spark exectors的启动总结

在spark启动之后，worker和master注册通信之后，在进入用户提交app中，new SparkContext之后就会在worker上分配exectors了。

首先在sparkContext中，会先创建和启动TaskScheduler和DAGSchedule

在创建TaskScheduler的时候也会创建schedulerBackend；下面看createTaskScheduler方法：

   private def createTaskScheduler(
       sc: SparkContext,
       master: String,
       deployMode: String): (SchedulerBackend, TaskScheduler) = {
     import SparkMasterRegex._

     // When running locally, don't try to re-execute tasks on failure.
     val MAX_LOCAL_TASK_FAILURES = 1

     master match {
       case "local" =>
         val scheduler = new TaskSchedulerImpl(sc, MAX_LOCAL_TASK_FAILURES, isLocal = true)
         val backend = new LocalSchedulerBackend(sc.getConf, scheduler, 1)
         scheduler.initialize(backend)
         (backend, scheduler)

       case LOCAL_N_REGEX(threads) =>
         def localCpuCount: Int = Runtime.getRuntime.availableProcessors()
         // local[*] estimates the number of cores on the machine; local[N] uses exactly N threads.
         val threadCount = if (threads == "*") localCpuCount else threads.toInt
         if (threadCount <= 0) {
           throw new SparkException(s"Asked to run locally with $threadCount threads")
         }
         val scheduler = new TaskSchedulerImpl(sc, MAX_LOCAL_TASK_FAILURES, isLocal = true)
         val backend = new LocalSchedulerBackend(sc.getConf, scheduler, threadCount)
         scheduler.initialize(backend)
         (backend, scheduler)

       case LOCAL_N_FAILURES_REGEX(threads, maxFailures) =>
         def localCpuCount: Int = Runtime.getRuntime.availableProcessors()
         // local[*, M] means the number of cores on the computer with M failures
         // local[N, M] means exactly N threads with M failures
         val threadCount = if (threads == "*") localCpuCount else threads.toInt
         val scheduler = new TaskSchedulerImpl(sc, maxFailures.toInt, isLocal = true)
         val backend = new LocalSchedulerBackend(sc.getConf, scheduler, threadCount)
         scheduler.initialize(backend)
         (backend, scheduler)

       case SPARK_REGEX(sparkUrl) =>
         val scheduler = new TaskSchedulerImpl(sc)
         val masterUrls = sparkUrl.split(",").map("spark://" + _)
         val backend = new StandaloneSchedulerBackend(scheduler, sc, masterUrls)
         scheduler.initialize(backend)
         (backend, scheduler)

       case LOCAL_CLUSTER_REGEX(numSlaves, coresPerSlave, memoryPerSlave) =>
         // Check to make sure memory requested <= memoryPerSlave. Otherwise Spark will just hang.
         val memoryPerSlaveInt = memoryPerSlave.toInt
         if (sc.executorMemory > memoryPerSlaveInt) {
           throw new SparkException(
             "Asked to launch cluster with %d MB RAM / worker but requested %d MB/worker".format(
               memoryPerSlaveInt, sc.executorMemory))
         }

         val scheduler = new TaskSchedulerImpl(sc)
         val localCluster = new LocalSparkCluster(
           numSlaves.toInt, coresPerSlave.toInt, memoryPerSlaveInt, sc.conf)
         val masterUrls = localCluster.start()
         val backend = new StandaloneSchedulerBackend(scheduler, sc, masterUrls)
         scheduler.initialize(backend)
         backend.shutdownCallback = (backend: StandaloneSchedulerBackend) => {
           localCluster.stop()
         }
         (backend, scheduler)

       case masterUrl =>
         val cm = getClusterManager(masterUrl) match {
           case Some(clusterMgr) => clusterMgr
           case None => throw new SparkException("Could not parse Master URL: '" + master + "'")
         }
         try {
           val scheduler = cm.createTaskScheduler(sc, masterUrl)
           val backend = cm.createSchedulerBackend(sc, masterUrl, scheduler)
           cm.initialize(scheduler, backend)
           (backend, scheduler)
         } catch {
           case se: SparkException => throw se
           case NonFatal(e) =>
             throw new SparkException("External scheduler cannot be instantiated", e)
         }
     }
   }

