[SPARK-7225][SQL] CombineLimits optimizer does not work

SQL ``` select key from (select key from src limit 100) t2 limit 10 ``` Optimized Logical Plan before modifying ``` == Optimized Logical Plan == Limit 10 Limit 100 Project key#3 MetastoreRelation default, src, None ``` Optimized Logical Plan after modifying ``` == Optimized Logical Plan == Limit 10 Project [key#1] MetastoreRelation default, src, None ``` Author: Zhongshuai Pei <799203320@qq.com> Author: DoingDone9 <799203320@qq.com> Closes apache#5770 from DoingDone9/limitOptimizer and squashes the following commits: c68eaa7 [Zhongshuai Pei] Update CombiningLimitsSuite.scala 97e18cf [Zhongshuai Pei] Update Optimizer.scala 19ab875 [Zhongshuai Pei] Update CombiningLimitsSuite.scala 7db4566 [Zhongshuai Pei] Update CombiningLimitsSuite.scala e2a491d [Zhongshuai Pei] Update Optimizer.scala f03fe7f [Zhongshuai Pei] Merge pull request alteryx#12 from apache/master f12fa50 [Zhongshuai Pei] Merge pull request alteryx#10 from apache/master f61210c [Zhongshuai Pei] Merge pull request alteryx#9 from apache/master 34b1a9a [Zhongshuai Pei] Merge pull request alteryx#8 from apache/master 802261c [DoingDone9] Merge pull request alteryx#7 from apache/master d00303b [DoingDone9] Merge pull request alteryx#6 from apache/master 98b134f [DoingDone9] Merge pull request alteryx#5 from apache/master 161cae3 [DoingDone9] Merge pull request alteryx#4 from apache/master c87e8b6 [DoingDone9] Merge pull request #3 from apache/master cb1852d [DoingDone9] Merge pull request #2 from apache/master c3f046f [DoingDone9] Merge pull request #1 from apache/master
markhamstra · Apr 30, 2015 · 4459514 · 4459514
1 parent ba49eb1
commit 4459514
Show file tree

Hide file tree

Showing 2 changed files with 26 additions and 8 deletions.
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala
@@ -36,7 +36,13 @@ object DefaultOptimizer extends Optimizer {
     // SubQueries are only needed for analysis and can be removed before execution.
     Batch("Remove SubQueries", FixedPoint(100),
       EliminateSubQueries) ::
-    Batch("Combine Limits", FixedPoint(100),
+    Batch("Operator Reordering", FixedPoint(100),
+      UnionPushdown,
+      CombineFilters,
+      PushPredicateThroughProject,
+      PushPredicateThroughJoin,
+      PushPredicateThroughGenerate,
+      ColumnPruning,
       CombineLimits) ::
     Batch("ConstantFolding", FixedPoint(100),
       NullPropagation,
@@ -49,13 +55,6 @@ object DefaultOptimizer extends Optimizer {
       OptimizeIn) ::
     Batch("Decimal Optimizations", FixedPoint(100),
       DecimalAggregates) ::
-    Batch("Filter Pushdown", FixedPoint(100),
-      UnionPushdown,
-      CombineFilters,
-      PushPredicateThroughProject,
-      PushPredicateThroughJoin,
-      PushPredicateThroughGenerate,
-      ColumnPruning) ::
     Batch("LocalRelation", FixedPoint(100),
       ConvertToLocalRelation) :: Nil
 }

diff --git a/...atalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/CombiningLimitsSuite.scala b/...atalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/CombiningLimitsSuite.scala
@@ -27,6 +27,8 @@ class CombiningLimitsSuite extends PlanTest {
 
   object Optimize extends RuleExecutor[LogicalPlan] {
     val batches =
+      Batch("Filter Pushdown", FixedPoint(100),
+        ColumnPruning) ::
       Batch("Combine Limit", FixedPoint(10),
         CombineLimits) ::
       Batch("Constant Folding", FixedPoint(10),
@@ -69,4 +71,21 @@ class CombiningLimitsSuite extends PlanTest {
 
     comparePlans(optimized, correctAnswer)
   }
+
+  test("limits: combines two limits after ColumnPruning") {
+    val originalQuery =
+      testRelation
+        .select('a)
+        .limit(2)
+        .select('a)
+        .limit(5)
+
+    val optimized = Optimize.execute(originalQuery.analyze)
+    val correctAnswer =
+      testRelation
+        .select('a)
+        .limit(2).analyze
+
+    comparePlans(optimized, correctAnswer)
+  }
 }