mridulm commented on code in PR #47815:
URL: https://github.com/apache/spark/pull/47815#discussion_r1747387516
##########
core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala:
##########
@@ -1234,17 +1242,23 @@ private[spark] class DAGScheduler(
jobIds.foreach(handleJobCancellation(_, Option(updatedReason)))
}
- private[scheduler] def handleJobTagCancelled(tag: String, reason:
Option[String]): Unit = {
- // Cancel all jobs belonging that have this tag.
+ private[scheduler] def handleJobTagCancelled(
+ tag: String,
+ reason: Option[String],
+ cancelledJobs: Option[Promise[Seq[ActiveJob]]]): Unit = {
+ // Cancel all jobs that have all provided tags.
// First finds all active jobs with this group id, and then kill stages
for them.
- val jobIds = activeJobs.filter { activeJob =>
+ val jobsToBeCancelled = activeJobs.filter { activeJob =>
Option(activeJob.properties).exists { properties =>
Option(properties.getProperty(SparkContext.SPARK_JOB_TAGS)).getOrElse("")
.split(SparkContext.SPARK_JOB_TAGS_SEP).filter(!_.isEmpty).toSet.contains(tag)
}
- }.map(_.jobId)
- val updatedReason = reason.getOrElse("part of cancelled job tag
%s".format(tag))
- jobIds.foreach(handleJobCancellation(_, Option(updatedReason)))
+ }
+ cancelledJobs.map(_.success(jobsToBeCancelled.toSeq))
Review Comment:
Do this after `handleJobCancellation`
##########
core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala:
##########
@@ -1234,17 +1242,23 @@ private[spark] class DAGScheduler(
jobIds.foreach(handleJobCancellation(_, Option(updatedReason)))
}
- private[scheduler] def handleJobTagCancelled(tag: String, reason:
Option[String]): Unit = {
- // Cancel all jobs belonging that have this tag.
+ private[scheduler] def handleJobTagCancelled(
+ tag: String,
+ reason: Option[String],
+ cancelledJobs: Option[Promise[Seq[ActiveJob]]]): Unit = {
+ // Cancel all jobs that have all provided tags.
// First finds all active jobs with this group id, and then kill stages
for them.
- val jobIds = activeJobs.filter { activeJob =>
+ val jobsToBeCancelled = activeJobs.filter { activeJob =>
Option(activeJob.properties).exists { properties =>
Option(properties.getProperty(SparkContext.SPARK_JOB_TAGS)).getOrElse("")
.split(SparkContext.SPARK_JOB_TAGS_SEP).filter(!_.isEmpty).toSet.contains(tag)
}
- }.map(_.jobId)
- val updatedReason = reason.getOrElse("part of cancelled job tag
%s".format(tag))
- jobIds.foreach(handleJobCancellation(_, Option(updatedReason)))
+ }
+ cancelledJobs.map(_.success(jobsToBeCancelled.toSeq))
Review Comment:
Do this after `handleJobCancellation` below
--
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]
