[SPARK-54022][SQL] Make DSv2 table resolution aware of cached tables #52764
+337
−62
There are no files selected for viewing
This file contains hidden or 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 hidden or 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 +1,28 @@ | ||
| /* | ||
| * 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.catalyst.analysis | ||
|
|
||
| import org.apache.spark.sql.catalyst.plans.logical.LogicalPlan | ||
|
|
||
| private[sql] trait RelationCache { | ||
| def lookup(nameParts: Seq[String], resolver: Resolver): Option[LogicalPlan] | ||
| } | ||
|
|
||
| private[sql] object RelationCache { | ||
| val empty: RelationCache = (_, _) => None | ||
| } | ||
This file contains hidden or 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 hidden or 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 hidden or 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 hidden or 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 hidden or 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 hidden or 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 |
|---|---|---|
|
|
@@ -22,6 +22,7 @@ import org.apache.hadoop.fs.{FileSystem, Path} | |
| import org.apache.spark.internal.{Logging, MessageWithContext} | ||
| import org.apache.spark.internal.LogKeys._ | ||
| import org.apache.spark.sql.catalyst.analysis.EliminateSubqueryAliases | ||
| import org.apache.spark.sql.catalyst.analysis.Resolver | ||
| import org.apache.spark.sql.catalyst.analysis.V2TableReference | ||
| import org.apache.spark.sql.catalyst.catalog.HiveTableRelation | ||
| import org.apache.spark.sql.catalyst.expressions.{Attribute, SubqueryExpression} | ||
|
|
@@ -30,13 +31,14 @@ import org.apache.spark.sql.catalyst.plans.logical.{IgnoreCachedData, LogicalPla | |
| import org.apache.spark.sql.catalyst.trees.TreePattern.PLAN_EXPRESSION | ||
| import org.apache.spark.sql.catalyst.util.sideBySide | ||
| import org.apache.spark.sql.classic.{Dataset, SparkSession} | ||
| import org.apache.spark.sql.connector.catalog.CatalogPlugin | ||
| import org.apache.spark.sql.connector.catalog.CatalogV2Implicits.{IdentifierHelper, MultipartIdentifierHelper} | ||
| import org.apache.spark.sql.connector.catalog.Identifier | ||
| import org.apache.spark.sql.execution.adaptive.AdaptiveSparkPlanHelper | ||
| import org.apache.spark.sql.execution.columnar.InMemoryRelation | ||
| import org.apache.spark.sql.execution.command.CommandUtils | ||
| import org.apache.spark.sql.execution.datasources.{FileIndex, HadoopFsRelation, LogicalRelation, LogicalRelationWithTable} | ||
| import org.apache.spark.sql.execution.datasources.v2.{DataSourceV2Relation, ExtractV2CatalogAndIdentifier, ExtractV2Table, FileTable, V2TableRefreshUtil} | ||
| import org.apache.spark.sql.internal.SQLConf | ||
| import org.apache.spark.storage.StorageLevel | ||
| import org.apache.spark.storage.StorageLevel.MEMORY_AND_DISK | ||
|
|
@@ -240,31 +242,51 @@ class CacheManager extends Logging with AdaptiveSparkPlanHelper { | |
| name: Seq[String], | ||
| conf: SQLConf, | ||
| includeTimeTravel: Boolean): Boolean = { | ||
| isMatchedTableOrView(plan, name, conf.resolver, includeTimeTravel) | ||
| } | ||
|
|
||
| private def isMatchedTableOrView( | ||
| plan: LogicalPlan, | ||
| name: Seq[String], | ||
| resolver: Resolver, | ||
| includeTimeTravel: Boolean): Boolean = { | ||
|
|
||
| EliminateSubqueryAliases(plan) match { | ||
| case LogicalRelationWithTable(_, Some(catalogTable)) => | ||
| isSameName(name, catalogTable.identifier.nameParts, resolver) | ||
|
|
||
| case DataSourceV2Relation(_, _, Some(catalog), Some(v2Ident), _, timeTravelSpec) => | ||
