Keep leases alive during long restores and exports; PR review fixes
CI / unit (8.2) (push) Has been cancelled
CI / unit (8.3) (push) Has been cancelled
CI / unit (8.4) (push) Has been cancelled
CI / psalm (push) Has been cancelled
CI / integration (mariadb, 32) (push) Has been cancelled
CI / integration (mariadb, 33) (push) Has been cancelled
CI / integration (mariadb, 34) (push) Has been cancelled
CI / integration (mariadb, 35) (push) Has been cancelled
CI / integration (pgsql, 32) (push) Has been cancelled
CI / integration (pgsql, 33) (push) Has been cancelled
CI / integration (pgsql, 34) (push) Has been cancelled
CI / integration (pgsql, 35) (push) Has been cancelled
CI / integration (sqlite, 32) (push) Has been cancelled
CI / integration (sqlite, 33) (push) Has been cancelled
CI / integration (sqlite, 34) (push) Has been cancelled
CI / integration (sqlite, 35) (push) Has been cancelled
CI / integration-targets (push) Has been cancelled
CI / integration-user (32) (push) Has been cancelled
CI / integration-user (33) (push) Has been cancelled
CI / integration-user (34) (push) Has been cancelled
CI / integration-user (35) (push) Has been cancelled
CI / integration-full-restore (push) Has been cancelled

Full restore, raw directory restore, per-user export and the safety export
held a fixed-TTL lease on the location that nothing refreshed. A restore or
export running longer than that TTL let a cleanup take over and delete data
still in use. They now refresh the lease while they work (per blob, per row
batch, per written chunk), throttled to once a minute.

Also:
- backup:prune still applies snapshot retention when user-export retention
  fails for a location.
- The recovery kit carries the deletion delay, so a disaster recovery keeps
  the original protection instead of falling back to 7 days. Older kits
  still import with the default.
- CI checkouts no longer persist the token in the git config.
- recoveryKit() has its real return type; the stale baseline entry is gone.
This commit is contained in:
2026-10-06 22:38:47 +02:00
parent cc09d74942
commit 70965dd4bd
13 changed files with 106 additions and 41 deletions
+5 -2
View File
@@ -93,7 +93,9 @@ final class KeyService {
$this->cached = $keys;
$this->appConfig->setValueString(Application::APP_ID, self::KEY_WRAPPED, json_encode($kit['wrapped_key'], JSON_THROW_ON_ERROR), true, true);
$this->appConfig->setValueString(Application::APP_ID, self::KEY_FINGERPRINT, $this->fingerprintOf($keys), true);
$this->appConfig->setValueInt(Application::APP_ID, self::KEY_DELETE_DELAY, self::DEFAULT_DELETE_DELAY, true);
// Kits from before this field existed fall back to the default.
$delay = (int)($kit['delete_delay_days'] ?? self::DEFAULT_DELETE_DELAY);
$this->appConfig->setValueInt(Application::APP_ID, self::KEY_DELETE_DELAY, ($delay >= 1 && $delay <= 365) ? $delay : self::DEFAULT_DELETE_DELAY, true);
$this->appConfig->setValueInt(Application::APP_ID, self::KEY_KIT_VERSION, (int)($kit['kit_version'] ?? 1), true);
// Having and successfully using a real kit file is stronger proof than the normal
// download-and-confirm flow it replaces.
