mirror of
https://github.com/abhigyanpatwari/GitNexus.git
synced 2026-09-08 22:22:52 +00:00
* Initial plan * fix(analyze): add WAL auto-checkpoint CLI control and default-off behavior * test(analyze): share lbug auto-checkpoint parsing and align validation * fix(analyze): always enable lbug auto-checkpoint and expose threshold control * refactor(lbug): inline always-on auto-checkpoint constructor arg * fix(analyze): guide checkpoint-threshold on Ladybug WAL checkpoint IO failures * test(analyze): cover checkpoint IO guidance and add integration guard * fix(analyze): tighten checkpoint IO detection and remove test hook * fix(analyze): remove checkpoint test hook and tighten error matching * fix(analyze): rename to wal-checkpoint-threshold, raise default, add manual checkpoint driver with retry Address review feedback on PR #1772: - Rename CLI flag, env var, AnalyzeOptions field, recovery-hint tag, and parser/constants from lbug-* to engine-neutral wal-* (matches the existing WAL_RECOVERY_SUGGESTION / isWalCorruptionError convention). - Raise default threshold from -1 (Ladybug stock ~16 MiB) to 64 MiB so users on the default config no longer hit the original rename/remove race. - Align both READMEs to publish 67108864 (64 MiB) instead of 65536 (which would have made the crash more frequent). - Add wal-checkpoint-driver.ts: a periodic manual CHECKPOINT driver wrapped in a 3-attempt jittered retry (50/200/500 ms), driven from runFullAnalysis. Opt-out via GITNEXUS_WAL_MANUAL_CHECKPOINT=0. Moves the race window into a JS-controllable retry surface while keeping native auto-checkpoint on. - Move LBUG_CHECKPOINT_RENAME_RE / REMOVE_RE plus the predicate (renamed to isLbugCheckpointIoError) into lbug-config.ts alongside isWalCorruptionError. Predicate is now exported. Add a permissive fallback matcher and pin the matched Ladybug version in comments. - Warn instead of silently defaulting when GITNEXUS_WAL_CHECKPOINT_THRESHOLD is set to a non-empty unparseable value (closes the CLI-vs-env asymmetry). - Add a typed RecoveryHint string-literal union in cli-message.ts so future hint tags can't drift. - Add a real integration test under test/integration/ that triggers a Ladybug checkpoint IO failure via a pre-existing directory at the rename target (portable across platforms; no test-only injection hook). - Add small-disk / CI caveat (32 MiB secondary suggestion) to the recovery hint and README env-var rows. - Document CLI/env precedence in the analyze --help block. - Help placeholder: <value> -> <bytes>. - Rename analyze-lbug-auto-checkpoint.test.ts to use the new wal-* token. * chore(lbug): remove dead jitteredDelay helper and apply prettier - Drop unused `jitteredDelay` function flagged by CodeQL in PR #1772; the retry loop already inlines the same calculation with the injectable `randomImpl` so the helper was dead. Move the non-cryptographic-by-design comment next to the actual jitter site. - Apply `prettier --write` to wal-checkpoint-driver.ts and the new integration test to absorb the PR autofix bot's formatting findings. --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: Gergő Magyar <gergomagyar@icloud.com> Co-authored-by: Test <test@example.com>
159 lines
6.3 KiB
TypeScript
159 lines
6.3 KiB
TypeScript
/**
|
|
* Unit tests for the manual WAL checkpoint driver (#1741 follow-up).
|
|
*
|
|
* The driver wraps a CHECKPOINT call in a bounded retry that fires only
|
|
* on `isLbugCheckpointIoError` shapes. These tests inject a fake
|
|
* `checkpointFn`, fake `sleepFn`, and fake `randomFn` to exercise the
|
|
* retry policy deterministically without touching a real LadybugDB.
|
|
*
|
|
* Integration-level coverage that the driver actually runs against a
|
|
* native engine lives in `test/integration/analyze-wal-checkpoint-failure.test.ts`.
