2021SC@SDUSC

目录

• 回顾
• 源码分析
• 总结

回顾

上次分析到了初始化一个leader对象，表示leader 节点的请求处理服务。

源码分析

开启线程用于接收 follower 的连接请求
如果超过半数的节点 follower 发送了ack；此时说明过半的 follower 节点已经完成数据同步
使用startZkServer()方法开启zookeeper

    void lead() throws IOException, InterruptedException {
        self.end_fle = Time.currentElapsedTime();
        long electionTimeTaken = self.end_fle - self.start_fle;
        self.setElectionTimeTaken(electionTimeTaken);
        LOG.info("LEADING - LEADER ELECTION TOOK - {}", electionTimeTaken);
        self.start_fle = 0;
        self.end_fle = 0;

        zk.registerJMX(new LeaderBean(this, zk), self.jmxLocalPeerBean);

        try {
            self.tick.set(0);
            zk.loadData();
            
            leaderStateSummary = new StateSummary(self.getCurrentEpoch(), zk.getLastProcessedZxid());

            // Start thread that waits for connection requests from 
            // new followers.
            cnxAcceptor = new LearnerCnxAcceptor();
            cnxAcceptor.start();
            
            readyToStart = true;
            long epoch = getEpochToPropose(self.getId(), self.getAcceptedEpoch());
            
            zk.setZxid(ZxidUtils.makeZxid(epoch, 0));
            
            synchronized(this){
                lastProposed = zk.getZxid();
            }
            
            newLeaderProposal.packet = new QuorumPacket(NEWLEADER, zk.getZxid(),
                    null, null);


            if ((newLeaderProposal.packet.getZxid() & 0xffffffffL) != 0) {
                LOG.info("NEWLEADER proposal has Zxid of "
                        + Long.toHexString(newLeaderProposal.packet.getZxid()));
            }
            
            waitForEpochAck(self.getId(), leaderStateSummary);
            self.setCurrentEpoch(epoch);

            // We have to get at least a majority of servers in sync with
            // us. We do this by waiting for the NEWLEADER packet to get
            // acknowledged
            try {
                waitForNewLeaderAck(self.getId(), zk.getZxid());
            } catch (InterruptedException e) {
                shutdown("Waiting for a quorum of followers, only synced with sids: [ "
                        + getSidSetString(newLeaderProposal.ackSet) + " ]");
                HashSet<Long> followerSet = new HashSet<Long>();
                for (LearnerHandler f : learners)
                    followerSet.add(f.getSid());
                    
                if (self.getQuorumVerifier().containsQuorum(followerSet)) {
                    LOG.warn("Enough followers present. "
                            + "Perhaps the initTicks need to be increased.");
                }
                Thread.sleep(self.tickTime);
                self.tick.incrementAndGet();
                return;
            }
                        
            startZkServer();

数据同步完成后和进行while循环以和leader进行信息交流

                syncWithLeader(newEpochZxid);                
                QuorumPacket qp = new QuorumPacket();
                while (this.isRunning()) {
                    readPacket(qp);
                    processPacket(qp);
                }

进行广播
通知集群中的全部节点提交事务以完成数据一致性

                case Leader.REQUEST:                    
                    bb = ByteBuffer.wrap(qp.getData());
                    sessionId = bb.getLong();
                    cxid = bb.getInt();
                    type = bb.getInt();
                    bb = bb.slice();
                    Request si;
                    if(type == OpCode.sync){
                        si = new LearnerSyncRequest(this, sessionId, cxid, type, bb, qp.getAuthinfo());
                    } else {
                        si = new Request(null, sessionId, cxid, type, bb, qp.getAuthinfo());
                    }
                    si.setOwner(this);
                    leader.zk.submitRequest(si);
                    break;
                default:
                    LOG.warn("unexpected quorum packet, type: {}", packetToString(qp));
                    break;
                }

总结

至此，
通过发现-同步-广播这三个阶段之后
Zab协议的数据恢复阶段完成。