Foundation lib for v1.12.0 cron rewrite. Atomic exclusive create via
fs.writeFileSync('wx'); on EEXIST resolves staleness with OR semantics:
stale if PID is dead OR mtime exceeds threshold. Either alone breaks the
lock — handles SIGKILL orphans (mtime), PID-reuse races (mtime), and
crashed-then-replaced runs (PID).
- acquireLock(lockPath, opts) → {lockPath, release()}
- staleThresholdMs default 1h; refreshIntervalMs opt-in for long runs
- registerCleanup default true (exit/SIGINT/SIGTERM/SIGHUP/uncaughtException)
- isPidAlive uses kill(pid, 0) with EPERM-as-alive nuance
12/12 tests pass: PID liveness, fixture concurrency, idempotent release,
stale variants (dead+old, live+old, fresh+live), staleThresholdMs honored.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
166 lines
4.5 KiB
JavaScript
166 lines
4.5 KiB
JavaScript
// lock-file.mjs — Exclusive lock with PID + mtime stale-detection.
|
|
// Zero dependencies. Uses fs.writeFileSync('wx') for atomic exclusive create.
|
|
// Stale-detection is OR-based: stale if PID is dead OR mtime exceeds threshold.
|
|
// Either condition alone is enough to break the lock — handles SIGKILL orphans
|
|
// (mtime alone) and PID-reuse races (mtime alone) and crashed-then-replaced
|
|
// runs (PID alone). Long runs may opt-in to mtime refresh via refreshIntervalMs.
|
|
|
|
import { writeFileSync, readFileSync, statSync, unlinkSync, utimesSync } from 'node:fs';
|
|
import { hostname } from 'node:os';
|
|
import { join } from 'node:path';
|
|
import { getCacheDir } from './cross-platform-paths.mjs';
|
|
|
|
const DEFAULT_STALE_THRESHOLD_MS = 60 * 60 * 1000; // 1 hour
|
|
const DEFAULT_LOCK_NAME = 'kb-update.lock';
|
|
|
|
/**
|
|
* Check whether a PID identifies a live process.
|
|
* @param {number} pid — POSIX process id
|
|
* @returns {boolean}
|
|
*/
|
|
export function isPidAlive(pid) {
|
|
if (typeof pid !== 'number' || !Number.isFinite(pid) || pid <= 0) {
|
|
return false;
|
|
}
|
|
try {
|
|
process.kill(pid, 0);
|
|
return true;
|
|
} catch (err) {
|
|
// EPERM means the process exists but we lack signal permission — still alive.
|
|
return err && err.code === 'EPERM';
|
|
}
|
|
}
|
|
|
|
function safeReadLock(lockPath) {
|
|
try {
|
|
return JSON.parse(readFileSync(lockPath, 'utf8'));
|
|
} catch {
|
|
return null;
|
|
}
|
|
}
|
|
|
|
function lockMtimeMs(lockPath) {
|
|
try {
|
|
return statSync(lockPath).mtimeMs;
|
|
} catch {
|
|
return null;
|
|
}
|
|
}
|
|
|
|
function writeLockFile(lockPath) {
|
|
writeFileSync(
|
|
lockPath,
|
|
JSON.stringify({
|
|
pid: process.pid,
|
|
started: Date.now(),
|
|
host: hostname(),
|
|
version: 1,
|
|
}),
|
|
{ flag: 'wx', encoding: 'utf8' }
|
|
);
|
|
}
|
|
|
|
/**
|
|
* Acquire an exclusive lock. Throws ELOCKED if held by a live, fresh holder.
|
|
* Cleans up stale locks (dead PID OR mtime older than staleThresholdMs).
|
|
*
|
|
* @param {string} [lockPath] — absolute lock-file path; defaults to <cache>/kb-update.lock
|
|
* @param {object} [opts]
|
|
* @param {number} [opts.staleThresholdMs] — default 3600000 (1h)
|
|
* @param {number} [opts.refreshIntervalMs] — if > 0, periodically utimes the lock
|
|
* @param {boolean} [opts.registerCleanup] — default true; install exit/signal handlers
|
|
* @returns {{lockPath: string, release: () => void}}
|
|
*/
|
|
export function acquireLock(lockPath, opts = {}) {
|
|
const staleThresholdMs = opts.staleThresholdMs ?? DEFAULT_STALE_THRESHOLD_MS;
|
|
const refreshIntervalMs = opts.refreshIntervalMs ?? 0;
|
|
const registerCleanup = opts.registerCleanup ?? true;
|
|
const path = lockPath || join(getCacheDir('ms-ai-architect'), DEFAULT_LOCK_NAME);
|
|
|
|
try {
|
|
writeLockFile(path);
|
|
} catch (err) {
|
|
if (!err || err.code !== 'EEXIST') throw err;
|
|
|
|
const data = safeReadLock(path);
|
|
const mtime = lockMtimeMs(path);
|
|
const holderPid = typeof data?.pid === 'number' ? data.pid : null;
|
|
const pidAlive = holderPid != null ? isPidAlive(holderPid) : false;
|
|
const ageMs = mtime != null ? Date.now() - mtime : Infinity;
|
|
const stale = !pidAlive || ageMs > staleThresholdMs;
|
|
|
|
if (!stale) {
|
|
const e = new Error(
|
|
`Lock held by PID ${holderPid} (started ${data?.started ?? 'unknown'})`
|
|
);
|
|
e.code = 'ELOCKED';
|
|
e.holderPid = holderPid;
|
|
throw e;
|
|
}
|
|
|
|
try {
|
|
unlinkSync(path);
|
|
} catch {
|
|
// best-effort
|
|
}
|
|
writeLockFile(path); // retry once
|
|
}
|
|
|
|
let refreshTimer = null;
|
|
let released = false;
|
|
|
|
const release = () => {
|
|
if (released) return;
|
|
released = true;
|
|
if (refreshTimer) {
|
|
clearInterval(refreshTimer);
|
|
refreshTimer = null;
|
|
}
|
|
try {
|
|
const data = safeReadLock(path);
|
|
if (!data || data.pid === process.pid) {
|
|
unlinkSync(path);
|
|
}
|
|
} catch {
|
|
// best-effort
|
|
}
|
|
};
|
|
|
|
if (refreshIntervalMs > 0) {
|
|
refreshTimer = setInterval(() => {
|
|
try {
|
|
const now = new Date();
|
|
utimesSync(path, now, now);
|
|
} catch {
|
|
// best-effort
|
|
}
|
|
}, refreshIntervalMs);
|
|
if (typeof refreshTimer.unref === 'function') {
|
|
refreshTimer.unref();
|
|
}
|
|
}
|
|
|
|
if (registerCleanup) {
|
|
const onExit = () => release();
|
|
process.once('exit', onExit);
|
|
process.once('SIGINT', () => {
|
|
release();
|
|
process.exit(130);
|
|
});
|
|
process.once('SIGTERM', () => {
|
|
release();
|
|
process.exit(143);
|
|
});
|
|
process.once('SIGHUP', () => {
|
|
release();
|
|
process.exit(129);
|
|
});
|
|
process.once('uncaughtException', (err) => {
|
|
release();
|
|
console.error(err);
|
|
process.exit(1);
|
|
});
|
|
}
|
|
|
|
return { lockPath: path, release };
|
|
}
|