sunchao commented on code in PR #109: URL: https://github.com/apache/arrow-datafusion-comet/pull/109#discussion_r1506353450
########## spark/src/test/scala/org/apache/comet/exec/CometNativeShuffleSuite.scala: ########## @@ -0,0 +1,198 @@ +/* + * 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.comet.exec + +import org.scalactic.source.Position +import org.scalatest.Tag + +import org.apache.hadoop.fs.Path +import org.apache.spark.sql.CometTestBase +import org.apache.spark.sql.comet.execution.shuffle.CometShuffleExchangeExec +import org.apache.spark.sql.execution.adaptive.AdaptiveSparkPlanHelper +import org.apache.spark.sql.functions.col + +import org.apache.comet.CometConf +import org.apache.comet.CometSparkSessionExtensions.isSpark34Plus + +class CometNativeShuffleSuite extends CometTestBase with AdaptiveSparkPlanHelper { + override protected def test(testName: String, testTags: Tag*)(testFun: => Any)(implicit + pos: Position): Unit = { + super.test(testName, testTags: _*) { + withSQLConf( + CometConf.COMET_EXEC_ENABLED.key -> "true", + CometConf.COMET_COLUMNAR_SHUFFLE_ENABLED.key -> "false", + CometConf.COMET_EXEC_SHUFFLE_ENABLED.key -> "true") { + testFun + } + } + } + + import testImplicits._ + + // TODO: this test takes ~5mins to run, we should reduce the test time. + test("fix: Too many task completion listener of ArrowReaderIterator causes OOM") { + withSQLConf(CometConf.COMET_BATCH_SIZE.key -> "1") { + withParquetTable((0 until 100000).map(i => (1, (i + 1).toLong)), "tbl") { + assert( + sql("SELECT * FROM tbl").repartition(201, $"_1").count() == sql("SELECT * FROM tbl") + .count()) + } + } + } + + test("native shuffle: different data type") { + Seq(true, false).foreach { dictionaryEnabled => + withTempDir { dir => + val path = new Path(dir.toURI.toString, "test.parquet") + makeParquetFileAllTypes(path, dictionaryEnabled = dictionaryEnabled, 1000) + var allTypes: Seq[Int] = (1 to 20) + if (isSpark34Plus) { + allTypes = allTypes.filterNot(Set(14, 17).contains) + } + allTypes.map(i => s"_$i").foreach { c => + withSQLConf("parquet.enable.dictionary" -> dictionaryEnabled.toString) { + readParquetFile(path.toString) { df => + val shuffled = df + .select($"_1") + .repartition(10, col(c)) + checkCometExchange(shuffled, 1, true) + checkSparkAnswerAndOperator(shuffled) + } + } + } + } + } + } + + test("hash-based native shuffle") { + withParquetTable((0 until 5).map(i => (i, (i + 1).toLong)), "tbl") { + val df = sql("SELECT * FROM tbl").sortWithinPartitions($"_1".desc) + val shuffled1 = df.repartition(10, $"_1") + + checkCometExchange(shuffled1, 1, true) + checkSparkAnswer(shuffled1) + + val shuffled2 = df.repartition(10, $"_1", $"_2") + + checkCometExchange(shuffled2, 1, true) + checkSparkAnswer(shuffled2) + + val shuffled3 = df.repartition(10, $"_2", $"_1") + + checkCometExchange(shuffled3, 1, true) + checkSparkAnswer(shuffled3) + } + } + + test("columnar shuffle: single partition") { Review Comment: Yea let me update this. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
