spark streaming之三 rdd,job的动态生成以及动态调度

前面一篇讲到了，DAG静态模板的生成。那么spark streaming会在每一个batch时间一到，就会根据DAG所形成的逻辑以及物理依赖链(dependencies)动态生成RDD以及由这些RDD组成的job,并形成一个job集合提交到集群当中执行。那么下面我们具体分析这三个步骤。

 

首先从JobScheduler讲起。在本节所需要了解的是JobScheduler的两个重要对象。jobExecutor与JobHandler。jobExecutor是一个名为streaming-job-executor的线程池，JobHandler是一个继承自Runnable的线程类。提交过来的JOB将提交到到这里执行。

private val jobExecutor =
    ThreadUtils.newDaemonFixedThreadPool(numConcurrentJobs, "streaming-job-executor")

 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="$batchUrl">$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)
      }
    }
  }
}

View Code