Spark之RDD弹性特性

private[spark] class TaskSchedulerImpl(
    val sc: SparkContext,
    val maxTaskFailures: Int,
    isLocal: Boolean = false)
  extends TaskScheduler with Logging
{
  def this(sc: SparkContext) = this(sc, sc.conf.getInt("spark.task.maxFailures", 4))

  val conf = sc.conf

private[scheduler] abstract class Stage(
    val id: Int,
    val rdd: RDD[_],
    val numTasks: Int,
    val parents: List[Stage],
    val firstJobId: Int,
    val callSite: CallSite)
  extends Logging {

  val numPartitions = rdd.partitions.length

  /** Set of jobs that this stage belongs to.属于这个工作集的Stage */
  val jobIds = new HashSet[Int]

  val pendingPartitions = new HashSet[Int]

  /** The ID to use for the next new attempt for this stage.用于此Stage的下一个新attempt的ID */
  private var nextAttemptId: Int = 0

  val name: String = callSite.shortForm
  val details: String = callSite.longForm

  /**
   * Pointer to the [StageInfo] object for the most recent attempt. This needs to be initialized
   * here, before any attempts have actually been created, because the DAGScheduler uses this
   * StageInfo to tell SparkListeners when a job starts (which happens before any stage attempts
   * have been created).
   * 最新的[StageInfo] Object指针，需要被初始化，任何attempts都是被创造出来的，因为DAGScheduler使用
   * StageInfo告诉SparkListeners工作何时开始（即发生前的任何阶段已经创建）
   */
  private var _latestInfo: StageInfo = StageInfo.fromStage(this, nextAttemptId)

  /**
   * Set of stage attempt IDs that have failed with a FetchFailure. We keep track of these
   * failures in order to avoid endless retries if a stage keeps failing with a FetchFailure.
   * We keep track of each attempt ID that has failed to avoid recording duplicate failures if
   * multiple tasks from the same stage attempt fail (SPARK-5945).
   * 设置Stage attempt IDs当失败时可以读取失败信息，跟踪这些失败，为了避免无休止的重复失败
   * 跟踪每一次attempt，以便避免记录重复故障，如果从同一stage创建多任务失败(SPARK-5945)
   */
  private val fetchFailedAttemptIds = new HashSet[Int]

  private[scheduler] def clearFailures() : Unit = {
    fetchFailedAttemptIds.clear()
  }

  /**
   * Check whether we should abort the failedStage due to multiple consecutive fetch failures.
   * 检查是否应该中止由于连续多次读取失败的stage
   * This method updates the running set of failed stage attempts and returns
   * true if the number of failures exceeds the allowable number of failures.
   * 如果失败的次数超过允许的次数，此方法更新失败stage attempts和返回的运行集
   */
  private[scheduler] def failedOnFetchAndShouldAbort(stageAttemptId: Int): Boolean = {
    fetchFailedAttemptIds.add(stageAttemptId)
    fetchFailedAttemptIds.size >= Stage.MAX_CONSECUTIVE_FETCH_FAILURES
  }

  /** Creates a new attempt for this stage by creating a new StageInfo with a new attempt ID. */
  // 在stage中创建一个新的attempt
  def makeNewStageAttempt(
      numPartitionsToCompute: Int,
      taskLocalityPreferences: Seq[Seq[TaskLocation]] = Seq.empty): Unit = {
    val metrics = new TaskMetrics
    metrics.register(rdd.sparkContext)
    _latestInfo = StageInfo.fromStage(
      this, nextAttemptId, Some(numPartitionsToCompute), metrics, taskLocalityPreferences)
    nextAttemptId += 1
  }

  /** Returns the StageInfo for the most recent attempt for this stage. */
  // 返回当前stage中最新的stageinfo
  def latestInfo: StageInfo = _latestInfo

  override final def hashCode(): Int = id

  override final def equals(other: Any): Boolean = other match {
    case stage: Stage => stage != null && stage.id == id
    case _ => false
  }