在这个方法中会根据配置的master的url来创建相应的TaskScheduler和schedulerBackend，如果是local则创建TaskSchedulerImpl和LocalSchedulerBackend，如果是Standalone则创建TaskSchedulerImpl和StandaloneSchedulerBackend，如果是其他，例如yarn，则会在getClusterManager方法中从加载的类文件中获取ExternalClusterManager类型的类，并调用其canCreate查看是否可以创建，来创建其他的TaskScheduler和scheduler。

下面就以Standalone模式来分析接下来的操作：

扎起创建完TaskSchedulerImpl和StandaloneSchedulerBackend之后会接着创建DAGScheduler，创建的时候回用到上面创建的TaskSchedulerImpl作为参数，在其创建的过程中也会创建一个eventProcessLoop，它是DAGScheduler接收处理各类消息的时间循环体，其继承自EventLoop，它会启动一个线程来处理eventQueue中保存的信息。下面是具体的代码：

 private[scheduler] val eventProcessLoop = new DAGSchedulerEventProcessLoop(this)
  taskScheduler.setDAGScheduler(this)
.............
private[scheduler] class DAGSchedulerEventProcessLoop(dagScheduler: DAGScheduler)
  extends EventLoop[DAGSchedulerEvent]("dag-scheduler-event-loop") with Logging
...............
private[spark] abstract class EventLoop[E](name: String) extends Logging {

  private val eventQueue: BlockingQueue[E] = new LinkedBlockingDeque[E]()

  private val stopped = new AtomicBoolean(false)

  private val eventThread = new Thread(name) {
    setDaemon(true)

    override def run(): Unit = {
      try {
        while (!stopped.get) {
          val event = eventQueue.take()
          try {
            onReceive(event)
          } catch {
            case NonFatal(e) =>
              try {
                onError(e)
              } catch {
                case NonFatal(e) => logError("Unexpected error in " + name, e)
              }
          }
        }
      } catch {
        case ie: InterruptedException => // exit even if eventQueue is not empty
        case NonFatal(e) => logError("Unexpected error in " + name, e)
      }
    }

  }
}

在OnReceive接收处理的事件信息在DAGScheduler中有定义：

private def doOnReceive(event: DAGSchedulerEvent): Unit = event match {
    case JobSubmitted(jobId, rdd, func, partitions, callSite, listener, properties) =>
      dagScheduler.handleJobSubmitted(jobId, rdd, func, partitions, callSite, listener, properties)

    case MapStageSubmitted(jobId, dependency, callSite, listener, properties) =>
      dagScheduler.handleMapStageSubmitted(jobId, dependency, callSite, listener, properties)

    case StageCancelled(stageId, reason) =>
      dagScheduler.handleStageCancellation(stageId, reason)

    case JobCancelled(jobId, reason) =>
      dagScheduler.handleJobCancellation(jobId, reason)

    case JobGroupCancelled(groupId) =>
      dagScheduler.handleJobGroupCancelled(groupId)

    case AllJobsCancelled =>
      dagScheduler.doCancelAllJobs()

    case ExecutorAdded(execId, host) =>
      dagScheduler.handleExecutorAdded(execId, host)

    case ExecutorLost(execId, reason) =>
      val workerLost = reason match {
        case SlaveLost(_, true) => true
        case _ => false
      }
      dagScheduler.handleExecutorLost(execId, workerLost)

    case WorkerRemoved(workerId, host, message) =>
      dagScheduler.handleWorkerRemoved(workerId, host, message)

    case BeginEvent(task, taskInfo) =>
      dagScheduler.handleBeginEvent(task, taskInfo)

    case SpeculativeTaskSubmitted(task) =>
      dagScheduler.handleSpeculativeTaskSubmitted(task)

