5.Spark Streaming流计算框架的运行流程源码分析2

 1 def start(): Unit = synchronized {
 2   if (isTrackerStarted) {
 3     throw new SparkException("ReceiverTracker already started")
 4   }
 5  
 6   if (!receiverInputStreams.isEmpty) {
 7     endpoint = ssc.env.rpcEnv.setupEndpoint(
 8       "ReceiverTracker", new ReceiverTrackerEndpoint(ssc.env.rpcEnv))
 9     if (!skipReceiverLaunch) launchReceivers()
10     logInfo("ReceiverTracker started")
11     trackerState = Started
12   }
13 }

/**
 * Get the receivers from the ReceiverInputDStreams, distributes them to the
 * worker nodes as a parallel collection, and runs them.
 */
private def launchReceivers(): Unit = {
  val receivers = receiverInputStreams.map(nis => {
    val rcvr = nis.getReceiver()
    rcvr.setReceiverId(nis.id)
    rcvr
  })
  runDummySparkJob()
  logInfo("Starting " + receivers.length + " receivers")
  endpoint.send(StartAllReceivers(receivers))
}
 

/**
 * Run the dummy Spark job to ensure that all slaves have registered. This avoids all the
 * receivers to be scheduled on the same node.
 *
 * TODO Should poll the executor number and wait for executors according to
 * "spark.scheduler.minRegisteredResourcesRatio" and
 * "spark.scheduler.maxRegisteredResourcesWaitingTime" rather than running a dummy job.
 */
private def runDummySparkJob(): Unit = {
  if (!ssc.sparkContext.isLocal) {
    ssc.sparkContext.makeRDD(1 to 50, 50).map(x => (x, 1)).reduceByKey(_ + _, 20).collect()
  }
  assert(getExecutors.nonEmpty)
}
 

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)
    }
 

/**
 * Start a receiver along with its scheduled executors
 */
private def startReceiver(
    receiver: Receiver[_],
    scheduledLocations: Seq[TaskLocation]): Unit = {
  def shouldStartReceiver: Boolean = {
 
    // ........... 此处省略1万字 (无关代码) , 呵呵哒 .........
 
  // Function to start the receiver on the worker node
  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)
        //实例化Receiver监控者
        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()))
  val future = ssc.sparkContext.submitJob[Receiver[_], Unit, Unit](
    receiverRDD, 
   startReceiverFunc, //提交Job时候传入startReceiverFunc这个方法，因为startReceiverFunc该方法是在Executor上执行的
  Seq(0), (_, _) => Unit, ())
 
  // 一直重启 receiver job直到 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))
      }
  }(submitJobThreadPool)
  logInfo(s"Receiver ${receiver.streamId} started")
}
 

/** Start the supervisor */
def start() {
  onStart()
  startReceiver()
}

override protected def onStart() {
  registeredBlockGenerators.foreach { _.start() }
}

/** Start receiver */
def startReceiver(): Unit = synchronized {
  try {
    if (onReceiverStart()) {
      logInfo("Starting receiver")
      receiverState = Started
      receiver.onStart()
      logInfo("Called receiver onStart")
    } else {
      // The driver refused us
      stop("Registered unsuccessfully because Driver refused to start receiver " + streamId, None)
    }
  } catch {
    case NonFatal(t) =>
      stop("Error starting receiver " + streamId, Some(t))
  }
}

override protected def onReceiverStart(): Boolean = {
  val msg = RegisterReceiver(
    streamId, receiver.getClass.getSimpleName, host, executorId, endpoint)
  trackerEndpoint.askWithRetry[Boolean](msg)
}

override def receiveAndReply(context: RpcCallContext): PartialFunction[Any, Unit] = {
  // Remote messages
  case RegisterReceiver(streamId, typ, host, executorId, receiverEndpoint) =>
    val successful =
      registerReceiver(streamId, typ, host, executorId, receiverEndpoint, context.senderAddress)
    context.reply(successful)
 

/** Register a receiver */
private def registerReceiver(
    streamId: Int,
    typ: String,
    host: String,
    executorId: String,
    receiverEndpoint: RpcEndpointRef,
    senderAddress: RpcAddress
  ): Boolean = {
  if (!receiverInputStreamIds.contains(streamId)) {
    throw new SparkException("Register received for unexpected id " + streamId)
  }
 
    // ........... 此处省略1万字 (无关代码) , 呵呵哒 .........
 
  if (!isAcceptable) {
    // Refuse it since it‘s scheduled to a wrong executor
    false
  } else {
    val name = s"${typ}-${streamId}"
    val receiverTrackingInfo = ReceiverTrackingInfo(
      streamId,
      ReceiverState.ACTIVE,
      scheduledLocations = None,
      runningExecutor = Some(ExecutorCacheTaskLocation(host, executorId)),
      name = Some(name),
      endpoint = Some(receiverEndpoint))
    receiverTrackingInfos.put(streamId, receiverTrackingInfo)
    listenerBus.post(StreamingListenerReceiverStarted(receiverTrackingInfo.toReceiverInfo))
    logInfo("Registered receiver for stream " + streamId + " from " + senderAddress)
    true
  }
}

private[streaming]
class SocketReceiver[T: ClassTag](
    host: String,
    port: Int,
    bytesToObjects: InputStream => Iterator[T],
    storageLevel: StorageLevel
  ) extends Receiver[T](storageLevel) with Logging {
 
  def onStart() {
    // Start the thread that receives data over a connection
    new Thread("Socket Receiver") {
      setDaemon(true)
      override def run() { receive() }
    }.start()
  }
 
