DStream与RDD关系是什么

* DStreams internally is characterized by a few basic properties:
* - A list of other DStreams that the DStream depends on
* - A time interval at which the DStream generates an RDD
* - A function that is used to generate an RDD after each time interval

// RDDs generated, marked as private[streaming] so that testsuites can access it
@transient
private[streaming] var generatedRDDs = new HashMap[Time, RDD[T]] ()

/**
* Get the RDD corresponding to the given time; either retrieve it from cache
* or compute-and-cache it.
*/
private[streaming] final def getOrCompute(time: Time): Option[RDD[T]] = {
// If RDD was already generated, then retrieve it from HashMap,
// or else compute the RDD
generatedRDDs.get(time).orElse {
// Compute the RDD if time is valid (e.g. correct time in a sliding window)
// of RDD generation, else generate nothing.
if (isTimeValid(time)) {

val rddOption = createRDDWithLocalProperties(time, displayInnerRDDOps = false) {
// Disable checks for existing output directories in jobs launched by the streaming
// scheduler, since we may need to write output to an existing directory during checkpoint
// recovery; see SPARK-4835 for more details. We need to have this call here because
// compute() might cause Spark jobs to be launched.
PairRDDFunctions.disableOutputSpecValidation.withValue(true) {
compute(time)
}
}

rddOption.foreach { case newRDD =>
// Register the generated RDD for caching and checkpointing
if (storageLevel != StorageLevel.NONE) {
newRDD.persist(storageLevel)
logDebug(s"Persisting RDD ${newRDD.id} for time $time to $storageLevel")
}
if (checkpointDuration != null && (time - zeroTime).isMultipleOf(checkpointDuration)) {
newRDD.checkpoint()
logInfo(s"Marking RDD ${newRDD.id} for time $time for checkpointing")
}
generatedRDDs.put(time, newRDD)
}
rddOption
} else {
None
}
}
}

/**
* Generates RDDs with blocks received by the receiver of this stream. */
override def compute(validTime: Time): Option[RDD[T]] = {
val blockRDD = {
if (validTime < graph.startTime) {
// If this is called for any time before the start time of the context,
// then this returns an empty RDD. This may happen when recovering from a
// driver failure without any write ahead log to recover pre-failure data.
new BlockRDD[T](ssc.sc, Array.empty)
} else {
// Otherwise, ask the tracker for all the blocks that have been allocated to this stream
// for this batch
val receiverTracker = ssc.scheduler.receiverTracker
val blockInfos = receiverTracker.getBlocksOfBatch(validTime).getOrElse(id, Seq.empty)

// Register the input blocks information into InputInfoTracker
val inputInfo = StreamInputInfo(id, blockInfos.flatMap(_.numRecords).sum)
ssc.scheduler.inputInfoTracker.reportInfo(validTime, inputInfo)

// Create the BlockRDD
createBlockRDD(validTime, blockInfos)
}
}
Some(blockRDD)
}

private[streaming] def createBlockRDD(time: Time, blockInfos: Seq[ReceivedBlockInfo]): RDD[T] = {
if (blockInfos.nonEmpty) {
val blockIds = blockInfos.map { _.blockId.asInstanceOf[BlockId] }.toArray

// Are WAL record handles present with all the blocks
val areWALRecordHandlesPresent = blockInfos.forall { _.walRecordHandleOption.nonEmpty }

if (areWALRecordHandlesPresent) {
// If all the blocks have WAL record handle, then create a WALBackedBlockRDD
val isBlockIdValid = blockInfos.map { _.isBlockIdValid() }.toArray
val walRecordHandles = blockInfos.map { _.walRecordHandleOption.get }.toArray
new WriteAheadLogBackedBlockRDD[T](
ssc.sparkContext, blockIds, walRecordHandles, isBlockIdValid)
} else {
// Else, create a BlockRDD. However, if there are some blocks with WAL info but not
// others then that is unexpected and log a warning accordingly.
if (blockInfos.find(_.walRecordHandleOption.nonEmpty).nonEmpty) {
if (WriteAheadLogUtils.enableReceiverLog(ssc.conf)) {
logError("Some blocks do not have Write Ahead Log information; " +
"this is unexpected and data may not be recoverable after driver failures")
} else {
logWarning("Some blocks have Write Ahead Log information; this is unexpected")
}
}
val validBlockIds = blockIds.filter { id =>
ssc.sparkContext.env.blockManager.master.contains(id)
}
if (validBlockIds.size != blockIds.size) {
logWarning("Some blocks could not be recovered as they were not found in memory. " +
"To prevent such data loss, enabled Write Ahead Log (see programming guide " +
"for more details.")
}
new BlockRDD[T](ssc.sc, validBlockIds)
}
} else {
// If no block is ready now, creating WriteAheadLogBackedBlockRDD or BlockRDD
// according to the configuration
if (WriteAheadLogUtils.enableReceiverLog(ssc.conf)) {
new WriteAheadLogBackedBlockRDD[T](
ssc.sparkContext, Array.empty, Array.empty, Array.empty)
} else {
new BlockRDD[T](ssc.sc, Array.empty)
}
}
}

private[streaming]
class MappedDStream[T: ClassTag, U: ClassTag] (
parent: DStream[T],
mapFunc: T => U
) extends DStream[U](parent.ssc) {

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

override def slideDuration: Duration = parent.slideDuration

override def compute(validTime: Time): Option[RDD[U]] = {
parent.getOrCompute(validTime).map(_.map[U](mapFunc))
}
}

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
}
}
}

/** Generate jobs and perform checkpoint for the given `time`. */
private def generateJobs(time: Time) {
// Set the SparkEnv in this thread, so that job generation code can access the environment
// Example: BlockRDDs are created in this thread, and it needs to access BlockManager
// Update: This is probably redundant after threadlocal stuff in SparkEnv has been removed.
SparkEnv.set(ssc.env)
Try {
//根据特定的时间获取具体的数据
jobScheduler.receiverTracker.allocateBlocksToBatch(time) // allocate received blocks to batch
//调用DStreamGraph的generateJobs生成Job
graph.generateJobs(time) // generate jobs using allocated block
} match {
case Success(jobs) =>
val streamIdToInputInfos = jobScheduler.inputInfoTracker.getInfo(time)
jobScheduler.submitJobSet(JobSet(time, jobs, streamIdToInputInfos))
case Failure(e) =>
jobScheduler.reportError("Error generating jobs for time " + time, e)
}
eventLoop.post(DoCheckpoint(time, clearCheckpointDataLater = false))
}

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
}