astelm/minio
1
0
Fork 0
mirror of https://github.com/pgsty/minio.git synced 2026-11-11 10:05:34 +03:00
Code Issues Packages Projects Releases Wiki Activity

fix(decom): tolerate offline drives within erasure quorum

Browse Source 
Verify migration progress and final source cleanup on every online drive, allowing disk-not-found failures within the configured read quorum. Preserve strict rejection of online metadata remnants, corruption and directory errors. Cover parent and child migration with an offline drive and reject outages beyond parity.

Signed-off-by: Feng Ruohang <rh@vonng.com>
This commit is contained in:
Feng Ruohang
2026-11-11 13:39:38 +08:00
parent 293ab78b4c
commit 8587e061bb
3 changed files with 126 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files
cmd/erasure-server-pool-decom.go
+17 -3
View File
@@ -777,7 +777,7 @@ func (z *erasureServerPools) decommissionPool(ctx context.Context, idx int, pool
}
// decommissionPoolWalk walks bucket bi of pool idx once and returns the number
// of snapshot versions verified absent from every source drive afterwards.
// of snapshot versions verified absent from every online source drive afterwards.
func (z *erasureServerPools) decommissionPoolWalk(ctx context.Context, idx int, pool *erasureSets, bi decomBucketInfo) (int64, error) {
if err := ctx.Err(); err != nil {
return 0, err
@@ -1271,7 +1271,7 @@ func (z *erasureServerPools) removeFreeVersions(ctx context.Context, bucket, obj
return nil
}
// checkAfterDecomBucket verifies that a source bucket is physically empty
// checkAfterDecomBucket verifies that a source bucket's online drives are empty
// before it is removed from the resumable decommission queue. ILM decisions
// are deliberately not treated as an exemption: an expired version remains
// until the expiry path has performed its logical delete, replication, and
@@ -1285,14 +1285,17 @@ func (z *erasureServerPools) checkAfterDecomBucket(ctx context.Context, idx int,
if len(disks) == 0 {
return toObjectErr(errErasureReadQuorum, bi.Name)
}
readQuorum := set.migrationReadQuorum(len(disks))
onlineCount := 0
for _, disk := range disks {
if disk == nil {
return toObjectErr(errDiskNotFound, bi.Name)
continue
}
// Quorum listings omit minority versions, and WalkDir can skip
// unreadable metadata. Inspect physical directory entries instead:
// even a corrupt or truncated xl.meta must keep this pool queued.
pending := []string{bi.Prefix}
diskOffline := false
for len(pending) > 0 {
if err := ctx.Err(); err != nil {
return err
@@ -1306,6 +1309,10 @@ func (z *erasureServerPools) checkAfterDecomBucket(ctx context.Context, idx int,
if errors.Is(err, errFileNotFound) || errors.Is(err, errVolumeNotFound) {
continue // A concurrent deletion can remove the directory.
}
if errors.Is(err, errDiskNotFound) {
diskOffline = true
break
}
if err != nil {
return err
}
@@ -1322,6 +1329,13 @@ func (z *erasureServerPools) checkAfterDecomBucket(ctx context.Context, idx int,
}
}
}
if diskOffline {
continue
}
onlineCount++
}
if onlineCount < readQuorum {
return toObjectErr(errErasureReadQuorum, bi.Name)
}
}
return ctx.Err()