zookeeper选举代码分析
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;
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 | 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;
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 | protected boolean termPredicate( HashMap<Long, Vote> votes, Vote vote) { HashSet<Long> set = new HashSet<Long>(); /* * First make the views consistent. Sometimes peers will have * different zxids for a server depending on timing. */ for (Map.Entry<Long,Vote> entry : votes.entrySet()) { if (vote.equals(entry.getValue())){ set.add(entry.getKey()); } } return self.getQuorumVerifier().containsQuorum(set); } public boolean containsQuorum(HashSet<Long> 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:
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 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 | 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++; 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 ; } } |
【推荐】国内首个AI IDE,深度理解中文开发场景,立即下载体验Trae
【推荐】编程新体验,更懂你的AI,立即体验豆包MarsCode编程助手
【推荐】抖音旗下AI助手豆包,你的智能百科全书,全免费不限次数
【推荐】轻量又高性能的 SSH 工具 IShell:AI 加持,快人一步
· 如何编写易于单元测试的代码
· 10年+ .NET Coder 心语,封装的思维:从隐藏、稳定开始理解其本质意义
· .NET Core 中如何实现缓存的预热?
· 从 HTTP 原因短语缺失研究 HTTP/2 和 HTTP/3 的设计差异
· AI与.NET技术实操系列:向量存储与相似性搜索在 .NET 中的实现
· 周边上新:园子的第一款马克杯温暖上架
· Open-Sora 2.0 重磅开源!
· 分享 3 个 .NET 开源的文件压缩处理库,助力快速实现文件压缩解压功能!
· Ollama——大语言模型本地部署的极速利器
· DeepSeek如何颠覆传统软件测试?测试工程师会被淘汰吗?