深入浅出etcd/raft —— 0x01 raftexample

func (h *httpKVAPI) ServeHTTP(w http.ResponseWriter, r *http.Request) {
	//... ...
	switch {
	case r.Method == "PUT":
		// ... ...
		h.store.Propose(key, string(v))    
		// ... ...
	case r.Method == "GET":
		if v, ok := h.store.Lookup(key); ok {
			// ... ...
		}
		// ... ...
	case r.Method == "POST":
		url, err := ioutil.ReadAll(r.Body)
		// ... ...
		cc := raftpb.ConfChange{
			Type:    raftpb.ConfChangeAddNode,
			NodeID:  nodeId,
			Context: url,
		}
		h.confChangeC <- cc
		// ... ...
	case r.Method == "DELETE":
		// ... ...
		cc := raftpb.ConfChange{
			Type:   raftpb.ConfChangeRemoveNode,
			NodeID: nodeId,
		}
		h.confChangeC <- cc
		// ... ...
	default:
		// ... ...
	}
}

// a key-value store backed by raft
type kvstore struct {
	proposeC    chan<- string // channel for proposing updates
	mu          sync.RWMutex
	kvStore     map[string]string // current committed key-value pairs
	snapshotter *snap.Snapshotter
}

func newKVStore(snapshotter *snap.Snapshotter, proposeC chan<- string, commitC <-chan *string, errorC <-chan error) *kvstore {
	s := &kvstore{proposeC: proposeC, kvStore: make(map[string]string), snapshotter: snapshotter}
	// replay log into key-value map
	s.readCommits(commitC, errorC)
	// read commits from raft into kvStore map until error
	go s.readCommits(commitC, errorC)
	return s
}

func (s *kvstore) Lookup(key string) (string, bool) {
	s.mu.RLock()
	defer s.mu.RUnlock()
	v, ok := s.kvStore[key]
	return v, ok
}

func (s *kvstore) Propose(k string, v string) {
	var buf bytes.Buffer
	if err := gob.NewEncoder(&buf).Encode(kv{k, v}); err != nil {
		log.Fatal(err)
	}
	s.proposeC <- buf.String()
}

func (s *kvstore) getSnapshot() ([]byte, error) {
	s.mu.RLock()
	defer s.mu.RUnlock()
	return json.Marshal(s.kvStore)
}

func (s *kvstore) recoverFromSnapshot(snapshot []byte) error {
	var store map[string]string
	if err := json.Unmarshal(snapshot, &store); err != nil {
		return err
	}
	s.mu.Lock()
	defer s.mu.Unlock()
	s.kvStore = store
	return nil
}

func (s *kvstore) readCommits(commitC <-chan *string, errorC <-chan error) {
	for data := range commitC {
		if data == nil {
			// done replaying log; new data incoming
			// OR signaled to load snapshot
			snapshot, err := s.snapshotter.Load()
			if err == snap.ErrNoSnapshot {
				return
			}
			if err != nil {
				log.Panic(err)
			}
			log.Printf("loading snapshot at term %d and index %d", snapshot.Metadata.Term, snapshot.Metadata.Index)
			if err := s.recoverFromSnapshot(snapshot.Data); err != nil {
				log.Panic(err)
			}
			continue
		}

		var dataKv kv
		dec := gob.NewDecoder(bytes.NewBufferString(*data))
		if err := dec.Decode(&dataKv); err != nil {
			log.Fatalf("raftexample: could not decode message (%v)", err)
		}
		s.mu.Lock()
		s.kvStore[dataKv.Key] = dataKv.Val
		s.mu.Unlock()
	}
	if err, ok := <-errorC; ok {
		log.Fatal(err)
	}
}

// A key-value stream backed by raft
type raftNode struct {
	proposeC    <-chan string            // proposed messages (k,v)
	confChangeC <-chan raftpb.ConfChange // proposed cluster config changes
	commitC     chan<- *string           // entries committed to log (k,v)
	errorC      chan<- error             // errors from raft session

	id          int      // client ID for raft session
	peers       []string // raft peer URLs
	join        bool     // node is joining an existing cluster
	waldir      string   // path to WAL directory
	snapdir     string   // path to snapshot directory
	getSnapshot func() ([]byte, error)
	lastIndex   uint64 // index of log at start

	confState     raftpb.ConfState
	snapshotIndex uint64
	appliedIndex  uint64

	// raft backing for the commit/error channel
	node        raft.Node
	raftStorage *raft.MemoryStorage
	wal         *wal.WAL

	snapshotter      *snap.Snapshotter
	snapshotterReady chan *snap.Snapshotter // signals when snapshotter is ready

	snapCount uint64
	transport *rafthttp.Transport
	stopc     chan struct{} // signals proposal channel closed
	httpstopc chan struct{} // signals http server to shutdown
	httpdonec chan struct{} // signals http server shutdown complete
}

c := make(chan int)

go func(){
  c <- 1 // block until there is a consumer
}()

go func(){
  <- c // block until there is a producer
}

close(c)
msg, ok := <- c // return immediately, msg is a empty value, ok is false

