[VL] Add sort merge join metrics #3920
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 +1,92 @@ | ||
| /* | ||
| * 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 io.glutenproject.execution | ||
|
|
||
| import io.glutenproject.GlutenConfig | ||
|
|
||
| import org.apache.spark.sql.execution.adaptive.AdaptiveSparkPlanHelper | ||
| import org.apache.spark.sql.internal.SQLConf | ||
|
|
||
| class VeloxMetricsSuite extends VeloxWholeStageTransformerSuite with AdaptiveSparkPlanHelper { | ||
| override protected val backend: String = "velox" | ||
| override protected val resourcePath: String = "/tpch-data-parquet-velox" | ||
| override protected val fileFormat: String = "parquet" | ||
|
|
||
| override def beforeAll(): Unit = { | ||
| super.beforeAll() | ||
|
|
||
| spark | ||
| .range(100) | ||
| .selectExpr("id as c1", "id % 3 as c2") | ||
| .write | ||
| .format("parquet") | ||
| .saveAsTable("metrics_t1") | ||
|
|
||
| spark | ||
| .range(200) | ||
| .selectExpr("id as c1", "id % 3 as c2") | ||
| .write | ||
| .format("parquet") | ||
| .saveAsTable("metrics_t2") | ||
| } | ||
|
|
||
| override protected def afterAll(): Unit = { | ||
| spark.sql("drop table metrics_t1") | ||
| spark.sql("drop table metrics_t2") | ||
|
|
||
| super.afterAll() | ||
| } | ||
|
|
||
| test("test sort merge join metrics") { | ||
|
There was a problem hiding this comment. @ulysses-you Do we need to add the test with post project? And also add the hash join test for both with pre project and post project? There was a problem hiding this comment. Join always has the post project. The numOutputRows/numOutputVectors metrics are from post project. |
||
| withSQLConf( | ||
| GlutenConfig.COLUMNAR_FPRCE_SHUFFLED_HASH_JOIN_ENABLED.key -> "false", | ||
| SQLConf.AUTO_BROADCASTJOIN_THRESHOLD.key -> "-1") { | ||
| // without preproject | ||
| runQueryAndCompare( | ||
| "SELECT * FROM metrics_t1 join metrics_t2 on metrics_t1.c1 = metrics_t2.c1" | ||
| ) { | ||
| df => | ||
| val smj = find(df.queryExecution.executedPlan) { | ||
| case _: SortMergeJoinExecTransformer => true | ||
| case _ => false | ||
| } | ||
| assert(smj.isDefined) | ||
| val metrics = smj.get.metrics | ||
| assert(metrics("numOutputRows").value == 100) | ||
| assert(metrics("numOutputVectors").value > 0) | ||
| assert(metrics("numOutputBytes").value > 0) | ||
| } | ||
|
|
||
| // with preproject | ||
| runQueryAndCompare( | ||
| "SELECT * FROM metrics_t1 join metrics_t2 on metrics_t1.c1 + 1 = metrics_t2.c1 + 1" | ||
| ) { | ||
| df => | ||
| val smj = find(df.queryExecution.executedPlan) { | ||
| case _: SortMergeJoinExecTransformer => true | ||
| case _ => false | ||
| } | ||
| assert(smj.isDefined) | ||
| val metrics = smj.get.metrics | ||
| assert(metrics("numOutputRows").value == 100) | ||
| assert(metrics("numOutputVectors").value > 0) | ||
| assert(metrics("streamPreProjectionCpuCount").value > 0) | ||
| assert(metrics("bufferPreProjectionCpuCount").value > 0) | ||
| } | ||
| } | ||
| } | ||
| } | ||
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.
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.
@ulysses-you What are the differences between stream and buffer? How can they be mapped to the left and right in a sort merge join?
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.
Merge join only supports inner and left outer, so the steam side is always left child and the buffer side is always right child. It's used to show the metrics pre-project for stream/buffer side.