[SQL] SPARK-6981: Factor out SparkPlanner and QueryExecution from SQLContext #6356
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
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 +1,85 @@ | ||
| /* | ||
| * 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 | ||
|
|
||
| import org.apache.spark.annotation.{Experimental, DeveloperApi} | ||
| import org.apache.spark.rdd.RDD | ||
| import org.apache.spark.sql.catalyst.{InternalRow, optimizer} | ||
| import org.apache.spark.sql.{SQLContext, Row} | ||
| import org.apache.spark.sql.catalyst.plans.logical.LogicalPlan | ||
|
|
||
| /** | ||
| * :: DeveloperApi :: | ||
| * The primary workflow for executing relational queries using Spark. Designed to allow easy | ||
| * access to the intermediate phases of query execution for developers. | ||
| */ | ||
| @DeveloperApi | ||
| class QueryExecution(val sqlContext: SQLContext, val logical: LogicalPlan) { | ||
| val analyzer = sqlContext.analyzer | ||
| val optimizer = sqlContext.optimizer | ||
| val planner = sqlContext.planner | ||
| val cacheManager = sqlContext.cacheManager | ||
| val prepareForExecution = sqlContext.prepareForExecution | ||
|
|
||
| def assertAnalyzed(): Unit = analyzer.checkAnalysis(analyzed) | ||
|
|
||
| lazy val analyzed: LogicalPlan = analyzer.execute(logical) | ||
| lazy val withCachedData: LogicalPlan = { | ||
| assertAnalyzed() | ||
| cacheManager.useCachedData(analyzed) | ||
| } | ||
| lazy val optimizedPlan: LogicalPlan = optimizer.execute(withCachedData) | ||
|
|
||
| // TODO: Don't just pick the first one... | ||
| lazy val sparkPlan: SparkPlan = { | ||
| SparkPlan.currentContext.set(sqlContext) | ||
| planner.plan(optimizedPlan).next() | ||
| } | ||
| // executedPlan should not be used to initialize any SparkPlan. It should be | ||
| // only used for execution. | ||
| lazy val executedPlan: SparkPlan = prepareForExecution.execute(sparkPlan) | ||
|
|
||
| /** Internal version of the RDD. Avoids copies and has no schema */ | ||
| lazy val toRdd: RDD[InternalRow] = executedPlan.execute() | ||
|
|
||
| protected def stringOrError[A](f: => A): String = | ||
| try f.toString catch { case e: Throwable => e.toString } | ||
|
|
||
| def simpleString: String = | ||
| s"""== Physical Plan == | ||
| |${stringOrError(executedPlan)} | ||
| """.stripMargin.trim | ||
|
|
||
|
|
||
| override def toString: String = { | ||
| def output = | ||
| analyzed.output.map(o => s"${o.name}: ${o.dataType.simpleString}").mkString(", ") | ||
|
|
||
| s"""== Parsed Logical Plan == | ||
| |${stringOrError(logical)} | ||
| |== Analyzed Logical Plan == | ||
| |${stringOrError(output)} | ||
| |${stringOrError(analyzed)} | ||
| |== Optimized Logical Plan == | ||
| |${stringOrError(optimizedPlan)} | ||
| |== Physical Plan == | ||
| |${stringOrError(executedPlan)} | ||
| |Code Generation: ${stringOrError(executedPlan.codegenEnabled)} | ||
| """.stripMargin.trim | ||
| } | ||
| } |
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 +1,92 @@ | ||
| /* | ||
| * 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 | ||
|
|
||
| import org.apache.spark.SparkContext | ||
| import org.apache.spark.annotation.Experimental | ||
| import org.apache.spark.sql._ | ||
| import org.apache.spark.sql.catalyst.expressions._ | ||
| import org.apache.spark.sql.execution.datasources.DataSourceStrategy | ||
|
|
||
| @Experimental | ||
| class SparkPlanner(val sqlContext: SQLContext) extends SparkStrategies { | ||
| val sparkContext: SparkContext = sqlContext.sparkContext | ||
|
|
||
| def codegenEnabled: Boolean = sqlContext.conf.codegenEnabled | ||
|
|
||
| def unsafeEnabled: Boolean = sqlContext.conf.unsafeEnabled | ||
|
|
||
| def numPartitions: Int = sqlContext.conf.numShufflePartitions | ||
