sunchao commented on code in PR #55839:
URL: https://github.com/apache/spark/pull/55839#discussion_r3650444053
##########
sql/core/src/main/scala/org/apache/spark/sql/execution/adaptive/AdaptiveSparkPlanExec.scala:
##########
@@ -395,6 +401,39 @@ case class AdaptiveSparkPlanExec(
.get.asInstanceOf[T]
}
+ private def cancelObsoleteStages(
+ newPhysicalPlan: SparkPlan,
+ stagesToReplace: Seq[QueryStageExec]): Seq[Int] = {
+ val newStages = newPhysicalPlan.collect {
+ case stage: QueryStageExec => stage
+ }
+ val obsoleteStages = stagesToReplace.collect {
+ case stage: ExchangeQueryStageExec
+ if !newStages.exists(newStage =>
+ newStage.id == stage.id ||
newStage.resultOption.eq(stage.resultOption)) => stage
+ }
+ obsoleteStages.foreach { stage =>
+ if (!stage.isMaterialized &&
!context.isSharedStageResult(stage.resultOption)) {
+ removeStageFromCache(stage)
+ try {
+ stage.cancel("The query stage is no longer referenced by the current
adaptive plan.")
+ } catch {
+ case NonFatal(t) =>
+ logError(s"Exception in cancelling obsolete query stage:
${stage.treeString}", t)
+ }
+ }
+ }
+ obsoleteStages.map(_.id)
Review Comment:
Good catch - fixed in `5a4b32a0b6d`. `cancelObsoleteStages` now uses
`flatMap` and returns `Some(stage.id)` only after `stage.cancel(...)` succeeds.
Materialized stages, shared/reused stages, and failed cancellations return
`None`, so their `StageFailure` events are not silently suppressed. I also
added explicit coverage for these cases and a deterministic regression for
concurrent exchange reuse and cancellation.
--
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]
