* fix(core): platformWriteSync must retry transient rename locks, not truncate readers (#1540) platformWriteSync fell back to a non-atomic fs.writeFileSync(filePath) on ANY error from the temp+rename path. On Windows, renameSync onto a target a reader holds open throws EPERM/EBUSY/EACCES (the common case for hot files like STATE.md), so the fallback fired and a concurrent reader saw the file mid-truncation. Mirror the capability-ledger rename-retry idiom: retry transient lock errnos (EPERM/EBUSY/EACCES) with a bounded Atomics.wait backoff; on a persistent lock, surface the error rather than do the truncating non-atomic write. Genuinely unrenameable cases (EXDEV cross-device) and tmp-write failures still fall back. Claude-Session: https://claude.ai/code/session_01R88n7Q54bAaVHFkDbbH1yz * chore(changeset): Fixed fragment for #1541 (platformWriteSync rename retry) Claude-Session: https://claude.ai/code/session_01R88n7Q54bAaVHFkDbbH1yz --------- Co-authored-by: Tom Boucher <trekkie@nomorestars.com>
This commit is contained in:
@@ -550,17 +550,71 @@ export function normalizeContent(filePath: string, content: string, opts: { enco
|
||||
return { content: normalized, encoding };
|
||||
}
|
||||
|
||||
// Rename errnos that are transient on Windows: a concurrent reader (or an AV
|
||||
// scanner / indexer) holding the target open makes renameSync fail briefly.
|
||||
// Same idiom as capability-ledger.cts / capability-consent.cts.
|
||||
const RENAME_RETRY_ERRNOS = new Set(['EPERM', 'EBUSY', 'EACCES']);
|
||||
const RENAME_MAX_ATTEMPTS = 3;
|
||||
const RENAME_RETRY_BACKOFF_MS = 50;
|
||||
|
||||
/** Synchronous best-effort backoff sleep (Atomics.wait — same idiom as io.cts). */
|
||||
let _renameSleepBuf: Int32Array | null = null;
|
||||
function renameBackoff(): void {
|
||||
if (_renameSleepBuf === null) _renameSleepBuf = new Int32Array(new SharedArrayBuffer(4));
|
||||
Atomics.wait(_renameSleepBuf, 0, 0, RENAME_RETRY_BACKOFF_MS);
|
||||
}
|
||||
|
||||
/**
|
||||
* Atomic publish with bounded retry on transient Windows lock errnos.
|
||||
* Returns null on success, or the final error if every attempt failed.
|
||||
*/
|
||||
function atomicRenameWithRetry(tmpPath: string, filePath: string): NodeJS.ErrnoException | null {
|
||||
let renameErr: NodeJS.ErrnoException | null = null;
|
||||
for (let attempt = 1; attempt <= RENAME_MAX_ATTEMPTS; attempt++) {
|
||||
try {
|
||||
fs.renameSync(tmpPath, filePath);
|
||||
return null;
|
||||
} catch (err) {
|
||||
renameErr = err as NodeJS.ErrnoException;
|
||||
if (attempt < RENAME_MAX_ATTEMPTS && RENAME_RETRY_ERRNOS.has(renameErr.code ?? '')) {
|
||||
renameBackoff();
|
||||
continue;
|
||||
}
|
||||
break;
|
||||
}
|
||||
}
|
||||
return renameErr;
|
||||
}
|
||||
|
||||
export function platformWriteSync(filePath: string, content: string, opts: { encoding?: BufferEncoding } = {}): void {
|
||||
const { content: normalized, encoding } = normalizeContent(filePath, content, opts);
|
||||
fs.mkdirSync(path.dirname(filePath), { recursive: true });
|
||||
const tmpPath = filePath + '.tmp.' + process.pid;
|
||||
|
||||
// Step 1: write the sibling tmp file. If THIS fails, nothing was published, so a
|
||||
// direct fallback write cannot truncate a concurrent reader of an existing file.
|
||||
try {
|
||||
fs.writeFileSync(tmpPath, normalized, encoding);
|
||||
fs.renameSync(tmpPath, filePath);
|
||||
} catch {
|
||||
try { fs.unlinkSync(tmpPath); } catch { /* already gone */ }
|
||||
fs.writeFileSync(filePath, normalized, encoding);
|
||||
return;
|
||||
}
|
||||
|
||||
// Step 2: atomic publish, retrying transient Windows locks.
|
||||
const renameErr = atomicRenameWithRetry(tmpPath, filePath);
|
||||
if (renameErr === null) return;
|
||||
|
||||
try { fs.unlinkSync(tmpPath); } catch { /* already gone */ }
|
||||
if (RENAME_RETRY_ERRNOS.has(renameErr.code ?? '')) {
|
||||
// A live reader still holds the target open after every retry. A non-atomic
|
||||
// direct write here would truncate that reader (the exact corruption this seam
|
||||
// exists to prevent), so surface the error instead of falling back.
|
||||
throw renameErr;
|
||||
}
|
||||
// Atomic publish is genuinely impossible here (e.g. EXDEV cross-device move):
|
||||
// fall back to a direct write to preserve write availability.
|
||||
fs.writeFileSync(filePath, normalized, encoding);
|
||||
}
|
||||
|
||||
export function platformReadSync(filePath: string, opts: { encoding?: BufferEncoding; required?: boolean } = {}): string | null {
|
||||
|
||||
Reference in New Issue
Block a user