内容上接第八篇。
原理图:
代码分析:
1. Executor/TaskRunner
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)")
execBackend.statusUpdate(taskId, TaskState.RUNNING, EMPTY_BYTE_BUFFER)
var taskStartTime: Long = 0
var taskStartCpu: Long = 0
startGCTime = computeTotalGcTime()
try {
// Must be set before updateDependencies() is called, in case fetching dependencies
// requires access to properties contained within (e.g. for access control).
Executor.taskDeserializationProps.set(taskDescription.properties)
// 准备工作,下载需要的files和jar包等
updateDependencies(taskDescription.addedFiles, taskDescription.addedJars)
// 反序列化task数据集
task = ser.deserialize[Task[Any]](
taskDescription.serializedTask, Thread.currentThread.getContextClassLoader)
task.localProperties = taskDescription.properties
task.setTaskMemoryManager(taskMemoryManager)
// If this task has been killed before we deserialized it, let's quit now. Otherwise,
// continue executing the task.
val killReason = reasonIfKilled
if (killReason.isDefined) {
// Throw an exception rather than returning, because returning within a try{} block
// causes a NonLocalReturnControl exception to be thrown. The NonLocalReturnControl
// exception will be caught by the catch block, leading to an incorrect ExceptionFailure
// for the task.
throw new TaskKilledException(killReason.get)
}
// The purpose of updating the epoch here is to invalidate executor map output status cache
// in case FetchFailures have occurred. In local mode `env.mapOutputTracker` will be
// MapOutputTrackerMaster and its cache invalidation is not based on epoch numbers so
// we don't need to make any special calls here.
if (!isLocal) {
logDebug("Task " + taskId + "'s epoch is " + task.epoch)
env.mapOutputTracker.asInstanceOf[MapOutputTrackerWorker].updateEpoch(task.epoch)
}
// Run the actual task and measure its runtime.
taskStartTime = System.currentTimeMillis()
taskStartCpu = if (threadMXBean.isCurrentThreadCpuTimeSupported) {
threadMXBean.getCurrentThreadCpuTime
} else 0L
var threwException = true
// 这里的value,对于ShuffleMapTask来说,就是MapStatus,封装了ShuffleMapTask计算数据的位置
// 后面如果还是一个ShuffleMapTask或ResultTask,
// 就会联系MapOutputTracker获取上一个ShuffleMapTask的输出位置,然后通过网络拉取数据
val value = Utils.tryWithSafeFinally {
val res = task.run(
taskAttemptId = taskId,
attemptNumber = taskDescription.attemptNumber,
metricsSystem = env.metricsSystem)
threwException = false
res
} {
val releasedLocks = env.blockManager.releaseAllLocksForTask(taskId)
val freedMemory = taskMemoryManager.cleanUpAllAllocatedMemory()
if (freedMemory > 0 && !threwException) {
val errMsg = s"Managed memory leak detected; size = $freedMemory bytes, TID = $taskId"
if (conf.getBoolean("spark.unsafe.exceptionOnMemoryLeak", false)) {
throw new SparkException(errMsg)
} else {
logWarning(errMsg)
}
}
if (releasedLocks.nonEmpty && !threwException) {
val errMsg =
s"${releasedLocks.size} block locks were not released by TID = $taskId:\n" +
releasedLocks.mkString("[", ", ", "]")
if (conf.getBoolean("spark.storage.exceptionOnPinLeak", false)) {
throw new SparkException(errMsg)
} else {
logInfo(errMsg)
}
}
}
task.context.fetchFailed.foreach { fetchFailure =>
// uh-oh. it appears the user code has caught the fetch-failure without throwing any
// other exceptions. Its *possible* this is what the user meant to do (though highly
// unlikely). So we will log an error and keep going.
