Github user cloud-fan commented on a diff in the pull request:
https://github.com/apache/spark/pull/18487#discussion_r128410279
--- Diff:
core/src/main/scala/org/apache/spark/storage/ShuffleBlockFetcherIterator.scala
---
@@ -443,12 +459,57 @@ final class ShuffleBlockFetcherIterator(
}
private def fetchUpToMaxBytes(): Unit = {
- // Send fetch requests up to maxBytesInFlight
- while (fetchRequests.nonEmpty &&
- (bytesInFlight == 0 ||
- (reqsInFlight + 1 <= maxReqsInFlight &&
- bytesInFlight + fetchRequests.front.size <= maxBytesInFlight))) {
- sendRequest(fetchRequests.dequeue())
+ // Send fetch requests up to maxBytesInFlight. If you cannot fetch
from a remote host
+ // immediately, defer the request until the next time it can be
processed.
+
+ // Process any outstanding deferred fetch requests if possible.
+ if (deferredFetchRequests.nonEmpty) {
+ for ((remoteAddress, defReqQueue) <- deferredFetchRequests) {
+ while (isRemoteBlockFetchable(defReqQueue) &&
+ !isRemoteAddressMaxedOut(remoteAddress, defReqQueue.front)) {
+ val request = defReqQueue.dequeue()
+ logDebug(s"Processing deferred fetch request for $remoteAddress
with "
+ + s"${request.blocks.length} blocks")
+ send(remoteAddress, request)
+ if (defReqQueue.isEmpty) {
+ deferredFetchRequests -= remoteAddress
+ }
+ }
+ }
+ }
+
+ // Process any regular fetch requests if possible.
+ while (isRemoteBlockFetchable(fetchRequests)) {
+ val request = fetchRequests.dequeue()
+ val remoteAddress = request.address
+ if (isRemoteAddressMaxedOut(remoteAddress, request)) {
+ logDebug(s"Deferring fetch request for $remoteAddress with
${request.blocks.size} blocks")
+ val defReqQueue = deferredFetchRequests.getOrElse(remoteAddress,
new Queue[FetchRequest]())
+ defReqQueue.enqueue(request)
+ deferredFetchRequests(remoteAddress) = defReqQueue
--- End diff --
the `defReqQueue` is mutable, so we don't need to do this.
---
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]
