org.apache.spark.executorExecutor
下面:TaskRunner
override def run(): Unit = {
val taskMemoryManager = new TaskMemoryManager(env.memoryManager, taskId)
val deserializeStartTime = System.currentTimeMillis()
Thread.currentThread.setContextClassLoader(replClassLoader)
val ser = env.closureSerializer.newInstance()
logInfo(s"Running $taskName (TID $taskId)")
execBackend.statusUpdate(taskId, TaskState.RUNNING, EMPTY_BYTE_BUFFER)//这个就是就是向Driver发送StatusUpdate方法,状态是RUNNING
var taskStart: Long = 0
startGCTime = computeTotalGcTime()
try {
val (taskFiles, taskJars, taskBytes) = Task.deserializeWithDependencies(serializedTask)//将serializedTask解析出来
updateDependencies(taskFiles, taskJars)//下载运行task需要的jar,文件等
task = ser.deserialize[Task[Any]](taskBytes, Thread.currentThread.getContextClassLoader)//把真正的task反序列化出来
task.setTaskMemoryManager(taskMemoryManager)
// If this task has been killed before we deserialized it, let's quit now. Otherwise,
// continue executing the task.
if (killed) {
// 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
}
logDebug("Task " + taskId + "'s epoch is " + task.epoch)
env.mapOutputTracker.updateEpoch(task.epoch)
// Run the actual task and measure its runtime.
taskStart = System.currentTimeMillis()
var threwException = true
val (value, accumUpdates) = try {
val res = task.run(//任务执行
taskAttemptId = taskId,
attemptNumber = attemptNumber,
metricsSystem = env.metricsSystem)
threwException = false
res
} finally {
val freedMemory = taskMemoryManager.cleanUpAllAllocatedMemory()//释放缓存
if (freedMemory > 0) {
val errMsg = s"Managed memory leak detected; size = $freedMemory bytes, TID = $taskId"
if (conf.getBoolean("spark.unsafe.exceptionOnMemoryLeak", false) && !threwException) {
throw new SparkException(errMsg)
} else {
logError(errMsg)
}
}
}
val taskFinish = System.currentTimeMillis()
// If the task has been killed, let's fail it.
if (task.killed) {
throw new TaskKilledException
}
val resultSer = env.serializer.newInstance()
val beforeSerialization = System.currentTimeMillis()
val valueBytes = resultSer.serialize(value)//将task运行结果序列化
val afterSerialization = System.currentTimeMillis()
for (m <- task.metrics) {
// 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.
m.setExecutorDeserializeTime(
(taskStart - deserializeStartTime) + task.executorDeserializeTime)
// We need to subtract Task.run()'s deserialization time to avoid double-counting
m.setExecutorRunTime((taskFinish - taskStart) - task.executorDeserializeTime)
m.setJvmGCTime(computeTotalGcTime() - startGCTime)
m.setResultSerializationTime(afterSerialization - beforeSerialization)
m.updateAccumulators()
}
val directResult = new DirectTaskResult(valueBytes, accumUpdates, task.metrics.orNull)
val serializedDirectResult = ser.serialize(directResult)
val resultSize = serializedDirectResult.limit
//这里将最终结果序列化成serializedDirectResult,并根据这个序列化之后的大小区分处理
// directSend = sending directly back to the driver
val serializedResult: ByteBuffer = {//最终结果序列化之后>1G
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 >= akkaFrameSize - AkkaUtils.reservedSizeBytes) {//最终结果序列化之后>10M,把序列化的结果作为一个Block存放在BlockManager里,而后将BlockManager返回的BlockID放在IndirectTaskResult对象中
val blockId = TaskResultBlockId(taskId)
env.blockManager.putBytes(
blockId, serializedDirectResult, 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 {//小数据可以直接处理
logInfo(s"Finished $taskName (TID $taskId). $resultSize bytes result sent to driver")
serializedDirectResult
}
}
execBackend.statusUpdate(taskId, TaskState.FINISHED, serializedResult)
} catch {
case ffe: FetchFailedException =>
val reason = ffe.toTaskEndReason
execBackend.statusUpdate(taskId, TaskState.FAILED, ser.serialize(reason))
case _: TaskKilledException | _: InterruptedException if task.killed =>
logInfo(s"Executor killed $taskName (TID $taskId)")
execBackend.statusUpdate(taskId, TaskState.KILLED, ser.serialize(TaskKilled))
case cDE: CommitDeniedException =>
val reason = cDE.toTaskEndReason
execBackend.statusUpdate(taskId, TaskState.FAILED, 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)
val metrics: Option[TaskMetrics] = Option(task).flatMap { task =>
task.metrics.map { m =>
m.setExecutorRunTime(System.currentTimeMillis() - taskStart)
m.setJvmGCTime(computeTotalGcTime() - startGCTime)
m.updateAccumulators()
m
}
}
val serializedTaskEndReason = {
try {
ser.serialize(new ExceptionFailure(t, metrics))
} catch {
case _: NotSerializableException =>
// t is not serializable so just send the stacktrace
ser.serialize(new ExceptionFailure(t, metrics, false))
}
}
execBackend.statusUpdate(taskId, TaskState.FAILED, serializedTaskEndReason)
// Don't forcibly exit unless the exception was inherently fatal, to avoid
// stopping other tasks unnecessarily.
