本文将以zookeeper的3.4.6版本作为源码分析版本。主要的代码类包括QuorumPeerMain、QuorumPeer、FastLeaderElection、QuorumMaj等。
假设有a,b,c三个zookeeper服务，serverid分别是1、2、3：
1.先启动集群中的a服务，先投票自己a为leader，并将投票信息发送给自己;
QuorumPeerMain对象调用QuorumPeer线程的startLeaderElection方法，最终调用FastLeaderElection的lookForLeader方法
2.再启动集群中的b服务，先投票自己b为leader，并将投票信息发送给自己和a服务；
3.a收到b的投票信息，服务a通过对比算法，选择b为leader，并通知自己和服务b;
protected boolean totalOrderPredicate(long newId, long newZxid, long newEpoch, long curId, long curZxid, long curEpoch) {
LOG.debug("id: " + newId + ", proposed id: " + curId + ", zxid: 0x" +
Long.toHexString(newZxid) + ", proposed zxid: 0x" + Long.toHexString(curZxid));
if(self.getQuorumVerifier().getWeight(newId) == 0){
return false;
}
/*
* We return true if one of the following three cases hold:
* 1- New epoch is higher
* 2- New epoch is the same as current epoch, but new zxid is higher
* 3- New epoch is the same as current epoch, new zxid is the same
* as current zxid, but server id is higher.
*/
return ((newEpoch > curEpoch) ||
((newEpoch == curEpoch) &&
((newZxid > curZxid) || ((newZxid == curZxid) && (newId > curId)))));
}4.服务a通过验证算法，确认b为leader;
5.服务b收到a的通知信息，通过验证算法b确认自身为leader；
protected boolean termPredicate(
HashMap votes,
Vote vote) {
HashSet set = new HashSet();
/*
* First make the views consistent. Sometimes peers will have
* different zxids for a server depending on timing.
*/
for (Map.Entry entry : votes.entrySet()) {
if (vote.equals(entry.getValue())){
set.add(entry.getKey());
}
}
return self.getQuorumVerifier().containsQuorum(set);
}
public boolean containsQuorum(HashSet set){
return (set.size() > half);
}
6.服务c启动后，发现集群已经选出leader为服务b;
7.下面的代码是选举过程中最重要的代码：
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 recvset = new HashMap();
HashMap outofelection = new HashMap();
int notTimeout = finalizeWait;
synchronized(this){
logicalclock++;
updateProposal(getInitId(), getInitLastLoggedZxid(), getPeerEpoch());
}
LOG.info("New election. My id = " + self.getId() +
", proposed zxid=0x" + Long.toHexString(proposedZxid));
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
*/
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:
System.out.println("receive message : electionEpoch,logicalclock"+n.electionEpoch+":"+logicalclock);
// 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,
logicalclock,
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(ooePredicate(recvset, outofelection, n)) {
self.setPeerState((n.leader == self.getId()) ?
ServerState.LEADING: learningState());
Vote endVote = new Vote(n.leader,
n.zxid,
n.electionEpoch,
n.peerEpoch);
leaveInstance(endVote);
return endVote;
}
}
/*
* Before joining an established ensemble, verify
* a majority is following the same leader.
*/
outofelection.put(n.sid, new Vote(n.version,
n.leader,
n.zxid,
n.electionEpoch,
n.peerEpoch,
n.state));
if(ooePredicate(outofelection, outofelection, n)) {
synchronized(this){
logicalclock = n.electionEpoch;
self.setPeerState((n.leader == self.getId()) ?
ServerState.LEADING: learningState());
}
Vote endVote = new Vote(n.leader,
n.zxid,
n.electionEpoch,
n.peerEpoch);
leaveInstance(endVote);
return endVote;
}
break;
default:
LOG.warn("Notification state unrecognized: {} (n.state), {} (n.sid)",
n.state, 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;
}
}