Spark应用执行流程

import org.apache.spark.{SparkConf, SparkContext}

object SparkWC {
  def main(args: Array[String]) {
    val sparkConf = new SparkConf()
    val sparkContext = new SparkContext(sparkConf)
    sparkContext.textFile(args(0))
          .flatMap(line => line.split(" "))
          .map(word => (word, 1))
          .reduceByKey(_ + _)
          .saveAsTextFile(args(1))
  }
}

def textFile(
      path: String,
      minPartitions: Int = defaultMinPartitions): RDD[String] = withScope {
    assertNotStopped()
    hadoopFile(path, classOf[TextInputFormat], classOf[LongWritable], classOf[Text],
      minPartitions).map(pair => pair._2.toString).setName(path)
  }

  def saveAsTextFile(path: String): Unit = withScope {
    // https://issues.apache.org/jira/browse/SPARK-2075
    //
    // NullWritable is a `Comparable` in Hadoop 1.+, so the compiler cannot find an implicit
    // Ordering for it and will use the default `null`. However, it's a `Comparable[NullWritable]`
    // in Hadoop 2.+, so the compiler will call the implicit `Ordering.ordered` method to create an
    // Ordering for `NullWritable`. That's why the compiler will generate different anonymous
    // classes for `saveAsTextFile` in Hadoop 1.+ and Hadoop 2.+.
    //
    // Therefore, here we provide an explicit Ordering `null` to make sure the compiler generate
    // same bytecodes for `saveAsTextFile`.
    val nullWritableClassTag = implicitly[ClassTag[NullWritable]]
    val textClassTag = implicitly[ClassTag[Text]]
    val r = this.mapPartitions { iter =>
      val text = new Text()
      iter.map { x =>
        text.set(x.toString)
        (NullWritable.get(), text)
      }
    }
    RDD.rddToPairRDDFunctions(r)(nullWritableClassTag, textClassTag, null)
      .saveAsHadoopFile[TextOutputFormat[NullWritable, Text]](path)
  }
  
  
  //接下来调用这个
  def saveAsHadoopFile[F <: OutputFormat[K, V]](
      path: String)(implicit fm: ClassTag[F]): Unit = self.withScope {
    saveAsHadoopFile(path, keyClass, valueClass, fm.runtimeClass.asInstanceOf[Class[F]])
  }
  
//省略一部分调用过程
...
...

//最后调用这个函数
  def saveAsHadoopDataset(conf: JobConf): Unit = self.withScope {
    // Rename this as hadoopConf internally to avoid shadowing (see SPARK-2038).
    val hadoopConf = conf
    val outputFormatInstance = hadoopConf.getOutputFormat
    val keyClass = hadoopConf.getOutputKeyClass
    val valueClass = hadoopConf.getOutputValueClass
    if (outputFormatInstance == null) {
      throw new SparkException("Output format class not set")
    }
    if (keyClass == null) {
      throw new SparkException("Output key class not set")
    }
    if (valueClass == null) {
      throw new SparkException("Output value class not set")
    }
    SparkHadoopUtil.get.addCredentials(hadoopConf)

    logDebug("Saving as hadoop file of type (" + keyClass.getSimpleName + ", " +
      valueClass.getSimpleName + ")")

    if (isOutputSpecValidationEnabled) {
      // FileOutputFormat ignores the filesystem parameter
      val ignoredFs = FileSystem.get(hadoopConf)
      hadoopConf.getOutputFormat.checkOutputSpecs(ignoredFs, hadoopConf)
    }

    val writer = new SparkHadoopWriter(hadoopConf)
    writer.preSetup()

    val writeToFile = (context: TaskContext, iter: Iterator[(K, V)]) => {
      // Hadoop wants a 32-bit task attempt ID, so if ours is bigger than Int.MaxValue, roll it
      // around by taking a mod. We expect that no task will be attempted 2 billion times.
      val taskAttemptId = (context.taskAttemptId % Int.MaxValue).toInt

      val outputMetricsAndBytesWrittenCallback: Option[(OutputMetrics, () => Long)] =
        initHadoopOutputMetrics(context)

      writer.setup(context.stageId, context.partitionId, taskAttemptId)
      writer.open()
      var recordsWritten = 0L