if (Utils.isFatalError(t)) {
SparkUncaughtExceptionHandler.uncaughtException(t)
}
} finally {
runningTasks.remove(taskId)
}
}
}
Task.run
final def run(
taskAttemptId: Long,
attemptNumber: Int,
metricsSystem: MetricsSystem)
: (T, AccumulatorUpdates) = {
context = new TaskContextImpl(
stageId,
partitionId,
taskAttemptId,
attemptNumber,
taskMemoryManager,
metricsSystem,
internalAccumulators,
runningLocally = false)
TaskContext.setTaskContext(context)
context.taskMetrics.setHostname(Utils.localHostName())
context.taskMetrics.setAccumulatorsUpdater(context.collectInternalAccumulators)
taskThread = Thread.currentThread()
if (_killed) {
kill(interruptThread = false)
}
try {
(runTask(context), context.collectAccumulators())
} finally {
context.markTaskCompleted()
try {
Utils.tryLogNonFatalError {
// Release memory used by this thread for unrolling blocks
SparkEnv.get.blockManager.memoryStore.releaseUnrollMemoryForThisTask()
// 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 {
TaskContext.unset()
}
}
}
了解下reduceByKey,方法在PairRDDFunctions中
/**
* Merge the values for each key using an associative reduce function. This will also perform
* the merging locally on each mapper before sending results to a reducer, similarly to a
* "combiner" in MapReduce.
*/
def reduceByKey(partitioner: Partitioner, func: (V, V) => V): RDD[(K, V)] = self.withScope {
combineByKeyWithClassTag[V]((v: V) => v, func, func, partitioner)
}
/**
* Merge the values for each key using an associative reduce function. This will also perform
* the merging locally on each mapper before sending results to a reducer, similarly to a
* "combiner" in MapReduce. Output will be hash-partitioned with numPartitions partitions.
*/
def reduceByKey(func: (V, V) => V, numPartitions: Int): RDD[(K, V)] = self.withScope {
reduceByKey(new HashPartitioner(numPartitions), func)
}
/**
* Merge the values for each key using an associative reduce function. This will also perform
* the merging locally on each mapper before sending results to a reducer, similarly to a
* "combiner" in MapReduce. Output will be hash-partitioned with the existing partitioner/
* parallelism level.
*/
def reduceByKey(func: (V, V) => V): RDD[(K, V)] = self.withScope {
reduceByKey(defaultPartitioner(self), func)
}
这里有3个不同的reduceByKey方法。我们可以手动设定reduce的个数,如果不指定的话,就可能不受控制了。
如果不指定reduce个数的话,规则如下:
1、如果自定义了分区函数partitioner的话,就按你的分区函数来走。
2、如果没有定义分区函数而是定义了reduce个数的话,默认分区函数就是根据reduce个数生成HashPartitioner
3、如果这个也没设置,那就按照reduce个数是"spark.default.parallelism"或者rdd.head.partitions.size来生成HashPartitioner
reduceByKey只是一个transformation,真正发挥作用是在action触发之后
还有两个比较重要的ShuffleMapTask和ResultTask,有时间看看他们的runtask方法