logError(s"TID ${taskId} completed successfully though internally it encountered " +
s"unrecoverable fetch failures! Most likely this means user code is incorrectly " +
s"swallowing Spark's internal ${classOf[FetchFailedException]}", fetchFailure)
}
val taskFinish = System.currentTimeMillis()
val taskFinishCpu = if (threadMXBean.isCurrentThreadCpuTimeSupported) {
threadMXBean.getCurrentThreadCpuTime
} else 0L
// If the task has been killed, let's fail it.
task.context.killTaskIfInterrupted()
val resultSer = env.serializer.newInstance()
val beforeSerialization = System.currentTimeMillis()
val valueBytes = resultSer.serialize(value)
val afterSerialization = System.currentTimeMillis()
// Deserialization happens in two parts: first, we deserialize a Task object, which
// includes the Partition. Second, Task.run() deserializes the RDD and function to be run.
// 一些统计信息,会展示在SparkUI上
task.metrics.setExecutorDeserializeTime(
(taskStartTime - deserializeStartTime) + task.executorDeserializeTime)
task.metrics.setExecutorDeserializeCpuTime(
(taskStartCpu - deserializeStartCpuTime) + task.executorDeserializeCpuTime)
// We need to subtract Task.run()'s deserialization time to avoid double-counting
task.metrics.setExecutorRunTime((taskFinish - taskStartTime) - task.executorDeserializeTime)
task.metrics.setExecutorCpuTime(
(taskFinishCpu - taskStartCpu) - task.executorDeserializeCpuTime)
task.metrics.setJvmGCTime(computeTotalGcTime() - startGCTime)
task.metrics.setResultSerializationTime(afterSerialization - beforeSerialization)
// Expose task metrics using the Dropwizard metrics system.
// Update task metrics counters
executorSource.METRIC_CPU_TIME.inc(task.metrics.executorCpuTime)
executorSource.METRIC_RUN_TIME.inc(task.metrics.executorRunTime)
executorSource.METRIC_JVM_GC_TIME.inc(task.metrics.jvmGCTime)
executorSource.METRIC_DESERIALIZE_TIME.inc(task.metrics.executorDeserializeTime)
executorSource.METRIC_DESERIALIZE_CPU_TIME.inc(task.metrics.executorDeserializeCpuTime)
executorSource.METRIC_RESULT_SERIALIZE_TIME.inc(task.metrics.resultSerializationTime)
executorSource.METRIC_SHUFFLE_FETCH_WAIT_TIME
.inc(task.metrics.shuffleReadMetrics.fetchWaitTime)
executorSource.METRIC_SHUFFLE_WRITE_TIME.inc(task.metrics.shuffleWriteMetrics.writeTime)
executorSource.METRIC_SHUFFLE_TOTAL_BYTES_READ
.inc(task.metrics.shuffleReadMetrics.totalBytesRead)
executorSource.METRIC_SHUFFLE_REMOTE_BYTES_READ
.inc(task.metrics.shuffleReadMetrics.remoteBytesRead)
executorSource.METRIC_SHUFFLE_REMOTE_BYTES_READ_TO_DISK
.inc(task.metrics.shuffleReadMetrics.remoteBytesReadToDisk)
executorSource.METRIC_SHUFFLE_LOCAL_BYTES_READ
.inc(task.metrics.shuffleReadMetrics.localBytesRead)
executorSource.METRIC_SHUFFLE_RECORDS_READ
.inc(task.metrics.shuffleReadMetrics.recordsRead)
executorSource.METRIC_SHUFFLE_REMOTE_BLOCKS_FETCHED
.inc(task.metrics.shuffleReadMetrics.remoteBlocksFetched)
executorSource.METRIC_SHUFFLE_LOCAL_BLOCKS_FETCHED
.inc(task.metrics.shuffleReadMetrics.localBlocksFetched)
executorSource.METRIC_SHUFFLE_BYTES_WRITTEN
.inc(task.metrics.shuffleWriteMetrics.bytesWritten)
executorSource.METRIC_SHUFFLE_RECORDS_WRITTEN
