SparkContext
源码版本2.4.7
上一篇分析完Executor的注册启动流程,接下来看rdd.action[foreach,collect,save,…]-> sc.runJob(rdd,iter=>f)
最终调用的的SparkContext的DAGScheduler的runJob
runJob->submitJob-> eventProcessLoop.post(JobSubmitted)->eventQueue
eventQueue->doOnReceive->dagScheduler.handleJobSubmitted
跟踪代码可知dagScheduler提交的job最终通过自身handleJobSubmitted方法处理
思考:为何不直接处理呢?
dagScheduler本身天生支持缓冲(eventQueue实现),避免任务堆积
/**
* Run a function on a given set of partitions in an RDD and pass the results to the given
* handler function. This is the main entry point for all actions in Spark.
*
* @param rdd target RDD to run tasks on
* @param func a function to run on each partition of the RDD
* @param partitions set of partitions to run on; some jobs may not want to compute on all
* partitions of the target RDD, e.g. for operations like `first()`
* @param resultHandler callback to pass each result to
*/
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()
}
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)
……
}
创建finalStage
RDD依赖关系其实可以抽象理解成一个单向列表-> 树
通过最后一个RDD的action算子,触发DAG去按着stage递归,通过栈结构遍历RDD寻找shuffle关系切割stage
创建finalStage,逐步划分Stage
submitStage(finalStage)
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.
//创建finalStage,逐步划分Stage
finalStage = createResultStage(finalRDD, func, partitions, jobId, callSite)
} catch {
……
}
// Job submitted, clear internal data.
barrierJobIdToNumTasksCheckFailures.remove(jobId)
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)
}
submitStage 逐步递归上级stage -> getMissingParentStages
/** Submits stage, but first recursively submits any missing parents. */
private def submitStage(stage: Stage) {
val jobId = activeJobForStage(stage)
if (jobId.isDefined) {
logDebug(s"submitStage($stage (name=${stage.name};" +
s"jobs=${stage.jobIds.toSeq.sorted.mkString(",")}))")
if (!waitingStages(stage) && !runningStages(stage) && !failedStages(stage)) {
//递归划分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)
}
}
getMissingParentStages,遇到ShuffleDependency则创建一个ShuffleMapStage,如果是窄依赖,递归下去
val missing = getMissingParentStages(stage).sortBy(_.id)根据id排序
id生成 nextStageId = new AtomicInteger(0)
保证递归有序
Stage有两种: ShuffleMapStage和最终的ResultStage
private def getMissingParentStages(stage: Stage): List[Stage] = {
val missing = new HashSet[Stage]
val visited = new HashSet[RDD[_]]
// We are manually maintaining a stack here to prevent StackOverflowError
// caused by recursively visiting
val waitingForVisit = new ArrayStack[RDD[_]]
def visit(rdd: RDD[_]) {
if (!visited(rdd)) {
visited += rdd
val rddHasUncachedPartitions = getCacheLocs(rdd).contains(Nil)
if (rddHasUncachedPartitions) {
for (dep <- rdd.dependencies) {
dep match {
case shufDep: ShuffleDependency[_, _, _] =>
val mapStage = getOrCreateShuffleMapStage(shufDep, stage.firstJobId)
if (!mapStage.isAvailable) {
missing += mapStage
}
case narrowDep: NarrowDependency[_] =>
waitingForVisit.push(narrowDep.rdd)
}
}
}
}
}
waitingForVisit.push(stage.rdd)
while (waitingForVisit.nonEmpty) {
visit(waitingForVisit.pop())
}
missing.toList
}
递归到没有父Stage的stage
submitMissingTasks(stage, jobId.get)
最终 taskScheduler.submitTasks(TaskSet) -> backend.reviveOffers()
/** 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)
// If there are tasks to execute, record the submission time of the stage. Otherwise,
// post the even without the submission time, which indicates that this stage was
// skipped.
if (partitionsToCompute.nonEmpty) {
stage.latestInfo.submissionTime = Some(clock.getTimeMillis())
}
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
var partitions: Array[Partition] = null
try {
// For ShuffleMapTask, serialize and broadcast (rdd, shuffleDep).
// For ResultTask, serialize and broadcast (rdd, func).
//序列化task
var taskBinaryBytes: Array[Byte] = null
// taskBinaryBytes and partitions are both effected by the checkpoint status. We need
// this synchronization in case another concurrent job is checkpointing this RDD, so we get a
// consistent view of both variables.
