本文详细解析了Apache Spark中执行计数任务的具体流程，从RDD的count方法开始，经过DAGScheduler调度，最终由TaskScheduler分配给Executor执行。
RDD.scala
def count(): Long = sc.runJob(this, Utils.getIteratorSize _).sum
SparkContext.scala
对runJob 方法有多个重写版本，列出最终调用 dagScheduler 的部分
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()
}
DAGScheduler
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
}
eventProcessLoop 是 DAGScheduler 的一个属性，声明部分如下：
private[scheduler] val eventProcessLoop = new DAGSchedulerEventProcessLoop(this)
而 DAGSchedulerEventProcessLoop 是 DAGScheduler 的一个内部类：
private[scheduler] class DAGSchedulerEventProcessLoop(dagScheduler: DAGScheduler)
构造函数当中传入一个 DAGScheduler 实例，下面是它doOnReceive方法的一部分
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)
我们找到 dagScheduler.handleJobSubmitted，
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)
}
然后是 submitStage，存在递归调用，红色字体分别是递归的出口和递归调用的地方，以final stage进入该函数，但是实际的调用顺序应该还是按照正常的顺序，逐次调用若干个stage，然后看一submitMissingTasks
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 =>
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 =>
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)
submitWaitingChildStages(stage)
}
}
在 submitMissingTasks 方法当中，找到 taskScheduler.submitTasks，
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()
}
backend的具体类型是StandaloneSchedulerBackend，而reviveOffers的实现在CoarseGrainedSchedulerBackend当中，
override def reviveOffers() {
driverEndpoint.send(ReviveOffers)
}
driverEndpoint.send(ReviveOffers) ，接收的地方在 CoarseGrainedSchedulerBackend 的内部类DriverEndpoint当中（需要参考我的另一篇文章，对spark的RPC机制有深入研究，到目前为止，整个程序的运行，仍然在driver上，但是已经在一个子线程当中）首先是类的声明部分：
class DriverEndpoint(override val rpcEnv: RpcEnv, sparkProperties: Seq[(String, String)])
extends ThreadSafeRpcEndpoint with Logging
然后是receive方法的一部分：
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))
}
下面我们看一下 launchTasks ，再重新回顾一下spark的任务结构，job -> stage -> task，每个stage内的多个task将会分布式的并发执行。看一下下面的代码，跟我们之前的理解，基本是可以对上号的。
private def launchTasks(tasks: Seq[Seq[TaskDescription]]) {
for (task <- tasks.flatten) { //循环任务列表
val serializedTask = ser.serialize(task) //序列化任务
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)))
}
}
}
上面红色代码，仍然使用NettyRpc机制，这次是把若干个task分别提交给spark集群当中的worker来进行处理，我们在CoarseGrainedExecutorBackend当中找到了对 LaunchTask 的接收部分，首先 CoarseGrainedExecutorBackend 类的声明部分：
private[spark] class CoarseGrainedExecutorBackend
然后是receive函数的声明部分：
override def receive: PartialFunction[Any, Unit]
然后是对LaunchTask的执行部分：
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)
}
到目前为止，count任务，已经分发给了各个worker的executor分别去执行。这次的源码解析比较粗糙，后续我们会有更详细更深入的分析和理解。
扫一扫
1171
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
