我是从RDD的collect函数进去的。
/**
* Return an array that contains all of the elements in this RDD.
*/
//调用了sparkContext的runJob
//返回一个Array集合
def collect(): Array[T] = withScope {
val results = sc.runJob(this, (iter: Iterator[T]) => iter.toArray)
Array.concat(results: _*)
}
/**
* Run a job on all partitions in an RDD and return the results in an array.
*/
def runJob[T, U: ClassTag](rdd: RDD[T], func: Iterator[T] => U): Array[U] = {
//对RDD每一个分区运行一次runJob，意思就是分区计算
runJob(rdd, func, 0 until rdd.partitions.length)
}
/**
* Run a job on a given set of partitions of an RDD, but take a function of type
* `Iterator[T] => U` instead of `(TaskContext, Iterator[T]) => U`.
*/
//重载函数
def runJob[T, U: ClassTag](
rdd: RDD[T],
func: Iterator[T] => U,
partitions: Seq[Int]): Array[U] = {
//防止反序列化失败
val cleanedFunc = clean(func)
runJob(rdd, (ctx: TaskContext, it: Iterator[T]) => cleanedFunc(it), partitions)
}
/**
* Run a function on a given set of partitions in an RDD and return the results as an array.
*/
def runJob[T, U: ClassTag](
rdd: RDD[T],
func: (TaskContext, Iterator[T]) => U,
partitions: Seq[Int]): Array[U] = {
//该数组用于获取每个分区的数据
val results = new Array[U](partitions.size)
//再次调用重载函数
runJob[T, U](rdd, func, partitions, (index, res) => results(index) = res)
results
}
/**
* Run a function on a given set of partitions in an RDD and pass the results to the given
* handler function. This is the main entry point for all actions in Spark.
*/
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")
}
//调用栈---就是能跟踪到代码的运行位置
val callSite = getCallSite
//清除函数里面不能序列化的对象
val cleanedFunc = clean(func)
logInfo("Starting job: " + callSite.shortForm)
if (conf.getBoolean("spark.logLineage", false)) {
logInfo("RDD's recursive dependencies:\n" + rdd.toDebugString)
}
//调用DAGScheduler的runJob
dagScheduler.runJob(rdd, cleanedFunc, partitions, callSite, resultHandler, localProperties.get)
progressBar.foreach(_.finishAll())
rdd.doCheckpoint()
}
/**
* Run an action job on the given RDD and pass all the results to the resultHandler function as
* they arrive.
*
* @param rdd target RDD to run tasks on
* @param func a function to run on each partition of the RDD
* @param partitions set of partitions to run on; some jobs may not want to compute on all
* partitions of the target RDD, e.g. for operations like first()
* @param callSite where in the user program this job was called
* @param resultHandler callback to pass each result to
* @param properties scheduler properties to attach to this job, e.g. fair scheduler pool name
*
* @throws Exception when the job fails
*/
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
//调用了submitJob方法。
val waiter = submitJob(rdd, func, partitions, callSite, resultHandler, properties)
//说明方法是异步的
waiter.awaitResult() match {
//任务运行成功后的处理
case JobSucceeded =>
logInfo("Job %d finished: %s, took %f s".format
(waiter.jobId, callSite.shortForm, (System.nanoTime - start) / 1e9))
//任务运行失败后的处理
case JobFailed(exception: 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
}
}
/**
* Submit an action job to the scheduler.
*
* @param rdd target RDD to run tasks on
* @param func a function to run on each partition of the RDD
* @param partitions set of partitions to run on; some jobs may not want to compute on all
* partitions of the target RDD, e.g. for operations like first()
* @param callSite where in the user program this job was called
* @param resultHandler callback to pass each result to
* @param properties scheduler properties to attach to this job, e.g. fair scheduler pool name
*
* @return a JobWaiter object that can be used to block until the job finishes executing
* or can be used to cancel the job.
*
* @throws IllegalArgumentException when partitions ids are illegal
*/
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.
//检查一下，确保没有产生一个没有RDD分区的task
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)
}
//获取到JobId
val jobId = nextJobId.getAndIncrement()
if (partitions.size == 0) {
// Return immediately if the job is running 0 tasks
//如果task没有了 就立刻返回一个JobWaiter
return new JobWaiter[U](this, jobId, 0, resultHandler)
}
assert(partitions.size > 0)
val func2 = func.asInstanceOf[(TaskContext, Iterator[_]) => _]
//创建一个JobWaiter
val waiter = new JobWaiter(this, jobId, partitions.size, resultHandler)
//通过DAGEventProcessLoop 去处理JobSubmitted
eventProcessLoop.post(JobSubmitted(
jobId, rdd, func2, partitions.toArray, callSite, waiter,
SerializationUtils.clone(properties)))
waiter
}
private def doOnReceive(event: DAGSchedulerEvent): Unit = event match {
case JobSubmitted(jobId, rdd, func, partitions, callSite, listener, properties) =>
//DAGEventProcessLoop 会去调用dagScheduler.handleJobSubmitted
dagScheduler.handleJobSubmitted(jobId, rdd, func, partitions, callSite, listener, properties)
}
private[scheduler] def handleJobSubmitted(jobId: Int,
finalRDD: RDD[_],
func: (TaskContext, Iterator[_]) => _,
partitions: Array[Int],
callSite: CallSite,
listener: JobListener,
properties: Properties) {
//创建了一个ResultStage空引用
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.
//创建stage时可能会发生异常（比如job在运行时文件被删了），所以需要手动抛出异常
//创建了一个ResultStage
finalStage = newResultStage(finalRDD, func, partitions, jobId, callSite)
} catch {
case e: Exception =>
logWarning("Creating new stage failed due to exception - job: " + jobId, e)
listener.jobFailed(e)
return
}
// 将所有信息包装创建ActiveJob
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()
//更新到HashMap---jobIdToActiveJob
jobIdToActiveJob(jobId) = job
//HasSet---activeJobs
activeJobs += job
//设置job
finalStage.setActiveJob(job)
//获取stageId的一个数组
val stageIds = jobIdToStageIds(jobId).toArray
val stageInfos = stageIds.flatMap(id => stageIdToStage.get(id).map(_.latestInfo))
//listenerBus 就是WEB的监听器 好大家从WEB页面观察到程序运行情况
listenerBus.post(
SparkListenerJobStart(job.jobId, jobSubmissionTime, stageInfos, properties))
//提交ResultStage
submitStage(finalStage)
//提交那些等待中的stage
submitWaitingStages()
}
/**
* ResultStages apply a function on some partitions of an RDD to compute the result of an action.
* The ResultStage object captures the function to execute, `func`, which will be applied to each
* partition, and the set of partition IDs, `partitions`. Some stages may not run on all partitions
* of the RDD, for actions like first() and lookup().
*/
//翻译 什么是ResuleStage:
//对于每一个action操作resultstage在RDD的分区上都会应用同一个函数计算的结果，就是真正进行计算的stage。
//ResultStage对象将这个函数应用在每一个RDD分区上，不过有的不用用在所有分区上，比如first()
private[spark] class ResultStage(
id: Int,
rdd: RDD[_],
val func: (TaskContext, Iterator[_]) => _,
val partitions: Array[Int],
parents: List[Stage],
firstJobId: Int,
callSite: CallSite)
extends Stage(id, rdd, partitions.length, parents, firstJobId, callSite) {
}