fix(decom): tolerate offline drives within erasure quorum

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>

cmd/erasure-server-pool-migration-progress_test.go

@@ -257,6 +257,27 @@ func TestDecommissionConcurrentParentDeleteRescansChildren(t *testing.T) {
 	}
 }
 
+func TestDecommissionDegradedPoolRescansChildren(t *testing.T) {
+	z, bucket := migrationTestPools(t)
+	putConsistencyObject(t, z, bucket, "k", 0, "parent", ObjectOptions{})
+	putConsistencyObject(t, z, bucket, "k/b", 0, "child", ObjectOptions{})
+	var wrapped int
+	t.Cleanup(conditionalPutSwapDisks(z.serverPools[0], "k", func(d StorageAPI) StorageAPI {
+		wrapped++
+		if wrapped == 1 {
+			return nil
+		}
+		return d
+	}))
+	if failed := migrationTestWalk(t, z, bucket, 0, "decommission"); failed != 0 {
+		t.Fatalf("failed moves: %d", failed)
+	}
+	mustIAM(t, z.checkAfterDecomBucket(t.Context(), 0, decomBucketInfo{Name: bucket}))
+	if body := migrationTestBody(t, z.GetObjectNInfo, bucket, "k/b", ""); body != "child" {
+		t.Fatalf("child reads %q", body)
+	}
+}
+
 func TestFreeVersionDecommissionRescansChildren(t *testing.T) {
 	f := newFreeVersionTest(t, "")
 	f.bucket = "free-parent"
@@ -407,6 +428,50 @@ func TestPoolsMigrationPhysicalProgress(t *testing.T) {
 	}
 }
 
+func TestCountAbsentMigrationVersionsToleratesConfiguredOfflineDrives(t *testing.T) {
+	makeDisks := func(offlineCount int, asError bool) []StorageAPI {
+		disks := make([]StorageAPI, 4)
+		for i := range disks {
+			disks[i] = migrationProgressRawDisk{err: errFileNotFound, reads: &atomic.Int32{}}
+		}
+		for i := range offlineCount {
+			if asError {
+				disks[i] = migrationProgressRawDisk{err: errDiskNotFound, reads: &atomic.Int32{}}
+			} else {
+				disks[i] = nil
+			}
+		}
+		return disks
+	}
+	snapshot := []FileInfo{{VersionID: mustGetUUID()}}
+	for _, tc := range []struct {
+		name      string
+		offline   int
+		parity    int
+		asError   bool
+		wantCount int
+		wantErr   bool
+	}{
+		{name: "nil-drive-within-parity", offline: 1, parity: 1, wantCount: 1},
+		{name: "read-error-within-parity", offline: 1, parity: 1, asError: true, wantCount: 1},
+		{name: "half-offline-within-parity", offline: 2, parity: 2, wantCount: 1},
+		{name: "offline-beyond-parity", offline: 2, parity: 1, wantErr: true},
+	} {
+		t.Run(tc.name, func(t *testing.T) {
+			disks := makeDisks(tc.offline, tc.asError)
+			er := erasureObjects{
+				setDriveCount:      len(disks),
+				defaultParityCount: tc.parity,
+				getDisks:           func() []StorageAPI { return disks },
+			}
+			got, err := er.countAbsentMigrationVersions(t.Context(), "bucket", "object", snapshot)
+			if got != tc.wantCount || (err != nil) != tc.wantErr {
+				t.Fatalf("removed=%d err=%v, want %d / error=%t", got, err, tc.wantCount, tc.wantErr)
+			}
+		})
+	}
+}
+
 // A successful quorum deletion can leave one source drive behind. It must not
 // count as physical removal or pass the final check, nor cause a retry loop.
 func TestDecommissionQuorumDeletionIsNotPhysicalProgress(t *testing.T) {
@@ -472,12 +537,20 @@ func TestDecommissionFinalVerificationFailsClosed(t *testing.T) {
 		t.Run(state, func(t *testing.T) {
 			z, bucket := migrationTestPools(t)
 			switch state {
-			case "offline-drive", "directory-error":
+			case "offline-drive":
+				set := z.serverPools[0].getHashedSet("k")
+				maxOffline := set.defaultParityCount + 1
+				wrapped := 0
 				t.Cleanup(conditionalPutSwapDisks(z.serverPools[0], "k", func(d StorageAPI) StorageAPI {
-					if state == "directory-error" {
-						return migrationProgressListFaultDisk{StorageAPI: d}
+					wrapped++
+					if wrapped <= maxOffline {
+						return nil
 					}
-					return nil
+					return d
+				}))
+			case "directory-error":
+				t.Cleanup(conditionalPutSwapDisks(z.serverPools[0], "k", func(d StorageAPI) StorageAPI {
+					return migrationProgressListFaultDisk{StorageAPI: d}
 				}))
 			default:
 				// Real metadata on only one drive, without a readable quorum.