Github user squito commented on a diff in the pull request:
https://github.com/apache/spark/pull/13646#discussion_r67005952
--- Diff: core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala
---
@@ -412,25 +390,48 @@ class DAGScheduler(
// We are manually maintaining a stack here to prevent
StackOverflowError
// caused by recursively visiting
val waitingForVisit = new Stack[RDD[_]]
- def visit(r: RDD[_]) {
- if (!visited(r)) {
- visited += r
- for (dep <- r.dependencies) {
- dep match {
- case shufDep: ShuffleDependency[_, _, _] =>
- if (!shuffleToMapStage.contains(shufDep.shuffleId)) {
- parents.push(shufDep)
- }
- case _ =>
- }
- waitingForVisit.push(dep.rdd)
+ waitingForVisit.push(rdd)
+ while (waitingForVisit.nonEmpty) {
+ val toVisit = waitingForVisit.pop()
+ if (!visited(toVisit)) {
+ visited += toVisit
+ getShuffleDependencies(toVisit).foreach { shuffleDep =>
+ if (!shuffleToMapStage.contains(shuffleDep.shuffleId)) {
+ parents.push(shuffleDep)
+ waitingForVisit.push(shuffleDep.rdd)
+ } // Otherwise, the dependency and it's ancestors have already
been registered.
}
}
}
+ parents
--- End diff --
while you're touching this, would be nice to rename `parents` to
`ancestors` here.
---
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.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
