Github user harishreedharan commented on a diff in the pull request:
https://github.com/apache/spark/pull/3026#discussion_r19698295
--- Diff:
streaming/src/main/scala/org/apache/spark/streaming/dstream/ReceiverInputDStream.scala
---
@@ -58,24 +54,45 @@ abstract class ReceiverInputDStream[T:
ClassTag](@transient ssc_ : StreamingCont
def stop() {}
- /** Ask ReceiverInputTracker for received data blocks and generates RDDs
with them. */
+ /**
+ * Generates RDDs with blocks received by the receiver of this stream. */
override def compute(validTime: Time): Option[RDD[T]] = {
- // 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
- // master failure
- if (validTime >= graph.startTime) {
- val blockInfo =
ssc.scheduler.receiverTracker.getReceivedBlockInfo(id)
- receivedBlockInfo(validTime) = blockInfo
- val blockIds = blockInfo.map {
_.blockStoreResult.blockId.asInstanceOf[BlockId] }
- Some(new BlockRDD[T](ssc.sc, blockIds))
- } else {
- Some(new BlockRDD[T](ssc.sc, Array.empty))
- }
- }
+ val blockRDD = {
- /** Get information on received blocks. */
- private[streaming] def getReceivedBlockInfo(time: Time) = {
- receivedBlockInfo.get(time).getOrElse(Array.empty[ReceivedBlockInfo])
+ 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 blockInfos =
+
ssc.scheduler.receiverTracker.getBlocksOfBatch(validTime).get(id).getOrElse(Seq.empty)
+ val blockStoreResults = blockInfos.map { _.blockStoreResult }
+ val blockIds = blockStoreResults.map {
_.blockId.asInstanceOf[BlockId] }.toArray
+
+ // Check whether all the results are of the same type
+ val resultTypes = blockStoreResults.map { _.getClass }.distinct
+ if (resultTypes.size > 1) {
+ logWarning("Multiple result types in block information, WAL
information will be ignored.")
+ }
+
+ // If all the results are of type WriteAheadLogBasedStoreResult,
then create
+ // WriteAheadLogBackedBlockRDD else create simple BlockRDD.
+ if (resultTypes.size == 1 && resultTypes.head ==
classOf[WriteAheadLogBasedStoreResult]) {
+ val logSegments = blockStoreResults.map {
+ _.asInstanceOf[WriteAheadLogBasedStoreResult].segment
+ }.toArray
+ // Since storeInBlockManager = false, the storage level does not
matter.
+ new WriteAheadLogBackedBlockRDD[T](ssc.sparkContext,
+ blockIds, logSegments, storeInBlockManager = false,
StorageLevel.NONE)
--- End diff --
If we are not storing in the BlockManager on recovery, does that param even
make sense? Shouldn't we be storing the recovered data in the BM - if the same
RDD is used for two distinct transformations, wouldn't it help if the data is
in the BM?
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
