mridulm commented on code in PR #42296:
URL: https://github.com/apache/spark/pull/42296#discussion_r1318086203
##########
core/src/main/scala/org/apache/spark/storage/ShuffleBlockFetcherIterator.scala:
##########
@@ -264,18 +272,22 @@ final class ShuffleBlockFetcherIterator(
case FetchBlockInfo(blockId, size, mapIndex) => (blockId.toString,
(size, mapIndex))
}.toMap
val remainingBlocks = new HashSet[String]() ++= infoMap.keys
- val deferredBlocks = new ArrayBuffer[String]()
+ val deferredBlocks = new HashMap[BlockManagerId, Queue[String]]()
val blockIds = req.blocks.map(_.blockId.toString)
val address = req.address
val requestStartTime = clock.nanoTime()
@inline def enqueueDeferredFetchRequestIfNecessary(): Unit = {
if (remainingBlocks.isEmpty && deferredBlocks.nonEmpty) {
- val blocks = deferredBlocks.map { blockId =>
- val (size, mapIndex) = infoMap(blockId)
- FetchBlockInfo(BlockId(blockId), size, mapIndex)
+ val newAddressToBlocks = new HashMap[BlockManagerId,
Queue[FetchBlockInfo]]()
+ deferredBlocks.foreach { case (blockManagerId, blockIds) =>
+ val blocks = blockIds.map { blockId =>
+ val (size, mapIndex) = infoMap(blockId)
+ FetchBlockInfo(BlockId(blockId), size, mapIndex)
+ }
+ newAddressToBlocks.put(blockManagerId, blocks)
}
Review Comment:
Why do we need the before address if it has been migrated ?
--
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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
