上一篇：ZooKeeper源码分析（四）Leader选举流程分析
先看一下图，对后面讲解的有一个大致了解
我们上一篇讲这个方法是Leader选举的方法，其实只是做了一个初始化而已，我们这一次就来看一看这个方法；
synchronized public void startLeaderElection() {
try {
/** 构造一轮投票，参数1：myid、参数2：Zxid、参数3：版本号 */
currentVote = new Vote(myid, getLastLoggedZxid(), getCurrentEpoch());
} catch(IOException e) {
RuntimeException re = new RuntimeException(e.getMessage());
re.setStackTrace(e.getStackTrace());
throw re;
}
/** 遍历找到自己的节点信息，并将自己的机器地址保存 */
for (QuorumServer p : getView().values()) {
if (p.id == myid) {
myQuorumAddr = p.addr;
break;
}
}
if (myQuorumAddr == null) {
throw new RuntimeException("My id " + myid + " not in the peer list");
}
/**
* zk本身提供了几种算法，如：0、1、2
* electionType 表示使用哪个选举算法，这个分支已经废弃了，可以不用看
*/
if (electionType == 0) {
try {
udpSocket = new DatagramSocket(myQuorumAddr.getPort());
responder = new ResponderThread();
responder.start();
} catch (SocketException e) {
throw new RuntimeException(e);
}
}
this.electionAlg = createElectionAlgorithm(electionType);
}createElectionAlgorithm方法
protected Election createElectionAlgorithm(int electionAlgorithm){
Election le=null;
//TODO: use a factory rather than a switch
switch (electionAlgorithm) {
case 0:
le = new LeaderElection(this);
break;
case 1:
le = new AuthFastLeaderElection(this);
break;
case 2:
le = new AuthFastLeaderElection(this, true);
break;
case 3:
/** 网络通信组件，用于zk节点之间通信 */
qcm = new QuorumCnxManager(this);
QuorumCnxManager.Listener listener = qcm.listener;
if(listener != null){
/** 启动一个listener，用来监听其他机器发送过来的请求 */
listener.start();
/** 通过这个组件也可以给其他节点发送请求 */
le = new FastLeaderElection(this, qcm);
} else {
LOG.error("Null listener when initializing cnx manager");
}
break;
default:
assert false;
}
return le;
}我们看完之后发现startLeaderElection方法只是对一些值进行了初始化，真正的逻辑还是调用了start方法，启动QuorumPeer这个线程之后才执行；
我们直接来到QuorumPeer的run方法，前面这一段可以不用看，就是初始化jvm的一些类，用来帮助我们观察zk节点的执行情况；
public void run() {
setName("QuorumPeer" + "[myid=" + getId() + "]" +
cnxnFactory.getLocalAddress());
LOG.debug("Starting quorum peer");
try {
jmxQuorumBean = new QuorumBean(this);
MBeanRegistry.getInstance().register(jmxQuorumBean, null);
for(QuorumServer s: getView().values()){
ZKMBeanInfo p;
if (getId() == s.id) {
p = jmxLocalPeerBean = new LocalPeerBean(this);
try {
MBeanRegistry.getInstance().register(p, jmxQuorumBean);
} catch (Exception e) {
LOG.warn("Failed to register with JMX", e);
jmxLocalPeerBean = null;
}
} else {
p = new RemotePeerBean(s);
try {
MBeanRegistry.getInstance().register(p, jmxQuorumBean);
} catch (Exception e) {
LOG.warn("Failed to register with JMX", e);
}
}
}
} catch (Exception e) {
LOG.warn("Failed to register with JMX", e);
jmxQuorumBean = null;
}
try {
/*
* Main loop
*/
while (running) {
switch (getPeerState()) {
case LOOKING:
/**
* 如果节点是刚刚启动状态则为LOOKING，在寻找Leader的过程中
* 如果说没有Leader，此时你就要发起投票给其他节点尝试去选举成为Leader
* 如果有Leader了，此时就将状态修改为follower
*/
LOG.info("LOOKING");
/** 是否启用只读模式 */
if (Boolean.getBoolean("readonlymode.enabled")) {
LOG.info("Attempting to start ReadOnlyZooKeeperServer");
// Create read-only server but don't start it immediately
final ReadOnlyZooKeeperServer roZk = new ReadOnlyZooKeeperServer(
logFactory, this,
new ZooKeeperServer.BasicDataTreeBuilder(),
this.zkDb);
// Instead of starting roZk immediately, wait some grace
// period before we decide we're partitioned.
//
// Thread is used here because otherwise it would require
// changes in each of election strategy classes which is
// unnecessary code coupling.
