Gossip协议是什么

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26

// Schedule is used to ensure the Tick is performed periodically. This
// function is safe to call multiple times. If the memberlist is already
// scheduled, then it won't do anything.
func (m *Memberlist) schedule() {
	m.tickerLock.Lock()
	defer m.tickerLock.Unlock()

	// 创建probe goroutine
	if m.config.ProbeInterval > 0 {
		t := time.NewTicker(m.config.ProbeInterval)
		go m.triggerFunc(m.config.ProbeInterval, t.C, stopCh, m.probe)
		m.tickers = append(m.tickers, t)
	}

	// 创建push/pull goroutine
	if m.config.PushPullInterval > 0 {
		go m.pushPullTrigger(stopCh)
	}

	// 创建gossip goroutine
	if m.config.GossipInterval > 0 && m.config.GossipNodes > 0 {
		t := time.NewTicker(m.config.GossipInterval)
		go m.triggerFunc(m.config.GossipInterval, t.C, stopCh, m.gossip)
		m.tickers = append(m.tickers, t)
	}
}

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87

HANDLE_REMOTE_FAILURE:
	// Get some random live nodes.
	m.nodeLock.RLock()
	kNodes := kRandomNodes(m.config.IndirectChecks, m.nodes, func(n *nodeState) bool {
		return n.Name == m.config.Name ||
			n.Name == node.Name ||
			n.State != StateAlive
	})
	m.nodeLock.RUnlock()

	// Attempt an indirect ping.
	expectedNacks := 0
	selfAddr, selfPort = m.getAdvertise()
	ind := indirectPingReq{
		SeqNo:      ping.SeqNo,
		Target:     node.Addr,
		Port:       node.Port,
		Node:       node.Name,
		SourceAddr: selfAddr,
		SourcePort: selfPort,
		SourceNode: m.config.Name,
	}
	for _, peer := range kNodes {
		// We only expect nack to be sent from peers who understand
		// version 4 of the protocol.
		if ind.Nack = peer.PMax >= 4; ind.Nack {
			expectedNacks++
		}

		if err := m.encodeAndSendMsg(peer.FullAddress(), indirectPingMsg, &ind); err != nil {
			m.logger.Printf("[ERR] memberlist: Failed to send indirect ping: %s", err)
		}
	}

	// Also make an attempt to contact the node directly over TCP. This
	// helps prevent confused clients who get isolated from UDP traffic
	// but can still speak TCP (which also means they can possibly report
	// misinformation to other nodes via anti-entropy), avoiding flapping in
	// the cluster.
	//
	// This is a little unusual because we will attempt a TCP ping to any
	// member who understands version 3 of the protocol, regardless of
	// which protocol version we are speaking. That's why we've included a
	// config option to turn this off if desired.
	fallbackCh := make(chan bool, 1)

	// Wait for the acks or timeout. Note that we don't check the fallback
	// channel here because we want to issue a warning below if that's the
	// *only* way we hear back from the peer, so we have to let this time
	// out first to allow the normal UDP-based acks to come in.
	select {
	case v := <-ackCh:
		if v.Complete == true {
			return
		}
	}

	// Finally, poll the fallback channel. The timeouts are set such that
	// the channel will have something or be closed without having to wait
	// any additional time here.
	for didContact := range fallbackCh {
		if didContact {
			m.logger.Printf("[WARN] memberlist: Was able to connect to %s but other probes failed, network may be misconfigured", node.Name)
			return
		}
	}

	// Update our self-awareness based on the results of this failed probe.
	// If we don't have peers who will send nacks then we penalize for any
	// failed probe as a simple health metric. If we do have peers to nack
	// verify, then we can use that as a more sophisticated measure of self-
	// health because we assume them to be working, and they can help us
	// decide if the probed node was really dead or if it was something wrong
	// with ourselves.
	awarenessDelta = 0
	if expectedNacks > 0 {
		if nackCount := len(nackCh); nackCount < expectedNacks {
			awarenessDelta += (expectedNacks - nackCount)
		}
	} else {
		awarenessDelta += 1
	}

	// No acks received from target, suspect it as failed.
	m.logger.Printf("[INFO] memberlist: Suspect %s has failed, no acks received", node.Name)
	s := suspect{Incarnation: node.Incarnation, Node: node.Name, From: m.config.Name}
	m.suspectNode(&s)

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45

// gossip is invoked every GossipInterval period to broadcast our gossip
// messages to a few random nodes.
func (m *Memberlist) gossip() {
	// Get some random live, suspect, or recently dead nodes
	m.nodeLock.RLock()
	kNodes := kRandomNodes(m.config.GossipNodes, m.nodes, func(n *nodeState) bool {
		if n.Name == m.config.Name {
			return true
		}

		switch n.State {
		case StateAlive, StateSuspect:
			return false

		case StateDead:
			return time.Since(n.StateChange) > m.config.GossipToTheDeadTime

		default:
			return true
		}
	})
	m.nodeLock.RUnlock()

	for _, node := range kNodes {
		// Get any pending broadcasts
		msgs := m.getBroadcasts(compoundOverhead, bytesAvail)
		if len(msgs) == 0 {
			return
		}

		addr := node.Address()
		if len(msgs) == 1 {
			// Send single message as is
			if err := m.rawSendMsgPacket(node.FullAddress(), &node.Node, msgs[0]); err != nil {
				m.logger.Printf("[ERR] memberlist: Failed to send gossip to %s: %s", addr, err)
			}
		} else {
			// Otherwise create and send a compound message
			compound := makeCompoundMessage(msgs)
			if err := m.rawSendMsgPacket(node.FullAddress(), &node.Node, compound.Bytes()); err != nil {
				m.logger.Printf("[ERR] memberlist: Failed to send gossip to %s: %s", addr, err)
			}
		}
	}
}

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25

// pushPull is invoked periodically to randomly perform a complete state
// exchange. Used to ensure a high level of convergence, but is also
// reasonably expensive as the entire state of this node is exchanged
// with the other node.
func (m *Memberlist) pushPull() {
	// Get a random live node
	m.nodeLock.RLock()
  // 随机抽取一个Alive的Node进行pushPull
	nodes := kRandomNodes(1, m.nodes, func(n *nodeState) bool {
		return n.Name == m.config.Name ||
			n.State != StateAlive
	})
	m.nodeLock.RUnlock()

	// If no nodes, bail
	if len(nodes) == 0 {
		return
	}
	node := nodes[0]

	// Attempt a push pull
	if err := m.pushPullNode(node.FullAddress(), false); err != nil {
		m.logger.Printf("[ERR] memberlist: Push/Pull with %s failed: %s", node.Name, err)
	}
}

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15

// pushPullNode does a complete state exchange with a specific node.
func (m *Memberlist) pushPullNode(a Address, join bool) error {
	defer metrics.MeasureSince([]string{"memberlist", "pushPullNode"}, time.Now())

	// 发送自己的状态信息并获取目标Node的状态信息
	remote, userState, err := m.sendAndReceiveState(a, join)
	if err != nil {
		return err
	}
  // 合并状态信息
	if err := m.mergeRemoteState(join, remote, userState); err != nil {
		return err
	}
	return nil
}