@@ -260,13 +262,14 @@ final class KeyService {
return $this->appConfig->getValueString(Application::APP_ID, self::KEY_FINGERPRINT, '', true);
}
/** @return array{version:int, app:string, fingerprint:string, created:string, wrapped_key:array, instructions:string} */
/** @return array{version:int, app:string, fingerprint:string, kit_version:int, delete_delay_days:int, confirmation_code:string, created:string, wrapped_key:array, slots:list<array{slot:int, label:string, created:int}>, instructions:string} */
public function recoveryKit(): array {
return [
'version' => 1,
'app' => 'NG Backup',
'fingerprint' => $this->fingerprint(),
'kit_version' => $this->kitVersion(),
'delete_delay_days' => $this->deleteDelayDays(),
'confirmation_code' => $this->kitCode(),
'created' => gmdate('c'),
'wrapped_key' => $this->wrappedKey(),
+11
View File
@@ -76,6 +76,17 @@ final class LeaseService {
$qb->executeStatement();
}
/** Wraps $refresh so calling it often (per file, per row batch) only touches the database every $seconds. */
public static function throttled(callable $refresh, int $seconds = 60): \Closure {
$last = time();
return static function () use ($refresh, $seconds, &$last): void {
if (time() - $last >= $seconds) {
$refresh();
$last = time();
}
};
}
/** Run $fn under a lease; $refresh() can be called during long work. */
public function with(string $name, string $mode, int $ttl, callable $fn): mixed {
$id = $this->acquire($name, $mode, $ttl);
+6 -6
View File
@@ -70,7 +70,8 @@ final class RestoreFullService {
if (!$check['ok']) {
throw new \RuntimeException($this->describeBlockers($check));
}
return $this->withSharedLock($target, function () use ($target, $snapshotId) {
return $this->withSharedLock($target, function (callable $refresh) use ($target, $snapshotId) {
$beat = LeaseService::throttled($refresh);
$repo = $this->targets->repository($target);
$meta = $repo->snapshotMeta($snapshotId);
@@ -100,7 +101,7 @@ final class RestoreFullService {
$ownAppConfig = $this->preserveOwnAppConfig();
$dumper = new DbDumper($this->db->getInner(), $prefix);
try {
$dumper->restore($repo, $manifest, $dbReport);
$dumper->restore($repo, $manifest, $dbReport, $beat);
} finally {
$this->restoreOwnAppConfig($ownAppConfig);
}
@@ -114,7 +115,7 @@ final class RestoreFullService {
$backupConfig = $this->fetchBackupConfig($target, $snapshotId);
$dataDir = rtrim($this->config->getSystemValueString('datadirectory'), '/');
$dataFiles = $this->restore->restoreToDirectory($target, $snapshotId, 'data', $dataDir, stripPrefix: true);
$dataFiles = $this->restore->restoreToDirectory($target, $snapshotId, 'data', $dataDir, stripPrefix: true, heartbeat: $beat);
// Last step: nothing after this may need $this->targets->repository($target) again.
if ($backupConfig !== []) {
@@ -215,9 +216,8 @@ final class RestoreFullService {
private function withSharedLock(Target $target, callable $fn): mixed {
try {
// No progress from DbDumper::restore()/Repository::restore() to refresh this lease
// against; a very large instance could in theory outrun this TTL (same limitation as
// RestoreService::restoreToDirectory(), see also UserBackupService).
// Refreshed during the database and data restore (per row batch, per blob), so a
// cleanup cannot take over the location while a long restore is still reading it.
return $this->leases->with(PruneService::lockKey($target), LeaseService::SHARED, 7200, $fn);
} catch (LockedException) {
throw new \RuntimeException('A cleanup of ' . $target->getName() . ' is in progress; try again later');
+11 -2
View File
@@ -156,14 +156,23 @@ final class RestoreService {
* Repository::restore()); used to restore "data/" or "config/" straight into the
* real data/config directory for occ backup:restore:full.
