spark CheckPoint的寫流程源碼分析

Checkpoint 寫數據時序圖：

 

1、開始checkpoint，即寫入 RDD 到 hdfs

開始 checkpoint 的入口 是在 SparkContext 提交 Job 時（提交 Job 是發生在 RDD 調用 action 算子時），即 在 SparkContext 的 runJob：

SparkContext.scala

/*This is the main entry point for all actions in Spark.*/
  def runJob[T, U: ClassTag](
      rdd: RDD[T],
      func: (TaskContext, Iterator[T]) => U,
      partitions: Seq[Int],
      resultHandler: (Int, U) => Unit): Unit = {
    if (stopped.get()) {
      throw new IllegalStateException("SparkContext has been shutdown")
    }
    val callSite = getCallSite
    val cleanedFunc = clean(func)
    logInfo("Starting job: " + callSite.shortForm)
    if (conf.getBoolean("spark.logLineage", false)) {
      logInfo("RDD's recursive dependencies:\n" + rdd.toDebugString)
    }
    dagScheduler.runJob(rdd, cleanedFunc, partitions, callSite, resultHandler, localProperties.get)
    progressBar.foreach(_.finishAll())
    rdd.doCheckpoint()
  }

2、RDD.scala 中的 doCheckpoint 方法：

  private[spark] def doCheckpoint(): Unit = {
    RDDOperationScope.withScope(sc, "checkpoint", allowNesting = false, ignoreParent = true) {
      if (!doCheckpointCalled) {
        doCheckpointCalled = true
        if (checkpointData.isDefined) {
          if (checkpointAllMarkedAncestors) {
            // TODO We can collect all the RDDs that needs to be checkpointed, and then checkpoint
            // them in parallel.
            // Checkpoint parents first because our lineage will be truncated after we
            // checkpoint ourselves
            dependencies.foreach(_.rdd.doCheckpoint())
          }
          checkpointData.get.checkpoint()
        } else {
          dependencies.foreach(_.rdd.doCheckpoint())
        }
      }
    }
  }

3、最終都會調用 RDDCheckpointData 的 checkpoint() ，看下代碼：

  final def checkpoint(): Unit = {
    // Guard against multiple threads checkpointing the same RDD by
    // atomically flipping the state of this RDDCheckpointData
    RDDCheckpointData.synchronized {
      if (cpState == Initialized) {
        cpState = CheckpointingInProgress
      } else {
        return
      }
    }
//抽象方法，是由子類實現。實現保存 RDD 功能，並返回一個 newRDD
    val newRDD = doCheckpoint()

    // Update our state and truncate the RDD lineage
    RDDCheckpointData.synchronized {
      cpRDD = Some(newRDD)
      cpState = Checkpointed
// 主要把 rdd 的 dependencies_、partitions_ 等 置爲 null，也就是斷開父依賴
      rdd.markCheckpointed()
    }
  }

4、調用了 doCheckpoint() 方法，此方法在子類 ReliableRDDCheckpointData 中實現，看下其實現代碼：

  protected override def doCheckpoint(): CheckpointRDD[T] = {
    val newRDD = ReliableCheckpointRDD.writeRDDToCheckpointDirectory(rdd, cpDir)

    // Optionally clean our checkpoint files if the reference is out of scope
    if (rdd.conf.getBoolean("spark.cleaner.referenceTracking.cleanCheckpoints", false)) {
      rdd.context.cleaner.foreach { cleaner =>
        cleaner.registerRDDCheckpointDataForCleanup(newRDD, rdd.id)
      }
    }

    logInfo(s"Done checkpointing RDD ${rdd.id} to $cpDir, new parent is RDD ${newRDD.id}")
    newRDD
  }

5、調用 ReliableCheckpointRDD 的 writeRDDToCheckpointDirectory 方法 創建了一個 RDD

  /**
   * Write RDD to checkpoint files and return a ReliableCheckpointRDD representing the RDD.
   */
  def writeRDDToCheckpointDirectory[T: ClassTag](
      originalRDD: RDD[T],
      checkpointDir: String,
      blockSize: Int = -1): ReliableCheckpointRDD[T] = {

    val sc = originalRDD.sparkContext

    // Create the output path for the checkpoint
    val checkpointDirPath = new Path(checkpointDir)
    val fs = checkpointDirPath.getFileSystem(sc.hadoopConfiguration)
    if (!fs.mkdirs(checkpointDirPath)) {
      throw new SparkException(s"Failed to create checkpoint path $checkpointDirPath")
    }

    // Save to file, and reload it as an RDD
    val broadcastedConf = sc.broadcast(
      new SerializableConfiguration(sc.hadoopConfiguration))
    // TODO: This is expensive because it computes the RDD again unnecessarily (SPARK-8582)
    sc.runJob(originalRDD,
      writePartitionToCheckpointFile[T](checkpointDirPath.toString, broadcastedConf) _)

    if (originalRDD.partitioner.nonEmpty) {
      writePartitionerToCheckpointDir(sc, originalRDD.partitioner.get, checkpointDirPath)
    }

    val newRDD = new ReliableCheckpointRDD[T](
      sc, checkpointDirPath.toString, originalRDD.partitioner)
    if (newRDD.partitions.length != originalRDD.partitions.length) {
      throw new SparkException(
        s"Checkpoint RDD $newRDD(${newRDD.partitions.length}) has different " +
          s"number of partitions from original RDD $originalRDD(${originalRDD.partitions.length})")
    }
    newRDD
  }

6、Save to file, and reload it as an RDD，可以將checkpoint文件reload成ReliableCheckpointRDD。