Spark源码分析6-Worker

Worker 主要负责管理excutor和driver，并向master报告excutor和driver的状态

Worker的启动

类似于master，创建了worker的actor

 

private[spark] object Worker {

  def main(argStrings: Array[String]) {
    val args = new WorkerArguments(argStrings)
    val (actorSystem, _) = startSystemAndActor(args.host, args.port, args.webUiPort, args.cores,
      args.memory, args.masters, args.workDir)
    actorSystem.awaitTermination()
  }

  def startSystemAndActor(host: String, port: Int, webUiPort: Int, cores: Int, memory: Int,
      masterUrls: Array[String], workDir: String, workerNumber: Option[Int] = None)
      : (ActorSystem, Int) =
  {
    // The LocalSparkCluster runs multiple local sparkWorkerX actor systems
    val conf = new SparkConf
    val systemName = "sparkWorker" + workerNumber.map(_.toString).getOrElse("")
    val actorName = "Worker"
    val (actorSystem, boundPort) = AkkaUtils.createActorSystem(systemName, host, port,
      conf = conf)
    actorSystem.actorOf(Props(classOf[Worker], host, boundPort, webUiPort, cores, memory,
      masterUrls, systemName, actorName,  workDir, conf), name = actorName)
    (actorSystem, boundPort)
  }

 worker actor 启动的时候调用PreStart函数，创建了webUI system,调用metricsSystem注册了workerSource，并向master注册worker

  override def preStart() {
    assert(!registered)
    logInfo("Starting Spark worker %s:%d with %d cores, %s RAM".format(
      host, port, cores, Utils.megabytesToString(memory)))
    sparkHome = new File(Option(System.getenv("SPARK_HOME")).getOrElse("."))
    logInfo("Spark home: " + sparkHome)
    createWorkDir()
    webUi = new WorkerWebUI(this, workDir, Some(webUiPort))
    context.system.eventStream.subscribe(self, classOf[RemotingLifecycleEvent])
    webUi.start()
    registerWithMaster()

    metricsSystem.registerSource(workerSource)
    metricsSystem.start()
  }

 worker需要处理的事件

override def receive = {
    case RegisteredWorker(masterUrl, masterWebUiUrl) =>
      logInfo("Successfully registered with master " + masterUrl)
      registered = true
      changeMaster(masterUrl, masterWebUiUrl)
      context.system.scheduler.schedule(0 millis, HEARTBEAT_MILLIS millis, self, SendHeartbeat)

    case SendHeartbeat =>
      masterLock.synchronized {
        if (connected) { master ! Heartbeat(workerId) }
      }

    case MasterChanged(masterUrl, masterWebUiUrl) =>
      logInfo("Master has changed, new master is at " + masterUrl)
      changeMaster(masterUrl, masterWebUiUrl)

      val execs = executors.values.
        map(e => new ExecutorDescription(e.appId, e.execId, e.cores, e.state))
      sender ! WorkerSchedulerStateResponse(workerId, execs.toList, drivers.keys.toSeq)

    case Heartbeat =>
      logInfo(s"Received heartbeat from driver ${sender.path}")

    case RegisterWorkerFailed(message) =>
      if (!registered) {
        logError("Worker registration failed: " + message)
        System.exit(1)
      }

    case LaunchExecutor(masterUrl, appId, execId, appDesc, cores_, memory_, execSparkHome_) =>
      if (masterUrl != activeMasterUrl) {
        logWarning("Invalid Master (" + masterUrl + ") attempted to launch executor.")
      } else {
        logInfo("Asked to launch executor %s/%d for %s".format(appId, execId, appDesc.name))
        // TODO (pwendell): We shuld make sparkHome an Option[String] in
        // ApplicationDescription to be more explicit about this.
        val effectiveSparkHome = Option(execSparkHome_).getOrElse(sparkHome.getAbsolutePath)
        val manager = new ExecutorRunner(appId, execId, appDesc, cores_, memory_,
          self, workerId, host, new File(effectiveSparkHome), workDir, akkaUrl, ExecutorState.RUNNING)
        executors(appId + "/" + execId) = manager
        manager.start()
        coresUsed += cores_
        memoryUsed += memory_
        masterLock.synchronized {
          master ! ExecutorStateChanged(appId, execId, manager.state, None, None)
        }
      }

    case ExecutorStateChanged(appId, execId, state, message, exitStatus) =>
      masterLock.synchronized {
        master ! ExecutorStateChanged(appId, execId, state, message, exitStatus)
      }
      val fullId = appId + "/" + execId
      if (ExecutorState.isFinished(state)) {
        val executor = executors(fullId)
        logInfo("Executor " + fullId + " finished with state " + state +
          message.map(" message " + _).getOrElse("") +
          exitStatus.map(" exitStatus " + _).getOrElse(""))
        executors -= fullId
        finishedExecutors(fullId) = executor
        coresUsed -= executor.cores
        memoryUsed -= executor.memory
      }

    case KillExecutor(masterUrl, appId, execId) =>
      if (masterUrl != activeMasterUrl) {
        logWarning("Invalid Master (" + masterUrl + ") attempted to launch executor " + execId)
      } else {
        val fullId = appId + "/" + execId
        executors.get(fullId) match {
          case Some(executor) =>
            logInfo("Asked to kill executor " + fullId)
            executor.kill()
          case None =>
            logInfo("Asked to kill unknown executor " + fullId)
        }
      }

    case LaunchDriver(driverId, driverDesc) => {
      logInfo(s"Asked to launch driver $driverId")
      val driver = new DriverRunner(driverId, workDir, sparkHome, driverDesc, self, akkaUrl)
      drivers(driverId) = driver
      driver.start()

      coresUsed += driverDesc.cores
      memoryUsed += driverDesc.mem
    }

    case KillDriver(driverId) => {
      logInfo(s"Asked to kill driver $driverId")
      drivers.get(driverId) match {
        case Some(runner) =>
          runner.kill()
        case None =>
          logError(s"Asked to kill unknown driver $driverId")
      }
    }

    case DriverStateChanged(driverId, state, exception) => {
      state match {
        case DriverState.ERROR =>
          logWarning(s"Driver $driverId failed with unrecoverable exception: ${exception.get}")
        case DriverState.FINISHED =>
          logInfo(s"Driver $driverId exited successfully")
        case DriverState.KILLED =>
          logInfo(s"Driver $driverId was killed by user")
      }
      masterLock.synchronized {
        master ! DriverStateChanged(driverId, state, exception)
      }
      val driver = drivers.remove(driverId).get
      finishedDrivers(driverId) = driver
      memoryUsed -= driver.driverDesc.mem
      coresUsed -= driver.driverDesc.cores
    }

    case x: DisassociatedEvent if x.remoteAddress == masterAddress =>
      logInfo(s"$x Disassociated !")
      masterDisconnected()

    case RequestWorkerState => {
      sender ! WorkerStateResponse(host, port, workerId, executors.values.toList,
        finishedExecutors.values.toList, drivers.values.toList,
        finishedDrivers.values.toList, activeMasterUrl, cores, memory,
        coresUsed, memoryUsed, activeMasterWebUiUrl)
    }
  }