-
Notifications
You must be signed in to change notification settings - Fork 377
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
[GLUTEN-2919][VL]Support orc format in hive scan
- Loading branch information
Showing
6 changed files
with
332 additions
and
3 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
163 changes: 163 additions & 0 deletions
163
.../spark32/src/test/scala/org/apache/spark/sql/hive/execution/GlutenHiveSQLQuerySuite.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 +1,163 @@ | ||
| /* | ||
| * 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.hive.execution | ||
|
|
||
| import io.glutenproject.execution.TransformSupport | ||
| import org.apache.spark.SparkConf | ||
| import org.apache.spark.internal.config | ||
| import org.apache.spark.internal.config.UI.UI_ENABLED | ||
| import org.apache.spark.sql.catalyst.TableIdentifier | ||
| import org.apache.spark.sql.{DataFrame, GlutenSQLTestsTrait, Row, SparkSession} | ||
| import org.apache.spark.sql.catalyst.expressions.CodegenObjectFactoryMode | ||
| import org.apache.spark.sql.catalyst.optimizer.ConvertToLocalRelation | ||
| import org.apache.spark.sql.execution.SparkPlan | ||
| import org.apache.spark.sql.execution.adaptive.{AdaptiveSparkPlanExec, ShuffleQueryStageExec} | ||
| import org.apache.spark.sql.hive.{HiveTableScanExecTransformer, HiveUtils} | ||
| import org.apache.spark.sql.internal.{SQLConf, StaticSQLConf} | ||
|
|
||
| import scala.reflect.ClassTag | ||
|
|
||
| class GlutenHiveSQLQuerySuite extends GlutenSQLTestsTrait { | ||
| private var _spark: SparkSession = null | ||
|
|
||
| override def beforeAll(): Unit = { | ||
| prepareWorkDir() | ||
| if (_spark == null) { | ||
| _spark = SparkSession.builder().config(sparkConf).enableHiveSupport().getOrCreate() | ||
| } | ||
|
|
||
| _spark.sparkContext.setLogLevel("info") | ||
| } | ||
|
|
||
| override protected def spark: SparkSession = _spark | ||
|
|
||
| protected def defaultSparkConf: SparkConf = { | ||
| val conf = new SparkConf() | ||
| .set("spark.master", "local[1]") | ||
| .set("spark.sql.test", "") | ||
| .set("spark.sql.testkey", "true") | ||
| .set(SQLConf.CODEGEN_FALLBACK.key, "false") | ||
| .set(SQLConf.CODEGEN_FACTORY_MODE.key, CodegenObjectFactoryMode.CODEGEN_ONLY.toString) | ||
| .set( | ||
| HiveUtils.HIVE_METASTORE_BARRIER_PREFIXES.key, | ||
| "org.apache.spark.sql.hive.execution.PairSerDe") | ||
| // SPARK-8910 | ||
| .set(UI_ENABLED, false) | ||
| .set(config.UNSAFE_EXCEPTION_ON_MEMORY_LEAK, true) | ||
| // Hive changed the default of hive.metastore.disallow.incompatible.col.type.changes | ||
| // from false to true. For details, see the JIRA HIVE-12320 and HIVE-17764. | ||
| .set("spark.hadoop.hive.metastore.disallow.incompatible.col.type.changes", "false") | ||
| // Disable ConvertToLocalRelation for better test coverage. Test cases built on | ||
| // LocalRelation will exercise the optimization rules better by disabling it as | ||
| // this rule may potentially block testing of other optimization rules such as | ||
| // ConstantPropagation etc. | ||
| .set(SQLConf.OPTIMIZER_EXCLUDED_RULES.key, ConvertToLocalRelation.ruleName) | ||
|
|
||
| conf.set( | ||
| StaticSQLConf.WAREHOUSE_PATH, | ||
