Skip to content
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

[SPARK-9236][Core] Make defaultPartitioner not reuse a parent RDD's partitioner if it has 0 partitions #7616

Closed
wants to merge 1 commit into from
Closed

[SPARK-9236][Core] Make defaultPartitioner not reuse a parent RDD's partitioner if it has 0 partitions #7616

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
2 changes: 1 addition & 1 deletion core/src/main/scala/org/apache/spark/Partitioner.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -56,7 +56,7 @@ object Partitioner {
*/
def defaultPartitioner(rdd: RDD[_], others: RDD[_]*): Partitioner = {
val bySize = (Seq(rdd) ++ others).sortBy(_.partitions.size).reverse
for (r <- bySize if r.partitioner.isDefined) {
for (r <- bySize if r.partitioner.isDefined && r.partitioner.get.numPartitions > 0) {
return r.partitioner.get
}
if (rdd.context.conf.contains("spark.default.parallelism")) {
Expand Down
23 changes: 23 additions & 0 deletions core/src/test/scala/org/apache/spark/rdd/PairRDDFunctionsSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -282,6 +282,29 @@ class PairRDDFunctionsSuite extends SparkFunSuite with SharedSparkContext {
))
}

// See SPARK-9326
test("cogroup with empty RDD") {
import scala.reflect.classTag
val intPairCT = classTag[(Int, Int)]

val rdd1 = sc.parallelize(Array((1, 1), (1, 2), (2, 1), (3, 1)))
val rdd2 = sc.emptyRDD[(Int, Int)](intPairCT)

val joined = rdd1.cogroup(rdd2).collect()
assert(joined.size > 0)
}

// See SPARK-9326
test("cogroup with groupByed RDD having 0 partitions") {
import scala.reflect.classTag
val intCT = classTag[Int]

val rdd1 = sc.parallelize(Array((1, 1), (1, 2), (2, 1), (3, 1)))
val rdd2 = sc.emptyRDD[Int](intCT).groupBy((x) => 5)
val joined = rdd1.cogroup(rdd2).collect()
assert(joined.size > 0)
}

test("rightOuterJoin") {
val rdd1 = sc.parallelize(Array((1, 1), (1, 2), (2, 1), (3, 1)))
val rdd2 = sc.parallelize(Array((1, 'x'), (2, 'y'), (2, 'z'), (4, 'w')))
Expand Down