Github user markhamstra commented on a diff in the pull request:
https://github.com/apache/spark/pull/1561#discussion_r15328329
--- Diff: core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala
---
@@ -315,13 +309,14 @@ class DAGScheduler(
*/
private def updateJobIdStageIdMaps(jobId: Int, stage: Stage) {
def updateJobIdStageIdMapsList(stages: List[Stage]) {
- if (!stages.isEmpty) {
+ if (stages.nonEmpty) {
val s = stages.head
- stageIdToJobIds.getOrElseUpdate(s.id, new HashSet[Int]()) += jobId
+ s.jobIds += jobId
jobIdToStageIds.getOrElseUpdate(jobId, new HashSet[Int]()) += s.id
- val parents = getParentStages(s.rdd, jobId)
- val parentsWithoutThisJobId = parents.filter(p =>
- !stageIdToJobIds.get(p.id).exists(_.contains(jobId)))
+ val parents: List[Stage] = getParentStages(s.rdd, jobId)
+ val parentsWithoutThisJobId = parents.filter { p: Stage =>
+ !p.jobIds.contains(jobId)
--- End diff --
could now do this as `filter { !_.jobIds.contains(jobId) }`
---
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 [email protected] or file a JIRA ticket
with INFRA.
---