| conf.get(StaticSQLConf.WAREHOUSE_PATH) + "/" + getClass.getCanonicalName) | ||
| } | ||
|
|
||
| /** | ||
| * Get all the children plan of plans. | ||
| * | ||
| * @param plans : | ||
| * the input plans. | ||
| * @return | ||
| */ | ||
| def getChildrenPlan(plans: Seq[SparkPlan]): Seq[SparkPlan] = { | ||
| if (plans.isEmpty) { | ||
| return Seq() | ||
| } | ||
|
|
||
| val inputPlans: Seq[SparkPlan] = plans.map { | ||
| case stage: ShuffleQueryStageExec => stage.plan | ||
| case plan => plan | ||
| } | ||
|
|
||
| var newChildren: Seq[SparkPlan] = Seq() | ||
| inputPlans.foreach { | ||
| plan => | ||
| newChildren = newChildren ++ getChildrenPlan(plan.children) | ||
| // To avoid duplication of WholeStageCodegenXXX and its children. | ||
| if (!plan.nodeName.startsWith("WholeStageCodegen")) { | ||
| newChildren = newChildren :+ plan | ||
| } | ||
| } | ||
| newChildren | ||
| } | ||
|
|
||
| /** | ||
| * Get the executed plan of a data frame. | ||
| * | ||
| * @param df : | ||
| * dataframe. | ||
| * @return | ||
| * A sequence of executed plans. | ||
| */ | ||
| def getExecutedPlan(df: DataFrame): Seq[SparkPlan] = { | ||
| df.queryExecution.executedPlan match { | ||
| case exec: AdaptiveSparkPlanExec => | ||
| getChildrenPlan(Seq(exec.executedPlan)) | ||
| case plan => | ||
| getChildrenPlan(Seq(plan)) | ||
| } | ||
| } | ||
|
|
||
| def checkOperatorMatch[T <: TransformSupport](df: DataFrame)(implicit tag: ClassTag[T]): Unit = { | ||
| val executedPlan = getExecutedPlan(df) | ||
| assert(executedPlan.exists(plan => plan.getClass == tag.runtimeClass)) | ||
| } | ||
|
|
||
| override def sparkConf: SparkConf = { | ||
| defaultSparkConf | ||
| .set("spark.plugins", "io.glutenproject.GlutenPlugin") | ||
| .set("spark.default.parallelism", "1") | ||
| .set("spark.memory.offHeap.enabled", "true") | ||
| .set("spark.memory.offHeap.size", "1024MB") | ||
| } | ||
| test("hive orc scan") { | ||
| withSQLConf("spark.sql.hive.convertMetastoreOrc" -> "false") { | ||
| sql("DROP TABLE IF EXISTS test_orc") | ||
| sql("CREATE TABLE test_orc (name STRING, favorite_color STRING) USING hive OPTIONS(fileFormat 'orc')") | ||
| sql("INSERT INTO test_orc VALUES('test_1', 'red')"); | ||
| val df = spark.sql("select * from test_orc") | ||
| checkAnswer(df, Seq(Row("test_1", "red"))) | ||
| checkOperatorMatch[HiveTableScanExecTransformer](df) | ||
| } | ||
| spark.sessionState.catalog.dropTable( | ||
| TableIdentifier("test_orc"), | ||
| ignoreIfNotExists = true, | ||
| purge = false) | ||
| } | ||
|
|
||
| test("hive orc scan") { | ||
| withSQLConf("spark.sql.hive.convertMetastoreOrc" -> "false") { | ||
| sql("DROP TABLE IF EXISTS test_orc") | ||
| sql("CREATE TABLE test_orc (name STRING, favorite_color STRING)" + | ||
| " USING hive OPTIONS(fileFormat 'orc')") | ||
| sql("INSERT INTO test_orc VALUES('test_1', 'red')"); | ||
| val df = spark.sql("select * from test_orc") | ||
| checkAnswer(df, Seq(Row("test_1", "red"))) | ||
| checkOperatorMatch[HiveTableScanExecTransformer](df) | ||
| } | ||
| spark.sessionState.catalog.dropTable( | ||
| TableIdentifier("test_orc"), | ||
| ignoreIfNotExists = true, | ||
| purge = false) | ||
| } | ||
| } |
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.