Github user viirya commented on a diff in the pull request:
https://github.com/apache/spark/pull/16677#discussion_r97786814
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/limit.scala ---
@@ -90,25 +95,101 @@ trait BaseLimitExec extends UnaryExecNode with
CodegenSupport {
}
/**
- * Take the first `limit` elements of each child partition, but do not
collect or shuffle them.
+ * Take the `limit` elements of the child output.
*/
-case class LocalLimitExec(limit: Int, child: SparkPlan) extends
BaseLimitExec {
+case class GlobalLimitExec(limit: Int, child: SparkPlan) extends
UnaryExecNode {
- override def outputOrdering: Seq[SortOrder] = child.outputOrdering
+ override def output: Seq[Attribute] = child.output
override def outputPartitioning: Partitioning = child.outputPartitioning
-}
-/**
- * Take the first `limit` elements of the child's single output partition.
- */
-case class GlobalLimitExec(limit: Int, child: SparkPlan) extends
BaseLimitExec {
+ override def outputOrdering: Seq[SortOrder] = child.outputOrdering
+
+ private val serializer: Serializer = new
UnsafeRowSerializer(child.output.size)
+
+ protected override def doExecute(): RDD[InternalRow] = {
+ val childRDD = child.execute()
+ val partitioner = LocalPartitioning(child.outputPartitioning,
+ childRDD.getNumPartitions)
+ val shuffleDependency = ShuffleExchange.prepareShuffleDependency(
+ childRDD, child.output, partitioner, serializer)
+ val numberOfOutput: Seq[Int] = if
(shuffleDependency.rdd.getNumPartitions != 0) {
+ // submitMapStage does not accept RDD with 0 partition.
+ // So, we will not submit this dependency.
+ val submittedStageFuture =
sparkContext.submitMapStage(shuffleDependency)
+ submittedStageFuture.get().numberOfOutput.toSeq
+ } else {
+ Nil
+ }
- override def requiredChildDistribution: List[Distribution] = AllTuples
:: Nil
+ // Try to keep child plan's original data parallelism or not. It is
enabled by default.
+ val respectChildParallelism = sqlContext.conf.enableParallelGlobalLimit
- override def outputPartitioning: Partitioning = child.outputPartitioning
+ val shuffled = new ShuffledRowRDD(shuffleDependency)
- override def outputOrdering: Seq[SortOrder] = child.outputOrdering
+ val sumOfOutput = numberOfOutput.sum
+ if (sumOfOutput <= limit) {
+ shuffled
+ } else if (!respectChildParallelism) {
+ // This is mainly for tests.
+ // We take the rows of each partition until we reach the required
limit number.
--- End diff --
Some tests like hive compatibility tests assume that the rows are returned
by the order of previous single partition. This branch is used for the tests.
---
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
