// makeRaft returns a Raft and its FSM, with snapshots based in the given dir.
func makeRaft(t *testing.T, dir string) (*raft.Raft, *MockFSM) {
snaps, err := raft.NewFileSnapshotStore(dir, 5, nil)
if err != nil {
t.Fatalf("err: %v", err)
}
fsm := &MockFSM{}
store := raft.NewInmemStore()
addr, trans := raft.NewInmemTransport("")
config := raft.DefaultConfig()
config.LocalID = raft.ServerID(fmt.Sprintf("server-%s", addr))
var members raft.Configuration
members.Servers = append(members.Servers, raft.Server{
Suffrage: raft.Voter,
ID: config.LocalID,
Address: addr,
})
err = raft.BootstrapCluster(config, store, store, snaps, trans, members)
if err != nil {
t.Fatalf("err: %v", err)
}
raft, err := raft.NewRaft(config, fsm, store, store, snaps, trans)
if err != nil {
t.Fatalf("err: %v", err)
}
timeout := time.After(10 * time.Second)
for {
if raft.Leader() != "" {
break
}
select {
case <-raft.LeaderCh():
case <-time.After(1 * time.Second):
// Need to poll because we might have missed the first
// go with the leader channel.
case <-timeout:
t.Fatalf("timed out waiting for leader")
}
}
return raft, fsm
}
// setupRaft is used to setup and initialize Raft
func (s *Server) setupRaft() error {
// If we have an unclean exit then attempt to close the Raft store.
defer func() {
if s.raft == nil && s.raftStore != nil {
if err := s.raftStore.Close(); err != nil {
s.logger.Printf("[ERR] consul: failed to close Raft store: %v", err)
}
}
}()
// Create the FSM.
var err error
s.fsm, err = NewFSM(s.tombstoneGC, s.config.LogOutput)
if err != nil {
return err
}
// Create a transport layer.
trans := raft.NewNetworkTransport(s.raftLayer, 3, 10*time.Second, s.config.LogOutput)
s.raftTransport = trans
// Make sure we set the LogOutput.
s.config.RaftConfig.LogOutput = s.config.LogOutput
// Our version of Raft protocol requires the LocalID to match the network
// address of the transport.
s.config.RaftConfig.LocalID = raft.ServerID(trans.LocalAddr())
// Build an all in-memory setup for dev mode, otherwise prepare a full
// disk-based setup.
var log raft.LogStore
var stable raft.StableStore
var snap raft.SnapshotStore
if s.config.DevMode {
store := raft.NewInmemStore()
s.raftInmem = store
stable = store
log = store
snap = raft.NewInmemSnapshotStore()
} else {
// Create the base raft path.
path := filepath.Join(s.config.DataDir, raftState)
if err := ensurePath(path, true); err != nil {
return err
}
// Create the backend raft store for logs and stable storage.
store, err := raftboltdb.NewBoltStore(filepath.Join(path, "raft.db"))
if err != nil {
return err
}
s.raftStore = store
stable = store
// Wrap the store in a LogCache to improve performance.
cacheStore, err := raft.NewLogCache(raftLogCacheSize, store)
if err != nil {
return err
}
log = cacheStore
// Create the snapshot store.
snapshots, err := raft.NewFileSnapshotStore(path, snapshotsRetained, s.config.LogOutput)
if err != nil {
return err
}
snap = snapshots
// For an existing cluster being upgraded to the new version of
// Raft, we almost never want to run recovery based on the old
// peers.json file. We create a peers.info file with a helpful
// note about where peers.json went, and use that as a sentinel
// to avoid ingesting the old one that first time (if we have to
// create the peers.info file because it's not there, we also
// blow away any existing peers.json file).
peersFile := filepath.Join(path, "peers.json")
peersInfoFile := filepath.Join(path, "peers.info")
if _, err := os.Stat(peersInfoFile); os.IsNotExist(err) {
if err := ioutil.WriteFile(peersInfoFile, []byte(peersInfoContent), 0755); err != nil {
return fmt.Errorf("failed to write peers.info file: %v", err)
}
// Blow away the peers.json file if present, since the
// peers.info sentinel wasn't there.
if _, err := os.Stat(peersFile); err == nil {
if err := os.Remove(peersFile); err != nil {
return fmt.Errorf("failed to delete peers.json, please delete manually (see peers.info for details): %v", err)
}
s.logger.Printf("[INFO] consul: deleted peers.json file (see peers.info for details)")
}
} else if _, err := os.Stat(peersFile); err == nil {
s.logger.Printf("[INFO] consul: found peers.json file, recovering Raft configuration...")
configuration, err := raft.ReadPeersJSON(peersFile)
if err != nil {
return fmt.Errorf("recovery failed to parse peers.json: %v", err)
}
tmpFsm, err := NewFSM(s.tombstoneGC, s.config.LogOutput)
if err != nil {
return fmt.Errorf("recovery failed to make temp FSM: %v", err)
}
if err := raft.RecoverCluster(s.config.RaftConfig, tmpFsm,
log, stable, snap, trans, configuration); err != nil {
return fmt.Errorf("recovery failed: %v", err)
}
if err := os.Remove(peersFile); err != nil {
return fmt.Errorf("recovery failed to delete peers.json, please delete manually (see peers.info for details): %v", err)
}
s.logger.Printf("[INFO] consul: deleted peers.json file after successful recovery")
}
}
// If we are in bootstrap or dev mode and the state is clean then we can
// bootstrap now.
if s.config.Bootstrap || s.config.DevMode {
hasState, err := raft.HasExistingState(log, stable, snap)
if err != nil {
return err
}
if !hasState {
// TODO (slackpad) - This will need to be updated when
// we add support for node IDs.
configuration := raft.Configuration{
Servers: []raft.Server{
raft.Server{
ID: raft.ServerID(trans.LocalAddr()),
Address: trans.LocalAddr(),
},
},
}
if err := raft.BootstrapCluster(s.config.RaftConfig,
log, stable, snap, trans, configuration); err != nil {
return err
}
}
}
// Setup the Raft store.
s.raft, err = raft.NewRaft(s.config.RaftConfig, s.fsm, log, stable, snap, trans)
if err != nil {
return err
}
// Start monitoring leadership.
go s.monitorLeadership()
return nil
}