mirror of
https://github.com/screentinker/screentinker.git
synced 2026-06-29 09:23:16 -06:00
ed3cf72b82
Continuously samples event-loop delay via perf_hooks.monitorEventLoopDelay() (C++-backed histogram; cheap). Each window persists mean/p50/p99/max to a new event_loop_lag table and recomputes a coarse load band (normal/elevated/critical) from the window p99. Standalone value: current lag is exposed on /api/status and band changes are logged, so site lag is diagnosable independent of throttling. The band feeds the #142 reconnect throttle (next commit) but ships first as its own subsystem. - event_loop_lag is bounded from day one: indexed on sampled_at + scheduled prune (LAG_TELEMETRY_RETENTION_DAYS, small default) modeled on the play_logs prune. Deliberately NOT another unbounded-growth table. - Band transitions are asymmetric: jump up immediately (tighten fast), release one level at a time after N calm samples below a deadband (release slow, no flap). Pure nextBand() function, unit-tested deterministically. - config: LAG_SAMPLE_INTERVAL_MS, LAG_RESOLUTION_MS, LAG_TELEMETRY_RETENTION_DAYS, LAG_PRUNE_INTERVAL_MS, LAG_ELEVATED_MS, LAG_CRITICAL_MS, LAG_RELEASE_SAMPLES. - tests: band-transition unit tests; integration proves sampling persists, stays bounded under the prune, and surfaces on /api/status. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
65 lines
2.9 KiB
JavaScript
65 lines
2.9 KiB
JavaScript
'use strict';
|
|
|
|
// #142 step 2 — integration: the lag monitor samples, persists to a BOUNDED table,
|
|
// and surfaces current lag on /api/status. Boots the real server with fast sampling
|
|
// and a tiny (fractional-day) retention so the prune is observable within the test.
|
|
|
|
const { test, before, after } = require('node:test');
|
|
const assert = require('node:assert/strict');
|
|
const { spawn } = require('node:child_process');
|
|
const path = require('node:path');
|
|
const os = require('node:os');
|
|
const fs = require('node:fs');
|
|
const crypto = require('node:crypto');
|
|
const Database = require('better-sqlite3');
|
|
|
|
const PORT = 3979;
|
|
const BASE = `http://127.0.0.1:${PORT}`;
|
|
const DATA_DIR = path.join(os.tmpdir(), 'st-lag-int-' + crypto.randomBytes(4).toString('hex'));
|
|
const LOG = path.join(os.tmpdir(), 'st-lag-int-' + crypto.randomBytes(4).toString('hex') + '.log');
|
|
let proc;
|
|
|
|
before(async () => {
|
|
const logFd = fs.openSync(LOG, 'w');
|
|
proc = spawn('node', ['server.js'], {
|
|
cwd: path.join(__dirname, '..'),
|
|
env: {
|
|
...process.env, DATA_DIR, SELF_HOSTED: 'true', PORT: String(PORT), NODE_ENV: 'test',
|
|
LAG_SAMPLE_INTERVAL_MS: '200', // sample fast
|
|
LAG_TELEMETRY_RETENTION_DAYS: '0.00001', // ~0.86s retention
|
|
LAG_PRUNE_INTERVAL_MS: '400', // prune often
|
|
},
|
|
stdio: ['ignore', logFd, logFd],
|
|
});
|
|
let up = false;
|
|
for (let i = 0; i < 80; i++) {
|
|
try { const r = await fetch(BASE + '/api/status'); if (r.ok) { up = true; break; } } catch { /* not yet */ }
|
|
await new Promise(r => setTimeout(r, 250));
|
|
}
|
|
if (!up) throw new Error('server did not boot:\n' + fs.readFileSync(LOG, 'utf8').slice(-2000));
|
|
});
|
|
|
|
after(() => { try { proc.kill('SIGKILL'); } catch { /* */ } });
|
|
|
|
test('/api/status exposes a current loop_lag snapshot', async () => {
|
|
const r = await fetch(BASE + '/api/status');
|
|
const body = await r.json();
|
|
assert.ok(body.loop_lag, 'loop_lag present on /api/status');
|
|
assert.ok(['normal', 'elevated', 'critical'].includes(body.loop_lag.band), 'band is a valid level');
|
|
assert.equal(typeof body.loop_lag.p99_ms, 'number', 'p99_ms is numeric');
|
|
assert.equal(typeof body.loop_lag.mean_ms, 'number', 'mean_ms is numeric');
|
|
});
|
|
|
|
test('lag samples are persisted AND bounded by retention prune (not unbounded)', async () => {
|
|
// Let it sample for ~3s. At 200ms/sample that is ~15 inserts, but with ~0.86s
|
|
// retention pruned every 400ms the table must stay small — proving the table
|
|
// can never become a second unbounded-growth table.
|
|
await new Promise(r => setTimeout(r, 3000));
|
|
const dbPath = path.join(DATA_DIR, 'db', 'remote_display.db');
|
|
const db = new Database(dbPath, { readonly: true });
|
|
const count = db.prepare('SELECT COUNT(*) c FROM event_loop_lag').get().c;
|
|
db.close();
|
|
assert.ok(count >= 1, 'lag samples are being persisted');
|
|
assert.ok(count < 15, `table is bounded by the prune (held ${count} rows over ~3s of 200ms sampling)`);
|
|
});
|