Github user jinxing64 commented on a diff in the pull request:
https://github.com/apache/spark/pull/17533#discussion_r109930532
--- Diff:
core/src/main/scala/org/apache/spark/scheduler/TaskSetManager.scala ---
@@ -512,6 +522,57 @@ private[spark] class TaskSetManager(
}
}
+ private[this] def sortPendingTasks(): Unit = {
+ val taskIndexs = (0 until numTasks).toArray
+ implicit def ord = new Ordering[Int] {
+ override def compare(x: Int, y: Int): Int =
+ getTaskInputSizeFromShuffledRDD(tasks(x)) compare
+ getTaskInputSizeFromShuffledRDD(tasks(y))
+ }
+ if (tasks.nonEmpty) {
+ // Sort the tasks based on their input size from ShuffledRDD.
+ pendingTasksForExecutor.foreach {
+ case (k, v) => pendingTasksForExecutor(k) = v.sorted
+ }
+ pendingTasksForHost.foreach {
+ case (k, v) => pendingTasksForHost(k) = v.sorted
+ }
+ pendingTasksForRack.foreach {
+ case (k, v) => pendingTasksForRack(k) = v.sorted
+ }
+ pendingTasksWithNoPrefs = pendingTasksWithNoPrefs.sorted
+ allPendingTasks = allPendingTasks.sorted
+ }
+ }
+
+ // Visible for testing
+ private[spark] def setTaskInputSizeFromShuffledRDD(inputSize:
Map[Task[_], Long]) = {
+ taskInputSizeFromShuffledRDD.clear()
+ inputSize.foreach{
+ case (k, v) => taskInputSizeFromShuffledRDD(k) = v
+ }
+ }
+
+ private[this] def getTaskInputSizeFromShuffledRDD(task: Task[_]): Long =
{
+ taskInputSizeFromShuffledRDD.get(task) match {
+ case Some(size) => size
+ case None =>
+ val size =
+ sched.dagScheduler.parentSplitsInShuffledRDD(task.stageId,
task.partitionId) match {
--- End diff --
I got it :)
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
