Spark分析之Standalone运行过程分析

$SPARK_HOME/sbin/start-master.sh

spark-daemon.sh start org.apache.spark.deploy.master.Master 1 --ip $SPARK_MASTER_IP --port $SPARK_MASTER_PORT --webui-port $SPARK_MASTER_WEBUI_PORT

14/07/22 13:41:33 INFO Remoting: Remoting started; listening on addresses :[akka.tcp://sparkMaster@hadoop000:7077]
14/07/22 13:41:33 INFO master.Master: Starting Spark master at spark://hadoop000:7077
14/07/22 13:41:33 INFO server.Server: jetty-8.y.z-SNAPSHOT
14/07/22 13:41:33 INFO server.AbstractConnector: Started SelectChannelConnector@0.0.0.0:8080
14/07/22 13:41:33 INFO ui.MasterWebUI: Started MasterWebUI at http://hadoop000:8080
14/07/22 13:41:33 INFO master.Master: I have been elected leader! New state: ALIVE

spark-daemon.sh start org.apache.spark.deploy.worker.Worker master-spark-URL

Worker.scala
　　　　==>preStart
　　　　　　==>registerWithMaster
　　　　　　　　==>tryRegisterAllMasters
　　　　　　　　　　==> actor ! RegisterWorker(workerId, host, port, cores, memory, webUi.boundPort, publicAddress)

Master.scala
　　==>case RegisterWorker(id, workerHost, workerPort, cores, memory, workerUiPort, publicAddress) => {
　　　　　　val worker = new WorkerInfo(id, workerHost, workerPort, cores, memory,
   　　　　sender, workerUiPort, publicAddress)
   　　　　if (registerWorker(worker)) {
   　　　　　　persistenceEngine.addWorker(worker)
　　　　　　　　sender ! RegisteredWorker(masterUrl, masterWebUiUrl)   //注册成功后向Worker发送注册成功信息
　　　　　　　　schedule()
　　　　　　}
　　　　}

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

Master.scala
　　==>case Heartbeat(workerId) => {
　　　　　　idToWorker.get(workerId) match {
          　　case Some(workerInfo) =>
　　　　　　　　　　workerInfo.lastHeartbeat = System.currentTimeMillis()
　　　　　　}
　　}

Master.scala
　　==>preStart
　　　　==>CheckForWorkerTimeOut
　　　　　　==>case CheckForWorkerTimeOut => {timeOutDeadWorkers()} //Check for, and remove, any timed-out workers

14/07/22 13:41:36 INFO master.Master: Registering worker hadoop000:48343 with 1 cores, 2.0 GB RAM

14/07/22 13:41:35 INFO Worker: Starting Spark worker hadoop000:48343 with 1 cores, 2.0 GB RAM
14/07/22 13:41:35 INFO Worker: Spark home: /home/spark/app/spark-1.0.1-bin-2.3.0-cdh5.0.0
14/07/22 13:41:35 INFO WorkerWebUI: Started WorkerWebUI at http://hadoop000:8081
14/07/22 13:41:35 INFO Worker: Connecting to master spark://hadoop000:7077...
14/07/22 13:41:36 INFO Worker: Successfully registered with master spark://hadoop000:7077

client = new AppClient(sc.env.actorSystem, masters, appDesc, this, conf)
client.start()

AppClient.scala
　　==>preStart
　　　　==>registerWithMaster
　　　　　　==>tryRegisterAllMasters
　　　　　　　　==>actor ! RegisterApplication(appDescription)

Master.scala
        ==>case RegisterApplication(description) => {
            logInfo("Registering app " + description.name)
            val app = createApplication(description, sender)
            registerApplication(app)
            logInfo("Registered app " + description.name + " with ID " + app.id)
            persistenceEngine.addApplication(app)
            sender ! RegisteredApplication(app.id, masterUrl)
            schedule()
        }

        ==>schedule
            ==>launchExecutor(worker, exec)
                ==> worker.addExecutor(exec)
                    worker.actor ! LaunchExecutor(masterUrl,exec.application.id, exec.id, exec.application.desc, exec.cores, exec.memory)
                    exec.application.driver ! ExecutorAdded(exec.id, worker.id, worker.hostPort, exec.cores, exec.memory)

