[SPARK-32282][SQL] Improve EnsureRquirement.reorderJoinKeys to handle more scenarios such as PartitioningCollection #29074
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,146 @@ | ||
| /* | ||
| * Licensed to the Apache Software Foundation (ASF) under one or more | ||
| * contributor license agreements. See the NOTICE file distributed with | ||
| * this work for additional information regarding copyright ownership. | ||
| * The ASF licenses this file to You under the Apache License, Version 2.0 | ||
| * (the "License"); you may not use this file except in compliance with | ||
| * the License. You may obtain a copy of the License at | ||
| * | ||
| * http://www.apache.org/licenses/LICENSE-2.0 | ||
| * | ||
| * Unless required by applicable law or agreed to in writing, software | ||
| * distributed under the License is distributed on an "AS IS" BASIS, | ||
| * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. | ||
| * See the License for the specific language governing permissions and | ||
| * limitations under the License. | ||
| */ | ||
|
|
||
| package org.apache.spark.sql.execution.exchange | ||
|
|
||
| import org.apache.spark.sql.catalyst.expressions.Literal | ||
| import org.apache.spark.sql.catalyst.plans.Inner | ||
| import org.apache.spark.sql.catalyst.plans.physical.{HashPartitioning, PartitioningCollection} | ||
| import org.apache.spark.sql.execution.{DummySparkPlan, SortExec} | ||
| import org.apache.spark.sql.execution.joins.SortMergeJoinExec | ||
| import org.apache.spark.sql.test.SharedSparkSession | ||
|
|
||
| class EnsureRequirementsSuite extends SharedSparkSession { | ||
| private val exprA = Literal(1) | ||
| private val exprB = Literal(2) | ||
| private val exprC = Literal(3) | ||
|
|
||
| test("reorder should handle PartitioningCollection") { | ||
| val plan1 = DummySparkPlan( | ||
| outputPartitioning = PartitioningCollection(Seq( | ||
| HashPartitioning(exprA :: exprB :: Nil, 5), | ||
| HashPartitioning(exprA :: Nil, 5)))) | ||
| val plan2 = DummySparkPlan() | ||
|
|
||
| // Test PartitioningCollection on the left side of join. | ||
| val smjExec1 = SortMergeJoinExec( | ||
| exprB :: exprA :: Nil, exprA :: exprB :: Nil, Inner, None, plan1, plan2) | ||
| EnsureRequirements(spark.sessionState.conf).apply(smjExec1) match { | ||
| case SortMergeJoinExec(leftKeys, rightKeys, _, _, | ||
| SortExec(_, _, | ||
| DummySparkPlan(_, _, PartitioningCollection(leftPartitionings), _, _), _), | ||
| SortExec(_, _, | ||
| ShuffleExchangeExec(HashPartitioning(rightPartitioningExpressions, _), _, _), _), _) => | ||
| assert(leftKeys !== smjExec1.leftKeys) | ||
|
There was a problem hiding this comment. is this check needed? We already check |
||
| assert(rightKeys !== smjExec1.rightKeys) | ||
| assert(leftKeys === leftPartitionings.head.asInstanceOf[HashPartitioning].expressions) | ||
|
There was a problem hiding this comment. can we simply check There was a problem hiding this comment. OK. I simplified the checks in this test. |
||
| assert(rightKeys === rightPartitioningExpressions) | ||
| case other => fail(other.toString) | ||
| } | ||
|
|
||
| // Test PartitioningCollection on the right side of join. | ||
| val smjExec2 = SortMergeJoinExec( | ||
| exprA :: exprB :: Nil, exprB :: exprA :: Nil, Inner, None, plan2, plan1) | ||
| EnsureRequirements(spark.sessionState.conf).apply(smjExec2) match { | ||
| case SortMergeJoinExec(leftKeys, rightKeys, _, _, | ||
| SortExec(_, _, | ||
| ShuffleExchangeExec(HashPartitioning(leftPartitioningExpressions, _), _, _), _), | ||
| SortExec(_, _, | ||
| DummySparkPlan(_, _, PartitioningCollection(rightPartitionings), _, _), _), _) => | ||
| assert(leftKeys !== smjExec2.leftKeys) | ||
| assert(rightKeys !== smjExec2.rightKeys) | ||
| assert(leftKeys === leftPartitioningExpressions) | ||
| assert(rightKeys === rightPartitionings.head.asInstanceOf[HashPartitioning].expressions) | ||
| case other => fail(other.toString) | ||
| } | ||
|
|
||
| // Both sides are PartitioningCollection, but left side cannot be reorderd to match | ||
| // and it should fall back to the right side. | ||
| val smjExec3 = SortMergeJoinExec( | ||
| exprA :: exprC :: Nil, exprB :: exprA :: Nil, Inner, None, plan1, plan1) | ||
