Skip to content

[SPARK][SPARK-10842]Eliminate creating duplicate stage while generate job dag #8923

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
suyanNone wants to merge 4 commits into from
Closed

[SPARK][SPARK-10842]Eliminate creating duplicate stage while generate job dag #8923

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
6211b75
Duplicate stage
suyanNone Sep 26, 2015
a11cdd9
Change getAncestorShuffleDependencies return type to Set
suyanNone Nov 13, 2015
66ae245
Return immutableSet
suyanNone Nov 16, 2015
513d0d8
Refine
suyanNone Apr 26, 2016
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 4 additions & 1 deletion core/src/main/scala/org/apache/spark/scheduler/DAGScheduler.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,6 +23,7 @@ import java.util.concurrent.TimeUnit
import java.util.concurrent.atomic.AtomicInteger

import scala.collection.Map
import scala.collection.immutable.Set
import scala.collection.mutable.{HashMap, HashSet, Stack}
import scala.concurrent.duration._
import scala.language.existentials
Expand Down Expand Up @@ -283,7 +284,9 @@ class DAGScheduler(
case None =>
// We are going to register ancestor shuffle dependencies
getAncestorShuffleDependencies(shuffleDep.rdd).foreach { dep =>
shuffleToMapStage(dep.shuffleId) = newOrUsedShuffleStage(dep, firstJobId)
if (!shuffleToMapStage.contains(dep.shuffleId)) {
shuffleToMapStage(dep.shuffleId) = newOrUsedShuffleStage(dep, firstJobId)
}
}
// Then register current shuffleDep
val stage = newOrUsedShuffleStage(shuffleDep, firstJobId)
Expand Down
20 changes: 20 additions & 0 deletions core/src/test/scala/org/apache/spark/scheduler/DAGSchedulerSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1901,6 +1901,26 @@ class DAGSchedulerSuite
assertDataStructuresEmpty()
}

test("Eliminate creating duplicate stage") {
val rdd2 = new MyRDD(sc, 2, Nil)
val rdd1 = new MyRDD(sc, 2, Nil)
val dep1 = new ShuffleDependency(rdd1, new HashPartitioner(1))
val dep2 = new ShuffleDependency(rdd2, new HashPartitioner(1))
val rdd3 = new MyRDD(sc, 1, List(dep1, dep2), tracker = mapOutputTracker)
val dep3 = new ShuffleDependency(rdd3, new HashPartitioner(2))
val dep4 = new ShuffleDependency(rdd3, new HashPartitioner(2))
val rdd4 = new MyRDD(sc, 2, List(dep3), tracker = mapOutputTracker)
val rdd5 = new MyRDD(sc, 2, List(dep4), tracker = mapOutputTracker)
val dep5 = new ShuffleDependency(rdd4, new HashPartitioner(1))
val dep6 = new ShuffleDependency(rdd5, new HashPartitioner(1))
val rdd6 = new MyRDD(sc, 1, List(dep5, dep6), tracker = mapOutputTracker)
val dep7 = new ShuffleDependency(rdd6, new HashPartitioner(2))
val rdd7 = new MyRDD(sc, 2, List(dep7), tracker = mapOutputTracker)
submit(rdd7, Array(0, 1))
assert(scheduler.stageIdToStage.size == 8)
assert(scheduler.shuffleToMapStage.size == 7)
}

/**
* Assert that the supplied TaskSet has exactly the given hosts as its preferred locations.
* Note that this checks only the host and not the executor ID.
Expand Down