Spark源码系列（七）Spark on yarn具体实现

  def runApp(): ApplicationId = {
    // 校验参数，内存不能小于384Mb，Executor的数量不能少于1个。
    validateArgs()
    // 这两个是父类的方法，初始化并且启动Client
    init(yarnConf)
    start()

    // 记录集群的信息(e.g, NodeManagers的数量，队列的信息).
    logClusterResourceDetails()

    // 准备提交请求到ResourcManager (specifically its ApplicationsManager (ASM)// Get a new client application.
    val newApp = super.createApplication()
    val newAppResponse = newApp.getNewApplicationResponse()
    val appId = newAppResponse.getApplicationId()
    // 检查集群的内存是否满足当前的作业需求
    verifyClusterResources(newAppResponse)

    // 准备资源和环境变量.
    //1.获得工作目录的具体地址: /.sparkStaging/appId/
    val appStagingDir = getAppStagingDir(appId)
　　//2.创建工作目录，设置工作目录权限，上传运行时所需要的jar包
    val localResources = prepareLocalResources(appStagingDir)
    //3.设置运行时需要的环境变量
    val launchEnv = setupLaunchEnv(localResources, appStagingDir)
　　//4.设置运行时JVM参数，设置SPARK_USE_CONC_INCR_GC为true的话，就使用CMS的垃圾回收机制
    val amContainer = createContainerLaunchContext(newAppResponse, localResources, launchEnv)

    // 设置application submission context. 
    val appContext = newApp.getApplicationSubmissionContext()
    appContext.setApplicationName(args.appName)
    appContext.setQueue(args.amQueue)
    appContext.setAMContainerSpec(amContainer)
    appContext.setApplicationType("SPARK")

    // 设置ApplicationMaster的内存，Resource是表示资源的类，目前有CPU和内存两种.
    val memoryResource = Records.newRecord(classOf[Resource]).asInstanceOf[Resource]
    memoryResource.setMemory(args.amMemory + YarnAllocationHandler.MEMORY_OVERHEAD)
    appContext.setResource(memoryResource)

    // 提交Application.
    submitApp(appContext)
    appId
  }

    while (!args.isEmpty) {
      args match {
        case ("--jar") :: value :: tail =>
          userJar = value
          args = tail

        case ("--class") :: value :: tail =>
          userClass = value
          args = tail

        case ("--args" | "--arg") :: value :: tail =>
          if (args(0) == "--args") {
            println("--args is deprecated. Use --arg instead.")
          }
          userArgsBuffer += value
          args = tail

        case ("--master-class" | "--am-class") :: value :: tail =>
          if (args(0) == "--master-class") {
            println("--master-class is deprecated. Use --am-class instead.")
          }
          amClass = value
          args = tail

        case ("--master-memory" | "--driver-memory") :: MemoryParam(value) :: tail =>
          if (args(0) == "--master-memory") {
            println("--master-memory is deprecated. Use --driver-memory instead.")
          }
          amMemory = value
          args = tail

        case ("--num-workers" | "--num-executors") :: IntParam(value) :: tail =>
          if (args(0) == "--num-workers") {
            println("--num-workers is deprecated. Use --num-executors instead.")
          }
          numExecutors = value
          args = tail

        case ("--worker-memory" | "--executor-memory") :: MemoryParam(value) :: tail =>
          if (args(0) == "--worker-memory") {
            println("--worker-memory is deprecated. Use --executor-memory instead.")
          }
          executorMemory = value
          args = tail

        case ("--worker-cores" | "--executor-cores") :: IntParam(value) :: tail =>
          if (args(0) == "--worker-cores") {
            println("--worker-cores is deprecated. Use --executor-cores instead.")
          }
          executorCores = value
          args = tail

        case ("--queue") :: value :: tail =>
          amQueue = value
          args = tail

        case ("--name") :: value :: tail =>
          appName = value
          args = tail

        case ("--addJars") :: value :: tail =>
          addJars = value
          args = tail

        case ("--files") :: value :: tail =>
          files = value
          args = tail

        case ("--archives") :: value :: tail =>
          archives = value
          args = tail

        case Nil =>
          if (userClass == null) {
            printUsageAndExit(1)
          }

        case _ =>
          printUsageAndExit(1, args)
      }
    }

  def run() {
    // 设置本地目录，默认是先使用yarn的YARN_LOCAL_DIRS目录，再到LOCAL_DIRS
    System.setProperty("spark.local.dir", getLocalDirs())

    // set the web ui port to be ephemeral for yarn so we don‘t conflict with
    // other spark processes running on the same box
    System.setProperty("spark.ui.port", "0")

    // when running the AM, the Spark master is always "yarn-cluster"
    System.setProperty("spark.master", "yarn-cluster")