Thread roZkMgr = new Thread() {
public void run() {
try {
// lower-bound grace period to 2 secs
sleep(Math.max(2000, tickTime));
if (ServerState.LOOKING.equals(getPeerState())) {
roZk.startup();
}
} catch (InterruptedException e) {
LOG.info("Interrupted while attempting to start ReadOnlyZooKeeperServer, not started");
} catch (Exception e) {
LOG.error("FAILED to start ReadOnlyZooKeeperServer", e);
}
}
};
try {
roZkMgr.start();
/**
* 比较关键的是这行代码
* makeLEStrategy方法是获取到之前根据electionType选择出来的选举算法
* lookForLeader方法则是根据相应的选举算法组件选择出来一个Leader
*/
setCurrentVote(makeLEStrategy().lookForLeader());
} catch (Exception e) {
LOG.warn("Unexpected exception",e);
setPeerState(ServerState.LOOKING);
} finally {
// If the thread is in the the grace period, interrupt
// to come out of waiting.
roZkMgr.interrupt();
roZk.shutdown();
}
} else {
try {
setCurrentVote(makeLEStrategy().lookForLeader());
} catch (Exception e) {
LOG.warn("Unexpected exception", e);
setPeerState(ServerState.LOOKING);
}
}
break;
case OBSERVING:
try {
LOG.info("OBSERVING");
setObserver(makeObserver(logFactory));
observer.observeLeader();
} catch (Exception e) {
LOG.warn("Unexpected exception",e );
} finally {
observer.shutdown();
setObserver(null);
setPeerState(ServerState.LOOKING);
}
break;
case FOLLOWING:
try {
LOG.info("FOLLOWING");
setFollower(makeFollower(logFactory));
follower.followLeader();
} catch (Exception e) {
LOG.warn("Unexpected exception",e);
} finally {
follower.shutdown();
setFollower(null);
setPeerState(ServerState.LOOKING);
}
break;
case LEADING:
LOG.info("LEADING");
try {
setLeader(makeLeader(logFactory));
leader.lead();
setLeader(null);
} catch (Exception e) {
LOG.warn("Unexpected exception",e);
} finally {
if (leader != null) {
leader.shutdown("Forcing shutdown");
setLeader(null);
}
setPeerState(ServerState.LOOKING);
}
break;
}
}
} finally {
LOG.warn("QuorumPeer main thread exited");
try {
MBeanRegistry.getInstance().unregisterAll();
} catch (Exception e) {
LOG.warn("Failed to unregister with JMX", e);
}
jmxQuorumBean = null;
jmxLocalPeerBean = null;
}
}FastLeaderElection的lookForLeader方法
public Vote lookForLeader() throws InterruptedException {
try {
self.jmxLeaderElectionBean = new LeaderElectionBean();
MBeanRegistry.getInstance().register(
self.jmxLeaderElectionBean, self.jmxLocalPeerBean);
} catch (Exception e) {
LOG.warn("Failed to register with JMX", e);
self.jmxLeaderElectionBean = null;
}
if (self.start_fle == 0) {
self.start_fle = System.currentTimeMillis();
}
try {
HashMap<Long, Vote> recvset = new HashMap<Long, Vote>();
HashMap<Long, Vote> outofelection = new HashMap<Long, Vote>();
int notTimeout = finalizeWait;
synchronized(this){
logicalclock++;
/** 更新投票信息 */
updateProposal(getInitId(), getInitLastLoggedZxid(), getPeerEpoch());
}
LOG.info("New election. My id = " + self.getId() +
", proposed zxid=0x" + Long.toHexString(proposedZxid));
/** 将自己的投票信息放入sendqueue队列，在由QuorumCnxManager消费投递给其他机器 */
sendNotifications();
/*
* Loop in which we exchange notifications until we find a leader
*/
while ((self.getPeerState() == ServerState.LOOKING) &&
(!stop)){
/*
* Remove next notification from queue, times out after 2 times
* the termination time
*/
/** 通过recvqueue队列接收其他机器发送过来的消息 */
Notification n = recvqueue.poll(notTimeout,
TimeUnit.MILLISECONDS);
/*
* Sends more notifications if haven't received enough.
* Otherwise processes new notification.
*/
if(n == null){
if(manager.haveDelivered()){
sendNotifications();
} else {
manager.connectAll();
}
/*
* Exponential backoff
*/
int tmpTimeOut = notTimeout*2;
notTimeout = (tmpTimeOut < maxNotificationInterval?
tmpTimeOut : maxNotificationInterval);
LOG.info("Notification time out: " + notTimeout);
}
else if(self.getVotingView().containsKey(n.sid)) {
/*
* Only proceed if the vote comes from a replica in the
* voting view.