    case GettingResultEvent(taskInfo) =>
      dagScheduler.handleGetTaskResult(taskInfo)

    case completion: CompletionEvent =>
      dagScheduler.handleTaskCompletion(completion)

    case TaskSetFailed(taskSet, reason, exception) =>
      dagScheduler.handleTaskSetFailed(taskSet, reason, exception)

    case ResubmitFailedStages =>
      dagScheduler.resubmitFailedStages()
  }

关于eventloop在sparkStreaming中job生出和处理中也有用到，都是同样的原理；

在sparkContext创建完成TaskScheduler和DAGScheduler之后，会调用taskScheduler.start来启动TaskScheduler。这里指向的是TaskSchedulerImpl

其首先会启动backend也就是StandaloneSchedulerBackend，然后在看是否开启了推测执行，如果开始则进行推测执行的相关操作，下面看看StandaloneSchedulerBackend的start方法

override def start() {
//调用父类的start方法，会根据配置参数创建DriverEndpointRef，这里的父类是CoarseGrainedSchedulerBackend
    super.start()

    // SPARK-21159. The scheduler backend should only try to connect to the launcher when in client
    // mode. In cluster mode, the code that submits the application to the Master needs to connect
    // to the launcher instead.
    if (sc.deployMode == "client") {
      launcherBackend.connect()
    }

    // The endpoint for executors to talk to us
    val driverUrl = RpcEndpointAddress(
      sc.conf.get("spark.driver.host"),
      sc.conf.get("spark.driver.port").toInt,
      CoarseGrainedSchedulerBackend.ENDPOINT_NAME).toString
//设置关于程序运行的参数变量
    val args = Seq(
      "--driver-url", driverUrl,
      "--executor-id", "{{EXECUTOR_ID}}",
      "--hostname", "{{HOSTNAME}}",
      "--cores", "{{CORES}}",
      "--app-id", "{{APP_ID}}",
      "--worker-url", "{{WORKER_URL}}")
    val extraJavaOpts = sc.conf.getOption("spark.executor.extraJavaOptions")
      .map(Utils.splitCommandString).getOrElse(Seq.empty)
    val classPathEntries = sc.conf.getOption("spark.executor.extraClassPath")
      .map(_.split(java.io.File.pathSeparator).toSeq).getOrElse(Nil)
    val libraryPathEntries = sc.conf.getOption("spark.executor.extraLibraryPath")
      .map(_.split(java.io.File.pathSeparator).toSeq).getOrElse(Nil)

    // When testing, expose the parent class path to the child. This is processed by
    // compute-classpath.{cmd,sh} and makes all needed jars available to child processes
    // when the assembly is built with the "*-provided" profiles enabled.
    val testingClassPath =
      if (sys.props.contains("spark.testing")) {
        sys.props("java.class.path").split(java.io.File.pathSeparator).toSeq
      } else {
        Nil
      }

    // Start executors with a few necessary configs for registering with the scheduler
    val sparkJavaOpts = Utils.sparkJavaOpts(conf, SparkConf.isExecutorStartupConf)
    val javaOpts = sparkJavaOpts ++ extraJavaOpts
//这里的CoarseGraninedExecutorBackend最后会在exector启动相当与exector容器
    val command = Command("org.apache.spark.executor.CoarseGrainedExecutorBackend",
      args, sc.executorEnvs, classPathEntries ++ testingClassPath, libraryPathEntries, javaOpts)
    val webUrl = sc.ui.map(_.webUrl).getOrElse("")
    val coresPerExecutor = conf.getOption("spark.executor.cores").map(_.toInt)
    // If we're using dynamic allocation, set our initial executor limit to 0 for now.
    // ExecutorAllocationManager will send the real initial limit to the Master later.
    val initialExecutorLimit =
      if (Utils.isDynamicAllocationEnabled(conf)) {
        Some(0)
      } else {
        None
      }
//这里包含了注册这个app的所有的信息
    val appDesc = ApplicationDescription(sc.appName, maxCores, sc.executorMemory, command,
      webUrl, sc.eventLogDir, sc.eventLogCodec, coresPerExecutor, initialExecutorLimit)
//创建AppClient，然后启动
    client = new StandaloneAppClient(sc.env.rpcEnv, masters, appDesc, this, conf)
    client.start()
    launcherBackend.setState(SparkAppHandle.State.SUBMITTED)
    waitForRegistration()
    launcherBackend.setState(SparkAppHandle.State.RUNNING)
  }