  /** Returns the sequence of partition ids that are missing (i.e. needs to be computed). */
  // 返回需要重新计算的分区标识的序列
  def findMissingPartitions(): Seq[Int]
}

private[scheduler] object Stage {
  // The number of consecutive failures allowed before a stage is aborted
  // 允许一个stage中止的连续故障数
  val MAX_CONSECUTIVE_FETCH_FAILURES = 4
}

  /**
   * Internal method to this RDD; will read from cache if applicable, or otherwise compute it.
   * This should ‘‘not‘‘ be called by users directly, but is available for implementors of custom
   * subclasses of RDD.
   * RDD的内部方法，将从合适的缓存中读取，否则计算它。这不应该被用户直接使用，但可用于实现自定义的子RDD
   */
  final def iterator(split: Partition, context: TaskContext): Iterator[T] = {
    if (storageLevel != StorageLevel.NONE) {
      getOrCompute(split, context)
    } else {
      computeOrReadCheckpoint(split, context)
    }
  }

  val NONE = new StorageLevel(false, false, false, false)
  val DISK_ONLY = new StorageLevel(true, false, false, false)
  val DISK_ONLY_2 = new StorageLevel(true, false, false, false, 2)
  val MEMORY_ONLY = new StorageLevel(false, true, false, true)
  val MEMORY_ONLY_2 = new StorageLevel(false, true, false, true, 2)
  val MEMORY_ONLY_SER = new StorageLevel(false, true, false, false)
  val MEMORY_ONLY_SER_2 = new StorageLevel(false, true, false, false, 2)
  val MEMORY_AND_DISK = new StorageLevel(true, true, false, true)
  val MEMORY_AND_DISK_2 = new StorageLevel(true, true, false, true, 2)
  val MEMORY_AND_DISK_SER = new StorageLevel(true, true, false, false)
  val MEMORY_AND_DISK_SER_2 = new StorageLevel(true, true, false, false, 2)
  val OFF_HEAP = new StorageLevel(true, true, true, false, 1)

  /**
   * Return a new RDD that is reduced into `numPartitions` partitions.
   *
   * This results in a narrow dependency, e.g. if you go from 1000 partitions
   * to 100 partitions, there will not be a shuffle, instead each of the 100
   * new partitions will claim 10 of the current partitions.
   *
   * However, if you‘re doing a drastic coalesce, e.g. to numPartitions = 1,
   * this may result in your computation taking place on fewer nodes than
   * you like (e.g. one node in the case of numPartitions = 1). To avoid this,
   * you can pass shuffle = true. This will add a shuffle step, but means the
   * current upstream partitions will be executed in parallel (per whatever
   * the current partitioning is).
   *
   * Note: With shuffle = true, you can actually coalesce to a larger number
   * of partitions. This is useful if you have a small number of partitions,
   * say 100, potentially with a few partitions being abnormally large. Calling
   * coalesce(1000, shuffle = true) will result in 1000 partitions with the
   * data distributed using a hash partitioner.
   */
  def coalesce(numPartitions: Int, shuffle: Boolean = false,
               partitionCoalescer: Option[PartitionCoalescer] = Option.empty)
              (implicit ord: Ordering[T] = null)
      : RDD[T] = withScope {
    require(numPartitions > 0, s"Number of partitions ($numPartitions) must be positive.")
    if (shuffle) {
      /** Distributes elements evenly across output partitions, starting from a random partition. */
      // 从随机分区开始，将元素均匀分布在输出分区上
      val distributePartition = (index: Int, items: Iterator[T]) => {
        var position = (new Random(index)).nextInt(numPartitions)
        items.map { t =>
          // Note that the hash code of the key will just be the key itself. The HashPartitioner
          // will mod it with the number of total partitions.
          // key的哈希码是key本身，HashPartitioner将它与总分区数进行取模运算
          position = position + 1
          (position, t)
        }
      } : Iterator[(Int, T)]

      // include a shuffle step so that our upstream tasks are still distributed
      // 包括一个shuffle步骤，使我们的上游任务仍然是分布式的
      new CoalescedRDD(
        new ShuffledRDD[Int, T, T](mapPartitionsWithIndex(distributePartition),
        new HashPartitioner(numPartitions)),
        numPartitions,
        partitionCoalescer).values
    } else {
      new CoalescedRDD(this, numPartitions, partitionCoalescer)
    }
  }