（图片来源：北风网）
进去RDD，随便点击一个action *** 作,比如foreach *** 作
def foreach(f: T => Unit): Unit = withScope {
val cleanF = sc.clean(f)
sc.runJob(this, (iter: Iterator[T]) => iter.foreach(cleanF))
}
进入runJob看看，来到了SparkContext的runJob
def runJob[T, U: ClassTag](rdd: RDD[T], func: Iterator[T] => U): Array[U] = {
runJob(rdd, func, 0 until rdd.partitions.length)
}
再进
def runJob[T, U: ClassTag](
rdd: RDD[T],
func: Iterator[T] => U,
partitions: Seq[Int]): Array[U] = {
val cleanedFunc = clean(func)
runJob(rdd, (ctx: TaskContext, it: Iterator[T]) => cleanedFunc(it), partitions)
}
再进
def runJob[T, U: ClassTag](
rdd: RDD[T],
func: (TaskContext, Iterator[T]) => U,
partitions: Seq[Int]): Array[U] = {
val results = new Array[U](partitions.size)
runJob[T, U](rdd, func, partitions, (index, res) => results(index) = res)
results
}
还要进
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()
}
到这，可以看到出现了dagScheduler.runJob
进去看看
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
}
}
可以看到，进去了一个submitJob，后面只是判断执行结果
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
}
可以看到，new JobWaiter中有一个eventProcessLoop，点进去
是DAGScheduler里重要的一个东西，叫DAGSchedulerEventProcessLoop
private[scheduler] val eventProcessLoop = new DAGSchedulerEventProcessLoop(this) taskScheduler.setDAGScheduler(this)
进去DAGSchedulerEventProcessLoop，发现它有一个方法
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)
case MapStageSubmitted(jobId, dependency, callSite, listener, properties) =>
dagScheduler.handleMapStageSubmitted(jobId, dependency, callSite, listener, properties)
case StageCancelled(stageId) =>
dagScheduler.handleStageCancellation(stageId)
case JobCancelled(jobId) =>
dagScheduler.handleJobCancellation(jobId)
case JobGroupCancelled(groupId) =>
dagScheduler.handleJobGroupCancelled(groupId)
case AllJobsCancelled =>
dagScheduler.doCancelAllJobs()
case ExecutorAdded(execId, host) =>
dagScheduler.handleExecutorAdded(execId, host)
case ExecutorLost(execId, reason) =>
val filesLost = reason match {
case SlaveLost(_, true) => true
case _ => false
}
dagScheduler.handleExecutorLost(execId, filesLost)
case BeginEvent(task, taskInfo) =>
dagScheduler.handleBeginEvent(task, taskInfo)
case GettingResultEvent(taskInfo) =>
dagScheduler.handleGetTaskResult(taskInfo)
case completion: CompletionEvent =>
dagScheduler.handleTaskCompletion(completion)
case TaskSetFailed(taskSet, reason, exception) =>
dagScheduler.handleTaskSetFailed(taskSet, reason, exception)
case ResubmitFailedStages =>
dagScheduler.resubmitFailedStages()
}
我们刚才是从JobSubmit进来的，所以看到case JobSubmit，可以看到调用了dagScheduler.handleJobSubmitted
再进到.handleJobSubmitted看看
private[scheduler] def handleJobSubmitted(jobId: Int,
finalRDD: RDD[_],
func: (TaskContext, Iterator[_]) => _,
partitions: Array[Int],
callSite: CallSite,
listener: JobListener,
properties: Properties) {
//第一步：使用触发job 的最后一个RDD，创建finalStage
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.