RDDCheckpointData.synchronized {
taskBinaryBytes = 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))
}
partitions = stage.rdd.partitions
}
//广播
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 e: Throwable =>
abortStage(stage, s"Task serialization failed: $e\n${Utils.exceptionString(e)}", Some(e))
runningStages -= stage
// Abort execution
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 = partitions(id)
stage.pendingPartitions += id
new ShuffleMapTask(stage.id, stage.latestInfo.attemptNumber,
taskBinary, part, locs, properties, serializedTaskMetrics, Option(jobId),
Option(sc.applicationId), sc.applicationAttemptId, stage.rdd.isBarrier())
}
case stage: ResultStage =>
partitionsToCompute.map { id =>
val p: Int = stage.partitions(id)
val part = partitions(p)
val locs = taskIdToLocations(id)
new ResultTask(stage.id, stage.latestInfo.attemptNumber,
taskBinary, part, locs, id, properties, serializedTaskMetrics,
Option(jobId), Option(sc.applicationId), sc.applicationAttemptId,
stage.rdd.isBarrier())
}
}
} 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)})")
//交给taskScheduler
taskScheduler.submitTasks(new TaskSet(
tasks.toArray, stage.id, stage.latestInfo.attemptNumber, jobId, properties))
} 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)
stage match {
case stage: ShuffleMapStage =>
logDebug(s"Stage ${stage} is actually done; " +
s"(available: ${stage.isAvailable}," +
s"available outputs: ${stage.numAvailableOutputs}," +
s"partitions: ${stage.numPartitions})")
markMapStageJobsAsFinished(stage)
case stage : ResultStage =>
logDebug(s"Stage ${stage} is actually done; (partitions: ${stage.numPartitions})")
}
submitWaitingChildStages(stage)
}
}
ReviveOffers->receive->makeOffers->scheduler.resourceOffers-> launchTasks(taskDescs)
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])
// Mark all the existing TaskSetManagers of this stage as zombie, as we are adding a new one.
// This is necessary to handle a corner case. Let's say a stage has 10 partitions and has 2
// TaskSetManagers: TSM1(zombie) and TSM2(active). TSM1 has a running task for partition 10
// and it completes. TSM2 finishes tasks for partition 1-9, and thinks he is still active
// because partition 10 is not completed yet. However, DAGScheduler gets task completion
// events for all the 10 partitions and thinks the stage is finished. If it's a shuffle stage
// and somehow it has missing map outputs, then DAGScheduler will resubmit it and create a
// TSM3 for it. As a stage can't have more than one active task set managers, we must mark
// TSM2 as zombie (it actually is).
stageTaskSets.foreach { case (_, ts) =>
ts.isZombie = true
}
stageTaskSets(taskSet.stageAttemptId) = manager
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 reviveOffers() {
driverEndpoint.send(ReviveOffers)
}
// Make fake resource offers on all executors
private def makeOffers() {
// Make sure no executor is killed while some task is launching on it
val taskDescs = withLock {
// Filter out executors under killing
val activeExecutors = executorDataMap.filterKeys(executorIsAlive)
val workOffers = activeExecutors.map {
case (id, executorData) =>
new WorkerOffer(id, executorData.executorHost, executorData.freeCores,
Some(executorData.executorAddress.hostPort))
}.toIndexedSeq
scheduler.resourceOffers(workOffers)
}
if (!taskDescs.isEmpty) {
launchTasks(taskDescs)
}
}
向Executor发起launchTask请求,Executor处理
executor.launchTask(this, taskDesc)
// Launch tasks returned by a set of resource offers
private def launchTasks(tasks: Seq[Seq[TaskDescription]]) {
for (task <- tasks.flatten) {
val serializedTask = TaskDescription.encode(task)
if (serializedTask.limit() >= maxRpcMessageSize) {
Option(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
logDebug(s"Launching task ${task.taskId} on executor id: ${task.executorId} hostname: " +
s"${executorData.executorHost}.")
executorData.executorEndpoint.send(LaunchTask(new SerializableBuffer(serializedTask)))
}
}
}
def launchTask(context: ExecutorBackend, taskDescription: TaskDescription): Unit = {
val tr = new TaskRunner(context, taskDescription)
runningTasks.put(taskDescription.taskId, tr)
threadPool.execute(tr)
}
![](https://img.laitimes.com/img/_0nNw4CM6IyYiwiM6ICdiwiIwczX0xiRGZkRGZ0Xy9GbvNGL2EzXlpXazxCerR1T4NWbiZHeXFGNk1mYoR2MMBjVtJWd0ckW65UbM5WOHJWa5kHT20ESjBjUIF2X0hXZ0xCMx81dvRWYoNHLrdEZwZ1Rh5WNXp1bwNjW1ZUba9VZwlHdssmch1mclRXY39CXldWYtlWPzNXZj9mcw1ycz9WL49zZuBnL2cDN4ADN0EjM3AjMxAjMwIzLc52YucWbp5GZzNmLn9Gbi1yZtl2Lc9CX6MHc0RHaiojIsJye.png)