This repository has been archived by the owner on Jun 14, 2024. It is now read-only.
-
Notifications
You must be signed in to change notification settings - Fork 114
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
12 changed files
with
275 additions
and
37 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
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
182 changes: 182 additions & 0 deletions
182
src/main/scala/com/microsoft/hyperspace/index/rules/WhyNotAnalyzer.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 +1,182 @@ | ||
| /* | ||
| * Copyright (2020) The Hyperspace Project Authors. | ||
| * | ||
| * Licensed 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 com.microsoft.hyperspace.index.rules | ||
|
|
||
| import org.apache.spark.internal.Logging | ||
| import org.apache.spark.sql.{DataFrame, SparkSession} | ||
| import org.apache.spark.sql.catalyst.plans.logical.LogicalPlan | ||
|
|
||
| import com.microsoft.hyperspace.{Hyperspace, HyperspaceException} | ||
| import com.microsoft.hyperspace.actions.Constants | ||
| import com.microsoft.hyperspace.index.{IndexLogEntry, IndexLogEntryTags} | ||
|
|
||
| object WhyNotAnalyzer extends Logging { | ||
|
|
||
| private def cleanupAnalysisTags(indexes: Seq[IndexLogEntry]): Unit = { | ||
| indexes.foreach { index => | ||
| index.unsetTagValueForAllPlan(IndexLogEntryTags.INDEX_PLAN_ANALYSIS_ENABLED) | ||
| index.unsetTagValueForAllPlan(IndexLogEntryTags.FILTER_REASONS) | ||
| index.unsetTagValueForAllPlan(IndexLogEntryTags.APPLICABLE_INDEX_RULES) | ||
| } | ||
| } | ||
|
|
||
| private def prepareTagsForAnalysis(indexes: Seq[IndexLogEntry]): Unit = { | ||
| indexes.foreach { index => | ||
| index.setTagValue(IndexLogEntryTags.INDEX_PLAN_ANALYSIS_ENABLED, true) | ||
|
|
||
| // Clean up previous reason tags. | ||
| index.unsetTagValueForAllPlan(IndexLogEntryTags.FILTER_REASONS) | ||
| index.unsetTagValueForAllPlan(IndexLogEntryTags.APPLICABLE_INDEX_RULES) | ||
| } | ||
| } | ||
|
|
||
| private def generateWhyNotString( | ||
| planWithoutHyperspace: LogicalPlan, | ||
| planWithHyperspace: LogicalPlan, | ||
| reasonStrings: Seq[(LogicalPlan, Seq[String])], | ||
| applyStrings: Seq[(LogicalPlan, Seq[String])]): String = { | ||
| val stringBuilder = new StringBuilder | ||
| val originalPlanString = planWithoutHyperspace.numberedTreeString.split('\n') | ||
|
|
||
| stringBuilder.append("\nPlan with Hyperspace\n") | ||
| stringBuilder.append("============================================\n") | ||
| stringBuilder.append(planWithHyperspace) | ||
| stringBuilder.append("\n\n") | ||
| stringBuilder.append("Plan without Hyperspace\n") | ||
| stringBuilder.append("============================================\n") | ||
| stringBuilder.append(originalPlanString.mkString("\n")) | ||
| stringBuilder.append("\n\n") | ||
|
|
||
| stringBuilder.append("********************************************\n") | ||
| stringBuilder.append(s"WhyNot Analysis\n") | ||
|
|
||
| reasonStrings.groupBy(_._1).foreach { | ||
| case (plan, stringsForPlan) => | ||
| val planStrLines = plan.toString.split('\n') | ||
| val firstLineStr = originalPlanString.find(str => str.endsWith(planStrLines.head)) | ||
| stringBuilder.append("============================================\n") | ||
| stringBuilder.append("Candidate plan:\n") | ||
| // Start with numbered plan string | ||
| stringBuilder.append(firstLineStr.get) | ||
| stringBuilder.append("\n") | ||
| val numberSpaces = " " * (firstLineStr.get.length - planStrLines.head.length) | ||
| stringBuilder.append(numberSpaces) | ||
| stringBuilder.append(planStrLines.tail.toSeq.mkString(s"\n$numberSpaces")) | ||
| stringBuilder.append("\n\nFailure reasons:\n") | ||
| stringsForPlan.foreach { | ||
| case (_, strings) => | ||
| stringBuilder.append("- ") | ||
| stringBuilder.append(strings.mkString("\n- ")) | ||
| stringBuilder.append("\n") | ||
| } | ||
| } | ||
|
|
||
| stringBuilder.append("\n") | ||
| if (applyStrings.nonEmpty) { | ||
| stringBuilder.append("********************************************\n") | ||
