karuppayya commented on a change in pull request #2415: URL: https://github.com/apache/iceberg/pull/2415#discussion_r645877484
########## File path: spark3/src/test/java/org/apache/iceberg/actions/TestRemoveFilesAction.java ########## @@ -0,0 +1,317 @@ +/* + * 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.iceberg.actions; + +import java.io.File; +import java.util.List; +import java.util.Set; +import java.util.concurrent.ConcurrentHashMap; +import java.util.concurrent.Executors; +import java.util.concurrent.atomic.AtomicInteger; +import org.apache.hadoop.conf.Configuration; +import org.apache.iceberg.AssertHelpers; +import org.apache.iceberg.DataFile; +import org.apache.iceberg.DataFiles; +import org.apache.iceberg.HasTableOperations; +import org.apache.iceberg.PartitionSpec; +import org.apache.iceberg.Schema; +import org.apache.iceberg.Table; +import org.apache.iceberg.TableProperties; +import org.apache.iceberg.TestHelpers; +import org.apache.iceberg.hadoop.HadoopTables; +import org.apache.iceberg.relocated.com.google.common.collect.ImmutableSet; +import org.apache.iceberg.relocated.com.google.common.collect.Maps; +import org.apache.iceberg.relocated.com.google.common.collect.Sets; +import org.apache.iceberg.spark.SparkTestBase; +import org.apache.iceberg.spark.actions.SparkActions; +import org.apache.iceberg.types.Types; +import org.junit.Assert; +import org.junit.Before; +import org.junit.Rule; +import org.junit.Test; +import org.junit.rules.TemporaryFolder; + +import static org.apache.iceberg.types.Types.NestedField.optional; + +public class TestRemoveFilesAction extends SparkTestBase { + private static final HadoopTables TABLES = new HadoopTables(new Configuration()); + private static final Schema SCHEMA = new Schema( + optional(1, "c1", Types.IntegerType.get()), + optional(2, "c2", Types.StringType.get()), + optional(3, "c3", Types.StringType.get()) + ); + private static final int SHUFFLE_PARTITIONS = 2; + + private static final PartitionSpec SPEC = PartitionSpec.builderFor(SCHEMA).identity("c1").build(); + + static final DataFile FILE_A = DataFiles.builder(SPEC) + .withPath("/path/to/data-a.parquet") + .withFileSizeInBytes(10) + .withPartition(TestHelpers.Row.of(0)) + .withRecordCount(1) + .build(); + static final DataFile FILE_B = DataFiles.builder(SPEC) + .withPath("/path/to/data-b.parquet") + .withFileSizeInBytes(10) + .withPartition(TestHelpers.Row.of(1)) + .withRecordCount(1) + .build(); + static final DataFile FILE_C = DataFiles.builder(SPEC) + .withPath("/path/to/data-c.parquet") + .withFileSizeInBytes(10) + .withPartition(TestHelpers.Row.of(2)) + .withRecordCount(1) + .build(); + static final DataFile FILE_D = DataFiles.builder(SPEC) + .withPath("/path/to/data-d.parquet") + .withFileSizeInBytes(10) + .withPartition(TestHelpers.Row.of(3)) + .withRecordCount(1) + .build(); + + @Rule + public TemporaryFolder temp = new TemporaryFolder(); + + private Table table; + + @Before + public void setupTableLocation() throws Exception { + File tableDir = temp.newFolder(); + String tableLocation = tableDir.toURI().toString(); + this.table = TABLES.create(SCHEMA, SPEC, Maps.newHashMap(), tableLocation); + spark.conf().set("spark.sql.shuffle.partitions", SHUFFLE_PARTITIONS); + } + + private void checkRemoveFilesResults(long expectedDatafiles, long expectedManifestsDeleted, + long expectedManifestListsDeleted, long expectedOtherFilesDeleted, + RemoveFiles.Result results) { + Assert.assertEquals("Incorrect number of manifest files deleted", + expectedManifestsDeleted, results.removedManifestsCount()); + Assert.assertEquals("Incorrect number of datafiles deleted", + expectedDatafiles, results.removedDataFilesCount()); + Assert.assertEquals("Incorrect number of manifest lists deleted", + expectedManifestListsDeleted, results.removedManifestListsCount()); + Assert.assertEquals("Incorrect number of other lists deleted", + expectedOtherFilesDeleted - 1, results.otherRemovedFilesCount()); + } + + @Test + public void dataFilesCleanupWithParallelTasks() { + table.newFastAppend() + .appendFile(FILE_A) + .commit(); + + table.newFastAppend() + .appendFile(FILE_B) + .commit(); + + table.newRewrite() + .rewriteFiles(ImmutableSet.of(FILE_B), ImmutableSet.of(FILE_D)) + .commit(); + + table.newRewrite() + .rewriteFiles(ImmutableSet.of(FILE_A), ImmutableSet.of(FILE_C)) + .commit(); + + Set<String> deletedFiles = Sets.newHashSet(); + Set<String> deleteThreads = ConcurrentHashMap.newKeySet(); + AtomicInteger deleteThreadsIndex = new AtomicInteger(0); + + RemoveFiles.Result result = getSparkActions().removeFiles(getMetadataLocation(table)) + .io(table.io()) + .executeRemoveWith(Executors.newFixedThreadPool(4, runnable -> { + Thread thread = new Thread(runnable); + thread.setName("remove-files-" + deleteThreadsIndex.getAndIncrement()); + thread.setDaemon(true); // daemon threads will be terminated abruptly when the JVM exits + return thread; + })) + .removeWith(s -> { + deleteThreads.add(Thread.currentThread().getName()); + deletedFiles.add(s); + }) + .execute(); + + // Verifies that the delete methods ran in the threads created by the provided ExecutorService ThreadFactory + Assert.assertEquals(deleteThreads, Review comment: checked org.apache.iceberg.util.Tasks.Builder#runParallel (The method that uses executor service to schedule the tasks), since the tasks are submitted serially in a loop, all 4 threads should be used -- 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. For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
