- executor启动
private[spark] class CoarseGrainedExecutorBackend(
override val rpcEnv: RpcEnv,
driverUrl: String,
executorId: String,
hostname: String,
cores: Int,
userClassPath: Seq[URL],
env: SparkEnv)
extends ThreadSafeRpcEndpoint with ExecutorBackend with Logging {
///
override def onStart() {
logInfo("Connecting to driver: " + driverUrl)
rpcEnv.asyncSetupEndpointRefByURI(driverUrl).flatMap { ref =>
// This is a very fast action so we can use "ThreadUtils.sameThread"
driver = Some(ref)
ref.ask[Boolean](RegisterExecutor(executorId, self, hostname, cores, extractLogUrls)) ///给driver发送RegisterExecutor消息
}(ThreadUtils.sameThread).onComplete {
// This is a very fast action so we can use "ThreadUtils.sameThread"
case Success(msg) =>
// Always receive `true`. Just ignore it
case Failure(e) =>
exitExecutor(1, s"Cannot register with driver: $driverUrl", e, notifyDriver = false)
}(ThreadUtils.sameThread)
}
///收到driver的消息
override def receive: PartialFunction[Any, Unit] = {
case RegisteredExecutor =>
logInfo("Successfully registered with driver")
try {
executor = new Executor(executorId, hostname, env, userClassPath, isLocal = false) ///创建Executor对象
} catch {
case NonFatal(e) =>
exitExecutor(1, "Unable to create executor due to " + e.getMessage, e)
}
2017-08-02 03:14:08 INFO Executor:54 - Starting executor ID 47 on host 192.168.22.157
代码：
/**
* Spark executor, backed by a threadpool to run tasks.
*
* This can be used with Mesos, YARN, and the standalone scheduler.
* An internal RPC interface is used for communication with the driver,
* except in the case of Mesos fine-grained mode.
*/
private[spark] class Executor(
executorId: String,
executorHostname: String,
env: SparkEnv,
userClassPath: Seq[URL] = Nil,
isLocal: Boolean = false,
uncaughtExceptionHandler: UncaughtExceptionHandler = SparkUncaughtExceptionHandler)
extends Logging {
logInfo(s"Starting executor ID $executorId on host $executorHostname")
///...
}
- driver注册executor
CoarseGrainedSchedulerBackend:
override def receiveAndReply(context: RpcCallContext): PartialFunction[Any, Unit] = {
case RegisterExecutor(executorId, executorRef, hostname, cores, logUrls) =>
if (executorDataMap.contains(executorId)) {
executorRef.send(RegisterExecutorFailed("Duplicate executor ID: " + executorId))
context.reply(true)
} else if (scheduler.nodeBlacklist != null &&
scheduler.nodeBlacklist.contains(hostname)) {
// If the cluster manager gives us an executor on a blacklisted node (because it
// already started allocating those resources before we informed it of our blacklist,
// or if it ignored our blacklist), then we reject that executor immediately.
logInfo(s"Rejecting $executorId as it has been blacklisted.")
executorRef.send(RegisterExecutorFailed(s"Executor is blacklisted: $executorId"))
context.reply(true)
} else {
// If the executor's rpc env is not listening for incoming connections, `hostPort`
// will be null, and the client connection should be used to contact the executor.