| val nameInCache = v2Ident.toQualifiedNameParts(catalog) | ||
| isSameName(name, nameInCache, resolver) && (includeTimeTravel || timeTravelSpec.isEmpty) | ||
|
|
||
| case r: V2TableReference => | ||
| isSameName(name, r.identifier.toQualifiedNameParts(r.catalog), resolver) | ||
|
|
||
| case v: View => | ||
| isSameName(name, v.desc.identifier.nameParts, resolver) | ||
|
|
||
| case HiveTableRelation(catalogTable, _, _, _, _) => | ||
| isSameName(name, catalogTable.identifier.nameParts, resolver) | ||
|
|
||
| case _ => false | ||
| } | ||
| } | ||
|
|
||
| private def isSameName( | ||
| name: Seq[String], | ||
| catalog: CatalogPlugin, | ||
| ident: Identifier, | ||
| resolver: Resolver): Boolean = { | ||
| isSameName(name, ident.toQualifiedNameParts(catalog), resolver) | ||
| } | ||
|
|
||
| private def isSameName( | ||
| name: Seq[String], | ||
| nameInCache: Seq[String], | ||
| resolver: Resolver): Boolean = { | ||
| nameInCache.length == name.length && nameInCache.zip(name).forall(resolver.tupled) | ||
| } | ||
|
|
||
| private def uncacheByCondition( | ||
| spark: SparkSession, | ||
| isMatchedPlan: LogicalPlan => Boolean, | ||
|
|
@@ -354,7 +376,7 @@ class CacheManager extends Logging with AdaptiveSparkPlanHelper { | |
| cd.cachedRepresentation.cacheBuilder.clearCache() | ||
| val sessionWithConfigsOff = getOrCloneSessionWithConfigsOff(spark) | ||
| val (newKey, newCache) = sessionWithConfigsOff.withActive { | ||
| val refreshedPlan = V2TableRefreshUtil.refresh(sessionWithConfigsOff, cd.plan) | ||
| val qe = sessionWithConfigsOff.sessionState.executePlan(refreshedPlan) | ||
| qe.normalized -> InMemoryRelation(cd.cachedRepresentation.cacheBuilder, qe) | ||
| } | ||
|
|
@@ -371,6 +393,35 @@ class CacheManager extends Logging with AdaptiveSparkPlanHelper { | |
| } | ||
| } | ||
|
|
||
| private[sql] def lookupCachedTable( | ||
|
Member
There was a problem hiding this comment. let's make it more straightforward:
Contributor
Author
There was a problem hiding this comment. @gengliangwang, I tested the rename locally, but not sure it would make the code any clearer. In fact, it only creates inconsistencies with other methods that accept name in args but don't have I feel |
||
| name: Seq[String], | ||
| resolver: Resolver): Option[LogicalPlan] = { | ||
| val cachedRelations = findCachedRelations(name, resolver) | ||
| cachedRelations match { | ||
| case cachedRelation +: _ => | ||
| CacheManager.logCacheOperation( | ||
| log"Relation cache hit for table ${MDC(TABLE_NAME, name.quoted)}") | ||
| Some(cachedRelation) | ||
|
Contributor
There was a problem hiding this comment. hmm we just return the first match? Shall we use the scan with the latest table version?
Contributor
Author
There was a problem hiding this comment. Well, we shouldn't have multiple matching relations after this change, but |
||
| case _ => | ||
| None | ||
| } | ||
| } | ||
|
|
||
| private def findCachedRelations( | ||
| name: Seq[String], | ||
| resolver: Resolver): Seq[LogicalPlan] = { | ||
| cachedData.flatMap { cd => | ||
| val plan = EliminateSubqueryAliases(cd.plan) | ||
| plan match { | ||
| case r @ ExtractV2CatalogAndIdentifier(catalog, ident) | ||
| if isSameName(name, catalog, ident, resolver) && r.timeTravelSpec.isEmpty => | ||
| Some(r) | ||
| case _ => | ||
| None | ||
| } | ||
| } | ||
| } | ||
|
|
||
| /** | ||
| * Optionally returns cached data for the given [[Dataset]] | ||
| */ | ||
|
|
||
Oops, something went wrong.
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.
Uh oh!
There was an error while loading. Please reload this page.
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 any relation cache in the future.