ivoson commented on code in PR #39459:
URL: https://github.com/apache/spark/pull/39459#discussion_r1122750718
##########
core/src/main/scala/org/apache/spark/storage/BlockManager.scala:
##########
@@ -1325,31 +1328,74 @@ private[spark] class BlockManager(
blockInfoManager.releaseAllLocksForTask(taskAttemptId)
}
+ /**
+ * Retrieve the given rdd block if it exists and is visible, otherwise call
the provided
+ * `makeIterator` method to compute the block, persist it, and return its
values.
+ *
+ * @return either a BlockResult if the block was successfully cached, or an
iterator if the block
+ * could not be cached.
+ */
+ def getOrElseUpdateRDDBlock[T](
+ taskId: Long,
+ blockId: RDDBlockId,
+ level: StorageLevel,
+ classTag: ClassTag[T],
+ makeIterator: () => Iterator[T]): Either[BlockResult, Iterator[T]] = {
+ val isCacheVisible = isRDDBlockVisible(blockId)
+ val res = getOrElseUpdate(blockId, level, classTag, makeIterator,
isCacheVisible)
+ if (res.isLeft && !isCacheVisible) {
+ // Block exists but not visible, report taskId -> blockId info to master.
+ master.updateRDDBlockTaskInfo(blockId, taskId)
+ }
+
+ res
+ }
+
/**
* Retrieve the given block if it exists, otherwise call the provided
`makeIterator` method
* to compute the block, persist it, and return its values.
*
* @return either a BlockResult if the block was successfully cached, or an
iterator if the block
* could not be cached.
*/
- def getOrElseUpdate[T](
+ private def getOrElseUpdate[T](
blockId: BlockId,
level: StorageLevel,
classTag: ClassTag[T],
- makeIterator: () => Iterator[T]): Either[BlockResult, Iterator[T]] = {
- // Attempt to read the block from local or remote storage. If it's
present, then we don't need
- // to go through the local-get-or-put path.
- get[T](blockId)(classTag) match {
- case Some(block) =>
- return Left(block)
- case _ =>
- // Need to compute the block.
+ makeIterator: () => Iterator[T],
+ isCacheVisible: Boolean = true): Either[BlockResult, Iterator[T]] = {
Review Comment:
done, thanks.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