Worker.scala
    ==>case LaunchExecutor(masterUrl, appId, execId, appDesc, cores_, memory_) =>
        logInfo("Asked to launch executor %s/%d for %s".format(appId, execId, appDesc.name))
        val manager = new ExecutorRunner(appId, execId, appDesc, cores_, memory_,
        self, workerId, host,
        appDesc.sparkHome.map(userSparkHome => new File(userSparkHome)).getOrElse(sparkHome),
        workDir, akkaUrl, ExecutorState.RUNNING)
        executors(appId + "/" + execId) = manager
        manager.start()
        coresUsed += cores_
        memoryUsed += memory_
        masterLock.synchronized {master ! ExecutorStateChanged(appId, execId, manager.state, None, None)}
    }

SparkDeploySchedulerBackend.scala
    ==>preStart   (CoarseGrainedSchedulerBackend)
        ==> case RegisterExecutor(executorId, hostPort, cores) =>
            logInfo("Registered executor: " + sender + " with ID " + executorId)
            sender ! RegisteredExecutor(sparkProperties)
            executorActor(executorId) = sender
            executorHost(executorId) = Utils.parseHostPort(hostPort)._1
            totalCores(executorId) = cores
            freeCores(executorId) = cores
            executorAddress(executorId) = sender.path.address
            addressToExecutorId(sender.path.address) = executorId
            totalCoreCount.addAndGet(cores)
            makeOffers()

CoarseGrainedExecutorBackend.scala
    case RegisteredExecutor(sparkProperties) =>
        ogInfo("Successfully registered with driver")
        executor = new Executor(executorId, Utils.parseHostPort(hostPort)._1, sparkProperties,false)

sc.textFile("hdfs://hadoop000:8020/hello.txt").flatMap(_.split(‘\t‘)).map((_,1)).reduceByKey(_+_).collect

CoarseGrainedSchedulerBackend.scala
    def makeOffers() {
        launchTasks(scheduler.resourceOffers(
            executorHost.toArray.map {case (id, host) => new WorkerOffer(id, host, freeCores(id))}))
        }   ==>executorActor(task.executorId) ! LaunchTask(new SerializableBuffer(serializedTask))
            ==>CoarseGrainedSchedulerBackend  case LaunchTask(data) =>
                  if (executor == null) {
                    logError("Received LaunchTask command but executor was null")
                    System.exit(1)
                  } else {
                    val ser = SparkEnv.get.closureSerializer.newInstance()
                    val taskDesc = ser.deserialize[TaskDescription](data.value)
                    logInfo("Got assigned task " + taskDesc.taskId)
                    executor.launchTask(this, taskDesc.taskId, taskDesc.serializedTask)
                  }    

14/07/22 15:25:27 INFO master.Master: Registering app Spark shell
14/07/22 15:25:27 INFO master.Master: Registered app Spark shell with ID app-20140722152527-0001
14/07/22 15:25:27 INFO master.Master: Launching executor app-20140722152527-0001/0 on worker worker-20140722134135-hadoop000-48343

Spark assembly has been built with Hive, including Datanucleus jars on classpath
14/07/22 15:25:27 INFO Worker: Asked to launch executor app-20140722152527-0001/0 for Spark shell
Spark assembly has been built with Hive, including Datanucleus jars on classpath
14/07/22 15:25:28 INFO ExecutorRunner: Launch command: "java" "-cp" "::/home/spark/app/spark-1.0.1-bin-2.3.0-cdh5.0.0/conf:/home/spark/app/spark-1.0.1-bin-2.3.0-cdh5.0.0/lib/spark-assembly-1.0.1-hadoop2.3.0-cdh5.0.0.jar:/home/spark/app/spark-1.0.1-bin-2.3.0-cdh5.0.0/lib/datanucleus-rdbms-3.2.1.jar:/home/spark/app/spark-1.0.1-bin-2.3.0-cdh5.0.0/lib/datanucleus-core-3.2.2.jar:/home/spark/app/spark-1.0.1-bin-2.3.0-cdh5.0.0/lib/datanucleus-api-jdo-3.2.1.jar" "-XX:MaxPermSize=128m" "-Xms1024M" "-Xmx1024M" "org.apache.spark.executor.CoarseGrainedExecutorBackend" "akka.tcp://spark@hadoop000:50515/user/CoarseGrainedScheduler" "0" "hadoop000" "1" "akka.tcp://sparkWorker@hadoop000:48343/user/Worker" "app-20140722152527-0001"

14/07/22 15:25:31 INFO cluster.SparkDeploySchedulerBackend: Registered executor: Actor[akka.tcp://sparkExecutor@hadoop000:45150/user/Executor#-791712793] with ID 0
14/07/22 15:25:31 INFO CoarseGrainedExecutorBackend: Successfully registered with driver