val executorAddress = if (executorRef.address != null) {
executorRef.address
} else {
context.senderAddress
}
logInfo(s"Registered executor $executorRef ($executorAddress) with ID $executorId")
addressToExecutorId(executorAddress) = executorId
totalCoreCount.addAndGet(cores)
totalRegisteredExecutors.addAndGet(1)
val data = new ExecutorData(executorRef, executorRef.address, hostname,
cores, cores, logUrls)
// This must be synchronized because variables mutated
// in this block are read when requesting executors
CoarseGrainedSchedulerBackend.this.synchronized {
executorDataMap.put(executorId, data)
if (currentExecutorIdCounter < executorId.toInt) {
currentExecutorIdCounter = executorId.toInt
}
if (numPendingExecutors > 0) {
numPendingExecutors -= 1
logDebug(s"Decremented number of pending executors ($numPendingExecutors left)")
}
}
executorRef.send(RegisteredExecutor)
// Note: some tests expect the reply to come after we put the executor in the map
context.reply(true)
listenerBus.post(
SparkListenerExecutorAdded(System.currentTimeMillis(), executorId, data))
makeOffers()
}
- executor执行任务
2017-08-02 03:21:02 INFO CoarseGrainedExecutorBackend:54 - Got assigned task 92
2017-08-02 03:21:02 INFO CoarseGrainedExecutorBackend:54 - Got assigned task 192
2017-08-02 03:21:02 INFO CoarseGrainedExecutorBackend:54 - Got assigned task 292
2017-08-02 03:21:02 INFO CoarseGrainedExecutorBackend:54 - Got assigned task 392
2017-08-02 03:21:02 INFO Executor:54 - Running task 212.0 in stage 1.0 (TID 292)
2017-08-02 03:21:02 INFO Executor:54 - Running task 312.0 in stage 1.0 (TID 392)
2017-08-02 03:21:02 INFO Executor:54 - Running task 112.0 in stage 1.0 (TID 192)
2017-08-02 03:21:02 INFO Executor:54 - Running task 12.0 in stage 1.0 (TID 92)
CoarseGrainedExecutorBackend:
case LaunchTask(data) =>
if (executor == null) {
exitExecutor(1, "Received LaunchTask command but executor was null")
} else {
val taskDesc = TaskDescription.decode(data.value)
logInfo("Got assigned task " + taskDesc.taskId)
executor.launchTask(this, taskDesc)
}
class TaskRunner(
execBackend: ExecutorBackend,
private val taskDescription: TaskDescription)
extends Runnable {
///...
override def run(): Unit = {
threadId = Thread.currentThread.getId
Thread.currentThread.setName(threadName)
val threadMXBean = ManagementFactory.getThreadMXBean
val taskMemoryManager = new TaskMemoryManager(env.memoryManager, taskId)
val deserializeStartTime = System.currentTimeMillis()
val deserializeStartCpuTime = if (threadMXBean.isCurrentThreadCpuTimeSupported) {
threadMXBean.getCurrentThreadCpuTime
} else 0L
Thread.currentThread.setContextClassLoader(replClassLoader)
val ser = env.closureSerializer.newInstance()
logInfo(s"Running $taskName (TID $taskId)")
...
val value = try {
val res = task.run( ///Task.run
taskAttemptId = taskId,
attemptNumber = taskDescription.attemptNumber,
metricsSystem = env.metricsSystem)
threwException = false
res
}
...
当executor执行完一个Task后，会更新任务状态：
execBackend.statusUpdate(taskId, TaskState.FINISHED, serializedResult)
CoarseGrainedExecutorBackend:
override def statusUpdate(taskId: Long, state: TaskState, data: ByteBuffer) {
val msg = StatusUpdate(executorId, taskId, state, data)
driver match {
case Some(driverRef) => driverRef.send(msg) ///send to driver
case None => logWarning(s"Drop $msg because has not yet connected to driver")
}
}
当driver收到StatusUpdate的消息后，会根据任务的完成情况（成功或者失败）分别进行处理：
private[spark]
class CoarseGrainedSchedulerBackend(scheduler: TaskSchedulerImpl, val rpcEnv: RpcEnv)
extends ExecutorAllocationClient with SchedulerBackend with Logging
{
///...
class DriverEndpoint(override val rpcEnv: RpcEnv, sparkProperties: Seq[(String, String)])
extends ThreadSafeRpcEndpoint with Logging {
///...
override def receive: PartialFunction[Any, Unit] = {
case StatusUpdate(executorId, taskId, state, data) =>
scheduler.statusUpdate(taskId, state, data.value) ///更新任务状态
if (TaskState.isFinished(state)) {
executorDataMap.get(executorId) match {
case Some(executorInfo) =>
executorInfo.freeCores += scheduler.CPUS_PER_TASK
makeOffers(executorId)
case None =>
// Ignoring the update since we don't know about the executor.
logWarning(s"Ignored task status update ($taskId state $state) " +
s"from unknown executor with ID $executorId")
}
}
TaskSchedulerImpl:
def statusUpdate(tid: Long, state: TaskState, serializedData: ByteBuffer) {
var failedExecutor: Option[String] = None
var reason: Option[ExecutorLossReason] = None
synchronized {
try {
taskIdToTaskSetManager.get(tid) match {
case Some(taskSet) =>
if (state == TaskState.LOST) {
// TaskState.LOST is only used by the deprecated Mesos fine-grained scheduling mode,
// where each executor corresponds to a single task, so mark the executor as failed.