| EnsureRequirements(spark.sessionState.conf).apply(smjExec3) match { | ||
| case SortMergeJoinExec(leftKeys, rightKeys, _, _, | ||
| SortExec(_, _, | ||
| ShuffleExchangeExec(HashPartitioning(leftPartitioningExpressions, _), _, _), _), | ||
| SortExec(_, _, | ||
| DummySparkPlan(_, _, PartitioningCollection(rightPartitionings), _, _), _), _) => | ||
| assert(leftKeys !== smjExec3.leftKeys) | ||
| assert(rightKeys !== smjExec3.rightKeys) | ||
| assert(leftKeys === leftPartitioningExpressions) | ||
| assert(rightKeys === rightPartitionings.head.asInstanceOf[HashPartitioning].expressions) | ||
| case other => fail(other.toString) | ||
| } | ||
| } | ||
|
|
||
| test("reorder should fallback to the other side partitioning") { | ||
| val plan1 = DummySparkPlan( | ||
| outputPartitioning = HashPartitioning(exprA :: exprB :: exprC :: Nil, 5)) | ||
| val plan2 = DummySparkPlan( | ||
| outputPartitioning = HashPartitioning(exprB :: exprC :: Nil, 5)) | ||
|
|
||
| // Test fallback to the right side, which has HashPartitioning. | ||
| val smjExec1 = SortMergeJoinExec( | ||
| exprA :: exprB :: Nil, exprC :: exprB :: Nil, Inner, None, plan1, plan2) | ||
| EnsureRequirements(spark.sessionState.conf).apply(smjExec1) match { | ||
| case SortMergeJoinExec(leftKeys, rightKeys, _, _, | ||
| SortExec(_, _, | ||
| ShuffleExchangeExec(HashPartitioning(leftPartitioningExpressions, _), _, _), _), | ||
| SortExec(_, _, | ||
| DummySparkPlan(_, _, HashPartitioning(rightPartitioningExpressions, _), _, _), _), _) => | ||
| assert(leftKeys !== smjExec1.leftKeys) | ||
| assert(rightKeys !== smjExec1.rightKeys) | ||
| assert(leftKeys === leftPartitioningExpressions) | ||
| assert(rightKeys === rightPartitioningExpressions) | ||
| case other => fail(other.toString) | ||
| } | ||
|
|
||
| // Test fallback to the right side, which has PartitioningCollection. | ||
| val plan3 = DummySparkPlan( | ||
| outputPartitioning = PartitioningCollection(Seq(HashPartitioning(exprB :: exprC :: Nil, 5)))) | ||
| val smjExec2 = SortMergeJoinExec( | ||
| exprA :: exprB :: Nil, exprC :: exprB :: Nil, Inner, None, plan1, plan3) | ||
| EnsureRequirements(spark.sessionState.conf).apply(smjExec2) match { | ||
| case SortMergeJoinExec(leftKeys, rightKeys, _, _, | ||
| SortExec(_, _, | ||
| ShuffleExchangeExec(HashPartitioning(leftPartitioningExpressions, _), _, _), _), | ||
| SortExec(_, _, | ||
| DummySparkPlan(_, _, PartitioningCollection(rightPartitionings), _, _), _), _) => | ||
| assert(leftKeys !== smjExec2.leftKeys) | ||
| assert(rightKeys !== smjExec2.rightKeys) | ||
| assert(leftKeys === leftPartitioningExpressions) | ||
| assert(rightKeys === rightPartitionings.head.asInstanceOf[HashPartitioning].expressions) | ||
| case other => fail(other.toString) | ||
| } | ||
|
|
||
| // The right side has HashPartitioning, so it is matched first, but no reordering match is | ||
| // found, and it should fall back to the left side, which has a PartitioningCollection. | ||
| val smjExec3 = SortMergeJoinExec( | ||
| exprC :: exprB :: Nil, exprA :: exprB :: Nil, Inner, None, plan3, plan1) | ||
| EnsureRequirements(spark.sessionState.conf).apply(smjExec3) match { | ||
| case SortMergeJoinExec(leftKeys, rightKeys, _, _, | ||
| SortExec(_, _, | ||
| DummySparkPlan(_, _, PartitioningCollection(leftPartitionings), _, _), _), | ||
| SortExec(_, _, | ||
| ShuffleExchangeExec(HashPartitioning(rightPartitioningExpressions, _), _, _), _), _) => | ||
| assert(leftKeys !== smjExec3.leftKeys) | ||
| assert(rightKeys !== smjExec3.rightKeys) | ||
| assert(leftKeys === leftPartitionings.head.asInstanceOf[HashPartitioning].expressions) | ||
| assert(rightKeys === rightPartitioningExpressions) | ||
| case other => fail(other.toString) | ||
| } | ||
| } | ||
| } | ||
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This can be also implemented by looking at left partitioning first then move to the right partitionoing:
However, I chose this way so that the behavior remains the same. If you have
leftPartitioning = PartitioningCollectionandrightPartitioning = HashPartitioning, it will match therightPartitioningfirst, which is the existing behavior.