.inc(task.metrics.shuffleWriteMetrics.recordsWritten)
executorSource.METRIC_INPUT_BYTES_READ
.inc(task.metrics.inputMetrics.bytesRead)
executorSource.METRIC_INPUT_RECORDS_READ
.inc(task.metrics.inputMetrics.recordsRead)
executorSource.METRIC_OUTPUT_BYTES_WRITTEN
.inc(task.metrics.outputMetrics.bytesWritten)
executorSource.METRIC_OUTPUT_RECORDS_WRITTEN
.inc(task.metrics.outputMetrics.recordsWritten)
executorSource.METRIC_RESULT_SIZE.inc(task.metrics.resultSize)
executorSource.METRIC_DISK_BYTES_SPILLED.inc(task.metrics.diskBytesSpilled)
executorSource.METRIC_MEMORY_BYTES_SPILLED.inc(task.metrics.memoryBytesSpilled)
// Note: accumulator updates must be collected after TaskMetrics is updated
val accumUpdates = task.collectAccumulatorUpdates()
// TODO: do not serialize value twice
val directResult = new DirectTaskResult(valueBytes, accumUpdates)
val serializedDirectResult = ser.serialize(directResult)
val resultSize = serializedDirectResult.limit()
// directSend = sending directly back to the driver
val serializedResult: ByteBuffer = {
if (maxResultSize > 0 && resultSize > maxResultSize) {
logWarning(s"Finished $taskName (TID $taskId). Result is larger than maxResultSize " +
s"(${Utils.bytesToString(resultSize)} > ${Utils.bytesToString(maxResultSize)}), " +
s"dropping it.")
ser.serialize(new IndirectTaskResult[Any](TaskResultBlockId(taskId), resultSize))
} else if (resultSize > maxDirectResultSize) {
val blockId = TaskResultBlockId(taskId)
env.blockManager.putBytes(
blockId,
new ChunkedByteBuffer(serializedDirectResult.duplicate()),
StorageLevel.MEMORY_AND_DISK_SER)
logInfo(
s"Finished $taskName (TID $taskId). $resultSize bytes result sent via BlockManager)")
ser.serialize(new IndirectTaskResult[Any](blockId, resultSize))
} else {
logInfo(s"Finished $taskName (TID $taskId). $resultSize bytes result sent to driver")
serializedDirectResult
}
}
setTaskFinishedAndClearInterruptStatus()
// 调用CoarseGrainedExecutorBackend的statusUpdate方法
execBackend.statusUpdate(taskId, TaskState.FINISHED, serializedResult)
} catch {
case t: TaskKilledException =>
logInfo(s"Executor killed $taskName (TID $taskId), reason: ${t.reason}")
val (accums, accUpdates) = collectAccumulatorsAndResetStatusOnFailure(taskStartTime)
val serializedTK = ser.serialize(TaskKilled(t.reason, accUpdates, accums))
execBackend.statusUpdate(taskId, TaskState.KILLED, serializedTK)
case _: InterruptedException | NonFatal(_) if
task != null && task.reasonIfKilled.isDefined =>
val killReason = task.reasonIfKilled.getOrElse("unknown reason")
logInfo(s"Executor interrupted and killed $taskName (TID $taskId), reason: $killReason")
val (accums, accUpdates) = collectAccumulatorsAndResetStatusOnFailure(taskStartTime)
val serializedTK = ser.serialize(TaskKilled(killReason, accUpdates, accums))
execBackend.statusUpdate(taskId, TaskState.KILLED, serializedTK)
case t: Throwable if hasFetchFailure && !Utils.isFatalError(t) =>
val reason = task.context.fetchFailed.get.toTaskFailedReason
if (!t.isInstanceOf[FetchFailedException]) {
// there was a fetch failure in the task, but some user code wrapped that exception
// and threw something else. Regardless, we treat it as a fetch failure.
