-
Notifications
You must be signed in to change notification settings - Fork 28.4k
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
10 changed files
with
147 additions
and
123 deletions.
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
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
110 changes: 110 additions & 0 deletions
110
sql/core/src/main/scala/org/apache/spark/sql/execution/bucketing/CoalesceBucketInJoin.scala
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 +1,110 @@ | ||
| /* | ||
| * 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.bucketing | ||
|
|
||
| import org.apache.spark.sql.catalyst.catalog.BucketSpec | ||
| import org.apache.spark.sql.catalyst.plans.Inner | ||
| import org.apache.spark.sql.catalyst.plans.logical.{Filter, Join, LogicalPlan, Project} | ||
| import org.apache.spark.sql.catalyst.rules.Rule | ||
| import org.apache.spark.sql.execution.datasources.{HadoopFsRelation, LogicalRelation} | ||
| import org.apache.spark.sql.internal.SQLConf | ||
|
|
||
| /** | ||
| * This rule injects a hint if one side of two bucketed tables can be coalesced | ||
| * when the two bucketed tables are inner-joined and they differ in the number of buckets. | ||
| */ | ||
| object CoalesceBucketInJoin extends Rule[LogicalPlan] { | ||
| val JOIN_HINT_COALESCED_NUM_BUCKETS: String = "JoinHintCoalescedNumBuckets" | ||
|
|
||
| private val sqlConf = SQLConf.get | ||
|
|
||
| private def isPlanEligible(plan: LogicalPlan): Boolean = { | ||
| def forall(plan: LogicalPlan)(p: LogicalPlan => Boolean): Boolean = { | ||
| p(plan) && plan.children.forall(forall(_)(p)) | ||
| } | ||
|
|
||
| forall(plan) { | ||
| case _: Filter | _: Project | _: LogicalRelation => true | ||
| case _ => false | ||
| } | ||
| } | ||
|
|
||
| private def getBucketSpec(plan: LogicalPlan): Option[BucketSpec] = { | ||
| if (isPlanEligible(plan)) { | ||
| plan.collectFirst { | ||
| case _ @ LogicalRelation(r: HadoopFsRelation, _, _, _) | ||
| if r.bucketSpec.nonEmpty && !r.options.contains(JOIN_HINT_COALESCED_NUM_BUCKETS) => | ||
| r.bucketSpec.get | ||
| } | ||
| } else { | ||
| None | ||
| } | ||
| } | ||
|
|
||
| private def mayCoalesce(numBuckets1: Int, numBuckets2: Int): Option[Int] = { | ||
| assert(numBuckets1 != numBuckets2) | ||
| val (small, large) = (math.min(numBuckets1, numBuckets2), math.max(numBuckets1, numBuckets2)) | ||
| // A bucket can be coalesced only if the bigger number of buckets is divisible by the smaller | ||
| // number of buckets because bucket id is calculated by modding the total number of buckets. | ||
| if ((large % small == 0) && | ||
| (large - small) <= sqlConf.getConf(SQLConf.COALESCE_BUCKET_IN_JOIN_MAX_NUM_BUCKETS_DIFF)) { | ||
| Some(small) | ||
| } else { | ||
| None | ||
| } | ||
| } | ||
|
|
||
| private def addBucketHint(plan: LogicalPlan, hint: (String, String)): LogicalPlan = { | ||
| plan.transformUp { | ||
| case l @ LogicalRelation(r: HadoopFsRelation, _, _, _) => | ||
| l.copy(relation = r.copy(options = r.options + hint)(r.sparkSession)) | ||
| } | ||
| } | ||
|
|
||
| def apply(plan: LogicalPlan): LogicalPlan = { | ||
| if (!sqlConf.getConf(SQLConf.COALESCE_BUCKET_IN_JOIN_ENABLED)) { | ||
| return plan | ||
| } | ||
|
|
||
| plan transform { | ||
| case join: Join if join.joinType == Inner => | ||
| val leftBucket = getBucketSpec(join.left) | ||
| val rightBucket = getBucketSpec(join.right) | ||
| if (leftBucket.isEmpty || rightBucket.isEmpty) { | ||
| return plan | ||
| } | ||
|
|
||
| val leftBucketNumber = leftBucket.get.numBuckets | ||
| val rightBucketNumber = rightBucket.get.numBuckets | ||
| if (leftBucketNumber == rightBucketNumber) { | ||
| return plan | ||
| } | ||
|
|
||
| mayCoalesce(leftBucketNumber, rightBucketNumber).map { coalescedNumBuckets => | ||
| val hint = JOIN_HINT_COALESCED_NUM_BUCKETS -> coalescedNumBuckets.toString | ||
| if (coalescedNumBuckets != leftBucketNumber) { | ||
| join.copy(left = addBucketHint(join.left, hint)) | ||
| } else { | ||
| join.copy(right = addBucketHint(join.right, hint)) | ||
| } | ||
| }.getOrElse(join) | ||
|
|
||
| case other => other | ||
| } | ||
| } | ||
| } |
78 changes: 0 additions & 78 deletions
78
sql/core/src/main/scala/org/apache/spark/sql/execution/bucketing/InjectBucketHint.scala
This file was deleted.
Oops, something went wrong.
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
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
Oops, something went wrong.