zhengruifeng commented on code in PR #37728:
URL: https://github.com/apache/spark/pull/37728#discussion_r959262174
##########
core/src/main/scala/org/apache/spark/rdd/RDD.scala:
##########
@@ -1523,22 +1523,28 @@ abstract class RDD[T: ClassTag](
* @return an array of top elements
*/
def takeOrdered(num: Int)(implicit ord: Ordering[T]): Array[T] = withScope {
- if (num == 0) {
+ if (num == 0 || this.getNumPartitions == 0) {
Array.empty
} else {
- val mapRDDs = mapPartitions { items =>
- // Priority keeps the largest elements, so let's reverse the ordering.
- val queue = new BoundedPriorityQueue[T](num)(ord.reverse)
- queue ++= collectionUtils.takeOrdered(items, num)(ord)
- Iterator.single(queue)
- }
- if (mapRDDs.partitions.length == 0) {
- Array.empty
- } else {
- mapRDDs.reduce { (queue1, queue2) =>
- queue1 ++= queue2
- queue1
- }.toArray.sorted(ord)
+ this.mapPartitionsWithIndex { case (pid, iter) =>
+ if (iter.nonEmpty) {
+ // Priority keeps the largest elements, so let's reverse the
ordering.
+ Iterator.single(collectionUtils.takeOrdered(iter, num)(ord).toArray)
+ } else if (pid == 0) {
+ // make sure partition 0 always returns an array to avoid reduce on
empty RDD
+ Iterator.single(Array.empty[T])
+ } else {
+ Iterator.empty
+ }
+ }.reduce { (array1, array2) =>
+ val iterator = collectionUtils.mergeOrdered[T](Seq(array1,
array2))(ord)
+ val array = Array.ofDim[T](math.min(num, array1.length +
array2.length))
+ var i = 0
+ while (i < array.length) {
+ array(i) = iterator.next()
+ i += 1
+ }
Review Comment:
nice!
--
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]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