*/
switch (n.state) {
case LOOKING:
// If notification > current, replace and send messages out
if (n.electionEpoch > logicalclock) {
logicalclock = n.electionEpoch;
recvset.clear();
if(totalOrderPredicate(n.leader, n.zxid, n.peerEpoch,
getInitId(), getInitLastLoggedZxid(), getPeerEpoch())) {
updateProposal(n.leader, n.zxid, n.peerEpoch);
} else {
updateProposal(getInitId(),
getInitLastLoggedZxid(),
getPeerEpoch());
}
sendNotifications();
} else if (n.electionEpoch < logicalclock) {
if(LOG.isDebugEnabled()){
LOG.debug("Notification election epoch is smaller than logicalclock. n.electionEpoch = 0x"
+ Long.toHexString(n.electionEpoch)
+ ", logicalclock=0x" + Long.toHexString(logicalclock));
}
break;
} else if (totalOrderPredicate(n.leader, n.zxid, n.peerEpoch,
proposedLeader, proposedZxid, proposedEpoch)) {
updateProposal(n.leader, n.zxid, n.peerEpoch);
sendNotifications();
}
if(LOG.isDebugEnabled()){
LOG.debug("Adding vote: from=" + n.sid +
", proposed leader=" + n.leader +
", proposed zxid=0x" + Long.toHexString(n.zxid) +
", proposed election epoch=0x" + Long.toHexString(n.electionEpoch));
}
recvset.put(n.sid, new Vote(n.leader, n.zxid, n.electionEpoch, n.peerEpoch));
if (termPredicate(recvset,
new Vote(proposedLeader, proposedZxid,
logicalclock, proposedEpoch))) {
// Verify if there is any change in the proposed leader
while((n = recvqueue.poll(finalizeWait,
TimeUnit.MILLISECONDS)) != null){
if(totalOrderPredicate(n.leader, n.zxid, n.peerEpoch,
proposedLeader, proposedZxid, proposedEpoch)){
recvqueue.put(n);
break;
}
}
/*
* This predicate is true once we don't read any new
* relevant message from the reception queue
*/
if (n == null) {
self.setPeerState((proposedLeader == self.getId()) ?
ServerState.LEADING: learningState());
Vote endVote = new Vote(proposedLeader,
proposedZxid, proposedEpoch);
leaveInstance(endVote);
return endVote;
}
}
break;
case OBSERVING:
LOG.debug("Notification from observer: " + n.sid);
break;
case FOLLOWING:
case LEADING:
/*
* Consider all notifications from the same epoch
* together.
*/
if(n.electionEpoch == logicalclock){
recvset.put(n.sid, new Vote(n.leader, n.zxid, n.electionEpoch, n.peerEpoch));
if(termPredicate(recvset, new Vote(n.leader,
n.zxid, n.electionEpoch, n.peerEpoch, n.state))
&& checkLeader(outofelection, n.leader, n.electionEpoch)) {
/**
* 如果接收到别人发送过来的请求，发现已经有人成为leader了
* 就判断一下leader是否是自己，如果是自己就将自己的状态修改为leader
* 否则就修改为follower或者observer
*/
self.setPeerState((n.leader == self.getId()) ?
ServerState.LEADING: learningState());
Vote endVote = new Vote(n.leader, n.zxid, n.peerEpoch);
leaveInstance(endVote);
return endVote;
}
}
/**
* Before joining an established ensemble, verify that
* a majority are following the same leader.
*/
outofelection.put(n.sid, new Vote(n.leader, n.zxid,
n.electionEpoch, n.peerEpoch, n.state));
if (termPredicate(outofelection, new Vote(n.leader,
n.zxid, n.electionEpoch, n.peerEpoch, n.state))
&& checkLeader(outofelection, n.leader, n.electionEpoch)) {
synchronized(this){
logicalclock = n.electionEpoch;
self.setPeerState((n.leader == self.getId()) ?
ServerState.LEADING: learningState());
}
Vote endVote = new Vote(n.leader, n.zxid, n.peerEpoch);
leaveInstance(endVote);
return endVote;
}
break;
default:
LOG.warn("Notification state unrecoginized: " + n.state
+ " (n.state), " + n.sid + " (n.sid)");
break;
}
} else {
LOG.warn("Ignoring notification from non-cluster member " + n.sid);
}
}
return null;
} finally {
try {
if(self.jmxLeaderElectionBean != null){
MBeanRegistry.getInstance().unregister(
self.jmxLeaderElectionBean);
}
} catch (Exception e) {
LOG.warn("Failed to unregister with JMX", e);
}
self.jmxLeaderElectionBean = null;
}
}