spark 1.6.0 core源码分析2 master启动流程

源码位置：org.apache.spark.deploy.master.Master.scala

def main(argStrings: Array[String]) {
    SignalLogger.register(log)
    val conf = new SparkConf
    val args = new MasterArguments(argStrings, conf)
    val (rpcEnv, _, _) = startRpcEnvAndEndpoint(args.host, args.port, args.webUiPort, conf)
    rpcEnv.awaitTermination()
  }

  /**
   * Start the Master and return a three tuple of:
   *   (1) The Master RpcEnv
   *   (2) The web UI bound port
   *   (3) The REST server bound port, if any
   */
  def startRpcEnvAndEndpoint(
      host: String,
      port: Int,
      webUiPort: Int,
      conf: SparkConf): (RpcEnv, Int, Option[Int]) = {
    val securityMgr = new SecurityManager(conf)
    val rpcEnv =<strong> RpcEnv.create</strong>(SYSTEM_NAME, host, port, conf, securityMgr)
    val masterEndpoint = rpcEnv.setupEndpoint(ENDPOINT_NAME,
      <strong>new Master(rpcEnv, rpcEnv.address, webUiPort, securityMgr, conf)</strong>)//启动8080端口服务
    val portsResponse = masterEndpoint.askWithRetry[BoundPortsResponse](BoundPortsRequest)
    (rpcEnv, portsResponse.webUIPort, portsResponse.restPort)
  }

创建 RpcEnv 默认使用netty通信

private def getRpcEnvFactory(conf: SparkConf): RpcEnvFactory = {
    val rpcEnvNames = Map(
      "akka" -> "org.apache.spark.rpc.akka.AkkaRpcEnvFactory",
      "netty" -> "org.apache.spark.rpc.netty.NettyRpcEnvFactory")
    val rpcEnvName = conf.get("spark.rpc", "netty")
    val rpcEnvFactoryClassName = rpcEnvNames.getOrElse(rpcEnvName.toLowerCase, rpcEnvName)
    Utils.classForName(rpcEnvFactoryClassName).newInstance().asInstanceOf[RpcEnvFactory]
  }

  def create(
      name: String,
      host: String,
      port: Int,
      conf: SparkConf,
      securityManager: SecurityManager,
      clientMode: Boolean = false): RpcEnv = {
    // Using Reflection to create the RpcEnv to avoid to depend on Akka directly
    val config = RpcEnvConfig(conf, name, host, port, securityManager, clientMode)
    getRpcEnvFactory(conf).create(config)
  }

解析spark相关的环境变量及方法参数，创建RpcEnvFactory用于与其它节点的交互，以前版本是akka，spark 1.6.0使用netty，可通过spark-default.xml 配置
spark.rpc 设置使用akka还是netty，启动一个netty NettyRpcEndpointRef

private[netty] class NettyRpcEnvFactory extends RpcEnvFactory with Logging {

  def create(config: RpcEnvConfig): RpcEnv = {
    val sparkConf = config.conf
    // Use JavaSerializerInstance in multiple threads is safe. However, if we plan to support
    // KryoSerializer in future, we have to use ThreadLocal to store SerializerInstance
    val javaSerializerInstance =
      new JavaSerializer(sparkConf).newInstance().asInstanceOf[JavaSerializerInstance]
    val nettyEnv =
      new NettyRpcEnv(sparkConf, javaSerializerInstance, config.host, config.securityManager)
    if (!config.clientMode) {
      val startNettyRpcEnv: Int => (NettyRpcEnv, Int) = { actualPort =>
        <strong>nettyEnv.startServer(actualPort) //启动netty服务 7077</strong>
        (nettyEnv, nettyEnv.address.port)
      }
      try {
        Utils.startServiceOnPort(config.port, startNettyRpcEnv, sparkConf, config.name)._1
      } catch {
        case NonFatal(e) =>
          nettyEnv.shutdown()
          throw e
      }
    }
    nettyEnv
  }
}

//start netty 7077端口服务

def startServer(port: Int): Unit = {
    val bootstraps: java.util.List[TransportServerBootstrap] =
      if (securityManager.isAuthenticationEnabled()) {
        java.util.Arrays.asList(new SaslServerBootstrap(transportConf, securityManager))
      } else {
        java.util.Collections.emptyList()
      }
    server = transportContext.createServer(host, port, bootstraps)
    dispatcher.registerRpcEndpoint(
      RpcEndpointVerifier.NAME, new RpcEndpointVerifier(this, dispatcher))
  }