|
|
*/
|
|
import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest';
|
|
import {
|
|
isManualCheckpointEnabled,
|
|
runCheckpointWithRetry,
|
|
startWalCheckpointDriver,
|
|
} from '../../src/core/lbug/wal-checkpoint-driver.js';
|
|
|
|
const makeCheckpointError = () =>
|
|
// Matches the strict rename matcher in lbug-config.ts.
|
|
new Error(
|
|
'Runtime exception: IO exception: Error renaming file /tmp/lbug.wal to /tmp/lbug.wal.checkpoint. ErrorMessage: Permission denied',
|
|
);
|
|
|
|
describe('runCheckpointWithRetry — retry policy', () => {
|
|
it('returns on first success with attempts=1 and no sleeps', async () => {
|
|
const checkpointFn = vi.fn().mockResolvedValue(true);
|
|
const sleepFn = vi.fn().mockResolvedValue(undefined);
|
|
const randomFn = vi.fn().mockReturnValue(0);
|
|
|
|
const result = await runCheckpointWithRetry({ checkpointFn, sleepFn, randomFn });
|
|
|
|
expect(result.attempts).toBe(1);
|
|
expect(result.flushed).toBe(true);
|
|
expect(checkpointFn).toHaveBeenCalledTimes(1);
|
|
expect(sleepFn).toHaveBeenCalledTimes(0);
|
|
});
|
|
|
|
it('retries up to 3 times on checkpoint IO errors and succeeds on the final attempt', async () => {
|
|
const checkpointFn = vi
|
|
.fn()
|
|
.mockRejectedValueOnce(makeCheckpointError())
|
|
.mockRejectedValueOnce(makeCheckpointError())
|
|
.mockResolvedValueOnce(true);
|
|
const sleepFn = vi.fn().mockResolvedValue(undefined);
|
|
// Fixed random returns 0, so jitter contributes 0 ms and we can
|
|
// assert exact delays against BASE_DELAYS_MS = [50, 200, 500].
|
|
const randomFn = vi.fn().mockReturnValue(0);
|
|
|
|
const result = await runCheckpointWithRetry({ checkpointFn, sleepFn, randomFn });
|
|
|
|
expect(result.attempts).toBe(3);
|
|
expect(result.flushed).toBe(true);
|
|
expect(checkpointFn).toHaveBeenCalledTimes(3);
|
|
// Sleeps happen between attempts: after attempt 1 (50 ms) and after
|
|
// attempt 2 (200 ms). No sleep after the final attempt.
|
|
expect(sleepFn).toHaveBeenCalledTimes(2);
|
|
expect(sleepFn).toHaveBeenNthCalledWith(1, 50);
|
|
expect(sleepFn).toHaveBeenNthCalledWith(2, 200);
|
|
});
|
|
|
|
it('rethrows the last error after exhausting all retries on persistent IO failures', async () => {
|
|
const persistent = makeCheckpointError();
|
|
const checkpointFn = vi.fn().mockRejectedValue(persistent);
|
|
const sleepFn = vi.fn().mockResolvedValue(undefined);
|
|
const randomFn = vi.fn().mockReturnValue(0);
|
|
|
|
await expect(runCheckpointWithRetry({ checkpointFn, sleepFn, randomFn })).rejects.toBe(
|
|
persistent,
|
|
);
|
|
|
|
expect(checkpointFn).toHaveBeenCalledTimes(3);
|
|
// Two backoffs (50 ms, 200 ms) but no sleep after the final attempt.
