如何进行JobScheduler内幕实现和深度思考

/**
* Apply a function to each RDD in this DStream. This is an output operator, so
* 'this' DStream will be registered as an output stream and therefore materialized.
* @param foreachFunc foreachRDD function
* @param displayInnerRDDOps Whether the detailed callsites and scopes of the RDDs generated
* in the `foreachFunc` to be displayed in the UI. If `false`, then
* only the scopes and callsites of `foreachRDD` will override those
* of the RDDs on the display.
*/
private def foreachRDD(
foreachFunc: (RDD[T], Time) => Unit,
displayInnerRDDOps: Boolean): Unit = {
new ForEachDStream(this,
context.sparkContext.clean(foreachFunc, false), displayInnerRDDOps).register()
}

/**
* An internal DStream used to represent output operations like DStream.foreachRDD.
* @param parent Parent DStream
* @param foreachFunc Function to apply on each RDD generated by the parent DStream
* @param displayInnerRDDOps Whether the detailed callsites and scopes of the RDDs generated
* by `foreachFunc` will be displayed in the UI; only the scope and
* callsite of `DStream.foreachRDD` will be displayed.
*/
private[streaming]
class ForEachDStream[T: ClassTag] (
parent: DStream[T],
foreachFunc: (RDD[T], Time) => Unit,
displayInnerRDDOps: Boolean
) extends DStream[Unit](parent.ssc) {

override def dependencies: List[DStream[_]] = List(parent)

override def slideDuration: Duration = parent.slideDuration

override def compute(validTime: Time): Option[RDD[Unit]] = None

override def generateJob(time: Time): Option[Job] = {
parent.getOrCompute(time) match {
case Some(rdd) =>
val jobFunc = () => createRDDWithLocalProperties(time, displayInnerRDDOps) {
foreachFunc(rdd, time)
}
Some(new Job(time, jobFunc))
case None => None
}
}
}

def generateJobs(time: Time): Seq[Job] = {
logDebug("Generating jobs for time " + time)
val jobs = this.synchronized {
outputStreams.flatMap { outputStream =>
val jobOption = outputStream.generateJob(time)
jobOption.foreach(_.setCallSite(outputStream.creationSite))
jobOption
}
}
logDebug("Generated " + jobs.length + " jobs for time " + time)
jobs
}

/**
* Generate a SparkStreaming job for the given time. This is an internal method that
* should not be called directly. This default implementation creates a job
* that materializes the corresponding RDD. Subclasses of DStream may override this
* to generate their own jobs.
*/
private[streaming] def generateJob(time: Time): Option[Job] = {
getOrCompute(time) match {
case Some(rdd) => {
val jobFunc = () => {
val emptyFunc = { (iterator: Iterator[T]) => {} }
context.sparkContext.runJob(rdd, emptyFunc)
}
Some(new Job(time, jobFunc))
}
case None => None
}
}

/**
* Print the first num elements of each RDD generated in this DStream. This is an output
* operator, so this DStream will be registered as an output stream and there materialized.
*/
def print(num: Int): Unit = ssc.withScope {
def foreachFunc: (RDD[T], Time) => Unit = {
(rdd: RDD[T], time: Time) => {
val firstNum = rdd.take(num + 1)
// scalastyle:off println
println("-------------------------------------------")
println("Time: " + time)
println("-------------------------------------------")
firstNum.take(num).foreach(println)
if (firstNum.length > num) println("...")
println()
// scalastyle:on println
}
}
foreachRDD(context.sparkContext.clean(foreachFunc), displayInnerRDDOps = false)
}