ravipesala commented on a change in pull request #3281: [WIP]Index server
performance improvement
URL: https://github.com/apache/carbondata/pull/3281#discussion_r293269822
##########
File path:
integration/spark2/src/main/scala/org/apache/carbondata/indexserver/DistributedRDDUtils.scala
##########
@@ -64,11 +64,21 @@ object DistributedRDDUtils {
if (invalidExecutorIds.nonEmpty) {
DistributedRDDUtils.invalidateExecutors(invalidExecutorIds.toSeq)
}
- (convertToPartition(legacySegments, tableUniqueName, executorsList) ++
- convertToPartition(sortedPartitions, tableUniqueName,
executorsList)).zipWithIndex.map {
- case (dataMapDistributable, index) =>
- new DataMapRDDPartition(rddId, index, dataMapDistributable)
- }
+ val groupedPartitions = (convertToPartition(legacySegments,
tableUniqueName, executorsList) ++
+ convertToPartition(sortedPartitions,
tableUniqueName, executorsList))
+ .groupBy {
+ partition =>
+ partition.getLocations.head
+ }
+ groupedPartitions.map {
+ case (location, dataMapDistributable) =>
Review comment:
Please remove this case
----------------------------------------------------------------
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