val fetchFailedCls = classOf[FetchFailedException].getName
logWarning(s"TID ${taskId} encountered a ${fetchFailedCls} and " +
s"failed, but the ${fetchFailedCls} was hidden by another " +
s"exception. Spark is handling this like a fetch failure and ignoring the " +
s"other exception: $t")
}
setTaskFinishedAndClearInterruptStatus()
execBackend.statusUpdate(taskId, TaskState.FAILED, ser.serialize(reason))
case CausedBy(cDE: CommitDeniedException) =>
val reason = cDE.toTaskCommitDeniedReason
setTaskFinishedAndClearInterruptStatus()
execBackend.statusUpdate(taskId, TaskState.KILLED, ser.serialize(reason))
case t: Throwable =>
// Attempt to exit cleanly by informing the driver of our failure.
// If anything goes wrong (or this was a fatal exception), we will delegate to
// the default uncaught exception handler, which will terminate the Executor.
logError(s"Exception in $taskName (TID $taskId)", t)
// SPARK-20904: Do not report failure to driver if if happened during shut down. Because
// libraries may set up shutdown hooks that race with running tasks during shutdown,
// spurious failures may occur and can result in improper accounting in the driver (e.g.
// the task failure would not be ignored if the shutdown happened because of premption,
// instead of an app issue).
if (!ShutdownHookManager.inShutdown()) {
val (accums, accUpdates) = collectAccumulatorsAndResetStatusOnFailure(taskStartTime)
val serializedTaskEndReason = {
try {
ser.serialize(new ExceptionFailure(t, accUpdates).withAccums(accums))
} catch {
case _: NotSerializableException =>
// t is not serializable so just send the stacktrace
ser.serialize(new ExceptionFailure(t, accUpdates, false).withAccums(accums))
}
}
setTaskFinishedAndClearInterruptStatus()
execBackend.statusUpdate(taskId, TaskState.FAILED, serializedTaskEndReason)
} else {
logInfo("Not reporting error to driver during JVM shutdown.")
}
// Don't forcibly exit unless the exception was inherently fatal, to avoid
// stopping other tasks unnecessarily.
if (!t.isInstanceOf[SparkOutOfMemoryError] && Utils.isFatalError(t)) {
uncaughtExceptionHandler.uncaughtException(Thread.currentThread(), t)
}
} finally {
runningTasks.remove(taskId)
}
}
2. Task/run
/**
* Called by [[org.apache.spark.executor.Executor]] to run this task.
*
* @param taskAttemptId an identifier for this task attempt that is unique within a SparkContext.
* @param attemptNumber how many times this task has been attempted (0 for the first attempt)
* @return the result of the task along with updates of Accumulators.
*/
final def run(
taskAttemptId: Long,
attemptNumber: Int,
metricsSystem: MetricsSystem): T = {
SparkEnv.get.blockManager.registerTask(taskAttemptId)
// TODO SPARK-24874 Allow create BarrierTaskContext based on partitions, instead of whether
// the stage is barrier.
// 执行上下文,记录了task执行的一些全局性的数据,比如重试次数,task属于哪个stage,task要处理的是rdd的哪个partition等
val taskContext = new TaskContextImpl(
stageId,
stageAttemptId, // stageAttemptId and stageAttemptNumber are semantically equal
partitionId,
taskAttemptId,
attemptNumber,
taskMemoryManager,
localProperties,
metricsSystem,
metrics)
context = if (isBarrier) {
new BarrierTaskContext(taskContext)
} else {
taskContext
}
TaskContext.setTaskContext(context)
taskThread = Thread.currentThread()
if (_reasonIfKilled != null) {
kill(interruptThread = false, _reasonIfKilled)
}
new CallerContext(
"TASK",
SparkEnv.get.conf.get(APP_CALLER_CONTEXT),
appId,
appAttemptId,
jobId,
Option(stageId),
Option(stageAttemptId),
Option(taskAttemptId),
Option(attemptNumber)).setCurrentContext()
try {
runTask(context) // 调用ShuffleMapTask runTask 或 ResultTask runTask
} catch {
case e: Throwable =>
// Catch all errors; run task failure callbacks, and rethrow the exception.
