turboFei commented on code in PR #3266:
URL: https://github.com/apache/celeborn/pull/3266#discussion_r2098371547
##########
client-spark/spark-3/src/main/scala/org/apache/spark/shuffle/celeborn/CelebornShuffleReader.scala:
##########
@@ -157,7 +157,47 @@ class CelebornShuffleReader[K, C](
val splitSkewPartitionWithoutMapRange =
ClientUtils.readSkewPartitionWithoutMapRange(conf, startMapIndex,
endMapIndex)
- (startPartition until endPartition).foreach { partitionId =>
+ // filter empty partition
+ val partitionIdList = List.range(startPartition, endPartition).filter(p =>
+ fileGroups.partitionGroups.containsKey(p))
+
+ def makeOpenStreamList(locations: JSet[PartitionLocation]): Unit = {
+ locations.asScala.foreach { location =>
+ partCnt += 1
+ val hostPort = location.hostAndFetchPort
+ if (!workerRequestMap.containsKey(hostPort)) {
+ try {
+ val client = shuffleClient.getDataClientFactory().createClient(
+ location.getHost,
+ location.getFetchPort)
+ val pbOpenStreamList = PbOpenStreamList.newBuilder()
+ pbOpenStreamList.setShuffleKey(shuffleKey)
+ workerRequestMap.put(
+ hostPort,
+ (client, new JArrayList[PartitionLocation], pbOpenStreamList))
+ } catch {
+ case ex: Exception =>
+
shuffleClient.excludeFailedFetchLocation(location.hostAndFetchPort, ex)
Review Comment:
```suggestion
shuffleClient.excludeFailedFetchLocation(hostPort, ex)
```
--
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]