      Utils.tryWithSafeFinallyAndFailureCallbacks {
        while (iter.hasNext) {
          val record = iter.next()
          writer.write(record._1.asInstanceOf[AnyRef], record._2.asInstanceOf[AnyRef])

          // Update bytes written metric every few records
          maybeUpdateOutputMetrics(outputMetricsAndBytesWrittenCallback, recordsWritten)
          recordsWritten += 1
        }
      }(finallyBlock = writer.close())
      writer.commit()
      outputMetricsAndBytesWrittenCallback.foreach { case (om, callback) =>
        om.setBytesWritten(callback())
        om.setRecordsWritten(recordsWritten)
      }
    }

    self.context.runJob(self, writeToFile)
    writer.commitJob()
  }

 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() //是否cache rdd
  }

  def runJob[T, U](
      rdd: RDD[T],
      func: (TaskContext, Iterator[T]) => U,
      partitions: Seq[Int],
      callSite: CallSite,
      resultHandler: (Int, U) => Unit,
      properties: Properties): Unit = {
    val start = System.nanoTime
    val waiter = submitJob(rdd, func, partitions, callSite, resultHandler, properties)
    // Note: Do not call Await.ready(future) because that calls `scala.concurrent.blocking`,
    // which causes concurrent SQL executions to fail if a fork-join pool is used. Note that
    // due to idiosyncrasies in Scala, `awaitPermission` is not actually used anywhere so it's
    // safe to pass in null here. For more detail, see SPARK-13747.
    val awaitPermission = null.asInstanceOf[scala.concurrent.CanAwait]
    waiter.completionFuture.ready(Duration.Inf)(awaitPermission)
    waiter.completionFuture.value.get match {
      case scala.util.Success(_) =>
        logInfo("Job %d finished: %s, took %f s".format
          (waiter.jobId, callSite.shortForm, (System.nanoTime - start) / 1e9))
      case scala.util.Failure(exception) =>
        logInfo("Job %d failed: %s, took %f s".format
          (waiter.jobId, callSite.shortForm, (System.nanoTime - start) / 1e9))
        // SPARK-8644: Include user stack trace in exceptions coming from DAGScheduler.
        val callerStackTrace = Thread.currentThread().getStackTrace.tail
        exception.setStackTrace(exception.getStackTrace ++ callerStackTrace)
        throw exception
    }
  }

  def submitJob[T, U](
      rdd: RDD[T],
      func: (TaskContext, Iterator[T]) => U,
      partitions: Seq[Int],
      callSite: CallSite,
      resultHandler: (Int, U) => Unit,
      properties: Properties): JobWaiter[U] = {
    // Check to make sure we are not launching a task on a partition that does not exist.
    val maxPartitions = rdd.partitions.length
    partitions.find(p => p >= maxPartitions || p < 0).foreach { p =>
      throw new IllegalArgumentException(
        "Attempting to access a non-existent partition: " + p + ". " +
          "Total number of partitions: " + maxPartitions)
    }

    val jobId = nextJobId.getAndIncrement()
    if (partitions.size == 0) {
      // Return immediately if the job is running 0 tasks
      return new JobWaiter[U](this, jobId, 0, resultHandler)
    }

    assert(partitions.size > 0)
    val func2 = func.asInstanceOf[(TaskContext, Iterator[_]) => _]
    val waiter = new JobWaiter(this, jobId, partitions.size, resultHandler)
    eventProcessLoop.post(JobSubmitted(
      jobId, rdd, func2, partitions.toArray, callSite, waiter,
      SerializationUtils.clone(properties)))
    waiter
  }

private def doOnReceive(event: DAGSchedulerEvent): Unit = event match {
  case JobSubmitted(jobId, rdd, func, partitions, callSite, listener, properties) =>
    dagScheduler.handleJobSubmitted(jobId, rdd, func, partitions, callSite, listener, properties)