val execId = taskIdToExecutorId.getOrElse(tid, throw new IllegalStateException(
"taskIdToTaskSetManager.contains(tid) <=> taskIdToExecutorId.contains(tid)"))
if (executorIdToRunningTaskIds.contains(execId)) {
reason = Some(
SlaveLost(s"Task $tid was lost, so marking the executor as lost as well."))
removeExecutor(execId, reason.get)
failedExecutor = Some(execId)
}
}
if (TaskState.isFinished(state)) {
cleanupTaskState(tid)
taskSet.removeRunningTask(tid)
if (state == TaskState.FINISHED) {
taskResultGetter.enqueueSuccessfulTask(taskSet, tid, serializedData) /// task success
} else if (Set(TaskState.FAILED, TaskState.KILLED, TaskState.LOST).contains(state)) {
taskResultGetter.enqueueFailedTask(taskSet, tid, state, serializedData) /// task failed
}
}
case None =>
logError(
("Ignoring update with state %s for TID %s because its task set is gone (this is " +
"likely the result of receiving duplicate task finished status updates) or its " +
"executor has been marked as failed.")
.format(state, tid))
}
} catch {
case e: Exception => logError("Exception in statusUpdate", e)
}
}
// Update the DAGScheduler without holding a lock on this, since that can deadlock
if (failedExecutor.isDefined) {
assert(reason.isDefined)
dagScheduler.executorLost(failedExecutor.get, reason.get)
backend.reviveOffers()
}
}
- driver处理任务结果
TaskResultGetter.enqueueSuccessfulTask -> TaskSchedulerImpl.handleSuccessfulTask -> TaskSetManager.handleSuccessfulTask -> DAGSsheduler.taskEnded
TaskSchedulerImpl:
def handleSuccessfulTask(
taskSetManager: TaskSetManager,
tid: Long,
taskResult: DirectTaskResult[_]): Unit = synchronized {
taskSetManager.handleSuccessfulTask(tid, taskResult)
}
DAGSsheduler:
/**
* Called by the TaskSetManager to report task completions or failures.
*/
def taskEnded(
task: Task[_],
reason: TaskEndReason,
result: Any,
accumUpdates: Seq[AccumulatorV2[_, _]],
taskInfo: TaskInfo): Unit = {
eventProcessLoop.post(
CompletionEvent(task, reason, result, accumUpdates, taskInfo))
}
/**
* Responds to a task finishing. This is called inside the event loop so it assumes that it can
* modify the scheduler's internal state. Use taskEnded() to post a task end event from outside.
*/
private[scheduler] def handleTaskCompletion(event: CompletionEvent) {
val task = event.task
val taskId = event.taskInfo.id
val stageId = task.stageId
val taskType = Utils.getFormattedClassName(task)
DAGSsheduler会根据任务的类型（ResultTask or ShuffleMapTask）分别处理。
DAGSsheduler:
/**
* Responds to a task finishing. This is called inside the event loop so it assumes that it can
* modify the scheduler's internal state. Use taskEnded() to post a task end event from outside.
*/
private[scheduler] def handleTaskCompletion(event: CompletionEvent) {
///...
task match {
case rt: ResultTask[_, _] => ///ResultTask
// Cast to ResultStage here because it's part of the ResultTask
// TODO Refactor this out to a function that accepts a ResultStage
val resultStage = stage.asInstanceOf[ResultStage]
resultStage.activeJob match {
case Some(job) =>
if (!job.finished(rt.outputId)) {
updateAccumulators(event)
job.finished(rt.outputId) = true
job.numFinished += 1
// If the whole job has finished, remove it
if (job.numFinished == job.numPartitions) { ///job所有task已经完成
markStageAsFinished(resultStage)
cleanupStateForJobAndIndependentStages(job)
listenerBus.post(
SparkListenerJobEnd(job.jobId, clock.getTimeMillis(), JobSucceeded))
}
// taskSucceeded runs some user code that might throw an exception. Make sure
// we are resilient against that.
try {
job.listener.taskSucceeded(rt.outputId, event.result)
} catch {
case e: Exception =>
// TODO: Perhaps we want to mark the resultStage as failed?
job.listener.jobFailed(new SparkDriverExecutionException(e))
}
}
case None =>
logInfo("Ignoring result from " + rt + " because its job has finished")
}