// flag : false -> break loop

for {
  if !flag {
    break
  }
  select {
  case <- c1:
    // ... ...
  case <- c2:
    // ... ...
  }
}

// doneC : chan struct{}

for {
  select {
  case <- doneC:
    break
  case <- c1:
    // ... ...
  case <- c2:
    // ... ...
  }
}

// newRaftNode initiates a raft instance and returns a committed log entry
// channel and error channel. Proposals for log updates are sent over the
// provided the proposal channel. All log entries are replayed over the
// commit channel, followed by a nil message (to indicate the channel is
// current), then new log entries. To shutdown, close proposeC and read errorC.
func newRaftNode(id int, peers []string, join bool, getSnapshot func() ([]byte, error), proposeC <-chan string,
	confChangeC <-chan raftpb.ConfChange) (<-chan *string, <-chan error, <-chan *snap.Snapshotter) {

	commitC := make(chan *string)
	errorC := make(chan error)

	rc := &raftNode{
		proposeC:    proposeC,
		confChangeC: confChangeC,
		commitC:     commitC,
		errorC:      errorC,
		id:          id,
		peers:       peers,
		join:        join,
		waldir:      fmt.Sprintf("raftexample-%d", id),
		snapdir:     fmt.Sprintf("raftexample-%d-snap", id),
		getSnapshot: getSnapshot,
		snapCount:   defaultSnapshotCount,
		stopc:       make(chan struct{}),
		httpstopc:   make(chan struct{}),
		httpdonec:   make(chan struct{}),

		snapshotterReady: make(chan *snap.Snapshotter, 1),
		// rest of structure populated after WAL replay
	}
	go rc.startRaft()
	return commitC, errorC, rc.snapshotterReady
}

func (rc *raftNode) startRaft() {
	if !fileutil.Exist(rc.snapdir) {
		if err := os.Mkdir(rc.snapdir, 0750); err != nil {
			log.Fatalf("raftexample: cannot create dir for snapshot (%v)", err)
		}
	}
	rc.snapshotter = snap.New(zap.NewExample(), rc.snapdir)
	rc.snapshotterReady <- rc.snapshotter

	oldwal := wal.Exist(rc.waldir)
	rc.wal = rc.replayWAL()

	rpeers := make([]raft.Peer, len(rc.peers))
	for i := range rpeers {
		rpeers[i] = raft.Peer{ID: uint64(i + 1)}
	}
	c := &raft.Config{
		ID:                        uint64(rc.id),
		ElectionTick:              10,
		HeartbeatTick:             1,
		Storage:                   rc.raftStorage,
		MaxSizePerMsg:             1024 * 1024,
		MaxInflightMsgs:           256,
		MaxUncommittedEntriesSize: 1 << 30,
	}

	if oldwal {
		rc.node = raft.RestartNode(c)
	} else {
		startPeers := rpeers
		if rc.join {
			startPeers = nil
		}
		rc.node = raft.StartNode(c, startPeers)
	}

	rc.transport = &rafthttp.Transport{
		Logger:      zap.NewExample(),
		ID:          types.ID(rc.id),
		ClusterID:   0x1000,
		Raft:        rc,
		ServerStats: stats.NewServerStats("", ""),
		LeaderStats: stats.NewLeaderStats(zap.NewExample(), strconv.Itoa(rc.id)),
		ErrorC:      make(chan error),
	}

	rc.transport.Start()
	for i := range rc.peers {
		if i+1 != rc.id {
			rc.transport.AddPeer(types.ID(i+1), []string{rc.peers[i]})
		}
	}

	go rc.serveRaft()
	go rc.serveChannels()
}

// replayWAL replays WAL entries into the raft instance.
func (rc *raftNode) replayWAL() *wal.WAL {
	log.Printf("replaying WAL of member %d", rc.id)
	snapshot := rc.loadSnapshot()
	w := rc.openWAL(snapshot)
	_, st, ents, err := w.ReadAll()
	if err != nil {
		log.Fatalf("raftexample: failed to read WAL (%v)", err)
	}
	rc.raftStorage = raft.NewMemoryStorage()
	if snapshot != nil {
		rc.raftStorage.ApplySnapshot(*snapshot)
	}
	rc.raftStorage.SetHardState(st)

	// append to storage so raft starts at the right place in log
	rc.raftStorage.Append(ents)
	// send nil once lastIndex is published so client knows commit channel is current
	if len(ents) > 0 {
		rc.lastIndex = ents[len(ents)-1].Index
	} else {
		rc.commitC <- nil
	}
	return w
}

func (rc *raftNode) serveChannels() {
	snap, err := rc.raftStorage.Snapshot()
	if err != nil {
		panic(err)
	}
	rc.confState = snap.Metadata.ConfState
	rc.snapshotIndex = snap.Metadata.Index
	rc.appliedIndex = snap.Metadata.Index

	defer rc.wal.Close()

	ticker := time.NewTicker(100 * time.Millisecond)
	defer ticker.Stop()

	// ... ...

