Github user yhuai commented on a diff in the pull request:
https://github.com/apache/spark/pull/9276#discussion_r43577781
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/Exchange.scala ---
@@ -202,12 +286,103 @@ private[sql] case class
EnsureRequirements(sqlContext: SQLContext) extends Rule[
private def canonicalPartitioning(requiredDistribution: Distribution):
Partitioning = {
requiredDistribution match {
case AllTuples => SinglePartition
- case ClusteredDistribution(clustering) =>
HashPartitioning(clustering, numPartitions)
- case OrderedDistribution(ordering) => RangePartitioning(ordering,
numPartitions)
+ case ClusteredDistribution(clustering) =>
+ HashPartitioning(clustering, numPreShufflePartitions)
+ case OrderedDistribution(ordering) => RangePartitioning(ordering,
numPreShufflePartitions)
case dist => sys.error(s"Do not know how to satisfy distribution
$dist")
}
}
+ private def withExchangeCoordinator(
+ children: Seq[SparkPlan],
+ requiredChildDistributions: Seq[Distribution]): Seq[SparkPlan] = {
+ val needsCoordinator =
--- End diff --
yes.
---
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 [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