private[scheduler] def handleJobSubmitted(jobId: Int,
    finalRDD: RDD[_],
    func: (TaskContext, Iterator[_]) => _,
    partitions: Array[Int],
    callSite: CallSite,
    listener: JobListener,
    properties: Properties) {
  var finalStage: ResultStage = null
  try {
    // New stage creation may throw an exception if, for example, jobs are run on a
    // HadoopRDD whose underlying HDFS files have been deleted.
    finalStage = newResultStage(finalRDD, func, partitions, jobId, callSite)
  } catch {
    case e: Exception =>
      logWarning("Creating new stage failed due to exception - job: " + jobId, e)
      listener.jobFailed(e)
      return
  }

  val job = new ActiveJob(jobId, finalStage, callSite, listener, properties)
  clearCacheLocs()
  logInfo("Got job %s (%s) with %d output partitions".format(
    job.jobId, callSite.shortForm, partitions.length))
  logInfo("Final stage: " + finalStage + " (" + finalStage.name + ")")
  logInfo("Parents of final stage: " + finalStage.parents)
  logInfo("Missing parents: " + getMissingParentStages(finalStage))

  val jobSubmissionTime = clock.getTimeMillis()
  jobIdToActiveJob(jobId) = job
  activeJobs += job
  finalStage.setActiveJob(job)
  val stageIds = jobIdToStageIds(jobId).toArray
  val stageInfos = stageIds.flatMap(id => stageIdToStage.get(id).map(_.latestInfo))
  listenerBus.post(
    SparkListenerJobStart(job.jobId, jobSubmissionTime, stageInfos, properties))
  submitStage(finalStage)

  submitWaitingStages()
}

/** Submits stage, but first recursively submits any missing parents. */
private def submitStage(stage: Stage) {
  val jobId = activeJobForStage(stage)
  if (jobId.isDefined) {
    logDebug("submitStage(" + stage + ")")
    if (!waitingStages(stage) && !runningStages(stage) && !failedStages(stage)) {
      val missing = getMissingParentStages(stage).sortBy(_.id)
      logDebug("missing: " + missing)
      if (missing.isEmpty) {
        logInfo("Submitting " + stage + " (" + stage.rdd + "), which has no missing parents")
        submitMissingTasks(stage, jobId.get)
      } else {
        for (parent <- missing) {
          submitStage(parent)
        }
        waitingStages += stage
      }
    }
  } else {
    abortStage(stage, "No active job for stage " + stage.id, None)
  }
}

private def submitMissingTasks(stage: Stage, jobId: Int) {
  logDebug("submitMissingTasks(" + stage + ")")
  // Get our pending tasks and remember them in our pendingTasks entry
  stage.pendingPartitions.clear()

  // First figure out the indexes of partition ids to compute.
  val partitionsToCompute: Seq[Int] = stage.findMissingPartitions()

  // Use the scheduling pool, job group, description, etc. from an ActiveJob associated
  // with this Stage
  val properties = jobIdToActiveJob(jobId).properties

  runningStages += stage
  // SparkListenerStageSubmitted should be posted before testing whether tasks are
  // serializable. If tasks are not serializable, a SparkListenerStageCompleted event
  // will be posted, which should always come after a corresponding SparkListenerStageSubmitted
  // event.
  stage match {
    case s: ShuffleMapStage =>
      outputCommitCoordinator.stageStart(stage = s.id, maxPartitionId = s.numPartitions - 1)
    case s: ResultStage =>
      outputCommitCoordinator.stageStart(
        stage = s.id, maxPartitionId = s.rdd.partitions.length - 1)
  }
  val taskIdToLocations: Map[Int, Seq[TaskLocation]] = try {
    stage match {
      case s: ShuffleMapStage =>
        partitionsToCompute.map { id => (id, getPreferredLocs(stage.rdd, id))}.toMap
      case s: ResultStage =>
        val job = s.activeJob.get
        partitionsToCompute.map { id =>
          val p = s.partitions(id)
          (id, getPreferredLocs(stage.rdd, p))
        }.toMap
    }
  } catch {
    case NonFatal(e) =>
      stage.makeNewStageAttempt(partitionsToCompute.size)
      listenerBus.post(SparkListenerStageSubmitted(stage.latestInfo, properties))
      abortStage(stage, s"Task creation failed: $e\n${Utils.exceptionString(e)}", Some(e))
      runningStages -= stage
      return
  }

  stage.makeNewStageAttempt(partitionsToCompute.size, taskIdToLocations.values.toSeq)
  listenerBus.post(SparkListenerStageSubmitted(stage.latestInfo, properties))