| stringBuilder.append("Applicable indexes\n") | ||
| applyStrings.groupBy(_._1).foreach { | ||
| case (plan, stringsForPlan) => | ||
| val planStrLines = plan.toString.split('\n') | ||
| val firstLineStr = originalPlanString.find(str => str.endsWith(planStrLines.head)) | ||
| stringBuilder.append("============================================\n") | ||
| stringBuilder.append("Source plan:\n") | ||
| // Start with numbered plan string | ||
| stringBuilder.append(firstLineStr.get) | ||
| stringBuilder.append("\n") | ||
| val numberSpaces = " " * (firstLineStr.get.length - planStrLines.head.length) | ||
| stringBuilder.append(numberSpaces) | ||
| stringBuilder.append(planStrLines.tail.toSeq.mkString(s"\n$numberSpaces")) | ||
| stringBuilder.append("\n\nApplicable indexes:\n") | ||
| stringsForPlan.foreach { | ||
| case (_, strings) => | ||
| stringBuilder.append("- ") | ||
| stringBuilder.append(strings.mkString("\n- ")) | ||
| stringBuilder.append("\n") | ||
| } | ||
| } | ||
| } | ||
| stringBuilder.toString | ||
| } | ||
|
|
||
| def whyNotIndexString(spark: SparkSession, df: DataFrame, indexName: String): String = { | ||
| val (planWithHyperspace, reasonStrings, applyStrings) = whyNotIndex(spark, df, indexName) | ||
| generateWhyNotString( | ||
| df.queryExecution.optimizedPlan, | ||
| planWithHyperspace, | ||
| reasonStrings, | ||
| applyStrings) | ||
| } | ||
|
|
||
| def whyNotIndexesString(spark: SparkSession, df: DataFrame): String = { | ||
| val (planWithHyperspace, reasonStrings, applyStrings) = whyNotIndexes(spark, df) | ||
| generateWhyNotString( | ||
| df.queryExecution.optimizedPlan, | ||
| planWithHyperspace, | ||
| reasonStrings, | ||
| applyStrings) | ||
| } | ||
|
|
||
| def whyNotIndex(spark: SparkSession, df: DataFrame, indexName: String) | ||
| : (LogicalPlan, Seq[(LogicalPlan, Seq[String])], Seq[(LogicalPlan, Seq[String])]) = { | ||
| val plan = df.queryExecution.optimizedPlan | ||
|
|
||
| val indexManager = Hyperspace.getContext(spark).indexCollectionManager | ||
| val allIndexes = | ||
| indexManager.getIndexes().filter(!_.state.equals(Constants.States.DOESNOTEXIST)) | ||
| val targetIndex = allIndexes.find(index => index.name.equals(indexName)) | ||
|
|
||
| if (targetIndex.isEmpty) { | ||
| throw HyperspaceException(s"Index with name $indexName could not be found.") | ||
| } else if (!targetIndex.get.state.equals(Constants.States.ACTIVE)) { | ||
| throw HyperspaceException( | ||
| s"Index with name $indexName is not ACTIVE state: ${targetIndex.get.state}") | ||
| } | ||
|
|
||
| val allActiveIndexes = allIndexes.filter(_.state.equals(Constants.States.ACTIVE)) | ||
| applyHyperspaceForAnalysis(plan, allActiveIndexes) | ||
| } | ||
|
|
||
| def whyNotIndexes(spark: SparkSession, df: DataFrame) | ||
| : (LogicalPlan, Seq[(LogicalPlan, Seq[String])], Seq[(LogicalPlan, Seq[String])]) = { | ||
| val plan = df.queryExecution.optimizedPlan | ||
|
|
||
| val indexManager = Hyperspace.getContext(spark).indexCollectionManager | ||
| val allActiveIndexes = indexManager.getIndexes(Seq(Constants.States.ACTIVE)) | ||
|
|
||
| if (allActiveIndexes.isEmpty) { | ||
| throw HyperspaceException(s"No available ACTIVE indexes") | ||
| } | ||
| applyHyperspaceForAnalysis(plan, allActiveIndexes) | ||
| } | ||
|
|
||
| def applyHyperspaceForAnalysis(plan: LogicalPlan, indexes: Seq[IndexLogEntry]) | ||
| : (LogicalPlan, Seq[(LogicalPlan, Seq[String])], Seq[(LogicalPlan, Seq[String])]) = { | ||
| try { | ||
| prepareTagsForAnalysis(indexes) | ||
| val candidateIndexes = CandidateIndexCollector.apply(plan, indexes) | ||
| val transformedPlan = new ScoreBasedIndexPlanOptimizer().apply(plan, candidateIndexes) | ||
| ( | ||
| transformedPlan, | ||
| indexes.flatMap(_.getTagValueForAllPlan(IndexLogEntryTags.FILTER_REASONS)), | ||
| indexes.flatMap(_.getTagValueForAllPlan(IndexLogEntryTags.APPLICABLE_INDEX_RULES))) | ||
| } finally { | ||
| cleanupAnalysisTags(indexes) | ||
| } | ||
| } | ||
|
|
||
| } |
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.