 
  /** Create a socket connection and receive data until receiver is stopped */
  def receive() {
    var socket: Socket = null
    try {
      logInfo("Connecting to " + host + ":" + port)
      socket = new Socket(host, port)
      logInfo("Connected to " + host + ":" + port)
      val iterator = bytesToObjects(socket.getInputStream())
      while(!isStopped && iterator.hasNext) {
        store(iterator.next)
      }
      if (!isStopped()) {
        restart("Socket data stream had no more data")
      } else {
        logInfo("Stopped receiving")
      }
    } catch {
        // ........... 此处省略1万字 (无关代码) , 呵呵哒 .........
  }
}

//根据创建StreamContext时传入的batchInterval，定时发送GenerateJobs消息
private val timer = new RecurringTimer(clock, ssc.graph.batchDuration.milliseconds,
  longTime => eventLoop.post(GenerateJobs(new Time(longTime))), "JobGenerator")
 
JobGenerator的start()方法：
/** Start generation of jobs */
def start(): Unit = synchronized {
  if (eventLoop != null) return // generator has already been started
 
  // Call checkpointWriter here to initialize it before eventLoop uses it to avoid a deadlock.
  // See SPARK-10125
  checkpointWriter
 
  eventLoop = new EventLoop[JobGeneratorEvent]("JobGenerator") {
    override protected def onReceive(event: JobGeneratorEvent): Unit = processEvent(event)
 
    override protected def onError(e: Throwable): Unit = {
      jobScheduler.reportError("Error in job generator", e)
    }
  }
 
  // 启动消息循环处理线程
  eventLoop.start()
 
  if (ssc.isCheckpointPresent) {
    restart()
  } else {
    // 开启定时生成Job的定时器
    startFirstTime()
  }
}

/** Generate jobs and perform checkpoint for the given `time`.  */
private def generateJobs(time: Time) {
  // Set the SparkEnv in this thread, so that job generation code can access the environment
  // Example: BlockRDDs are created in this thread, and it needs to access BlockManager
  // Update: This is probably redundant after threadlocal stuff in SparkEnv has been removed.
  SparkEnv.set(ssc.env)
  Try {
 
    // 根据特定的时间获取具体的数据
    jobScheduler.receiverTracker.allocateBlocksToBatch(time) // allocate received blocks to batch
    //调用DStreamGraph的generateJobs生成Job
    graph.generateJobs(time) // generate jobs using allocated block
  } match {
    case Success(jobs) =>
      val streamIdToInputInfos = jobScheduler.inputInfoTracker.getInfo(time)
      jobScheduler.submitJobSet(JobSet(time, jobs, streamIdToInputInfos))
    case Failure(e) =>
      jobScheduler.reportError("Error generating jobs for time " + time, e)
  }
  eventLoop.post(DoCheckpoint(time, clearCheckpointDataLater = false))
}

// 输出流：具体Action的输出操作
private val outputStreams = new ArrayBuffer[DStream[_]]()
 
def generateJobs(time: Time): Seq[Job] = {
  logDebug("Generating jobs for time " + time)
  val jobs = this.synchronized {
    outputStreams.flatMap { outputStream =>
      val jobOption = outputStream.generateJob(time)
      jobOption.foreach(_.setCallSite(outputStream.creationSite))
      jobOption
    }
  }
  logDebug("Generated " + jobs.length + " jobs for time " + time)
  jobs
}

def submitJobSet(jobSet: JobSet) {
  if (jobSet.jobs.isEmpty) {
    logInfo("No jobs added for time " + jobSet.time)
  } else {
    listenerBus.post(StreamingListenerBatchSubmitted(jobSet.toBatchInfo))
    jobSets.put(jobSet.time, jobSet)
    jobSet.jobs.foreach(job => jobExecutor.execute(new JobHandler(job)))
    logInfo("Added jobs for time " + jobSet.time)
  }
}

private class JobHandler(job: Job) extends Runnable with Logging {
    import JobScheduler._
 
    def run() {
      try {
    
         //  *********** 此处省略无关代码 *******************
 
        // We need to assign `eventLoop` to a temp variable. Otherwise, because
        // `JobScheduler.stop(false)` may set `eventLoop` to null when this method is running, then
        // it‘s possible that when `post` is called, `eventLoop` happens to null.
        var _eventLoop = eventLoop
        if (_eventLoop != null) {
          _eventLoop.post(JobStarted(job, clock.getTimeMillis()))
          // Disable checks for existing output directories in jobs launched by the streaming
          // scheduler, since we may need to write output to an existing directory during checkpoint
          // recovery; see SPARK-4835 for more details.
          PairRDDFunctions.disableOutputSpecValidation.withValue(true) {
            job.run()
          }
          _eventLoop = eventLoop
          if (_eventLoop != null) {
            _eventLoop.post(JobCompleted(job, clock.getTimeMillis()))
          }
        } else {
          // JobScheduler has been stopped.
        }
      } finally {
        ssc.sc.setLocalProperty(JobScheduler.BATCH_TIME_PROPERTY_KEY, null)
        ssc.sc.setLocalProperty(JobScheduler.OUTPUT_OP_ID_PROPERTY_KEY, null)
      }
    }
  }
}