  // TODO: Maybe we can keep the taskBinary in Stage to avoid serializing it multiple times.
  // Broadcasted binary for the task, used to dispatch tasks to executors. Note that we broadcast
  // the serialized copy of the RDD and for each task we will deserialize it, which means each
  // task gets a different copy of the RDD. This provides stronger isolation between tasks that
  // might modify state of objects referenced in their closures. This is necessary in Hadoop
  // where the JobConf/Configuration object is not thread-safe.
  var taskBinary: Broadcast[Array[Byte]] = null
  try {
    // For ShuffleMapTask, serialize and broadcast (rdd, shuffleDep).
    // For ResultTask, serialize and broadcast (rdd, func).
    val taskBinaryBytes: Array[Byte] = stage match {
      case stage: ShuffleMapStage =>
        JavaUtils.bufferToArray(
          closureSerializer.serialize((stage.rdd, stage.shuffleDep): AnyRef))
      case stage: ResultStage =>
        JavaUtils.bufferToArray(closureSerializer.serialize((stage.rdd, stage.func): AnyRef))
    }

    taskBinary = sc.broadcast(taskBinaryBytes)
  } catch {
    // In the case of a failure during serialization, abort the stage.
    case e: NotSerializableException =>
      abortStage(stage, "Task not serializable: " + e.toString, Some(e))
      runningStages -= stage

      // Abort execution
      return
    case NonFatal(e) =>
      abortStage(stage, s"Task serialization failed: $e\n${Utils.exceptionString(e)}", Some(e))
      runningStages -= stage
      return
  }

  val tasks: Seq[Task[_]] = try {
    stage match {
      case stage: ShuffleMapStage =>
        partitionsToCompute.map { id =>
          val locs = taskIdToLocations(id)
          val part = stage.rdd.partitions(id)
          new ShuffleMapTask(stage.id, stage.latestInfo.attemptId,
            taskBinary, part, locs, stage.latestInfo.taskMetrics, properties)
        }

      case stage: ResultStage =>
        val job = stage.activeJob.get
        partitionsToCompute.map { id =>
          val p: Int = stage.partitions(id)
          val part = stage.rdd.partitions(p)
          val locs = taskIdToLocations(id)
          new ResultTask(stage.id, stage.latestInfo.attemptId,
            taskBinary, part, locs, id, properties, stage.latestInfo.taskMetrics)
        }
    }
  } catch {
    case NonFatal(e) =>
      abortStage(stage, s"Task creation failed: $e\n${Utils.exceptionString(e)}", Some(e))
      runningStages -= stage
      return
  }

  if (tasks.size > 0) {
    logInfo("Submitting " + tasks.size + " missing tasks from " + stage + " (" + stage.rdd + ")")
    stage.pendingPartitions ++= tasks.map(_.partitionId)
    logDebug("New pending partitions: " + stage.pendingPartitions)
    taskScheduler.submitTasks(new TaskSet(
      tasks.toArray, stage.id, stage.latestInfo.attemptId, jobId, properties))
    stage.latestInfo.submissionTime = Some(clock.getTimeMillis())
  } else {
    // Because we posted SparkListenerStageSubmitted earlier, we should mark
    // the stage as completed here in case there are no tasks to run
    markStageAsFinished(stage, None)

    val debugString = stage match {
      case stage: ShuffleMapStage =>
        s"Stage ${stage} is actually done; " +
          s"(available: ${stage.isAvailable}," +
          s"available outputs: ${stage.numAvailableOutputs}," +
          s"partitions: ${stage.numPartitions})"
      case stage : ResultStage =>
        s"Stage ${stage} is actually done; (partitions: ${stage.numPartitions})"
    }
    logDebug(debugString)
  }
}