既然创建了NettyRpcEnvFactory，就执行了master的onStart方法。

  override def onStart(): Unit = {
    logInfo("Starting Spark master at " + masterUrl)
    logInfo(s"Running Spark version ${org.apache.spark.SPARK_VERSION}")
    webUi = new MasterWebUI(this, webUiPort)
    webUi.bind()
    masterWebUiUrl = "http://" + masterPublicAddress + ":" + webUi.boundPort //这里会启一个定时调度，检查timeout的worker进程。如果有worker超时，则将状态置为DEAD，并清理一些内存中关于该worker的信息。如果该worker中有Executor进程，则向driver发送ExecutorUpdated消息，表明该Executor也已经不可用了。如果该worker中有Driver进程，且配置driver是可以relaunch的，则重新调度在可用的worker节点上启动，不然的话就删除该Driver的内存信息。只有在该worker超时很多次之后，才真正删除，之前其实只是让该worker不被选中执行任务而已。
    checkForWorkerTimeOutTask = forwardMessageThread.scheduleAtFixedRate(new Runnable {
      override def run(): Unit = Utils.tryLogNonFatalError {
        self.send(CheckForWorkerTimeOut)
      }
    }, 0, WORKER_TIMEOUT_MS, TimeUnit.MILLISECONDS)

    if (restServerEnabled) {
      val port = conf.getInt("spark.master.rest.port", 6066)
      restServer = Some(new StandaloneRestServer(address.host, port, conf, self, masterUrl))
    }
    restServerBoundPort = restServer.map(_.start())

    masterMetricsSystem.registerSource(masterSource)
    masterMetricsSystem.start()
    applicationMetricsSystem.start()
    // Attach the master and app metrics servlet handler to the web ui after the metrics systems are
    // started.
    masterMetricsSystem.getServletHandlers.foreach(webUi.attachHandler)
    applicationMetricsSystem.getServletHandlers.foreach(webUi.attachHandler)

    val serializer = new JavaSerializer(conf) //master ha 过程
    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))
    }
    persistenceEngine = persistenceEngine_
    leaderElectionAgent = leaderElectionAgent_
  }

master主动处理的流程大致就完了，之后就接受其他的请求来被动处理。

worker节点的注册方法

override def receiveAndReply(context: RpcCallContext): PartialFunction[Any, Unit] = {
    case RegisterWorker(
        id, workerHost, workerPort, workerRef, cores, memory, workerUiPort, publicAddress) => {
      logInfo("Registering worker %s:%d with %d cores, %s RAM".format(
        workerHost, workerPort, cores, Utils.megabytesToString(memory)))
      if (state == RecoveryState.STANDBY) {
        context.reply(MasterInStandby)
      } else if (idToWorker.contains(id)) { //注册过
        context.reply(RegisterWorkerFailed("Duplicate worker ID"))
      } else {
        val worker = new WorkerInfo(id, workerHost, workerPort, cores, memory,
          workerRef, workerUiPort, publicAddress)
        if (registerWorker(worker)) {//将worker信息加入master内存中
          persistenceEngine.addWorker(worker)
          context.reply(RegisteredWorker(self, masterWebUiUrl))
          schedule()//调度
        } else {
          val workerAddress = worker.endpoint.address
          logWarning("Worker registration failed. Attempted to re-register worker at same " +
            "address: " + workerAddress)
          context.reply(RegisterWorkerFailed("Attempted to re-register worker at same address: "
            + workerAddress))
        }
      }
    }

/**
   * Schedule the currently available resources among waiting apps. This method will be called
   * every time a new app joins or resource availability changes.
   */
  private def schedule(): Unit = {
    if (state != RecoveryState.ALIVE) { return }
    // Drivers take strict precedence over executors
    val shuffledWorkers = Random.shuffle(workers) // Randomization helps balance drivers
    for (worker <- shuffledWorkers if worker.state == WorkerState.ALIVE) {
      for (driver <- waitingDrivers) {
        if (worker.memoryFree >= driver.desc.mem && worker.coresFree >= driver.desc.cores) {
          launchDriver(worker, driver)//向worker发送LaunchDriver消息  
          waitingDrivers -= driver
        }
      }
    }
    startExecutorsOnWorkers()//向worker发送LaunchExecutor消息，并向driver发送ExecutorAdded消息
  }

  private def launchExecutor(worker: WorkerInfo, exec: ExecutorDesc): Unit = {
    logInfo("Launching executor " + exec.fullId + " on worker " + worker.id)
    worker.addExecutor(exec)
    worker.endpoint.send(LaunchExecutor(masterUrl,
      exec.application.id, exec.id, exec.application.desc, exec.cores, exec.memory))
    exec.application.driver.send(
      ExecutorAdded(exec.id, worker.id, worker.hostPort, exec.cores, exec.memory))
  }<pre name="code" class="java">

case RequestSubmitDriver(description)//请求提交Driver消息，记录Driver的信息并调度

case RequestKillDriver(driverId)

case RequestDriverStatus(driverId)

case RegisterApplication(description)//提交Application，记录Application的信息并调度

case ExecutorStateChanged(appId, execId, state, message, exitStatus)

case DriverStateChanged(driverId, state, exception)

case Heartbeat(workerId)//心跳，用于worker节点的保活

case ExecutorStateChanged(appId, execId, state, message, exitStatus)

case DriverStateChanged(driverId, state, exception)

case MasterChangeAcknowledged(appId)

case WorkerSchedulerStateResponse

case AttachCompletedRebuildUI

方法较多，大多数都是看其名知其意