}

func (rc *raftNode) serveChannels() {

	// ... ...

	// send proposals over raft
	go func() {
		confChangeCount := uint64(0)

		for rc.proposeC != nil && rc.confChangeC != nil {
			select {
			case prop, ok := <-rc.proposeC:
				if !ok {
					rc.proposeC = nil
				} else {
					// blocks until accepted by raft state machine
					rc.node.Propose(context.TODO(), []byte(prop))
				}

			case cc, ok := <-rc.confChangeC:
				if !ok {
					rc.confChangeC = nil
				} else {
					confChangeCount++
					cc.ID = confChangeCount
					rc.node.ProposeConfChange(context.TODO(), cc)
				}
			}
		}
		// client closed channel; shutdown raft if not already
		close(rc.stopc)
	}()

	// ... ...

}

func (rc *raftNode) serveChannels() {

	// ... ...

	// event loop on raft state machine updates
	for {
		select {
		case <-ticker.C:
			rc.node.Tick()

		// store raft entries to wal, then publish over commit channel
		case rd := <-rc.node.Ready():
			rc.wal.Save(rd.HardState, rd.Entries)
			if !raft.IsEmptySnap(rd.Snapshot) {
				rc.saveSnap(rd.Snapshot)
				rc.raftStorage.ApplySnapshot(rd.Snapshot)
				rc.publishSnapshot(rd.Snapshot)
			}
			rc.raftStorage.Append(rd.Entries)
			rc.transport.Send(rd.Messages)
			if ok := rc.publishEntries(rc.entriesToApply(rd.CommittedEntries)); !ok {
				rc.stop()
				return
			}
			rc.maybeTriggerSnapshot()
			rc.node.Advance()

		case err := <-rc.transport.ErrorC:
			rc.writeError(err)
			return

		case <-rc.stopc:
			rc.stop()
			return
		}
	}

	// ... ...

}

// Ready encapsulates the entries and messages that are ready to read,
// be saved to stable storage, committed or sent to other peers.
// All fields in Ready are read-only.
type Ready struct {
	// The current volatile state of a Node.
	// SoftState will be nil if there is no update.
	// It is not required to consume or store SoftState.
	*SoftState

	// The current state of a Node to be saved to stable storage BEFORE
	// Messages are sent.
	// HardState will be equal to empty state if there is no update.
	pb.HardState

	// ReadStates can be used for node to serve linearizable read requests locally
	// when its applied index is greater than the index in ReadState.
	// Note that the readState will be returned when raft receives msgReadIndex.
	// The returned is only valid for the request that requested to read.
	ReadStates []ReadState

	// Entries specifies entries to be saved to stable storage BEFORE
	// Messages are sent.
	Entries []pb.Entry

	// Snapshot specifies the snapshot to be saved to stable storage.
	Snapshot pb.Snapshot

	// CommittedEntries specifies entries to be committed to a
	// store/state-machine. These have previously been committed to stable
	// store.
	CommittedEntries []pb.Entry

	// Messages specifies outbound messages to be sent AFTER Entries are
	// committed to stable storage.
	// If it contains a MsgSnap message, the application MUST report back to raft
	// when the snapshot has been received or has failed by calling ReportSnapshot.
	Messages []pb.Message

	// MustSync indicates whether the HardState and Entries must be synchronously
	// written to disk or if an asynchronous write is permissible.
	MustSync bool
}

// publishEntries writes committed log entries to commit channel and returns
// whether all entries could be published.
func (rc *raftNode) publishEntries(ents []raftpb.Entry) bool {
	for i := range ents {
		switch ents[i].Type {
		case raftpb.EntryNormal:
			if len(ents[i].Data) == 0 {
				// ignore empty messages
				break
			}
			s := string(ents[i].Data)
			select {
			case rc.commitC <- &s:
			case <-rc.stopc:
				return false
			}

		case raftpb.EntryConfChange:
			var cc raftpb.ConfChange
			cc.Unmarshal(ents[i].Data)
			rc.confState = *rc.node.ApplyConfChange(cc)
			switch cc.Type {
			case raftpb.ConfChangeAddNode:
				if len(cc.Context) > 0 {
					rc.transport.AddPeer(types.ID(cc.NodeID), []string{string(cc.Context)})
				}
			case raftpb.ConfChangeRemoveNode:
				if cc.NodeID == uint64(rc.id) {
					log.Println("I've been removed from the cluster! Shutting down.")
					return false
				}
				rc.transport.RemovePeer(types.ID(cc.NodeID))
			}
		}

		// after commit, update appliedIndex
		rc.appliedIndex = ents[i].Index

		// special nil commit to signal replay has finished
		if ents[i].Index == rc.lastIndex {
			select {
			case rc.commitC <- nil:
			case <-rc.stopc:
				return false
			}
		}
	}
	return true
}