spark streaming之三 rdd,job的动态生成以及动态调度

 private class JobHandler(job: Job) extends Runnable with Logging {
    import JobScheduler._

    def run() {
      val oldProps = ssc.sparkContext.getLocalProperties
      try {
        ssc.sparkContext.setLocalProperties(SerializationUtils.clone(ssc.savedProperties.get()))
        val formattedTime = UIUtils.formatBatchTime(
          job.time.milliseconds, ssc.graph.batchDuration.milliseconds, showYYYYMMSS = false)
        val batchUrl = s"/streaming/batch/?id=${job.time.milliseconds}"
        val batchLinkText = s"[output operation ${job.outputOpId}, batch time ${formattedTime}]"

        ssc.sc.setJobDescription(
          s"""Streaming job from <a href="http://t.zoukankan.com/$batchUrl">$batchLinkText</a>""")
        ssc.sc.setLocalProperty(BATCH_TIME_PROPERTY_KEY, job.time.milliseconds.toString)
        ssc.sc.setLocalProperty(OUTPUT_OP_ID_PROPERTY_KEY, job.outputOpId.toString)
        // Checkpoint all RDDs marked for checkpointing to ensure their lineages are
        // truncated periodically. Otherwise, we may run into stack overflows (SPARK-6847).
        ssc.sparkContext.setLocalProperty(RDD.CHECKPOINT_ALL_MARKED_ANCESTORS, "true")

        // 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.sparkContext.setLocalProperties(oldProps)
      }
    }
  }
}

 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)
    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()//
    jobGenerator.start()//
    executorAllocationManager.foreach(_.start())
    logInfo("Started JobScheduler")
  }