Spark源码解读(3)——从集群启动到Job提交

1，Master启动

Master启动过程主要做了两件事：

1）启动一个守护线程定时对Worker的TimeOut进行Check，默认TimeOut时间为60s

    checkForWorkerTimeOutTask = forwardMessageThread.scheduleAtFixedRate(new Runnable {
      override def run(): Unit = Utils.tryLogNonFatalError {
        self.send(CheckForWorkerTimeOut)
      }
    }, 0, WORKER_TIMEOUT_MS, TimeUnit.MILLISECONDS)

    case CheckForWorkerTimeOut => {
      timeOutDeadWorkers()
    }

  /** Check for, and remove, any timed-out workers */
  private def timeOutDeadWorkers() {
    // Copy the workers into an array so we don't modify the hashset while iterating through it
    val currentTime = System.currentTimeMillis()
    val toRemove = workers.filter(_.lastHeartbeat < currentTime - WORKER_TIMEOUT_MS).toArray
    for (worker <- toRemove) {
      if (worker.state != WorkerState.DEAD) {
        logWarning("Removing %s because we got no heartbeat in %d seconds".format(
          worker.id, WORKER_TIMEOUT_MS / 1000))
        removeWorker(worker)
      } else {
        if (worker.lastHeartbeat < currentTime - ((REAPER_ITERATIONS + 1) * WORKER_TIMEOUT_MS)) {
          workers -= worker // we've seen this DEAD worker in the UI, etc. for long enough; cull it
        }
      }
    }
  }

  private def removeWorker(worker: WorkerInfo) {
    logInfo("Removing worker " + worker.id + " on " + worker.host + ":" + worker.port)
    worker.setState(WorkerState.DEAD)
    idToWorker -= worker.id
    addressToWorker -= worker.endpoint.address
    for (exec <- worker.executors.values) {
      logInfo("Telling app of lost executor: " + exec.id)
      exec.application.driver.send(ExecutorUpdated(
        exec.id, ExecutorState.LOST, Some("worker lost"), None))
      exec.application.removeExecutor(exec)
    }
    for (driver <- worker.drivers.values) {
      if (driver.desc.supervise) {
        logInfo(s"Re-launching ${driver.id}")
        relaunchDriver(driver)
      } else {
        logInfo(s"Not re-launching ${driver.id} because it was not supervised")
        removeDriver(driver.id, DriverState.ERROR, None)
      }
    }
    persistenceEngine.removeWorker(worker)
  }

当Master发现Worker心跳超时，则将白Worker移除，如果该Worker上有Executor运行，则在移除改Executor的同时通知改Executor对应的Driver，如果该Worker上运行着Driver，则需要判断该Driver是否处于监视状态，以决定是否重启。

2）选主

    val (persistenceEngine_, leaderElectionAgent_) = RECOVERY_MODE match {
      case "ZOOKEEPER" =>
        logInfo("Persisting recovery state to ZooKeeper")
        val zkFactory =
          new ZooKeeperRecoveryModeFactory(conf, serializer)
        (zkFactory.createPersistenceEngine(), zkFactory.createLeaderElectionAgent(this))
      case "FILESYSTEM" =>
        val fsFactory =
          new FileSystemRecoveryModeFactory(conf, serializer)
        (fsFactory.createPersistenceEngine(), fsFactory.createLeaderElectionAgent(this))
      case "CUSTOM" =>
        val clazz = Utils.classForName(conf.get("spark.deploy.recoveryMode.factory"))
        val factory = clazz.getConstructor(classOf[SparkConf], classOf[Serializer])
          .newInstance(conf, serializer)
          .asInstanceOf[StandaloneRecoveryModeFactory]
        (factory.createPersistenceEngine(), factory.createLeaderElectionAgent(this))
      case _ =>
        (new BlackHolePersistenceEngine(), new MonarchyLeaderAgent(this))
    }

通常使用Zookeeper模式

关于选主这里便有以下几种情况：

1）第一次启动，其中一个Master当选主

2）检测到当前处于Active的Master宕机，处于Standby状态的Master当选为主

3）处于Active状态的Master发现自己不再是Active

第一种情况最为简单，第二种情况需要从持久化引擎中读取状态，恢复到内存，第三种情况则直接选择主动宕机。

    case ElectedLeader => {
      val (storedApps, storedDrivers, storedWorkers) = persistenceEngine.readPersistedData(rpcEnv)
      state = if (storedApps.isEmpty && storedDrivers.isEmpty && storedWorkers.isEmpty) {
        RecoveryState.ALIVE
      } else {
        RecoveryState.RECOVERING
      }
      logInfo("I have been elected leader! New state: " + state)
      if (state == RecoveryState.RECOVERING) {
        beginRecovery(storedApps, storedDrivers, storedWorkers)
        recoveryCompletionTask = forwardMessageThread.schedule(new Runnable {
          override def run(): Unit = Utils.tryLogNonFatalError {
            self.send(CompleteRecovery)
          }
        }, WORKER_TIMEOUT_MS, TimeUnit