Github user guowei2 commented on a diff in the pull request:
https://github.com/apache/spark/pull/1822#discussion_r16235116
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/SparkStrategies.scala ---
@@ -134,15 +134,26 @@ private[sql] abstract class SparkStrategies extends
QueryPlanner[SparkPlan] {
groupingExpressions,
partialComputation,
child) =>
- execution.Aggregate(
- partial = false,
- namedGroupingAttributes,
- rewrittenAggregateExpressions,
- execution.Aggregate(
- partial = true,
- groupingExpressions,
- partialComputation,
- planLater(child))) :: Nil
+
+ val preAggregate = execution.OnHeapAggregate(
--- End diff --
i think map side aggregate does not need external, for data in one
partition (1 task) isn't large enough to the JVM heap size .also user can
easily control the partition data size.
In most cases, OOM occur on reduce side.
---
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]
