Merge pull request #11924 from tangcong/fix-crc-mismatch

wal: fix crc mismatch crash bug

Author: gyuho

CHANGELOG-3.5.md

@@ -119,6 +119,7 @@ Note that any `etcd_debugging_*` metrics are experimental and subject to change.
   - Previously, server restore fails if it had crashed after persisting raft hard state but before saving snapshot.
   - See https://github.com/etcd-io/etcd/issues/10219 for more.
 - Improve logging around snapshot send and receive.
+- Add [missing CRC checksum check in WAL validate method otherwise causes panic](https://github.com/etcd-io/etcd/pull/11924).
 
 ### Package `embed`
 

wal/wal.go

@@ -567,6 +567,14 @@ func ValidSnapshotEntries(lg *zap.Logger, walDir string) ([]walpb.Snapshot, erro
 			snaps = append(snaps, loadedSnap)
 		case stateType:
 			state = mustUnmarshalState(rec.Data)
+		case crcType:
+			crc := decoder.crc.Sum32()
+			// current crc of decoder must match the crc of the record.
+			// do no need to match 0 crc, since the decoder is a new one at this case.
+			if crc != 0 && rec.Validate(crc) != nil {
+				return nil, ErrCRCMismatch
+			}
+			decoder.updateCRC(rec.Crc)
 		}
 	}
 	// We do not have to read out all the WAL entries

wal/wal_test.go

@@ -1052,3 +1052,60 @@ func TestValidSnapshotEntries(t *testing.T) {
 		t.Errorf("expected walSnaps %+v, got %+v", expected, walSnaps)
 	}
 }
+
+// TestValidSnapshotEntriesAfterPurgeWal ensure that there are many wal files, and after cleaning the first wal file,
+// it can work well.
+func TestValidSnapshotEntriesAfterPurgeWal(t *testing.T) {
+	oldSegmentSizeBytes := SegmentSizeBytes
+	SegmentSizeBytes = 64
+	defer func() {
+		SegmentSizeBytes = oldSegmentSizeBytes
+	}()
+	p, err := ioutil.TempDir(os.TempDir(), "waltest")
+	if err != nil {
+		t.Fatal(err)
+	}
+	defer os.RemoveAll(p)
+	snap0 := walpb.Snapshot{Index: 0, Term: 0}
+	snap1 := walpb.Snapshot{Index: 1, Term: 1}
+	state1 := raftpb.HardState{Commit: 1, Term: 1}
+	snap2 := walpb.Snapshot{Index: 2, Term: 1}
+	snap3 := walpb.Snapshot{Index: 3, Term: 2}
+	state2 := raftpb.HardState{Commit: 3, Term: 2}
+	func() {
+		w, err := Create(zap.NewExample(), p, nil)
+		if err != nil {
+			t.Fatal(err)
+		}
+		defer w.Close()
+
+		// snap0 is implicitly created at index 0, term 0
+		if err = w.SaveSnapshot(snap1); err != nil {
+			t.Fatal(err)
+		}
+		if err = w.Save(state1, nil); err != nil {
+			t.Fatal(err)
+		}
+		if err = w.SaveSnapshot(snap2); err != nil {
+			t.Fatal(err)
+		}
+		if err = w.SaveSnapshot(snap3); err != nil {
+			t.Fatal(err)
+		}
+		for i := 0; i < 128; i++ {
+			if err = w.Save(state2, nil); err != nil {
+				t.Fatal(err)
+			}
+		}
+
+	}()
+	files, _, err := selectWALFiles(nil, p, snap0)
+	if err != nil {
+		t.Fatal(err)
+	}
+	os.Remove(p + "/" + files[0])
+	_, err = ValidSnapshotEntries(zap.NewExample(), p)
+	if err != nil {
+		t.Fatal(err)
+	}
+}