From 962878843b611fa6229e3ee67bb22e2a4bc283cd Mon Sep 17 00:00:00 2001 From: Yin Huai Date: Thu, 19 Nov 2015 11:02:17 -0800 Subject: [SPARK-11840][SQL] Restore the 1.5's behavior of planning a single distinct aggregation. The impact of this change is for a query that has a single distinct column and does not have any grouping expression like `SELECT COUNT(DISTINCT a) FROM table` The plan will be changed from ``` AGG-2 (count distinct) Shuffle to a single reducer Partial-AGG-2 (count distinct) AGG-1 (grouping on a) Shuffle by a Partial-AGG-1 (grouping on 1) ``` to the following one (1.5 uses this) ``` AGG-2 AGG-1 (grouping on a) Shuffle to a single reducer Partial-AGG-1(grouping on a) ``` The first plan is more robust. However, to better benchmark the impact of this change, we should use 1.5's plan and use the conf of `spark.sql.specializeSingleDistinctAggPlanning` to control the plan. Author: Yin Huai Closes #9828 from yhuai/distinctRewriter. --- .../spark/sql/catalyst/analysis/DistinctAggregationRewriter.scala | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/DistinctAggregationRewriter.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/DistinctAggregationRewriter.scala index c0c960471a..9c78f6d4cc 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/DistinctAggregationRewriter.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/DistinctAggregationRewriter.scala @@ -126,8 +126,8 @@ case class DistinctAggregationRewriter(conf: CatalystConf) extends Rule[LogicalP val shouldRewrite = if (conf.specializeSingleDistinctAggPlanning) { // When the flag is set to specialize single distinct agg planning, // we will rely on our Aggregation strategy to handle queries with a single - // distinct column and this aggregate operator does have grouping expressions. - distinctAggGroups.size > 1 || (distinctAggGroups.size == 1 && a.groupingExpressions.isEmpty) + // distinct column. + distinctAggGroups.size > 1 } else { distinctAggGroups.size >= 1 } -- cgit v1.2.3