screentinker/server/test/image-ops.test.js
ScreenTinker 5171f09f96 Run image decoding on a worker thread
Fixes the blocker the previous commit shipped with. Pure-JS decoding costs ~1s of
solid CPU for a 12MP photo, and in-process that is not a slow upload but a stalled
event loop — no heartbeats, no socket traffic. thumbnail-backfill.js walks a whole
library at boot, so it reproduced #240 (blocked loop -> missed heartbeats -> panels
offline -> reconnect churn) from our own maintenance. sharp never did this because
libvips works on a threadpool.

image-ops.js is now a dispatcher over image-ops-worker.js; the work moved unchanged
to image-ops-core.js, so callers and their failure contract are untouched.

Measured on a 12MP photo: 1079ms wall with the loop stalled 1003ms, to 1881ms wall
for two ops with ZERO stalls and 185 timer ticks serviced. Wall time is worse and
that is fine — it is off the main thread now.

Design notes, all load-bearing:
  - ONE JOB AT A TIME. A decoded 12MP bitmap is ~48MB of RGBA; overlapping jobs
    multiply peak memory by queue depth, which is the wrong failure on the small
    targets this change exists to reach. Costs no throughput — the work is CPU-bound
    and one busy worker already saturates its core.
  - unref'd while idle, ref'd only in flight. Otherwise scripts/backfill-rotation-
    dims.js never exits and `node --test` hangs forever. Verified: a CLI-style run
    exits in 104ms, code 0.
  - decode failures reply as messages, so one bad upload cannot tear down the worker
    and take unrelated queued jobs with it.
  - in-process fallback if a thread cannot be had, warned rather than silent.

test/image-ops.test.js pins the loop-liveness property, which no functional test
would catch. Its thresholds were mutation-tested against the inline path: the first
version passed there too (4MP stalls only ~355ms, under a non-flaky threshold), so
the fixture is 12MP and the thresholds sit in the gap between the two behaviours —
worker ~90 ticks/~0ms, inline ~3 ticks/~897ms. It now fails inline, as a guard must.

1647/1647 pass. Ingest re-verified with node_modules/sharp moved aside.
2026-08-13 11:26:47 -05:00

91 lines
5.1 KiB
JavaScript

'use strict';
// Image decoding is pure JavaScript now (no native sharp), so its CPU cost lands on whichever
// thread runs it — ~1s of solid work for a 12MP photo. In-process that is a stalled event loop:
// no heartbeats, no socket traffic, panels marked offline, reconnect churn — #240 arriving from
// our own thumbnail backfill. lib/image-ops therefore hosts the work on a worker thread, and
// these bites pin the properties that makes it safe, none of which a functional test would catch.
const { test, after } = require('node:test');
const assert = require('node:assert/strict');
const fs = require('node:fs');
const os = require('node:os');
const path = require('node:path');
const sharp = require('sharp'); // devDependency: fixture generator only, never shipped
const imageOps = require('../lib/image-ops');
const tmp = fs.mkdtempSync(path.join(os.tmpdir(), 'image-ops-'));
after(async () => { await imageOps.shutdown(); fs.rmSync(tmp, { recursive: true, force: true }); });
// 12MP — a phone photo, and the size the thresholds below are calibrated against. Smaller is
// tempting for test speed but defeats the point: at 4MP the inline path stalls only ~350ms, which
// slips under any threshold loose enough not to be flaky, so the guard stops detecting the very
// regression it exists for. Measured: inline ~1000ms stall / ~2 timers serviced, worker ~0ms / ~90.
async function bigPhoto(name = 'big.jpg') {
const p = path.join(tmp, name);
if (!fs.existsSync(p)) {
// Random pixels, not a flat fill: a solid colour compresses to almost nothing and decodes far
// faster than any real photo, which would quietly defeat the timing assertion below.
const px = Buffer.allocUnsafe(4000 * 3000 * 3);
for (let i = 0; i < px.length; i++) px[i] = (i * 2654435761) & 0xff;
fs.writeFileSync(p, await sharp(px, { raw: { width: 4000, height: 3000, channels: 3 } }).jpeg().toBuffer());
}
return p;
}
test('image work does not stall the event loop (#240)', async () => {
const src = await bigPhoto();
let ticks = 0, worstGap = 0, last = Date.now();
const timer = setInterval(() => { ticks++; worstGap = Math.max(worstGap, Date.now() - last - 10); last = Date.now(); }, 10);
const started = Date.now();
await imageOps.writeThumbnail(src, path.join(tmp, 'thumb.jpg'), 320, 70);
const elapsed = Date.now() - started;
clearInterval(timer);
// The point is not that it was fast — it is that the loop kept running while it was slow.
// Thresholds sit in the gap between the two behaviours (worker ~90 ticks / ~0ms stall, inline
// ~2 ticks / ~1000ms stall), far enough from both to bite without being flaky.
assert.ok(ticks >= 20, `event loop serviced only ${ticks} timers in ${elapsed}ms — it is being blocked`);
assert.ok(worstGap < 200, `event loop stalled ${worstGap}ms in one go — image work is on the main thread`);
assert.ok(fs.existsSync(path.join(tmp, 'thumb.jpg')), 'thumbnail was still written');
});
test('an undecodable image rejects without killing the worker', async () => {
const bad = path.join(tmp, 'corrupt.jpg');
fs.writeFileSync(bad, Buffer.from('not an image'));
await assert.rejects(() => imageOps.metadata(bad), 'corrupt input must reject, so ingest records nulls');
// Crash isolation: one bad upload must not take out the queued work of unrelated callers.
const ok = path.join(tmp, 'fine.png');
fs.writeFileSync(ok, await sharp({ create: { width: 40, height: 25, channels: 3, background: '#123456' } }).png().toBuffer());
assert.deepEqual(await imageOps.metadata(ok), { width: 40, height: 25, orientation: 1 });
});
test('concurrent callers are serialized, and each still gets its own answer', async () => {
// Serialization bounds peak memory to ONE decoded bitmap (a 12MP photo is ~48MB of RGBA);
// overlapping jobs would multiply that by the queue depth on exactly the small targets this
// change exists to reach. Correctness under concurrency is what is asserted here.
const sizes = [[30, 10], [60, 20], [90, 30], [120, 40]];
const files = await Promise.all(sizes.map(async ([w, h], i) => {
const p = path.join(tmp, `c${i}.png`);
fs.writeFileSync(p, await sharp({ create: { width: w, height: h, channels: 3, background: '#0a0' } }).png().toBuffer());
return p;
}));
const got = await Promise.all(files.map(f => imageOps.metadata(f)));
assert.deepEqual(got.map(m => [m.width, m.height]), sizes, 'replies must not be crossed between queued jobs');
});
test('#170 EXIF orientation is applied by the decoder, so dimensions are as DISPLAYED', async () => {
// orientation 6 = "rotate 90° CW to display": a 30x100 stored buffer DISPLAYS as 100x30.
const p = path.join(tmp, 'rot6.jpg');
fs.writeFileSync(p, await sharp({ create: { width: 30, height: 100, channels: 3, background: '#00ff00' } })
.withMetadata({ orientation: 6 }).jpeg().toBuffer());
const meta = await imageOps.metadata(p);
assert.equal(meta.width, 100, 'EXIF-rotated image measures as displayed, not as stored');
assert.equal(meta.height, 30);
// Reported as 1 because the rotation is already applied — imageDisplayDims() must NOT swap again.
assert.equal(meta.orientation, 1, 'a tag of 6 here would double-rotate downstream');
});