Files
gbrain/test/db-lock-heartbeat-takeover.test.ts
T
03ffc6ebdb v0.42.37.0 fix(jobs): reap stale locks, bound disconnect, complete cooperative-abort (#1972) (#2015)
* fix(jobs): reap stale dead-holder cycle/sync locks (#1972)

A crashed sync (OOM, recycle, SIGKILL) stranded its gbrain_cycle_locks row
until something contended for it — reclaim was on-contention only. Add a
host-scoped background reaper: reapDeadHolderLocks deletes locks whose holder
PID is provably dead on this host, scoped to the gbrain-sync:*/gbrain-cycle*
namespaces only (never elections/supervisor/reindex), with a snapshot-matched
delete (date_trunc on acquired_at) that is TOCTOU-safe against PID reuse.
Reuses isHolderDeadLocally (same-host + ESRCH + 60s grace). doctor --fix now
auto-reaps for no-autopilot brains. DRY: selectLockRows + shared mapper now
back inspectLock + listStaleLocks (killed the triplication).

* fix(db): bound pool disconnect so teardown can't eat CLI output (#1972)

pool.end() against PgBouncer transaction-mode never drained, so disconnect
blocked until the CLI's 10s force-exit fired and process.exit()'d mid-write,
truncating stdout (e.g. #1959's relational query returned empty). Add a
gbrain-owned endPoolBounded(pool): Promise.race of pool.end({timeout}) against
a hard timer, so teardown is bounded regardless of what postgres.js does and is
testable. connection-manager ends its direct + read pools concurrently so the
per-pool bounds don't stack. PGLite disconnect is unaffected.

* fix(cycle): complete cooperative-abort coverage + wire lock reaper (#1972)

v0.42.29 made only the embed phase honor the abort signal; a 24h pull still
showed force-evicts from a long non-embed phase ignoring it. Thread the signal
into every cycle-reachable long loop: extract (extractForSlugs + the full-walk
extractLinksFromDir/extractTimelineFromDir), extract_facts (per-page loop +
embed signal + the phantom-redirect 30s lock-retry), and consolidate's bucket
loop. Add a terminal abort check so an aborted cycle never stamps
last_full_cycle_at as a completed run (Codex #9). lint now yields + checks
abort every 200 pages (it's synchronous; the yield is what lets the signal
land). New phase-duration force-evict attribution log names any phase that
crosses the 30s deadline. Wire reapDeadHolderLocks at cycle start.

* chore: bump version and changelog (v0.42.38.0)

#1972 — stale-lock reaper, bounded pool disconnect, and complete
cooperative-abort coverage across cycle phases.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* docs(key-files): current-state for the #1972 reaper, bounded disconnect, abort coverage

document-release: update db-lock.ts (reapDeadHolderLocks + selectLockRows DRY),
db.ts (endPoolBounded), and abort-check.ts (coverage now spans extract/
extract_facts/consolidate/lint + terminal guard) entries to current truth.

* test(isolation): fix shard-order flakes exposed by #1972's new test files

Adding 3 new test files reshuffled the hash-based shards, exposing two
pre-existing test-isolation bugs:

- cycle-consolidate.test.ts assumed the global legacy-embedding preload's
  1536-d gateway config still held at initSchema, but a co-sharded test that
  calls resetGateway() in teardown nulls it, so initSchema fell back to the
  1280-d default and built a halfvec(1280) facts column its 1536-d fixtures
  can't fill. Re-pin the legacy OpenAI/1536 config in beforeAll (the pattern
  legacy-embedding-preload.ts documents for 1536-d fixture tests).
- db-lock-heartbeat-takeover.test.ts (merged from master's #1794) mutated
  process.env.GBRAIN_LOCK_STEAL_GRACE_SECONDS raw, tripping check:test-isolation
  rule R1. Convert to withEnv().