override def submitTasks(taskSet: TaskSet) {
  val tasks = taskSet.tasks
  logInfo("Adding task set " + taskSet.id + " with " + tasks.length + " tasks")
  this.synchronized {
    val manager = createTaskSetManager(taskSet, maxTaskFailures)
    val stage = taskSet.stageId
    val stageTaskSets =
      taskSetsByStageIdAndAttempt.getOrElseUpdate(stage, new HashMap[Int, TaskSetManager])
    stageTaskSets(taskSet.stageAttemptId) = manager
    val conflictingTaskSet = stageTaskSets.exists { case (_, ts) =>
      ts.taskSet != taskSet && !ts.isZombie
    }
    if (conflictingTaskSet) {
      throw new IllegalStateException(s"more than one active taskSet for stage $stage:" +
        s" ${stageTaskSets.toSeq.map{_._2.taskSet.id}.mkString(",")}")
    }
    schedulableBuilder.addTaskSetManager(manager, manager.taskSet.properties)

    if (!isLocal && !hasReceivedTask) {
      starvationTimer.scheduleAtFixedRate(new TimerTask() {
        override def run() {
          if (!hasLaunchedTask) {
            logWarning("Initial job has not accepted any resources; " +
              "check your cluster UI to ensure that workers are registered " +
              "and have sufficient resources")
          } else {
            this.cancel()
          }
        }
      }, STARVATION_TIMEOUT_MS, STARVATION_TIMEOUT_MS)
    }
    hasReceivedTask = true
  }
  backend.reviveOffers()
}

override def receive: PartialFunction[Any, Unit] = {
...
case ReviveOffers =>
  makeOffers()
...
  }

private def makeOffers() {
  // Filter out executors under killing
  val activeExecutors = executorDataMap.filterKeys(executorIsAlive)
  val workOffers = activeExecutors.map { case (id, executorData) =>
    new WorkerOffer(id, executorData.executorHost, executorData.freeCores)
  }.toSeq
  launchTasks(scheduler.resourceOffers(workOffers))
}

private def launchTasks(tasks: Seq[Seq[TaskDescription]]) {
  for (task <- tasks.flatten) {
    val serializedTask = ser.serialize(task)
    if (serializedTask.limit >= maxRpcMessageSize) {
      scheduler.taskIdToTaskSetManager.get(task.taskId).foreach { taskSetMgr =>
        try {
          var msg = "Serialized task %s:%d was %d bytes, which exceeds max allowed: " +
            "spark.rpc.message.maxSize (%d bytes). Consider increasing " +
            "spark.rpc.message.maxSize or using broadcast variables for large values."
          msg = msg.format(task.taskId, task.index, serializedTask.limit, maxRpcMessageSize)
          taskSetMgr.abort(msg)
        } catch {
          case e: Exception => logError("Exception in error callback", e)
        }
      }
    }
    else {
      val executorData = executorDataMap(task.executorId)
      executorData.freeCores -= scheduler.CPUS_PER_TASK

      logInfo(s"Launching task ${task.taskId} on executor id: ${task.executorId} hostname: " +
        s"${executorData.executorHost}.")

      executorData.executorEndpoint.send(LaunchTask(new SerializableBuffer(serializedTask)))
    }
  }
}

override def receive: PartialFunction[Any, Unit] = {
...

    case LaunchTask(data) =>
      if (executor == null) {
        exitExecutor(1, "Received LaunchTask command but executor was null")
      } else {
        val taskDesc = ser.deserialize[TaskDescription](data.value)
        logInfo("Got assigned task " + taskDesc.taskId)
        executor.launchTask(this, taskId = taskDesc.taskId, attemptNumber = taskDesc.attemptNumber,
          taskDesc.name, taskDesc.serializedTask)
      }
...
}

def launchTask(
    context: ExecutorBackend,
    taskId: Long,
    attemptNumber: Int,
    taskName: String,
    serializedTask: ByteBuffer): Unit = {
  val tr = new TaskRunner(context, taskId = taskId, attemptNumber = attemptNumber, taskName,
    serializedTask)
  runningTasks.put(taskId, tr)
  threadPool.execute(tr)
}