try {
context.markTaskFailed(e)
} catch {
case t: Throwable =>
e.addSuppressed(t)
}
context.markTaskCompleted(Some(e))
throw e
} finally {
try {
// Call the task completion callbacks. If "markTaskCompleted" is called twice, the second
// one is no-op.
context.markTaskCompleted(None)
} finally {
try {
Utils.tryLogNonFatalError {
// Release memory used by this thread for unrolling blocks
SparkEnv.get.blockManager.memoryStore.releaseUnrollMemoryForThisTask(MemoryMode.ON_HEAP)
SparkEnv.get.blockManager.memoryStore.releaseUnrollMemoryForThisTask(
MemoryMode.OFF_HEAP)
// Notify any tasks waiting for execution memory to be freed to wake up and try to
// acquire memory again. This makes impossible the scenario where a task sleeps forever
// because there are no other tasks left to notify it. Since this is safe to do but may
// not be strictly necessary, we should revisit whether we can remove this in the
// future.
val memoryManager = SparkEnv.get.memoryManager
memoryManager.synchronized { memoryManager.notifyAll() }
}
} finally {
// Though we unset the ThreadLocal here, the context member variable itself is still
// queried directly in the TaskRunner to check for FetchFailedExceptions.
TaskContext.unset()
}
}
}
}
3. ShuffleMapTask
一个ShuffleMapTask会将一个RDD切分为多个bucket
// 返回MapStatus
override def runTask(context: TaskContext): MapStatus = {
// Deserialize the RDD using the broadcast variable.
val threadMXBean = ManagementFactory.getThreadMXBean
val deserializeStartTime = System.currentTimeMillis()
val deserializeStartCpuTime = if (threadMXBean.isCurrentThreadCpuTimeSupported) {
threadMXBean.getCurrentThreadCpuTime
} else 0L
val ser = SparkEnv.get.closureSerializer.newInstance()
// 反序列化拿到RDD
// task运行在多个executor中,都是并行运行,可能不在同一个地方,但是一个stage的task要处理的rdd是一样的
// task是通过broadcast variable拿到自己要处理的数据
val (rdd, dep) = ser.deserialize[(RDD[_], ShuffleDependency[_, _, _])](
ByteBuffer.wrap(taskBinary.value), Thread.currentThread.getContextClassLoader)
_executorDeserializeTime = System.currentTimeMillis() - deserializeStartTime
_executorDeserializeCpuTime = if (threadMXBean.isCurrentThreadCpuTimeSupported) {
threadMXBean.getCurrentThreadCpuTime - deserializeStartCpuTime
} else 0L
var writer: ShuffleWriter[Any, Any] = null
try {
val manager = SparkEnv.get.shuffleManager
writer = manager.getWriter[Any, Any](dep.shuffleHandle, partitionId, context)
// 调用rdd的iterator方法,传入了当前rdd要处理的partition
// 用开发者自定义的算子处理该rdd的partition
// 返回的数据都是通过ShuffleWriter经过HashPartitioner进行分区之后,写入自己对应的bucket
writer.write(rdd.iterator(partition, context).asInstanceOf[Iterator[_ <: Product2[Any, Any]]])
// 返回结果MapStatus
// MapStatus里面封装了ShuffleMapTask计算后的数据存储位置,其实就是BlockManager相关的信息
writer.stop(success = true).get
} catch {
case e: Exception =>
try {
if (writer != null) {
writer.stop(success = false)
}
} catch {
case e: Exception =>
log.debug("Could not stop writer", e)
}
throw e
}
}
4. RDD
/**
* 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)
}
}
/**
* 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) {
firstParent[T].iterator(split, context)
} else {
compute(split, context)
}
}
举例:MapPartitionsRDD compute
private[spark] class MapPartitionsRDD[U: ClassTag, T: ClassTag](
