Github user JoshRosen commented on a diff in the pull request: https://github.com/apache/spark/pull/4629#discussion_r24778077 --- Diff: core/src/main/scala/org/apache/spark/SparkContext.scala --- @@ -961,7 +961,14 @@ class SparkContext(config: SparkConf) extends Logging with ExecutorAllocationCli } /** Build the union of a list of RDDs. */ - def union[T: ClassTag](rdds: Seq[RDD[T]]): RDD[T] = new UnionRDD(this, rdds) + def union[T: ClassTag](rdds: Seq[RDD[T]]): RDD[T] = { + val partitioners = rdds.map(_.partitioner).toSet + if (partitioners.size == 1 && partitioners.head.isDefined) { + new PartitionerAwareUnionRDD(this, rdds) + } else { + new UnionRDD(this, rdds) + } + } /** Build the union of a list of RDDs passed as variable-length arguments. */ def union[T: ClassTag](first: RDD[T], rest: RDD[T]*): RDD[T] = --- End diff -- Can we change this method to call the `union` method that you modified so the change will take effect here, too?
--- 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 infrastruct...@apache.org or file a JIRA ticket with INFRA. --- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org