接下来看client的start方法，其主要是创建了一个ClientEndpoint；ClientEndpoint继承了ThreadSafeRpcEndpoint，在创建的过程中会调用他的onStart方法

在ClientEndpoint的方法中主要是调用了registerWithMaster(1)方法,最终调用的是tryRegisterAllMasters方法：

这里向master发送了一个　消息；接下来看看master对这个消息的处理：

可以看到最后调用的是master的registerApplication方法，其主要就是获取传递到master关于app的数据，然后添加这个app倒Waitingapps中，其后给driver发送registeredApplication消息，

最后调用scheduler方法，其实scheduler在worker启动的时候已经调用过，因此exector，在worker启动完成之后就已经启动了，此处只是新的app过来，因此需要调用scheduler来为app分配资源：

在schedule方法中，首先会进行shuffle操作，类似模拟随机选取操作，然后返回新的随机选取的集合并且过滤出来存活的worker，然后给等待调度的driver分配worker；利用while循环遍历每个woker，若满足申请的内存和core，则分配资源，并结束分配，获取下个等待调度的dirver。。。。在dirver分配到worker之后会调用launchDriver方法：

这个方法向worker发送了一个LaunchDriver消息：然后更新了driver的信息，接下来看看worker对消息的处理，

这里创建了一个DriverRunner并且进行了启动，接下来看start方法：

在prepareAndRunDriver中：

可以看到worker启动了一个线程来启动driver，driver利用command的参数builder而成，参数在sparkSubmit启动启动app的时候发送给master加入waitingDrivers中

接下来看startExecutorOnWorkers方法：

其中主要逻辑就是根据等待的app依次来分配资源，过滤满足需要的内存和core的worker来运行app，最后调用allocateWorkerResourseToExectors，然后在调用了launchExecutor方法：

可以看到master向worker发送了启动execitor的信息，下面看worker对这个信息的处理即可：

 case LaunchExecutor(masterUrl, appId, execId, appDesc, cores_, memory_) =>
      if (masterUrl != activeMasterUrl) {
        logWarning("Invalid Master (" + masterUrl + ") attempted to launch executor.")
      } else {
        try {
          logInfo("Asked to launch executor %s/%d for %s".format(appId, execId, appDesc.name))

          // 创建exector的工作目录
          val executorDir = new File(workDir, appId + "/" + execId)
          if (!executorDir.mkdirs()) {
            throw new IOException("Failed to create directory " + executorDir)
          }