*/
public function restoreToDirectory(Target $target, string $snapshotId, string $prefix, string $directory, bool $stripPrefix = false): int {
public function restoreToDirectory(Target $target, string $snapshotId, string $prefix, string $directory, bool $stripPrefix = false, ?callable $heartbeat = null): int {
if ($prefix !== '' && !Repository::isSafePath($prefix)) {
throw new \InvalidArgumentException('Invalid path: ' . $prefix);
}
if (!is_dir($directory) && !mkdir($directory, 0750, true) && !is_dir($directory)) {
throw new \RuntimeException("Cannot create $directory");
}
return $this->withSharedLock($target, fn () => $this->targets->repository($target)->restore($snapshotId, $directory, trim($prefix, '/') === '' ? '' : trim($prefix, '/') . '/', $stripPrefix), 3600);
return $this->withSharedLock($target, function (callable $refresh) use ($target, $snapshotId, $prefix, $directory, $stripPrefix, $heartbeat): int {
$own = LeaseService::throttled($refresh);
$beat = static function () use ($own, $heartbeat): void {
$own();
if ($heartbeat !== null) {
$heartbeat();
}
};
return $this->targets->repository($target)->restore($snapshotId, $directory, trim($prefix, '/') === '' ? '' : trim($prefix, '/') . '/', $stripPrefix, $beat);
}, 3600);
}
private function writeFile(Repository $repo, Folder $dest, string $relPath, array $entry): void {
+3 -6
View File
@@ -34,9 +34,9 @@ final class UserBackupService {
/** @throws UserMigrationException when user_migration is not enabled, or the export itself fails */
public function backupUser(Target $target, IUser $user): string {
$service = $this->locator->get();
return $this->withSharedLock($target, function () use ($target, $user, $service) {
return $this->withSharedLock($target, function (callable $refresh) use ($target, $user, $service) {
$repo = $this->targets->repository($target);
$dest = new RepositoryExportDestination($repo, $user->getUID());
$dest = new RepositoryExportDestination($repo, $user->getUID(), LeaseService::throttled($refresh));
$service->export($dest, $user);
// A short exclusive lock around the catalog write only: the shared lock above
// allows another concurrent backup (full or per-user) to be writing the catalog at
@@ -49,10 +49,7 @@ final class UserBackupService {
private function withSharedLock(Target $target, callable $fn): mixed {
try {
// UserMigrationService::export() exposes no progress, so unlike
// RestoreService::restoreUserFiles() this lease cannot be refreshed mid-call; a very
// large account could in theory outrun this TTL. Resumable, step-based per-user
// backup (like the main BackupService run) is a possible future improvement.
// Refreshed by RepositoryExportDestination as it writes data, so a long export keeps it.
return $this->leases->with(PruneService::lockKey($target), LeaseService::SHARED, 3600, $fn);
} catch (LockedException) {
throw new \RuntimeException('A cleanup of ' . $target->getName() . ' is in progress; try again later');
+3 -4
View File
@@ -45,7 +45,7 @@ final class UserRestoreService {
/** @throws UserMigrationException when user_migration is not enabled, or the restore itself fails */
public function restoreUser(Target $target, string $manifestPath, string $mode = self::MODE_REPLACE): IUser {
$service = $this->locator->get();
return $this->withSharedLock($target, function () use ($target, $manifestPath, $mode, $service): IUser {
return $this->withSharedLock($target, function (callable $refresh) use ($target, $manifestPath, $mode, $service): IUser {
$repo = $this->targets->repository($target);
// Only ever read a manifest the verified catalog actually recorded: a path alone
// (even one this app generated before) proves nothing about it still being current
@@ -80,7 +80,7 @@ final class UserRestoreService {
if ($existing !== null) {
// Never import over a live account: export its current state first, so nothing
// is lost if the restore turns out to be the wrong choice.
$safety = new RepositoryExportDestination($repo, $originalUid);
$safety = new RepositoryExportDestination($repo, $originalUid, LeaseService::throttled($refresh));
$service->export($safety, $existing);
$safetyManifestPath = $safety->manifestPath();
// Same race as UserBackupService::backupUser(): reopen the repository inside the
@@ -119,8 +119,7 @@ final class UserRestoreService {
private function withSharedLock(Target $target, callable $fn): mixed {
try {
// See UserBackupService::withSharedLock(): UserMigrationService exposes no progress,
// so this lease cannot be refreshed mid-call.
// Refreshed while the safety export writes data (see UserBackupService::withSharedLock()).
return $this->leases->with(PruneService::lockKey($target), LeaseService::SHARED, 3600, $fn);
} catch (LockedException) {
throw new \RuntimeException('A cleanup of ' . $target->getName() . ' is in progress; try again later');