tillrohrmann commented on a change in pull request #10362:
[FLINK-14792][coordination] Implement TE cluster partition release
URL: https://github.com/apache/flink/pull/10362#discussion_r394485816
##########
File path:
flink-runtime/src/main/java/org/apache/flink/runtime/io/network/partition/TaskExecutorPartitionTrackerImpl.java
##########
@@ -76,39 +78,58 @@ public void
promoteJobPartitions(Collection<ResultPartitionID> partitionsToPromo
final Collection<PartitionTrackerEntry<JobID,
TaskExecutorPartitionInfo>> partitionTrackerEntries =
stopTrackingPartitions(partitionsToPromote);
- final Map<TaskExecutorPartitionInfo, Set<ResultPartitionID>>
newClusterPartitions = partitionTrackerEntries.stream()
- .collect(Collectors.groupingBy(
- PartitionTrackerEntry::getMetaInfo,
-
Collectors.mapping(PartitionTrackerEntry::getResultPartitionId,
Collectors.toSet())));
-
- newClusterPartitions.forEach(
- (dataSetMetaInfo, newPartitionEntries) ->
clusterPartitions.compute(dataSetMetaInfo, (ignored, existingPartitions) -> {
- if (existingPartitions == null) {
- return newPartitionEntries;
+ partitionTrackerEntries.forEach(
+ partitionTrackerEntry ->
clusterPartitions.compute(partitionTrackerEntry.getMetaInfo().getIntermediateDataSetId(),
(key, existingEntry) -> {
+ if (existingEntry == null) {
+ final Set<ResultPartitionID> newSet =
new HashSet<>();
+
newSet.add(partitionTrackerEntry.getResultPartitionId());
+ return new PartitionEntry(newSet ,
partitionTrackerEntry.getMetaInfo().getNumberOfPartitions());
} else {
-
existingPartitions.addAll(newPartitionEntries);
- return existingPartitions;
+
existingEntry.addPartition(partitionTrackerEntry.getResultPartitionId());
+ return existingEntry;
}
- }));
+ })
+ );
}
@Override
public void stopTrackingAndReleaseAllClusterPartitions() {
-
clusterPartitions.values().forEach(shuffleEnvironment::releasePartitionsLocally);
+
clusterPartitions.values().stream().map(PartitionEntry::getPartitionIds).forEach(shuffleEnvironment::releasePartitionsLocally);
clusterPartitions.clear();
}
@Override
public ClusterPartitionReport createClusterPartitionReport() {
- List<ClusterPartitionReport.ClusterPartitionReportEntry>
collect = clusterPartitions.entrySet().stream().map(entry -> {
- TaskExecutorPartitionInfo dataSetMetaInfo =
entry.getKey();
- Set<ResultPartitionID> partitionsIds = entry.getValue();
- return new
ClusterPartitionReport.ClusterPartitionReportEntry(
- dataSetMetaInfo.getIntermediateDataSetId(),
- partitionsIds,
- dataSetMetaInfo.getNumberOfPartitions());
- }).collect(Collectors.toList());
-
- return new ClusterPartitionReport(collect);
+ List<ClusterPartitionReport.ClusterPartitionReportEntry>
reportEntries = clusterPartitions.entrySet().stream().map(entry ->
+ new ClusterPartitionReport.ClusterPartitionReportEntry(
+ entry.getKey(),
+ entry.getValue().getPartitionIds(),
+ entry.getValue().getTotalNumberOfPartitions()))
+ .collect(Collectors.toList());
+
+ return new ClusterPartitionReport(reportEntries);
+ }
+
+ private static class PartitionEntry {
Review comment:
Maybe calling it `PartitionSet` because it is a set of partitions.
----------------------------------------------------------------
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]
With regards,
Apache Git Services