---------

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-09 22:28:44 -07:00

158 lines
6.0 KiB
TypeScript

/**
* #1794 — heartbeat-aware lock takeover + direct-pool refresh.
*
* The lock-thrash fix: a holder that refreshed within the steal-grace window is
* NOT stolen even if its TTL lapsed (starved-but-alive), while a holder that
* stopped refreshing past the grace IS stolen. These tests isolate the ON
* CONFLICT grace logic by holding with `process.pid` (alive) so the dead-pid
* auto-takeover path can't fire — a successful steal therefore proves the
* grace/last_refreshed_at predicate did it.
*
* Plus the commit-8 causal-mechanism check: setImmediate yields let a
* setInterval tick fire during a busy loop (the reason the import loop's
* maybeYield keeps the refresh heartbeat alive).
*/
import { describe, test, expect, beforeAll, afterAll, beforeEach } from 'bun:test';
import { hostname } from 'os';
import { PGLiteEngine } from '../src/core/pglite-engine.ts';
import { withEnv } from './helpers/with-env.ts';
import {
tryAcquireDbLock,
resolveStealGraceSeconds,
DEFAULT_STEAL_GRACE_SECONDS,
} from '../src/core/db-lock.ts';
let engine: PGLiteEngine;
beforeAll(async () => {
engine = new PGLiteEngine();
await engine.connect({ database_url: '' });
await engine.initSchema();
});
afterAll(async () => {
await engine.disconnect();
});
beforeEach(async () => {
await engine.executeRaw(`DELETE FROM gbrain_cycle_locks WHERE id LIKE 'test-hb-%'`);
});
const LOCAL = hostname();
/**
* Seed a TTL-EXPIRED lock held by an ALIVE pid (process.pid), with a chosen
* last_refreshed_at age (or NULL). Alive holder → dead-pid auto-takeover can't
* fire, so the only reclaim path is the ON CONFLICT grace predicate.
*/
async function seedExpiredLock(id: string, refreshedSecondsAgo: number | null): Promise<void> {
if (refreshedSecondsAgo === null) {
await engine.executeRaw(
`INSERT INTO gbrain_cycle_locks (id, holder_pid, holder_host, acquired_at, ttl_expires_at, last_refreshed_at)
VALUES ($1, $2, $3, NOW() - INTERVAL '1 hour', NOW() - INTERVAL '5 minutes', NULL)`,
[id, process.pid, LOCAL],
);
} else {
await engine.executeRaw(
`INSERT INTO gbrain_cycle_locks (id, holder_pid, holder_host, acquired_at, ttl_expires_at, last_refreshed_at)
VALUES ($1, $2, $3, NOW() - INTERVAL '1 hour', NOW() - INTERVAL '5 minutes', NOW() - ($4 || ' seconds')::interval)`,
[id, process.pid, LOCAL, String(refreshedSecondsAgo)],
);
}
}
async function refreshedAge(id: string): Promise<Date | null> {
const rows = await engine.executeRaw<{ last_refreshed_at: string | null }>(
`SELECT last_refreshed_at FROM gbrain_cycle_locks WHERE id = $1`,
[id],
);
const v = rows[0]?.last_refreshed_at ?? null;
return v ? new Date(v) : null;
}
describe('resolveStealGraceSeconds', () => {
test('derives ~2 refresh ticks from the TTL (30min → 600s)', () => {
// refresh ~ttl/6 = 5min = 300s; *2 = 600s.
expect(resolveStealGraceSeconds(30)).toBe(DEFAULT_STEAL_GRACE_SECONDS);
expect(resolveStealGraceSeconds(30)).toBe(600);
});
test('floors at 60s for tiny TTLs', () => {
expect(resolveStealGraceSeconds(1)).toBe(60);
});
test('env override wins', async () => {
await withEnv({ GBRAIN_LOCK_STEAL_GRACE_SECONDS: '123' }, async () => {
expect(resolveStealGraceSeconds(30)).toBe(123);
});
});
test('bad env override falls back to derived', async () => {
await withEnv({ GBRAIN_LOCK_STEAL_GRACE_SECONDS: 'nope' }, async () => {
expect(resolveStealGraceSeconds(30)).toBe(600);
});
});
});
describe('heartbeat-aware takeover (ON CONFLICT grace predicate)', () => {
test('FRESH holder is NOT stolen even with an expired TTL', async () => {
// ttl expired 5min ago, but refreshed 1s ago → inside the 600s grace.
await seedExpiredLock('test-hb-fresh', 1);
const handle = await tryAcquireDbLock(engine, 'test-hb-fresh', 30);
expect(handle).toBeNull();
});
test('STALE-refresh holder IS stolen (refresh older than the grace)', async () => {
// ttl expired AND last refresh 20min ago (> 600s grace) → stealable, even
// though the holder pid is alive (proves the grace path, not auto-takeover).
await seedExpiredLock('test-hb-stale', 1200);
const handle = await tryAcquireDbLock(engine, 'test-hb-stale', 30);
expect(handle).not.toBeNull();
await handle!.release();
});
test('NULL last_refreshed_at (pre-v98 row) IS stolen on TTL expiry', async () => {
await seedExpiredLock('test-hb-null', null);
const handle = await tryAcquireDbLock(engine, 'test-hb-null', 30);
expect(handle).not.toBeNull();
await handle!.release();
});
test('a reclaimed handle refresh() bumps last_refreshed_at (direct pool path)', async () => {
await seedExpiredLock('test-hb-bump', 1200);
const handle = await tryAcquireDbLock(engine, 'test-hb-bump', 30);
expect(handle).not.toBeNull();
const before = await refreshedAge('test-hb-bump');
// Small real delay so NOW() advances measurably between acquire and refresh.
await new Promise((r) => setTimeout(r, 20));
await handle!.refresh();
const after = await refreshedAge('test-hb-bump');
expect(before).not.toBeNull();
expect(after).not.toBeNull();
expect(after!.getTime()).toBeGreaterThan(before!.getTime());
await handle!.release();
});
});
describe('event-loop yield keeps timers alive (commit 8 mechanism)', () => {
test('setTimeout(0) yields let a setInterval heartbeat fire during a busy loop', async () => {
let ticks = 0;
const iv = setInterval(() => { ticks++; }, 2);
try {
// Mirror the import loop's maybeYield: setTimeout(0) enters the timers
// phase, so the setInterval heartbeat can fire mid-loop. (A setImmediate
// loop starves the timers phase in Bun — the reason maybeYield uses
// setTimeout, not setImmediate.) Bound by wall-clock so the 2ms interval
// has real time to fire.
const start = Date.now();
while (Date.now() - start < 40) {
await new Promise<void>((r) => setTimeout(r, 0));
}
} finally {
clearInterval(iv);
}
expect(ticks).toBeGreaterThan(0);
});
});