Fix pool migration cleanup and physical progress

Count removal only after every source drive confirms version absence, including free records and concurrently deleted parents. Retire successful candidates independently with the existing source, destination and tier ownership checks. Reject ambiguous raw reads, verify remaining metadata directly, and propagate cancellation.

Signed-off-by: Feng Ruohang <rh@vonng.com>
(cherry picked from commit b1a97c7e6cc7ab5f44110b5b8258afb60a50053e)

cmd/erasure-server-pool-migration.go

@@ -17,7 +17,117 @@
 
 package cmd
 
-import xhttp "github.com/minio/minio/internal/http"
+import (
+	"context"
+	"errors"
+
+	xhttp "github.com/minio/minio/internal/http"
+	"github.com/pgsty/silo-pkg/v3/sync/errgroup"
+)
+
+func migrationVersionKey(versionID string) string {
+	if versionID == "" || versionID == nullVersionID {
+		return nullVersionID
+	}
+	return versionID
+}
+
+// countAbsentMigrationVersions counts snapshot versions that no source drive
+// holds anymore, including free versions. A pool-level NotFound is insufficient:
+// the ordinary read path can return it for inconsistent metadata. Only readable
+// per-drive metadata (or physical absence) proves progress for another walk.
+// The caller holds the object's writer lock while checking the source.
+func (er erasureObjects) countAbsentMigrationVersions(ctx context.Context, bucket, object string, versions []FileInfo) (int, error) {
+	if err := ctx.Err(); err != nil {
+		return 0, err
+	}
+	if len(versions) == 0 {
+		return 0, nil
+	}
+	absent := make(map[string]struct{}, len(versions))
+	for _, version := range versions {
+		absent[migrationVersionKey(version.VersionID)] = struct{}{}
+	}
+	disks := er.getDisks()
+	if len(disks) == 0 {
+		return 0, toObjectErr(errErasureReadQuorum, bucket, object)
+	}
+	stored := make([][]FileInfo, len(disks))
+	g := errgroup.WithNErrs(len(disks))
+	for i := range disks {
+		g.Go(func() error {
+			if disks[i] == nil {
+				return errDiskNotFound
+			}
+			raw, err := disks[i].ReadXL(ctx, bucket, object, false)
+			if errors.Is(err, errFileNotFound) {
+				// ReadXL also returns NotFound for an empty xl.meta, and may
+				// ignore legacy metadata. Confirm physical absence before using
+				// that result as progress. This does not descend into child keys.
+				// Both reads run in parallel across drives, once per object.
+				entries, err := disks[i].ListDir(ctx, "", bucket, object, -1)
+				if err != nil && !errors.Is(err, errFileNotFound) && !errors.Is(err, errVolumeNotFound) {
+					return err
+				}
+				for _, entry := range entries {
+					if entry == xlStorageFormatFile || entry == xlStorageFormatFileV1 {
+						return errFileCorrupt
+					}
+				}
+				return nil
+			}
+			if errors.Is(err, errVolumeNotFound) {
+				return nil
+			}
+			if err != nil {
+				return err
+			}
+			// allParts=false omits part details, not free versions. Decode every
+			// version before concluding absence, so corrupt metadata fails closed.
+			fivs, err := getAllFileInfoVersions(raw.Buf, bucket, object, false)
+			stored[i] = fivs.Versions
+			return err
+		}, i)
+	}
+	errs := g.Wait()
+	if err := ctx.Err(); err != nil {
+		return 0, err
+	}
+	for i, err := range errs {
+		if err != nil {
+			return 0, toObjectErr(err, bucket, object)
+		}
+		for _, version := range stored[i] {
+			delete(absent, migrationVersionKey(version.VersionID))
+		}
+	}
+	if err := ctx.Err(); err != nil {
+		return 0, err
+	}
+	return len(absent), nil
+}
+
+// countAbsentMigrationVersions checks ignored walk entries without authorizing
+// their deletion. A concurrent client delete may have uncovered child keys.
+func (z *erasureServerPools) countAbsentMigrationVersions(ctx context.Context, bucket, object string, source int, versions []FileInfo) (int, error) {
+	if err := ctx.Err(); err != nil {
+		return 0, err
+	}
+	if len(versions) == 0 {
+		return 0, nil
+	}
+	object = encodeDirObject(object)
+	lk := z.NewNSLock(bucket, object)
+	lkctx, err := lk.GetLock(ctx, globalOperationTimeout)
+	if err != nil {
+		if ctx.Err() != nil {
+			return 0, ctx.Err()
+		}
+		return 0, err
+	}
+	defer lk.Unlock(lkctx)
+	return z.serverPools[source].getHashedSet(object).countAbsentMigrationVersions(lkctx.Context(), bucket, object, versions)
+}
 
 // migrationObjectMetadata restores tags removed from the read representation.
 // Keep the original revision, including ordered empty states, for the existing