【Spark三十八】Spark Checkpoint机制

SparkContext中对于checkpoint的操作

  def runJob[T, U: ClassTag](
      rdd: RDD[T],
      func: (TaskContext, Iterator[T]) => U,
      partitions: Seq[Int],
      allowLocal: Boolean,
      resultHandler: (Int, U) => Unit) {
    if (dagScheduler == null) {
      throw new SparkException("SparkContext has been shutdown")
    }
    val callSite = getCallSite
    val cleanedFunc = clean(func)
    logInfo("Starting job: " + callSite.shortForm)
    dagScheduler.runJob(rdd, cleanedFunc, partitions, callSite, allowLocal,
      resultHandler, localProperties.get)
    progressBar.foreach(_.finishAll())
    rdd.doCheckpoint() ///第一次Job执行完成时，将RDD进行checkpoint，注意，此时的RDD是整个Job的最后一个RDD。
  }

RDD的doCheckpoint方法

  /**
   * Performs the checkpointing of this RDD by saving this. It is called after a job using this RDD
   * has completed (therefore the RDD has been materialized and potentially stored in memory).
   * doCheckpoint() is called recursively on the parent RDDs.
   */
  private[spark] def doCheckpoint() {
    if (!doCheckpointCalled) {
      doCheckpointCalled = true
      if (checkpointData.isDefined) {
        checkpointData.get.doCheckpoint()
      } else {
        dependencies.foreach(_.rdd.doCheckpoint())
      }
    }
  }