 　　// 设置优先级为30，和mapreduce的优先级一样。它比HDFS的优先级高，因为它的操作是清理该作业在hdfs上面的Staging目录
    ShutdownHookManager.get().addShutdownHook(new AppMasterShutdownHook(this), 30)

    appAttemptId = getApplicationAttemptId()
　　// 通过yarn.resourcemanager.am.max-attempts来设置，默认是2
　　// 目前发现它只在清理Staging目录的时候用
    isLastAMRetry = appAttemptId.getAttemptId() >= maxAppAttempts
    amClient = AMRMClient.createAMRMClient()
    amClient.init(yarnConf)
    amClient.start()

    // setup AmIpFilter for the SparkUI - do this before we start the UI
　　//  方法的介绍说是yarn用来保护ui界面的，我感觉是设置ip代理的
    addAmIpFilter()
　　//  注册ApplicationMaster到内部的列表里
    ApplicationMaster.register(this)

    // 安全认证相关的东西，默认是不开启的，省得给自己找事
    val securityMgr = new SecurityManager(sparkConf)

    // 启动driver程序 
    userThread = startUserClass()

    // 等待SparkContext被实例化，主要是等待spark.driver.port property被使用
　　// 等待结束之后，实例化一个YarnAllocationHandler
    waitForSparkContextInitialized()

    // Do this after Spark master is up and SparkContext is created so that we can register UI Url.
　　// 向yarn注册当前的ApplicationMaster, 这个时候isFinished不能为true，是true就说明程序失败了
    synchronized {
      if (!isFinished) {
        registerApplicationMaster()
        registered = true
      }
    }

    // 申请Container来启动Executor
    allocateExecutors()

    // 等待程序运行结束
    userThread.join()

    System.exit(0)
  }

  private def allocateExecutors() {
    try {
      logInfo("Allocating " + args.numExecutors + " executors.")
      // 分host、rack、任意机器三种类型向ResourceManager提交ContainerRequest
　　　 // 请求的Container数量可能大于需要的数量
      yarnAllocator.addResourceRequests(args.numExecutors)
      // Exits the loop if the user thread exits.
      while (yarnAllocator.getNumExecutorsRunning < args.numExecutors && userThread.isAlive) {
        if (yarnAllocator.getNumExecutorsFailed >= maxNumExecutorFailures) {
          finishApplicationMaster(FinalApplicationStatus.FAILED, "max number of executor failures reached")
        }
　　　　 // 把请求回来的资源进行分配，并释放掉多余的资源
        yarnAllocator.allocateResources()
        ApplicationMaster.incrementAllocatorLoop(1)
        Thread.sleep(100)
      }
    } finally {
      // In case of exceptions, etc - ensure that count is at least ALLOCATOR_LOOP_WAIT_COUNT,
      // so that the loop in ApplicationMaster#sparkContextInitialized() breaks.
      ApplicationMaster.incrementAllocatorLoop(ApplicationMaster.ALLOCATOR_LOOP_WAIT_COUNT)
    }
    logInfo("All executors have launched.")

    // 启动一个线程来状态报告
    if (userThread.isAlive) {
      // Ensure that progress is sent before YarnConfiguration.RM_AM_EXPIRY_INTERVAL_MS elapses.
      val timeoutInterval = yarnConf.getInt(YarnConfiguration.RM_AM_EXPIRY_INTERVAL_MS, 120000)

      // we want to be reasonably responsive without causing too many requests to RM.
      val schedulerInterval = sparkConf.getLong("spark.yarn.scheduler.heartbeat.interval-ms", 5000)

      // must be <= timeoutInterval / 2.
      val interval = math.min(timeoutInterval / 2, schedulerInterval)

      launchReporterThread(interval)
    }
  }

  def allocateResources() {
    // We have already set the container request. Poll the ResourceManager for a response.
    // This doubles as a heartbeat if there are no pending container requests.
　　// 之前已经提交过Container请求了，现在只需要获取response即可 
    val progressIndicator = 0.1f
    val allocateResponse = amClient.allocate(progressIndicator)

    val allocatedContainers = allocateResponse.getAllocatedContainers()
    if (allocatedContainers.size > 0) {
      var numPendingAllocateNow = numPendingAllocate.addAndGet(-1 * allocatedContainers.size)

      if (numPendingAllocateNow < 0) {
        numPendingAllocateNow = numPendingAllocate.addAndGet(-1 * numPendingAllocateNow)
      }

      val hostToContainers = new HashMap[String, ArrayBuffer[Container]]()

      for (container <- allocatedContainers) {
　　　　 // 内存 > Executor所需内存 + 384
        if (isResourceConstraintSatisfied(container)) {
          // 把container收入名册当中，等待发落
          val host = container.getNodeId.getHost
          val containersForHost = hostToContainers.getOrElseUpdate(host, new ArrayBuffer[Container]())
          containersForHost += container
        } else {
          // 内存不够，释放掉它
          releaseContainer(container)
        }
      }

