mirror of
https://github.com/etcd-io/etcd.git
synced 2024-09-27 06:25:44 +00:00
3221454cab
Fix https://github.com/coreos/etcd/issues/7470. This patch removes unnecessary term look-up in 'createMergedSnapshotMessage', which can trigger panic if raft entry at etcdProgress.appliedi got compacted by subsequent 'MsgSnap' messages--if a follower is being (in this case, network latency spikes) slow, it could receive subsequent 'MsgSnap' requests from leader. etcd server-side 'applyAll' routine and raft's Ready processing routine becomes asynchronous after raft entries are persisted. And given that raft Ready routine takes less time to finish, it is possible that second 'MsgSnap' is being handled, while the slow 'applyAll' is still processing the first(old) 'MsgSnap'. Then raft Ready routine can compact the log entries at future index to 'applyAll'. That is how 'createMergedSnapshotMessage' tried to look up raft term with outdated etcdProgress.appliedi. Signed-off-by: Gyu-Ho Lee <gyuhox@gmail.com>
69 lines
2.0 KiB
Go
69 lines
2.0 KiB
Go
// Copyright 2015 The etcd Authors
|
|
//
|
|
// Licensed under the Apache License, Version 2.0 (the "License");
|
|
// you may not use this file except in compliance with the License.
|
|
// You may obtain a copy of the License at
|
|
//
|
|
// http://www.apache.org/licenses/LICENSE-2.0
|
|
//
|
|
// Unless required by applicable law or agreed to in writing, software
|
|
// distributed under the License is distributed on an "AS IS" BASIS,
|
|
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
// See the License for the specific language governing permissions and
|
|
// limitations under the License.
|
|
|
|
package etcdserver
|
|
|
|
import (
|
|
"io"
|
|
|
|
"github.com/coreos/etcd/mvcc/backend"
|
|
"github.com/coreos/etcd/raft/raftpb"
|
|
"github.com/coreos/etcd/snap"
|
|
)
|
|
|
|
// createMergedSnapshotMessage creates a snapshot message that contains: raft status (term, conf),
|
|
// a snapshot of v2 store inside raft.Snapshot as []byte, a snapshot of v3 KV in the top level message
|
|
// as ReadCloser.
|
|
func (s *EtcdServer) createMergedSnapshotMessage(m raftpb.Message, snapt, snapi uint64, confState raftpb.ConfState) snap.Message {
|
|
// get a snapshot of v2 store as []byte
|
|
clone := s.store.Clone()
|
|
d, err := clone.SaveNoCopy()
|
|
if err != nil {
|
|
plog.Panicf("store save should never fail: %v", err)
|
|
}
|
|
|
|
// commit kv to write metadata(for example: consistent index).
|
|
s.KV().Commit()
|
|
dbsnap := s.be.Snapshot()
|
|
// get a snapshot of v3 KV as readCloser
|
|
rc := newSnapshotReaderCloser(dbsnap)
|
|
|
|
// put the []byte snapshot of store into raft snapshot and return the merged snapshot with
|
|
// KV readCloser snapshot.
|
|
snapshot := raftpb.Snapshot{
|
|
Metadata: raftpb.SnapshotMetadata{
|
|
Index: snapi,
|
|
Term: snapt,
|
|
ConfState: confState,
|
|
},
|
|
Data: d,
|
|
}
|
|
m.Snapshot = snapshot
|
|
|
|
return *snap.NewMessage(m, rc, dbsnap.Size())
|
|
}
|
|
|
|
func newSnapshotReaderCloser(snapshot backend.Snapshot) io.ReadCloser {
|
|
pr, pw := io.Pipe()
|
|
go func() {
|
|
n, err := snapshot.WriteTo(pw)
|
|
if err == nil {
|
|
plog.Infof("wrote database snapshot out [total bytes: %d]", n)
|
|
}
|
|
pw.CloseWithError(err)
|
|
snapshot.Close()
|
|
}()
|
|
return pr
|
|
}
|