|
|
expect(sleepFn).toHaveBeenCalledTimes(2);
|
|
expect(sleepFn).toHaveBeenNthCalledWith(1, 50);
|
|
expect(sleepFn).toHaveBeenNthCalledWith(2, 200);
|
|
});
|
|
|
|
it('does NOT retry non-checkpoint errors (e.g. WAL corruption surfaces immediately)', async () => {
|
|
const corruption = new Error('Runtime exception: Corrupted wal file.');
|
|
const checkpointFn = vi.fn().mockRejectedValue(corruption);
|
|
const sleepFn = vi.fn().mockResolvedValue(undefined);
|
|
|
|
await expect(runCheckpointWithRetry({ checkpointFn, sleepFn })).rejects.toBe(corruption);
|
|
|
|
expect(checkpointFn).toHaveBeenCalledTimes(1);
|
|
expect(sleepFn).toHaveBeenCalledTimes(0);
|
|
});
|
|
|
|
it('jitter is bounded: 0 <= jitter < 50 ms regardless of random source', async () => {
|
|
const checkpointFn = vi
|
|
.fn()
|
|
.mockRejectedValueOnce(makeCheckpointError())
|
|
.mockResolvedValueOnce(true);
|
|
const sleepFn = vi.fn().mockResolvedValue(undefined);
|
|
// Random returns 0.999... — jitter should still be <50 ms (floor).
|
|
const randomFn = vi.fn().mockReturnValue(0.9999);
|
|
|
|
await runCheckpointWithRetry({ checkpointFn, sleepFn, randomFn });
|
|
|
|
expect(sleepFn).toHaveBeenCalledTimes(1);
|
|
const delay = sleepFn.mock.calls[0][0] as number;
|
|
expect(delay).toBe(50 + Math.floor(0.9999 * 50)); // == 99
|
|
});
|
|
});
|
|
|
|
describe('isManualCheckpointEnabled — env var parsing', () => {
|
|
let originalEnv: string | undefined;
|
|
beforeEach(() => {
|
|
originalEnv = process.env.GITNEXUS_WAL_MANUAL_CHECKPOINT;
|
|
});
|
|
afterEach(() => {
|
|
if (originalEnv === undefined) delete process.env.GITNEXUS_WAL_MANUAL_CHECKPOINT;
|
|
else process.env.GITNEXUS_WAL_MANUAL_CHECKPOINT = originalEnv;
|
|
});
|
|
|
|
it('defaults to enabled when the env var is unset', () => {
|
|
delete process.env.GITNEXUS_WAL_MANUAL_CHECKPOINT;
|
|
expect(isManualCheckpointEnabled()).toBe(true);
|
|
});
|
|
|
|
it.each(['0', 'false', 'FALSE', 'off', 'no', ' 0 '])(
|
|
'returns false for opt-out value %s',
|
|
(value) => {
|
|
process.env.GITNEXUS_WAL_MANUAL_CHECKPOINT = value;
|
|
expect(isManualCheckpointEnabled()).toBe(false);
|
|
},
|
|
);
|
|
|
|
it.each(['1', 'true', 'on', 'yes', ''])('returns true for non-opt-out value %s', (value) => {
|
|
process.env.GITNEXUS_WAL_MANUAL_CHECKPOINT = value;
|
|
expect(isManualCheckpointEnabled()).toBe(true);
|
|
});
|
|
});
|
|
|
|
describe('startWalCheckpointDriver — lifecycle', () => {
|
|
let originalEnv: string | undefined;
|
|
beforeEach(() => {
|
|
originalEnv = process.env.GITNEXUS_WAL_MANUAL_CHECKPOINT;
|
|
});
|
|
afterEach(() => {
|
|
if (originalEnv === undefined) delete process.env.GITNEXUS_WAL_MANUAL_CHECKPOINT;
|
|
else process.env.GITNEXUS_WAL_MANUAL_CHECKPOINT = originalEnv;
|
|
});
|
|
|
|
it('returns a no-op handle when manual checkpoint is disabled', async () => {
|
|
process.env.GITNEXUS_WAL_MANUAL_CHECKPOINT = '0';
|
|
const driver = startWalCheckpointDriver({ periodMs: 10 });
|
|
// stop() must resolve cleanly even when no interval was scheduled.
|
|
await expect(driver.stop()).resolves.toBeUndefined();
|
|
});
|
|
|
|
it('stop() is idempotent (second call resolves without throwing)', async () => {
|
|
process.env.GITNEXUS_WAL_MANUAL_CHECKPOINT = '0';
|
|
const driver = startWalCheckpointDriver({ periodMs: 10 });
|
|
await driver.stop();
|
|
await expect(driver.stop()).resolves.toBeUndefined();
|
|
});
|
|
});
|