mirror of
https://github.com/pgsty/minio.git
synced 2026-11-10 01:31:52 +03:00
fix(restore): return from a failed restore without waiting for its cleanup
A failed or canceled native restore cleared its ongoing marker under a fresh one-minute deadline, while the restore itself could still hold the object lock that the cleanup waits for. The request then stalled for about a minute (60 s in TestNativeRestoreWithoutOuterLock and TestRestoreRecoversStrandedMarker). Try the cleanup for 100 ms and leave the rest to the bounded background retries, which already exist for the pools path and now also serve the single-set path. Each retry still takes the object lock afresh and clears only the marker of its own attempt. The CI restore race step drops from about 260 s to 37 s. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Signed-off-by: Feng Ruohang <rh@vonng.com>
This commit is contained in:
@@ -43,6 +43,11 @@ const (
|
||||
// restoreTakeoverWait bounds how long a POST waits for the restore lock
|
||||
// of its version. A running restore holds it for its whole run.
|
||||
restoreTakeoverWait = 2 * time.Second
|
||||
// restoreResetAttemptTimeout bounds the synchronous cleanup attempt made
|
||||
// after a restore fails. A caller whose context has ended must not wait for
|
||||
// another object operation to release the restore lock; the recovery loop
|
||||
// below retries the cleanup after this attempt gives up.
|
||||
restoreResetAttemptTimeout = 100 * time.Millisecond
|
||||
// restoreCleanupTimeout bounds each status reset and convergence pass.
|
||||
restoreCleanupTimeout = time.Minute
|
||||
)
|
||||
@@ -639,6 +644,10 @@ func (z *erasureServerPools) recoverRestoreStatus(bucket, object string, opts Ob
|
||||
func (z *erasureServerPools) resetRestoreStatus(bucket, object string, opts ObjectOptions) error {
|
||||
ctx, cancel := context.WithTimeout(GlobalContext, restoreCleanupTimeout)
|
||||
defer cancel()
|
||||
return z.resetRestoreStatusWithContext(ctx, bucket, object, opts)
|
||||
}
|
||||
|
||||
func (z *erasureServerPools) resetRestoreStatusWithContext(ctx context.Context, bucket, object string, opts ObjectOptions) error {
|
||||
lk := z.restoreLock(bucket, object)
|
||||
lkctx, err := lk.GetLock(ctx, globalOperationTimeout)
|
||||
if err != nil {
|
||||
|
||||
Reference in New Issue
Block a user