override def runTask(context: TaskContext): MapStatus = {
  // Deserialize the RDD using the broadcast variable.
  val deserializeStartTime = System.currentTimeMillis()
  val ser = SparkEnv.get.closureSerializer.newInstance()
  val (rdd, dep) = ser.deserialize[(RDD[_], ShuffleDependency[_, _, _])](
    ByteBuffer.wrap(taskBinary.value), Thread.currentThread.getContextClassLoader)
  _executorDeserializeTime = System.currentTimeMillis() - deserializeStartTime

  var writer: ShuffleWriter[Any, Any] = null
  try {
    val manager = SparkEnv.get.shuffleManager
    writer = manager.getWriter[Any, Any](dep.shuffleHandle, partitionId, context)
    writer.write(rdd.iterator(partition, context).asInstanceOf[Iterator[_ <: Product2[Any, Any]]])
    writer.stop(success = true).get
  } catch {
    case e: Exception =>
      try {
        if (writer != null) {
          writer.stop(success = false)
        }
      } catch {
        case e: Exception =>
          log.debug("Could not stop writer", e)
      }
      throw e
  }
}

  override def runTask(context: TaskContext): U = {
    // Deserialize the RDD and the func using the broadcast variables.
    val deserializeStartTime = System.currentTimeMillis()
    val ser = SparkEnv.get.closureSerializer.newInstance()
    val (rdd, func) = ser.deserialize[(RDD[T], (TaskContext, Iterator[T]) => U)](
      ByteBuffer.wrap(taskBinary.value), Thread.currentThread.getContextClassLoader)
    _executorDeserializeTime = System.currentTimeMillis() - deserializeStartTime

    func(context, rdd.iterator(partition, context))
  }

final def iterator(split: Partition, context: TaskContext): Iterator[T] = {
  if (storageLevel != StorageLevel.NONE) {
    getOrCompute(split, context)
  } else {
    computeOrReadCheckpoint(split, context)
  }
}

private[spark] def computeOrReadCheckpoint(split: Partition, context: TaskContext): Iterator[T] =
{
  if (isCheckpointedAndMaterialized) {
    firstParent[T].iterator(split, context)
  } else {
    compute(split, context)
  }
}

/**
 * Mark this RDD for checkpointing. It will be saved to a file inside the checkpoint
 * directory set with `SparkContext#setCheckpointDir` and all references to its parent
 * RDDs will be removed. This function must be called before any job has been
 * executed on this RDD. It is strongly recommended that this RDD is persisted in
 * memory, otherwise saving it on a file will require recomputation.
 */
def checkpoint(): Unit = RDDCheckpointData.synchronized {
  // NOTE: we use a global lock here due to complexities downstream with ensuring
  // children RDD partitions point to the correct parent partitions. In the future
  // we should revisit this consideration.
  if (context.checkpointDir.isEmpty) {
    throw new SparkException("Checkpoint directory has not been set in the SparkContext")
  } else if (checkpointData.isEmpty) {
    checkpointData = Some(new ReliableRDDCheckpointData(this))
  }
}

/** 
 * Enumeration to manage state transitions of an RDD through checkpointing 
 * [ Initialized --> checkpointing in progress --> checkpointed ]. 
 */  
private[spark] object CheckpointState extends Enumeration {  
  type CheckpointState = Value  
  val Initialized, CheckpointingInProgress, Checkpointed = Value  
} 

override def compute(split: Partition, context: TaskContext): Iterator[U] =
f(context, split.index, firstParent[T].iterator(split, context))

override def compute(split: Partition, context: TaskContext): Iterator[(K, C)] = {
  val dep = dependencies.head.asInstanceOf[ShuffleDependency[K, V, C]]
  SparkEnv.get.shuffleManager.getReader(dep.shuffleHandle, split.index, split.index + 1, context)
    .read()
    .asInstanceOf[Iterator[(K, C)]]
}