kafka 集群管理-controller是如何选举的

KafkaServer.startup()
kafkaController.startup()
controllerElector.startup -> elect
  def elect: Boolean = {
    val timestamp = SystemTime.milliseconds.toString
    //构建一个数据信息
    //比如有version
    //有自己broker id号
    //有时间戳
    val electString = Json.encode(Map("version" -> 1, "brokerid" -> brokerId, "timestamp" -> timestamp))
    //要去获取controller的 id号。

    //我们用的是场景驱动的方式，此时此刻应该就是我们的第一台服务器
    //第一次启动，那么肯定还没有controller的，所以他这儿应该是获取不到
    //ID
    //如果是第一次启动，那么返回值是-1
    leaderId = getControllerID

    /* 
     * We can get here during the initial startup and the handleDeleted ZK callback. Because of the potential race condition, 
     * it's possible that the controller has already been elected when we get here. This check will prevent the following 
     * createEphemeralPath method from getting into an infinite loop if this broker is already the controller.
     */
    if(leaderId != -1) {
       debug("Broker %d has been elected as leader, so stopping the election process.".format(leaderId))
      //如果代码执行到这儿说明，之前就已经完成选举了。
       return amILeader
    }

    try {
      //创建一个临时目录（如果有同学不知道ZK的临时目录有什么特点，自己下去了解一下）
      // 创建这样的一个目录 /controller/，然后把这个目录里面写上一些自己的信息

      val zkCheckedEphemeral = new ZKCheckedEphemeral(electionPath,
                                                      electString,
                                                      controllerContext.zkUtils.zkConnection.getZookeeper,
                                                      JaasUtils.isZkSecurityEnabled())
      //创建目录
      zkCheckedEphemeral.create()
      info(brokerId + " successfully elected as leader")
      //也就是当前的服务器就是controller服务器了
      leaderId = brokerId
      //如果创建完了，自己就成为了leader ，也就是controller了。

      //这个是一个函数
      //当一个controller被选举出来以后，就会执行这个函数。
      onBecomingLeader()
    }

-> getControllerID
  // /controller/写数据（broker id号）
  private def getControllerID(): Int = {
    //从/controller目录下面去获取数据
    controllerContext.zkUtils.readDataMaybeNull(electionPath)._1 match {
        //如果获取到了数据，那么返回了的应该就是一个ID，这个id号就是某个broker的id号
        //也就是说这个broker 就是controller
       case Some(controller) => KafkaController.parseControllerId(controller)
         //如果获取不到就返回-1
       case None => -1
    }
  }

onBecomingLeader -> ZookeeperLeaderElector
->  private val controllerElector = new ZookeeperLeaderElector(controllerContext, ZkUtils.ControllerPath, onControllerFailover,
  -> onControllerFailover
    def onControllerFailover() {
    if(isRunning) {
      info("Broker %d starting become controller state transition".format(config.brokerId))
      //read controller epoch from zk
      readControllerEpochFromZookeeper()
      // increment the controller epoch
      incrementControllerEpoch(zkUtils.zkClient)

      // before reading source of truth from zookeeper, register the listeners to get broker/topic callbacks
      //这个函数最重要的一个内容，就是注册各种监听器
      //注册这些监听器的目的就是用来监听zk的目录的变化的。
      //这些监听器是谁注册的呢？肯定是controller注册的了。
      //换句话说，我们的一个controller一旦被选举出来以后
      //干的第一个事，就是在ZK上面对各种各样的目录设置的了监听器
      //其实说实话，controller就是通过监听这些目录的变化
      //来管理Kafka集群的。
      registerReassignedPartitionsListener()
      registerIsrChangeNotificationListener()
      registerPreferredReplicaElectionListener()
      //TODO 监听分区的变化
      partitionStateMachine.registerListeners()
      //TODO 我们通过这儿注册了一个监听器，
      //然后通过这个监听器，感知到集群里面有新的broker进来了。
      replicaStateMachine.registerListeners()
      initializeControllerContext()
      replicaStateMachine.startup()
      partitionStateMachine.startup()
      // register the partition change listeners for all existing topics on failover
      controllerContext.allTopics.foreach(topic => partitionStateMachine.registerPartitionChangeListener(topic))
      info("Broker %d is ready to serve as the new controller with epoch %d".format(config.brokerId, epoch))
      maybeTriggerPartitionReassignment()
      maybeTriggerPreferredReplicaElection()
      /* send partition leadership info to all live brokers */
      sendUpdateMetadataRequest(controllerContext.liveOrShuttingDownBrokerIds.toSeq)
      if (config.autoLeaderRebalanceEnable) {
        info("starting the partition rebalance scheduler")
        autoRebalanceScheduler.startup()
        autoRebalanceScheduler.schedule("partition-rebalance-thread", checkAndTriggerPartitionRebalance,
          5, config.leaderImbalanceCheckIntervalSeconds.toLong, TimeUnit.SECONDS)
      }
      deleteTopicManager.start()
    }
    else
      info("Controller has been shut down, aborting startup/failover")
  }