Github user viirya commented on a diff in the pull request: https://github.com/apache/spark/pull/15596#discussion_r84815874 --- Diff: sql/core/src/main/scala/org/apache/spark/sql/execution/limit.scala --- @@ -36,14 +36,15 @@ import org.apache.spark.util.Utils case class CollectLimitExec(limit: Int, child: SparkPlan) extends UnaryExecNode { override def output: Seq[Attribute] = child.output override def outputPartitioning: Partitioning = SinglePartition - override def executeCollect(): Array[InternalRow] = child.executeTake(limit) - private val serializer: Serializer = new UnsafeRowSerializer(child.output.size) + override def requiredChildDistribution: List[Distribution] = AllTuples :: Nil + override def executeCollect(): Array[InternalRow] = { + child.collect { --- End diff -- That seems a good idea. I once thought about the difference between `GlobalLimitExec` and `CollectLimitExec` during refactoring this. But decided not to change too much. Looks like I could remove `CollectLimitExec`.
--- 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