cloud-fan commented on a change in pull request #32287:
URL: https://github.com/apache/spark/pull/32287#discussion_r622773346
##########
File path:
core/src/main/scala/org/apache/spark/storage/ShuffleBlockFetcherIterator.scala
##########
@@ -261,14 +283,38 @@ final class ShuffleBlockFetcherIterator(
results.put(new SuccessFetchResult(BlockId(blockId),
infoMap(blockId)._2,
address, infoMap(blockId)._1, buf, remainingBlocks.isEmpty))
logDebug("remainingBlocks: " + remainingBlocks)
+ enqueueDeferredFetchRequestIfNecessary()
}
}
logTrace(s"Got remote block $blockId after
${Utils.getUsedTimeNs(startTimeNs)}")
}
override def onBlockFetchFailure(blockId: String, e: Throwable): Unit = {
logError(s"Failed to get block(s) from
${req.address.host}:${req.address.port}", e)
- results.put(new FailureFetchResult(BlockId(blockId),
infoMap(blockId)._2, address, e))
+ val (size, mapIndex) = infoMap(blockId)
+ e match {
+ // Catching OOM and do something based on it is only a workaround
for handling the
+ // Netty OOM issue, which is not the best way towards memory
management. We can
+ // get rid of it when we find a way to manage Netty's memory
precisely.
Review comment:
Can we describe the entire process of handling OOM in the comment here?
e.g. how we delay other fetch requests, how we handle consecutive failures, etc.
--
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.
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