//可以看到这里传入finalRDD,调用createResultStage
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
}
//第二步：使用finalStage创建一个job
//job的最后一个stage就是finalStage
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()
//第三步：将job加入内存缓存中
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))
//第四步：使用finalStage提交Stage
submitStage(finalStage)
}
这个就是DAGScheduler的job调度的核心入口
进入createResultStage看看
private def createResultStage(
rdd: RDD[_],
func: (TaskContext, Iterator[_]) => _,
partitions: Array[Int],
jobId: Int,
callSite: CallSite): ResultStage = {
val parents = getOrCreateParentStages(rdd, jobId)
val id = nextStageId.getAndIncrement()
//创建ResultStage
val stage = new ResultStage(id, rdd, func, partitions, parents, jobId, callSite)
stageIdToStage(id) = stage
updateJobIdStageIdMaps(jobId, stage)
stage
}
创建了stage并返回
进入第四步的submitStage看看
private def submitStage(stage: Stage) {
val jobId = activeJobForStage(stage)
if (jobId.isDefined) {
logDebug("submitStage(" + stage + ")")
if (!waitingStages(stage) && !runningStages(stage) && !failedStages(stage)) {
//这里，调用了getMissingParentStages去获取当前stage的父stage，很重要
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)
}
}
跟进getMissingParentStages看看，这里涉及了stage的划分算法
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
//初始化了一个栈
val waitingForVisit = new Stack[RDD[_]]
//while中进来visit
def visit(rdd: RDD[_]) {
if (!visited(rdd)) {
visited += rdd
val rddHasUncachedPartitions = getCacheLocs(rdd).contains(Nil)
if (rddHasUncachedPartitions) {
//遍历rdd的依赖
for (dep <- rdd.dependencies) {
dep match {
//宽依赖
case shufDep: ShuffleDependency[_, _, _] =>
//在这使用宽依赖的rdd，创建stage，并将isShuffleMap设置为true，默认最后一个stage不是shuffleMap stage，之前都是shuffleMap stage
val mapStage = getOrCreateShuffleMapStage(shufDep, stage.firstJobId)
if (!mapStage.isAvailable) {
missing += mapStage
}
//窄依赖，直接放栈中，类似深搜
case narrowDep: NarrowDependency[_] =>
waitingForVisit.push(narrowDep.rdd)
}
}
}
}
}
//先往栈里push了一个rdd
waitingForVisit.push(stage.rdd)
//如果栈不空
while (waitingForVisit.nonEmpty) {
//对栈中的最后一个rdd，调用visit，
visit(waitingForVisit.pop())
}
missing.toList
}
这个宽窄依赖的逻辑区别就说明了：stage的区分是靠宽依赖窄依赖来区别的，即，stage的划分算法就是这个
进入宽依赖的getOrCreateShuffleMapStage看看
private def getOrCreateShuffleMapStage(
shuffleDep: ShuffleDependency[_, _, _],
firstJobId: Int): ShuffleMapStage = {
shuffleIdToMapStage.get(shuffleDep.shuffleId) match {
case Some(stage) =>
stage
case None =>
// Create stages for all missing ancestor shuffle dependencies.
getMissingAncestorShuffleDependencies(shuffleDep.rdd).foreach { dep =>
// Even though getMissingAncestorShuffleDependencies only returns shuffle dependencies
// that were not already in shuffleIdToMapStage, it's possible that by the time we
// get to a particular dependency in the foreach loop, it's been added to
// shuffleIdToMapStage by the stage creation process for an earlier dependency. See
// SPARK-13902 for more information.
if (!shuffleIdToMapStage.contains(dep.shuffleId)) {
createShuffleMapStage(dep, firstJobId)
}
}
// Finally, create a stage for the given shuffle dependency.
createShuffleMapStage(shuffleDep, firstJobId)
}
}
进入最后的createShuffleMapStage
def createShuffleMapStage(shuffleDep: ShuffleDependency[_, _, _], jobId: Int): ShuffleMapStage = {
val rdd = shuffleDep.rdd
val numTasks = rdd.partitions.length
val parents = getOrCreateParentStages(rdd, jobId)
val id = nextStageId.getAndIncrement()
val stage = new ShuffleMapStage(id, rdd, numTasks, parents, jobId, rdd.creationSite, shuffleDep)
stageIdToStage(id) = stage
shuffleIdToMapStage(shuffleDep.shuffleId) = stage
updateJobIdStageIdMaps(jobId, stage)
if (mapOutputTracker.containsShuffle(shuffleDep.shuffleId)) {
// A previously run stage generated partitions for this shuffle, so for each output
// that's still available, copy information about that output location to the new stage
// (so we don't unnecessarily re-compute that data).
