zhengruifeng commented on a change in pull request #31480:
URL: https://github.com/apache/spark/pull/31480#discussion_r579585816
##########
File path: core/src/main/scala/org/apache/spark/rdd/OrderedRDDFunctions.scala
##########
@@ -73,7 +75,23 @@ class OrderedRDDFunctions[K : Ordering : ClassTag,
* because it can push the sorting down into the shuffle machinery.
*/
def repartitionAndSortWithinPartitions(partitioner: Partitioner): RDD[(K,
V)] = self.withScope {
- new ShuffledRDD[K, V, V](self, partitioner).setKeyOrdering(ordering)
+ if (self.partitioner == Some(partitioner)) {
+ self.mapPartitions(iter => {
+ val context = TaskContext.get
+ val sorter = new ExternalSorter[K, V, V](context, None, None,
Some(ordering))
+ sorter.insertAll(iter)
+ context.taskMetrics.incMemoryBytesSpilled(sorter.memoryBytesSpilled)
+ context.taskMetrics.incDiskBytesSpilled(sorter.diskBytesSpilled)
+ context.taskMetrics.incPeakExecutionMemory(sorter.peakMemoryUsedBytes)
+ // Use completion callback to stop sorter if task was
finished/cancelled.
+ context.addTaskCompletionListener[Unit](_ => sorter.stop)
+ val outputIter = new InterruptibleIterator(context,
+ sorter.iterator.asInstanceOf[Iterator[(K, V)]])
+ CompletionIterator[(K, V), Iterator[(K, V)]](outputIter, sorter.stop)
+ }, preservesPartitioning = true)
+ } else {
Review comment:
I misunderstood your previous comments. I am going to unify this in some
way.
----------------------------------------------------------------
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]
