StreamingContext初始化与Receiver启动原理

Spark Streaming创建时会初始化DStreamGraph和JobScheduler等关键组件，然后调用数据输入方法拉取数据形成Dstream，然后使用Dstream的一系列Transform转换操作，最后调用output方法来出发batch job的执行。

上述初始化操作执行完之后，需要调用start方法来启动程序的执行，它会创建另外两个重要的组件：ReceiverTracker和JobGenerator。

另外，启动Spark Streaming应用程序的输入Dstream对应的Receiver，它是在集群中某个Worker节点中的Executor中启动的。

1.

// Spark Streaming类
  // 保存了开发者定义的Spark Streaming Application中一系列的Dstream的依赖关系，以及相互之间的算子应用
  private[streaming] val graph: DStreamGraph = {
    if (isCheckpointPresent) {
      _cp.graph.setContext(this)
      _cp.graph.restoreCheckpointData()
      _cp.graph
    } else {
      require(_batchDur != null, "Batch duration for StreamingContext cannot be null")
      val newGraph = new DStreamGraph()
      newGraph.setBatchDuration(_batchDur)
      newGraph
    }
  }

2.

// Spark Streaming类
  // JobGenerator会负责每隔batch interval生成一个job，然后通过JobScheduler来调度和提交job
  // 底层还是基于Spark的核心计算引擎：DAGScheduler、TaskScheduler...
  private[streaming] val scheduler = new JobScheduler(this)

3.

// Spark Streaming类
  /**
   * Start the execution of the streams.
   *
   * @throws IllegalStateException if the StreamingContext is already stopped.
   */
  def start(): Unit = synchronized {
    state match {
      case INITIALIZED =>
        startSite.set(DStream.getCreationSite())
        StreamingContext.ACTIVATION_LOCK.synchronized {
          StreamingContext.assertNoOtherContextIsActive()
          try {
            validate()

            // Start the streaming scheduler in a new thread, so that thread local properties
            // like call sites and job groups can be reset without affecting those of the
            // current thread.
            ThreadUtils.runInNewThread("streaming-start") {
              sparkContext.setCallSite(startSite.get)
              sparkContext.clearJobGroup()
              sparkContext.setLocalProperty(SparkContext.SPARK_JOB_INTERRUPT_ON_CANCEL, "false")
              savedProperties.set(SerializationUtils.clone(sparkContext.localProperties.get()))
              scheduler.start() // 调用JobScheduler的start方法
            }
            state = StreamingContextState.ACTIVE
            scheduler.listenerBus.post(
              StreamingListenerStreamingStarted(System.currentTimeMillis()))
          } catch {
            case NonFatal(e) =>
              logError("Error starting the context, marking it as stopped", e)
              scheduler.stop(false)
              state = StreamingContextState.STOPPED
              throw e
          }
          StreamingContext.setActiveContext(this)
        }
        logDebug("Adding shutdown hook") // force eager creation of logger
        shutdownHookRef = ShutdownHookManager.addShutdownHook(
          StreamingContext.SHUTDOWN_HOOK_PRIORITY)(() => stopOnShutdown())
        // Registering Streaming Metrics at the start of the StreamingContext
        assert(env.metricsSystem != null)
        env.metricsSystem.registerSource(streamingSource)
        uiTab.foreach(_.attach())
        logInfo("StreamingContext started")
      case ACTIVE =>
        logWarning("StreamingContext has already been started")
      case STOPPED =>
        throw new IllegalStateException("StreamingContext has already been stopped")
    }
  }

4. 

// JobScheduler类
  def start(): Unit = synchronized {
    if (eventLoop != null) return // scheduler has already been started

    logDebug("Starting JobScheduler")
    eventLoop = new EventLoop[JobSchedulerEvent]("JobScheduler") {
      override protected def onReceive(event: JobSchedulerEvent): Unit = processEvent(event)

      override protected def onError(e: Throwable): Unit = reportError("Error in job scheduler", e)
    }
    eventLoop.start()

    // attach rate controllers of input streams to receive batch completion updates
    for {
      inputDStream <- ssc.graph.getInputStreams
      rateController <- inputDStream.rateController
    } ssc.addStreamingListener(rateController)

    listenerBus.start()
    receiverTracker = new ReceiverTracker(ssc) // 创建ReceiverTracker组件
    inputInfoTracker = new InputInfoTracker(ssc)

    val executorAllocClient: ExecutorAllocationClient = ssc.sparkContext.schedulerBackend match {
      case b: ExecutorAllocationClient => b.asInstanceOf[ExecutorAllocationClient]
      case _ => null
    }

    executorAllocationManager = ExecutorAllocationManager.createIfEnabled(
      executorAllocClient,
      receiverTracker,
      ssc.conf,
      ssc.graph.batchDuration.milliseconds,
      clock)
    executorAllocationManager.foreach(ssc.addStreamingListener)
    receiverTracker.start() // 启动receiverTracker
    jobGenerator.start() //启动JobGenerator
    executorAllocationManager.foreach(_.start())
    logInfo("Started JobScheduler")
  }

5.