|
|
||
| def strategies: Seq[Strategy] = | ||
| sqlContext.experimental.extraStrategies ++ ( | ||
| DataSourceStrategy :: | ||
| DDLStrategy :: | ||
| TakeOrderedAndProject :: | ||
| HashAggregation :: | ||
| Aggregation :: | ||
| LeftSemiJoin :: | ||
| EquiJoinSelection :: | ||
| InMemoryScans :: | ||
| BasicOperators :: | ||
| CartesianProduct :: | ||
| BroadcastNestedLoopJoin :: Nil) | ||
|
|
||
| /** | ||
| * Used to build table scan operators where complex projection and filtering are done using | ||
| * separate physical operators. This function returns the given scan operator with Project and | ||
| * Filter nodes added only when needed. For example, a Project operator is only used when the | ||
| * final desired output requires complex expressions to be evaluated or when columns can be | ||
| * further eliminated out after filtering has been done. | ||
| * | ||
| * The `prunePushedDownFilters` parameter is used to remove those filters that can be optimized | ||
| * away by the filter pushdown optimization. | ||
| * | ||
| * The required attributes for both filtering and expression evaluation are passed to the | ||
| * provided `scanBuilder` function so that it can avoid unnecessary column materialization. | ||
| */ | ||
| def pruneFilterProject( | ||
| projectList: Seq[NamedExpression], | ||
| filterPredicates: Seq[Expression], | ||
| prunePushedDownFilters: Seq[Expression] => Seq[Expression], | ||
| scanBuilder: Seq[Attribute] => SparkPlan): SparkPlan = { | ||
|
|
||
| val projectSet = AttributeSet(projectList.flatMap(_.references)) | ||
| val filterSet = AttributeSet(filterPredicates.flatMap(_.references)) | ||
| val filterCondition = | ||
| prunePushedDownFilters(filterPredicates).reduceLeftOption(catalyst.expressions.And) | ||
|
|
||
| // Right now we still use a projection even if the only evaluation is applying an alias | ||
| // to a column. Since this is a no-op, it could be avoided. However, using this | ||
| // optimization with the current implementation would change the output schema. | ||
| // TODO: Decouple final output schema from expression evaluation so this copy can be | ||
| // avoided safely. | ||
|
|
||
| if (AttributeSet(projectList.map(_.toAttribute)) == projectSet && | ||
| filterSet.subsetOf(projectSet)) { | ||
| // When it is possible to just use column pruning to get the right projection and | ||
| // when the columns of this projection are enough to evaluate all filter conditions, | ||
| // just do a scan followed by a filter, with no extra project. | ||
| val scan = scanBuilder(projectList.asInstanceOf[Seq[Attribute]]) | ||
| filterCondition.map(Filter(_, scan)).getOrElse(scan) | ||
| } else { | ||
| val scan = scanBuilder((projectSet ++ filterSet).toSeq) | ||
| Project(projectList, filterCondition.map(Filter(_, scan)).getOrElse(scan)) | ||
| } | ||
| } | ||
| } |
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
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.
@marmbrus This changes the signature of
queryExecution. Is there anyway that we can preserve the binary compatibility?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.
Should we preserve binary compatibility for developer API? At least MIMA doesn't complain about it...
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.
QueryExecution extends SQLContext#QueryExecution so binary compatibility should be preserved
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.
The signature of the function to retrieve it has changed though. I think that we should rename this parameter and add a method that constructs a new instance of the inner subclass to return with the name
queryExecution. I think its worth rerunning the optimizer to not have to recompile all our perf tools.