spark 2.1 Stage and ResultStage and ShuffleMapStage

Stage

/**
 * A stage is a set of parallel tasks all computing the same function that need to run as part
 * of a Spark job, where all the tasks have the same shuffle dependencies. Each DAG of tasks run
 * by the scheduler is split up into stages at the boundaries where shuffle occurs, and then the
 * DAGScheduler runs these stages in topological order.
 *
 * Each Stage can either be a shuffle map stage, in which case its tasks' results are input for
 * other stage(s), or a result stage, in which case its tasks directly compute a Spark action
 * (e.g. count(), save(), etc) by running a function on an RDD. For shuffle map stages, we also
 * track the nodes that each output partition is on.
 *
 * Each Stage also has a firstJobId, identifying the job that first submitted the stage.  When FIFO
 * scheduling is used, this allows Stages from earlier jobs to be computed first or recovered
 * faster on failure.
 *
 * Finally, a single stage can be re-executed in multiple attempts due to fault recovery. In that
 * case, the Stage object will track multiple StageInfo objects to pass to listeners or the web UI.
 * The latest one will be accessible through latestInfo.
 *
 * @param id Unique stage ID
 * @param rdd RDD that this stage runs on: for a shuffle map stage, it's the RDD we run map tasks
 *   on, while for a result stage, it's the target RDD that we ran an action on
 * @param numTasks Total number of tasks in stage; result stages in particular may not need to
 *   compute all partitions, e.g. for first(), lookup(), and take().
 * @param parents List of stages that this stage depends on (through shuffle dependencies).
 * @param firstJobId ID of the first job this stage was part of, for FIFO scheduling.
 * @param callSite Location in the user program associated with this stage: either where the target
 *   RDD was created, for a shuffle map stage, or where the action for a result stage was called.
 */
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. */
  val jobIds = new HashSet[Int]

  val pendingPartitions = new HashSet[Int]

  /** The ID to use for the next new attempt for this stage. */
  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).
   */
  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).
   */
  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.
   *
   * This method updates the running set of failed stage attempts and returns
   * true if the number of failures exceeds the allowable number of failures.
   */
  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. */
  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. */
  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). */
  def findMissingPartitions(): Seq[Int]
}

private[scheduler] object Stage {
  // The number of consecutive failures allowed before a stage is aborted
  val MAX_CONSECUTIVE_FETCH_FAILURES = 4
}

ShuffleMapStage

/**
 * ShuffleMapStages are intermediate stages in the execution DAG that produce data for a shuffle.
 * They occur right before each shuffle operation, and might contain multiple pipelined operations
 * before that (e.g. map and filter). When executed, they save map output files that can later be
 * fetched by reduce tasks. The `shuffleDep` field describes the shuffle each stage is part of,
 * and variables like `outputLocs` and `numAvailableOutputs` track how many map outputs are ready.
 *
 * ShuffleMapStages can also be submitted independently as jobs with DAGScheduler.submitMapStage.
 * For such stages, the ActiveJobs that submitted them are tracked in `mapStageJobs`. Note that
 * there can be multiple ActiveJobs trying to compute the same shuffle map stage.
 */
private[spark] class ShuffleMapStage(
    id: Int,
    rdd: RDD[_],
    numTasks: Int,
    parents: List[Stage],
    firstJobId: Int,
    callSite: CallSite,
    val shuffleDep: ShuffleDependency[_, _, _])
  extends Stage(id, rdd, numTasks, parents, firstJobId, callSite) {

  private[this] var _mapStageJobs: List[ActiveJob] = Nil

  private[this] var _numAvailableOutputs: Int = 0

  /**
   * List of [[MapStatus]] for each partition. The index of the array is the map partition id,
   * and each value in the array is the list of possible [[MapStatus]] for a partition
   * (a single task might run multiple times).
   */
  private[this] val outputLocs = Array.fill[List[MapStatus]](numPartitions)(Nil)

  override def toString: String = "ShuffleMapStage " + id

  /**
   * Returns the list of active jobs,
   * i.e. map-stage jobs that were submitted to execute this stage independently (if any).
   */
  def mapStageJobs: Seq[ActiveJob] = _mapStageJobs

  /** Adds the job to the active job list. */
  def addActiveJob(job: ActiveJob): Unit = {
    _mapStageJobs = job :: _mapStageJobs
  }

  /** Removes the job from the active job list. */
  def removeActiveJob(job: ActiveJob): Unit = {
    _mapStageJobs = _mapStageJobs.filter(_ != job)
  }

  /**
   * Number of partitions that have shuffle outputs.
   * When this reaches [[numPartitions]], this map stage is ready.
   * This should be kept consistent as `outputLocs.filter(!_.isEmpty).size`.
   */
  def numAvailableOutputs: Int = _numAvailableOutputs

  /**
   * Returns true if the map stage is ready, i.e. all partitions have shuffle outputs.
   * This should be the same as `outputLocs.contains(Nil)`.
   */
  def isAvailable: Boolean = _numAvailableOutputs == numPartitions

  /** Returns the sequence of partition ids that are missing (i.e. needs to be computed). */
  override def findMissingPartitions(): Seq[Int] = {
    val missing = (0 until numPartitions).filter(id => outputLocs(id).isEmpty)
    assert(missing.size == numPartitions - _numAvailableOutputs,
      s"${missing.size} missing, expected ${numPartitions - _numAvailableOutputs}")
    missing
  }

  def addOutputLoc(partition: Int, status: MapStatus): Unit = {
    val prevList = outputLocs(partition)
    outputLocs(partition) = status :: prevList
    if (prevList == Nil) {
      _numAvailableOutputs += 1
    }
  }

  def removeOutputLoc(partition: Int, bmAddress: BlockManagerId): Unit = {
    val prevList = outputLocs(partition)
    val newList = prevList.filterNot(_.location == bmAddress)
    outputLocs(partition) = newList
    if (prevList != Nil && newList == Nil) {
      _numAvailableOutputs -= 1
    }
  }

  /**
   * Returns an array of [[MapStatus]] (index by partition id). For each partition, the returned
   * value contains only one (i.e. the first) [[MapStatus]]. If there is no entry for the partition,
   * that position is filled with null.
   */
  def outputLocInMapOutputTrackerFormat(): Array[MapStatus] = {
    outputLocs.map(_.headOption.orNull)
  }

  /**
   * Removes all shuffle outputs associated with this executor. Note that this will also remove
   * outputs which are served by an external shuffle server (if one exists), as they are still
   * registered with this execId.
   */
  def removeOutputsOnExecutor(execId: String): Unit = {
    var becameUnavailable = false
    for (partition <- 0 until numPartitions) {
      val prevList = outputLocs(partition)
      val newList = prevList.filterNot(_.location.executorId == execId)
      outputLocs(partition) = newList
      if (prevList != Nil && newList == Nil) {
        becameUnavailable = true
        _numAvailableOutputs -= 1
      }
    }
    if (becameUnavailable) {
      logInfo("%s is now unavailable on executor %s (%d/%d, %s)".format(
        this, execId, _numAvailableOutputs, numPartitions, isAvailable))
    }
  }
}