          // Create local dirs for the executor. These are passed to the executor via the
          // SPARK_EXECUTOR_DIRS environment variable, and deleted by the Worker when the
          // application finishes.
          val appLocalDirs = appDirectories.getOrElse(appId, {
            val localRootDirs = Utils.getOrCreateLocalRootDirs(conf)
            val dirs = localRootDirs.flatMap { dir =>
              try {
                val appDir = Utils.createDirectory(dir, namePrefix = "executor")
                Utils.chmod700(appDir)
                Some(appDir.getAbsolutePath())
              } catch {
                case e: IOException =>
                  logWarning(s"${e.getMessage}. Ignoring this directory.")
                  None
              }
            }.toSeq
            if (dirs.isEmpty) {
              throw new IOException("No subfolder can be created in " +
                s"${localRootDirs.mkString(",")}.")
            }
            dirs
          })
          appDirectories(appId) = appLocalDirs
//创建executorRunner来真正运行executor
          val manager = new ExecutorRunner(
            appId,
            execId,
            appDesc.copy(command = Worker.maybeUpdateSSLSettings(appDesc.command, conf)),
            cores_,
            memory_,
            self,
            workerId,
            host,
            webUi.boundPort,
            publicAddress,
            sparkHome,
            executorDir,
            workerUri,
            conf,
            appLocalDirs, ExecutorState.RUNNING)
          executors(appId + "/" + execId) = manager
//executorRunner启动
          manager.start()
          coresUsed += cores_
          memoryUsed += memory_
//通知masterexecitor状态
          sendToMaster(ExecutorStateChanged(appId, execId, manager.state, None, None))
        } catch {
          case e: Exception =>
            logError(s"Failed to launch executor $appId/$execId for ${appDesc.name}.", e)
            if (executors.contains(appId + "/" + execId)) {
              executors(appId + "/" + execId).kill()
              executors -= appId + "/" + execId
            }
            sendToMaster(ExecutorStateChanged(appId, execId, ExecutorState.FAILED,
              Some(e.toString), None))
        }
      }

在ExecutorRunner的run方法最后启动一个线程调用的是fetchAndRunExector方法

 private def fetchAndRunExecutor() {
    try {
      // 通过应用程序的信息和环境配置创建构造器builder
      val builder = CommandUtils.buildProcessBuilder(appDesc.command, new SecurityManager(conf),
        memory, sparkHome.getAbsolutePath, substituteVariables)
      val CoarseGrainedExecutorBackend = builder.command()
      val formattedCommand = command.asScala.mkString("\"", "\" \"", "\"")
      logInfo(s"Launch command: $formattedCommand")

      builder.directory(executorDir)
      builder.environment.put("SPARK_EXECUTOR_DIRS", appLocalDirs.mkString(File.pathSeparator))
      // In case we are running this from within the Spark Shell, avoid creating a "scala"
      // parent process for the executor command
      builder.environment.put("SPARK_LAUNCH_WITH_SCALA", "0")

      // 添加webUi相关设置
      val baseUrl =
        if (conf.getBoolean("spark.ui.reverseProxy", false)) {
          s"/proxy/$workerId/logPage/?appId=$appId&executorId=$execId&logType="
        } else {
          s"http://$publicAddress:$webUiPort/logPage/?appId=$appId&executorId=$execId&logType="
        }
      builder.environment.put("SPARK_LOG_URL_STDERR", s"${baseUrl}stderr")
      builder.environment.put("SPARK_LOG_URL_STDOUT", s"${baseUrl}stdout")
//启动构造器，这里实际创建的CorarseGrainedExecutorBackend
      process = builder.start()
      val header = "Spark Executor Command: %s\n%s\n\n".format(
        formattedCommand, "=" * 40)

      // Redirect its stdout and stderr to files
      val stdout = new File(executorDir, "stdout")
      stdoutAppender = FileAppender(process.getInputStream, stdout, conf)

      val stderr = new File(executorDir, "stderr")
      Files.write(header, stderr, StandardCharsets.UTF_8)
      stderrAppender = FileAppender(process.getErrorStream, stderr, conf)

      // Wait for it to exit; executor may exit with code 0 (when driver instructs it to shutdown)
      // or with nonzero exit code
//情启动executor的进程，并等待退出
      val exitCode = process.waitFor()
      state = ExecutorState.EXITED
      val message = "Command exited with code " + exitCode
//通知worker关于executor的状态
      worker.send(ExecutorStateChanged(appId, execId, state, Some(message), Some(exitCode)))
    } catch {
      case interrupted: InterruptedException =>
        logInfo("Runner thread for executor " + fullId + " interrupted")
        state = ExecutorState.KILLED
        killProcess(None)
      case e: Exception =>
        logError("Error running executor", e)
        state = ExecutorState.FAILED
        killProcess(Some(e.toString))
    }
  }

到此work的executor已经启动就等taskScheduler调度的task来运行。