Spark Executor 執行 rdd task
阿新 • • 發佈：2018-12-04
##本文探究executor 執行rdd 時的回溯實現
處理 submitJob提交的job
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 = createResultStage(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) }
提交stage
/** 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") //提交task submitMissingTasks(stage, jobId.get) } else { for (parent <- missing) { submitStage(parent) } waitingStages += stage } } } else { abortStage(stage, "No active job for stage " + stage.id, None) } }
提交任務的入口
submitMissingTasks(stage: Stage, jobId: Int)
/** Called when stage's parents are available and we can now do its task. */ private def submitMissingTasks(stage: Stage, jobId: Int) { logDebug("submitMissingTasks(" + stage + ")") // 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 => 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 { val serializedTaskMetrics = closureSerializer.serialize(stage.latestInfo.taskMetrics).array() stage match { case stage: ShuffleMapStage => stage.pendingPartitions.clear() partitionsToCompute.map { id => val locs = taskIdToLocations(id) val part = stage.rdd.partitions(id) stage.pendingPartitions += id new ShuffleMapTask(stage.id, stage.latestInfo.attemptId, taskBinary, part, locs, properties, serializedTaskMetrics, Option(jobId), Option(sc.applicationId), sc.applicationAttemptId) } case stage: ResultStage => 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, serializedTaskMetrics, Option(jobId), Option(sc.applicationId), sc.applicationAttemptId) } } } 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(s"Submitting ${tasks.size} missing tasks from $stage (${stage.rdd}) (first 15 " + s"tasks are for partitions ${tasks.take(15).map(_.partitionId)})") //提交task 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) submitWaitingChildStages(stage) } }
executor 執行
def launchTask(context: ExecutorBackend, taskDescription: TaskDescription): Unit = {
val tr = new TaskRunner(context, taskDescription)
runningTasks.put(taskDescription.taskId, tr)
threadPool.execute(tr)
}
TaskRunner 的run方法
反序列化的操作封裝在 TaskDescription
class TaskRunner(
execBackend: ExecutorBackend,
private val taskDescription: TaskDescription)
extends Runnable {
override def run(): Unit = {
val value = try {
val res = task.run(
taskAttemptId = taskId,
attemptNumber = taskDescription.attemptNumber,
metricsSystem = env.metricsSystem)
threwException = false
res
}
}
}
task.run
final def run(
taskAttemptId: Long,
attemptNumber: Int,
metricsSystem: MetricsSystem): T = {
...
try {
runTask(context)
}
...
}
task runTask()
(以ShuffleMapTask 舉例)
override def runTask(context: TaskContext): MapStatus = {
...
val (rdd, dep) = ser.deserialize[(RDD[_], ShuffleDependency[_, _, _])](
ByteBuffer.wrap(taskBinary.value), Thread.currentThread.getContextClassLoader)
...
try {
val manager = SparkEnv.get.shuffleManager
writer = manager.getWriter[Any, Any](dep.shuffleHandle, partitionId, context)
//rdd.iterator 登場了
writer.write(rdd.iterator(partition, context).asInstanceOf[Iterator[_ <: Product2[Any, Any]]])
writer.stop(success = true).get
}
...
}
rdd iterator
/**
* 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.
*/
final def iterator(split: Partition, context: TaskContext): Iterator[T] = {
if (storageLevel != StorageLevel.NONE) {
getOrCompute(split, context)
} else {
computeOrReadCheckpoint(split, context)
}
}
computeOrReadCheckpoint
/**
* Compute an RDD partition or read it from a checkpoint if the RDD is checkpointing.
*/
private[spark] def computeOrReadCheckpoint(split: Partition, context: TaskContext): Iterator[T] =
{
if (isCheckpointedAndMaterialized) {
//追溯父RDD了
firstParent[T].iterator(split, context)
} else {
compute(split, context)
}
}