zookeeper集群有两种工作状态,一种是恢复状态(选leader状态),一种是广播状态(正常工作状态)。好比公司的管理一样,高层开会后决定职责任务,然后各部门负责人专职专管。
以下代码的循环体就是集群工作的循环状态。可以看到每个机器都会保存自己现在的状态,enum类型参数,总共有四种状态LOOKING, FOLLOWING, LEADING, OBSERVING。这四种状态也就对应四种角色,之前也介绍了机器角色的功能,这里不多说。
以下代码来自QuarumPeer.class 和 FastLeadElection。QuarumPeer是集群启动状态的核心代码。这里先介绍比较核心的 部分。 以下代码是机器工作时候的主循环代码,可以看到在机器保存running的时候,他会不停的根据自己的状态去做该状态应该做的事情。FastLeadElection是当机器处于looking状态时候要做的事情,会同步leader或者和其它机器共同选取leader。
updateThreadName();
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 {
RemotePeerBean rBean = new RemotePeerBean(s);
try {
MBeanRegistry.getInstance().register(rBean, jmxQuorumBean);
jmxRemotePeerBean.put(s.id, rBean);
} 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:
LOG.info("LOOKING");
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, 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();
reconfigFlagClear();
if (shuttingDownLE) {
shuttingDownLE = false;
startLeaderElection();
}
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 {
reconfigFlagClear();
if (shuttingDownLE) {
shuttingDownLE = false;
startLeaderElection();
}
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);
updateServerState();
}
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);
updateServerState();
}
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);
}
updateServerState();
}
break;
}
start_fle = Time.currentElapsedTime();
}
} finally {
LOG.warn("QuorumPeer main thread exited");
MBeanRegistry instance = MBeanRegistry.getInstance();
instance.unregister(jmxQuorumBean);
instance.unregister(jmxLocalPeerBean);
for (RemotePeerBean remotePeerBean : jmxRemotePeerBean.values()) {
instance.unregister(remotePeerBean);
}
jmxQuorumBean = null;
jmxLocalPeerBean = null;
jmxRemotePeerBean = null;
}
}
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 = Time.currentElapsedTime();
}
try {
//准备选举工作
HashMap<Long, Vote> recvset = new HashMap<Long, Vote>();
HashMap<Long, Vote> outofelection = new HashMap<Long, Vote>();
int notTimeout = finalizeWait;
synchronized(this){
logicalclock.incrementAndGet();
updateProposal(getInitId(), getInitLastLoggedZxid(), getPeerEpoch());
}
LOG.info("New election. My id = " + self.getId() +
", proposed zxid=0x" + Long.toHexString(proposedZxid));
//发出通知
sendNotifications();
/*
* Loop in which we exchange notifications until we find a leader
*/
//这个循环一直进行直到找到leader
while ((self.getPeerState() == ServerState.LOOKING) &&
(!stop)){
/*
* Remove next notification from queue, times out after 2 times
* the termination time
*/
//接收其它机器到来的通知
Notification n = recvqueue.poll(notTimeout,
TimeUnit.MILLISECONDS);
/*
* Sends more notifications if haven't received enough.
* Otherwise processes new notification.
*/
if(n == null){
//没有收到反馈就接着发出通知
if(manager.haveDelivered()){
sendNotifications();
} else {
manager.connectAll();
}
/*
* Exponential backoff
*/
int tmpTimeOut = notTimeout*2;
notTimeout = (tmpTimeOut < maxNotificationInterval?
tmpTimeOut : maxNotificationInterval);
LOG.info("Notification time out: " + notTimeout);
} //合法性检验
else if (self.getCurrentAndNextConfigVoters().contains(n.sid)) {
/*
* Only proceed if the vote comes from a replica in the current or next
* voting view.
*/
switch (n.state) {
case LOOKING:
if (getInitLastLoggedZxid() == -1) {
LOG.debug("Ignoring notification as our zxid is -1");
break;
}
if (n.zxid == -1) {
LOG.debug("Ignoring notification from member with -1 zxid" + n.sid);
break;
}
// If notification > current, replace and send messages out
if (n.electionEpoch > logicalclock.get()) {
logicalclock.set(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.get()) {
if(LOG.isDebugEnabled()){
LOG.debug("Notification election epoch is smaller than logicalclock. n.electionEpoch = 0x"
+ Long.toHexString(n.electionEpoch)
+ ", logicalclock=0x" + Long.toHexString(logicalclock.get()));
}
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.get(), 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.get()){
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)) {
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.
* Only peer epoch is used to check that the votes come
* from the same ensemble. This is because there is at
* least one corner case in which the ensemble can be
* created with inconsistent zxid and election epoch
* info. However, given that only one ensemble can be
* running at a single point in time and that each
* epoch is used only once, using only the epoch to
* compare the votes is sufficient.
*
* @see https://issues.apache.org/jira/browse/ZOOKEEPER-1732
*/
outofelection.put(n.sid, new Vote(n.leader,
IGNOREVALUE, IGNOREVALUE, n.peerEpoch, n.state));
if (termPredicate(outofelection, new Vote(n.leader,
IGNOREVALUE, IGNOREVALUE, n.peerEpoch, n.state))
&& checkLeader(outofelection, n.leader, IGNOREVALUE)) {
synchronized(this){
logicalclock.set(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;
}
}
英文注释写的比较清晰,不太需要加注释了。接下来会关注QuorumPeer的对外服务,以及机器间通信相关代码