      // 找到合适的container来使用.
      val dataLocalContainers = new HashMap[String, ArrayBuffer[Container]]()
      val rackLocalContainers = new HashMap[String, ArrayBuffer[Container]]()
      val offRackContainers = new HashMap[String, ArrayBuffer[Container]]()
　　　 // 遍历所有的host
      for (candidateHost <- hostToContainers.keySet) {
        val maxExpectedHostCount = preferredHostToCount.getOrElse(candidateHost, 0)
        val requiredHostCount = maxExpectedHostCount - allocatedContainersOnHost(candidateHost)

        val remainingContainersOpt = hostToContainers.get(candidateHost)
        var remainingContainers = remainingContainersOpt.get
　　　　　　
        if (requiredHostCount >= remainingContainers.size) {
          // 需要的比现有的多，把符合数据本地性的添加到dataLocalContainers映射关系里
          dataLocalContainers.put(candidateHost, remainingContainers)
          // 没有containner剩下的.
          remainingContainers = null
        } else if (requiredHostCount > 0) {
          // 获得的container比所需要的多，把多余的释放掉
          val (dataLocal, remaining) = remainingContainers.splitAt(remainingContainers.size - requiredHostCount)
          dataLocalContainers.put(candidateHost, dataLocal)

          for (container <- remaining) releaseContainer(container)
          remainingContainers = null
        }

        // 数据所在机器已经分配满任务了，只能在同一个rack里面挑选了
        if (remainingContainers != null) {
          val rack = YarnAllocationHandler.lookupRack(conf, candidateHost)
          if (rack != null) {
            val maxExpectedRackCount = preferredRackToCount.getOrElse(rack, 0)
            val requiredRackCount = maxExpectedRackCount - allocatedContainersOnRack(rack) -
              rackLocalContainers.getOrElse(rack, List()).size

            if (requiredRackCount >= remainingContainers.size) {
              // Add all remaining containers to to `dataLocalContainers`.
              dataLocalContainers.put(rack, remainingContainers)
              remainingContainers = null
            } else if (requiredRackCount > 0) {
              // Container list has more containers that we need for data locality.
              val (rackLocal, remaining) = remainingContainers.splitAt(remainingContainers.size - requiredRackCount)
              val existingRackLocal = rackLocalContainers.getOrElseUpdate(rack, new ArrayBuffer[Container]())

              existingRackLocal ++= rackLocal
              remainingContainers = remaining
            }
          }
        }

        if (remainingContainers != null) {
          // 还是不够，只能放到别的rack的机器上运行了
          offRackContainers.put(candidateHost, remainingContainers)
        }
      }

      // 按照数据所在机器、同一个rack、任意机器来排序
      val allocatedContainersToProcess = new ArrayBuffer[Container](allocatedContainers.size)
      allocatedContainersToProcess ++= TaskSchedulerImpl.prioritizeContainers(dataLocalContainers)
      allocatedContainersToProcess ++= TaskSchedulerImpl.prioritizeContainers(rackLocalContainers)
      allocatedContainersToProcess ++= TaskSchedulerImpl.prioritizeContainers(offRackContainers)

      // 遍历选择了的Container，为每个Container启动一个ExecutorRunnable线程专门负责给它发送命令
      for (container <- allocatedContainersToProcess) {
        val numExecutorsRunningNow = numExecutorsRunning.incrementAndGet()
        val executorHostname = container.getNodeId.getHost
        val containerId = container.getId
　　　　　// 内存需要大于Executor的内存 + 384
        val executorMemoryOverhead = (executorMemory + YarnAllocationHandler.MEMORY_OVERHEAD)

        if (numExecutorsRunningNow > maxExecutors) {
          // 正在运行的比需要的多了，释放掉多余的Container
          releaseContainer(container)
          numExecutorsRunning.decrementAndGet()
        } else {
          val executorId = executorIdCounter.incrementAndGet().toString
          val driverUrl = "akka.tcp://spark@%s:%s/user/%s".format(
            sparkConf.get("spark.driver.host"),
            sparkConf.get("spark.driver.port"),
            CoarseGrainedSchedulerBackend.ACTOR_NAME)


          // To be safe, remove the container from `pendingReleaseContainers`.
          pendingReleaseContainers.remove(containerId)
         // 把container记录到已分配的rack的映射关系当中
          val rack = YarnAllocationHandler.lookupRack(conf, executorHostname)
          allocatedHostToContainersMap.synchronized {
            val containerSet = allocatedHostToContainersMap.getOrElseUpdate(executorHostname,
              new HashSet[ContainerId]())

            containerSet += containerId
            allocatedContainerToHostMap.put(containerId, executorHostname)

            if (rack != null) {
              allocatedRackCount.put(rack, allocatedRackCount.getOrElse(rack, 0) + 1)
            }
          }
　　　　　　// 启动一个线程给它进行跟踪服务，给它发送运行Executor的命令
          val executorRunnable = new ExecutorRunnable(
            container,
            conf,
            sparkConf,
            driverUrl,
            executorId,
            executorHostname,
            executorMemory,
            executorCores)
          new Thread(executorRunnable).start()
        }
      }
      
  }