var prev: RDD[T],
f: (TaskContext, Int, Iterator[T]) => Iterator[U], // (TaskContext, partition index, iterator)
preservesPartitioning: Boolean = false,
isFromBarrier: Boolean = false,
isOrderSensitive: Boolean = false)
extends RDD[U](prev) {
override val partitioner = if (preservesPartitioning) firstParent[T].partitioner else None
override def getPartitions: Array[Partition] = firstParent[T].partitions
// f 为开发者自定义算子或函数
override def compute(split: Partition, context: TaskContext): Iterator[U] =
f(context, split.index, firstParent[T].iterator(split, context))
override def clearDependencies() {
super.clearDependencies()
prev = null
}
@transient protected lazy override val isBarrier_ : Boolean =
isFromBarrier || dependencies.exists(_.rdd.isBarrier())
override protected def getOutputDeterministicLevel = {
if (isOrderSensitive && prev.outputDeterministicLevel == DeterministicLevel.UNORDERED) {
DeterministicLevel.INDETERMINATE
} else {
super.getOutputDeterministicLevel
}
}
}
5. 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) // 向CoarseGrainedSchedulerBackend发送消息
case None => logWarning(s"Drop $msg because has not yet connected to driver")
}
}
6. CoarseGrainedSchedulerBackend
// 接收到StatusUpdate
override def receive: PartialFunction[Any, Unit] = {
case StatusUpdate(executorId, taskId, state, data) =>
scheduler.statusUpdate(taskId, state, data.value) // TaskSchedulerImpl
if (TaskState.isFinished(state)) {
executorDataMap.get(executorId) match {
case Some(executorInfo) =>
executorInfo.freeCores += scheduler.CPUS_PER_TASK
makeOffers(executorId)
case None =>
// Ignoring the update since we don't know about the executor.
logWarning(s"Ignored task status update ($taskId state $state) " +
s"from unknown executor with ID $executorId")
}
}
7. TaskSchedulerImpl
def statusUpdate(tid: Long, state: TaskState, serializedData: ByteBuffer) {
var failedExecutor: Option[String] = None
var reason: Option[ExecutorLossReason] = None
synchronized {
try {
// 失败或成功分别做处理
Option(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)
} else if (Set(TaskState.FAILED, TaskState.KILLED, TaskState.LOST).contains(state)) {
taskResultGetter.enqueueFailedTask(taskSet, tid, state, serializedData)
}
}
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()
}
}
附:ResultTask runTask代码:
override def runTask(context: TaskContext): U = {
// Deserialize the RDD and the func using the broadcast variables.
val threadMXBean = ManagementFactory.getThreadMXBean
val deserializeStartTime = System.currentTimeMillis()
val deserializeStartCpuTime = if (threadMXBean.isCurrentThreadCpuTimeSupported) {
threadMXBean.getCurrentThreadCpuTime
} else 0L
val ser = SparkEnv.get.closureSerializer.newInstance()
val (rdd, func) = ser.deserialize[(RDD[T], (TaskContext, Iterator[T]) => U)](
ByteBuffer.wrap(taskBinary.value), Thread.currentThread.getContextClassLoader)
_executorDeserializeTime = System.currentTimeMillis() - deserializeStartTime
_executorDeserializeCpuTime = if (threadMXBean.isCurrentThreadCpuTimeSupported) {
threadMXBean.getCurrentThreadCpuTime - deserializeStartCpuTime
} else 0L
// 通过rdd的iterator执行开发这自定义的算子或函数
// 没有后续task,不需要返回值
func(context, rdd.iterator(partition, context))
}