val serLocs = mapOutputTracker.getSerializedMapOutputStatuses(shuffleDep.shuffleId)
val locs = MapOutputTracker.deserializeMapStatuses(serLocs)
(0 until locs.length).foreach { i =>
if (locs(i) ne null) {
// locs(i) will be null if missing
stage.addOutputLoc(i, locs(i))
}
}
} else {
// Kind of ugly: need to register RDDs with the cache and map output tracker here
// since we can't do it in the RDD constructor because # of partitions is unknown
logInfo("Registering RDD " + rdd.id + " (" + rdd.getCreationSite + ")")
mapOutputTracker.registerShuffle(shuffleDep.shuffleId, rdd.partitions.length)
}
//返回一个stage
stage
}
OK，回到submitStage，stage划分算法实际上是由getMissingParentStages和submitStage共同组成的，为了方便，再拷下来看看
private def submitStage(stage: Stage) {
val jobId = activeJobForStage(stage)
if (jobId.isDefined) {
logDebug("submitStage(" + stage + ")")
if (!waitingStages(stage) && !runningStages(stage) && !failedStages(stage)) {
//这里，调用了getMissingParentStages去获取当前stage的父stage，很重要
val missing = getMissingParentStages(stage).sortBy(_.id)
logDebug("missing: " + missing)
//如果没有父stage
if (missing.isEmpty) {
logInfo("Submitting " + stage + " (" + stage.rdd + "), which has no missing parents")
submitMissingTasks(stage, jobId.get)
} else {
//如果拿到了父stage，则递归调用submitStage，提交父stage，并将当前stage ，放入waitingStages队列中等待执行
//这里的递归就是stage划分算法的精髓
//递归直到最初的stage没有父stage
//然后提交第一个stage，
for (parent <- missing) {
submitStage(parent)
}
waitingStages += stage
}
}
} else {
abortStage(stage, "No active job for stage " + stage.id, None)
}
}
stage划分算法很重要，必须知道自己的application被划分为几个job，每个job被分为几个stage，每个stage包括哪些代码，如果出现错误，才能从stage定位到具体代码，从而排查问题，或者性能调优。
（job的划分：action *** 作；stage划分：宽依赖）
总结：
- 从finalstage倒退
- 从宽依赖进行新stage划分
- 使用递归优先提交父stage
OK，然后来看看submitMissingTasks的细节
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.
//计算需要创建的task数量
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
//将stage加入runningStages队列
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: $en${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: $en${Utils.exceptionString(e)}", Some(e))
runningStages -= stage
return
}
//为stage创建tasks
val tasks: Seq[Task[_]] = try {
stage match {
case stage: ShuffleMapStage =>
partitionsToCompute.map { id =>
//给每个partition创建task
//给每个task计算最佳位置
val locs = taskIdToLocations(id)
val part = stage.rdd.partitions(id)
new ShuffleMapTask(stage.id, stage.latestInfo.attemptId,
taskBinary, part, locs, stage.latestInfo.taskMetrics, properties, 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, stage.latestInfo.taskMetrics,
Option(jobId), Option(sc.applicationId), sc.applicationAttemptId)
}
}
} catch {
case NonFatal(e) =>
abortStage(stage, s"Task creation failed: $en${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)
//针对stage的task，创建taskSet对象，调用TaskScheuler的submitTasks
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)
}
}
其中涉及的计算task最佳位置算法
taskIdToLocations(id)
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
}
进入getPreferredLocs
private[spark]
def getPreferredLocs(rdd: RDD[_], partition: Int): Seq[TaskLocation] = {
getPreferredLocsInternal(rdd, partition, new HashSet)
}
进入getPreferredLocsInternal，计算每个task的partition的最佳位置，其实就是从stage的最后一个rdd开始，寻找哪些rdd被cache或者checkpoint了，然后task 的最佳位置就是被缓存的partition的位置，这样task就在那个节点上执行，不需要计算之前的rdd
private def getPreferredLocsInternal(
rdd: RDD[_],
partition: Int,
visited: HashSet[(RDD[_], Int)]): Seq[TaskLocation] = {
// If the partition has already been visited, no need to re-visit.
// This avoids exponential path exploration. SPARK-695
if (!visited.add((rdd, partition))) {
// Nil has already been returned for previously visited partitions.
return Nil
}
// If the partition is cached, return the cache locations
//寻找是否缓存
val cached = getCacheLocs(rdd)(partition)
if (cached.nonEmpty) {
return cached
}
// If the RDD has some placement preferences (as is the case for input RDDs), get those
//寻找是否checkpoint
val rddPrefs = rdd.preferredLocations(rdd.partitions(partition)).toList
if (rddPrefs.nonEmpty) {
return rddPrefs.map(TaskLocation(_))
}
// If the RDD has narrow dependencies, pick the first partition of the first narrow dependency
// that has any placement preferences. Ideally we would choose based on transfer sizes,
// but this will do for now.
//递归调用自己，寻找父RDD，是否缓存或者checkpoint
rdd.dependencies.foreach {
case n: NarrowDependency[_] =>
for (inPart <- n.getParents(partition)) {
val locs = getPreferredLocsInternal(n.rdd, inPart, visited)
if (locs != Nil) {
return locs
}
}
case _ =>
}
//如果从最后一个rdd到最开始的rdd，都没有chche或者checkpoint，那就没有最佳位置
Nil
}
计算完了task的最佳位置，还要看如何分配task，涉及askScheduler，后面再看
欢迎分享，转载请注明来源：内存溢出
微信扫一扫
支付宝扫一扫
评论列表（0条）