|
||
}
|
||
|
||
function parseArgs(argv: string[]): Record<string, string> {
|
||
const out: Record<string, string> = {};
|
||
for (let i = 0; i < argv.length; i++) {
|
||
const a = argv[i];
|
||
if (a === '--results') out.results = argv[++i];
|
||
else if (a === '--prev') out.prev = argv[++i];
|
||
else if (a === '--repo') out.repo = argv[++i];
|
||
}
|
||
return out;
|
||
}
|
||
|
||
function main(): void {
|
||
const args = parseArgs(process.argv.slice(2));
|
||
const prevDir = args.prev ?? fetchPreviousPerf(args.repo || process.env.GITHUB_REPOSITORY, process.env.GITHUB_SHA);
|
||
const { block, regressed } = buildPerfReport({ resultsDir: args.results, prevDir });
|
||
process.stdout.write((block || '(no perf-*.json found)') + '\n');
|
||
if (regressed) console.error('[perf] a stable metric regressed >10% vs previous main (track-only, not failing)');
|
||
}
|
||
|
||
if (require.main === module) main();
|