江苏龙网

  1. 主页 > 生活百科 > >

zookeeper源码分析之一服务端启动过程( 六 )

ZooKeeper

调用
/** * load the database from the disk onto memory and also add * the transactions to the committedlog in memory. * @return the last valid zxid on disk * @throws IOException */ public long loadDataBase() throws IOException { PlayBackListener listener=new PlayBackListener(){ public void onTxnLoaded(TxnHeader hdr,Record txn){ Request r = new Request(0, hdr.getCxid(),hdr.getType(), hdr, txn, hdr.getZxid()); addCommittedProposal(r); } }; long zxid = snapLog.restore(dataTree,sessionsWithTimeouts,listener); initialized = true; return zxid; } /** * maintains a list of last <i>committedLog</i> * or so committed requests. This is used for * fast follower synchronization. * @param request committed request */ public void addCommittedProposal(Request request) { WriteLock wl = logLock.writeLock(); try { wl.lock(); if (committedLog.size() > commitLogCount) { committedLog.removeFirst(); minCommittedLog = committedLog.getFirst().packet.getZxid(); } if (committedLog.isEmpty()) { minCommittedLog = request.zxid; maxCommittedLog = request.zxid; } ByteArrayOutputStream baos = new ByteArrayOutputStream(); BinaryOutputArchive boa = BinaryOutputArchive.getArchive(baos); try { request.getHdr().serialize(boa, "hdr"); if (request.getTxn() != null) { request.getTxn().serialize(boa, "txn"); } baos.close(); } catch (IOException e) { LOG.error("This really should be impossible", e); } QuorumPacket pp = new QuorumPacket(Leader.PROPOSAL, request.zxid, baos.toByteArray(), null); Proposal p = new Proposal(); p.packet = pp; p.request = request; committedLog.add(p); maxCommittedLog = p.packet.getZxid(); } finally { wl.unlock(); } }3.2.2 启动NettyServerCnxnFactory绑定服务
@Override public void start() { LOG.info("binding to port " + localAddress); parentChannel = bootstrap.bind(localAddress); }3.2.3 选举算法
synchronized public void startLeaderElection() { try { if (getPeerState() == ServerState.LOOKING) { currentVote = new Vote(myid, getLastLoggedZxid(), getCurrentEpoch()); } } catch(IOException e) { RuntimeException re = new RuntimeException(e.getMessage()); re.setStackTrace(e.getStackTrace()); throw re; } // if (!getView().containsKey(myid)) { // throw new RuntimeException("My id " + myid + " not in the peer list"); //} 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); }调用
@SuppressWarnings("deprecation") 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: qcm = new QuorumCnxManager(this); QuorumCnxManager.Listener listener = qcm.listener; if(listener != null){ listener.start(); FastLeaderElection fle = new FastLeaderElection(this, qcm); fle.start(); le = fle; } else { LOG.error("Null listener when initializing cnx manager"); } break; default: assert false; } return le; }调用选举方法：
/** * Starts a new round of leader election. Whenever our QuorumPeer * changes its state to LOOKING, this method is invoked, and it * sends notifications to all other peers. */ 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 { 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)); 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.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 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; } }


推荐阅读


上一篇：达到物理网卡上限，突然几十万的请求访问Redis的某个key如何解决

下一篇：从底层彻底搞懂String，StringBuilder，StringBuffer的实现