// ReceiverTracker类
  /** Start the endpoint and receiver execution thread. */
  def start(): Unit = synchronized {
    if (isTrackerStarted) {
      throw new SparkException("ReceiverTracker already started")
    }

    if (!receiverInputStreams.isEmpty) {
      endpoint = ssc.env.rpcEnv.setupEndpoint(
        "ReceiverTracker", new ReceiverTrackerEndpoint(ssc.env.rpcEnv))
      if (!skipReceiverLaunch) launchReceivers() // 使用异步的方式启动Receiver
      logInfo("ReceiverTracker started")
      trackerState = Started
    }
  }

6.

// ReceiverTracker类
  /**
   * Get the receivers from the ReceiverInputDStreams, distributes them to the
   * worker nodes as a parallel collection, and runs them.
   */
  private def launchReceivers(): Unit = {
    // receiverInputStreams是从SparkStreamingContext的DStreamGraph中取出的。
    // 每创建一个Dstream，都会放入receiverInputStreams中
    val receivers = receiverInputStreams.map { nis =>
      val rcvr = nis.getReceiver()
      rcvr.setReceiverId(nis.id)
      rcvr
    }

    runDummySparkJob()

    logInfo("Starting " + receivers.length + " receivers")
    endpoint.send(StartAllReceivers(receivers))
  }

7.

 /** RpcEndpoint to receive messages from the receivers. */
  private class ReceiverTrackerEndpoint(override val rpcEnv: RpcEnv) extends ThreadSafeRpcEndpoint {

    private val walBatchingThreadPool = ExecutionContext.fromExecutorService(
      ThreadUtils.newDaemonCachedThreadPool("wal-batching-thread-pool"))

    @volatile private var active: Boolean = true

    override def receive: PartialFunction[Any, Unit] = {
      // Local messages
      case StartAllReceivers(receivers) =>
        val scheduledLocations = schedulingPolicy.scheduleReceivers(receivers, getExecutors)
        for (receiver <- receivers) {
          val executors = scheduledLocations(receiver.streamId)
          updateReceiverScheduledExecutors(receiver.streamId, executors)
          receiverPreferredLocations(receiver.streamId) = receiver.preferredLocation
          startReceiver(receiver, executors) // 启动Receiver
        }
...
...
}

8.

    /**
     * Start a receiver along with its scheduled executors
     */
    private def startReceiver(
        receiver: Receiver[_],
        scheduledLocations: Seq[TaskLocation]): Unit = {
      def shouldStartReceiver: Boolean = {
        // It's okay to start when trackerState is Initialized or Started
        !(isTrackerStopping || isTrackerStopped)
      }

      val receiverId = receiver.streamId
      if (!shouldStartReceiver) {
        onReceiverJobFinish(receiverId)
        return
      }

      val checkpointDirOption = Option(ssc.checkpointDir)
      val serializableHadoopConf =
        new SerializableConfiguration(ssc.sparkContext.hadoopConfiguration)

      // Function to start the receiver on the worker node
      // 这里定义了一个函数，启动Receiver的函数：这里只是定义，还没有执行，到这里还是在Driver上执行的
      // 这个函数实际调用执行是在worker上进行的
      val startReceiverFunc: Iterator[Receiver[_]] => Unit =
        (iterator: Iterator[Receiver[_]]) => {
          if (!iterator.hasNext) {
            throw new SparkException(
              "Could not start receiver as object not found.")
          }
          if (TaskContext.get().attemptNumber() == 0) {
            val receiver = iterator.next()
            assert(iterator.hasNext == false)
            val supervisor = new ReceiverSupervisorImpl(
              receiver, SparkEnv.get, serializableHadoopConf.value, checkpointDirOption)
            supervisor.start()
            supervisor.awaitTermination()
          } else {
            // It's restarted by TaskScheduler, but we want to reschedule it again. So exit it.
          }
        }

      // Create the RDD using the scheduledLocations to run the receiver in a Spark job
      val receiverRDD: RDD[Receiver[_]] =
        if (scheduledLocations.isEmpty) {
          ssc.sc.makeRDD(Seq(receiver), 1)
        } else {
          val preferredLocations = scheduledLocations.map(_.toString).distinct
          ssc.sc.makeRDD(Seq(receiver -> preferredLocations))
        }
      receiverRDD.setName(s"Receiver $receiverId")
      ssc.sparkContext.setJobDescription(s"Streaming job running receiver $receiverId")
      ssc.sparkContext.setCallSite(Option(ssc.getStartSite()).getOrElse(Utils.getCallSite()))

      // 这里开始将Receiver分发到worker上去启动，会调用之前定义的startReceiverFunc
      val future = ssc.sparkContext.submitJob[Receiver[_], Unit, Unit](
        receiverRDD, startReceiverFunc, Seq(0), (_, _) => Unit, ())
      // We will keep restarting the receiver job until ReceiverTracker is stopped
      future.onComplete {
        case Success(_) =>
          if (!shouldStartReceiver) {
            onReceiverJobFinish(receiverId)
          } else {
            logInfo(s"Restarting Receiver $receiverId")
            self.send(RestartReceiver(receiver))
          }
        case Failure(e) =>
          if (!shouldStartReceiver) {
            onReceiverJobFinish(receiverId)
          } else {
            logError("Receiver has been stopped. Try to restart it.", e)
            logInfo(s"Restarting Receiver $receiverId")
            self.send(RestartReceiver(receiver))
          }
      }(ThreadUtils.sameThread)
      logInfo(s"Receiver ${receiver.streamId} started")
    }