rdblue commented on code in PR #6371: URL: https://github.com/apache/iceberg/pull/6371#discussion_r1053556414
########## spark/v3.3/spark-extensions/src/test/java/org/apache/iceberg/spark/extensions/TestStoragePartitionedJoinsInRowLevelOperations.java: ########## @@ -0,0 +1,283 @@ +/* + * 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.spark.extensions; + +import static org.apache.iceberg.RowLevelOperationMode.COPY_ON_WRITE; +import static org.apache.iceberg.RowLevelOperationMode.MERGE_ON_READ; + +import java.util.Map; +import org.apache.iceberg.RowLevelOperationMode; +import org.apache.iceberg.TableProperties; +import org.apache.iceberg.relocated.com.google.common.collect.ImmutableList; +import org.apache.iceberg.relocated.com.google.common.collect.ImmutableMap; +import org.apache.iceberg.spark.SparkCatalogConfig; +import org.apache.iceberg.spark.SparkSQLProperties; +import org.apache.spark.sql.execution.SparkPlan; +import org.apache.spark.sql.internal.SQLConf; +import org.junit.After; +import org.junit.Assert; +import org.junit.Test; +import org.junit.runners.Parameterized; + +public class TestStoragePartitionedJoinsInRowLevelOperations extends SparkExtensionsTestBase { + + private static final String OTHER_TABLE_NAME = "other_table"; + + // open file cost and split size are set as 16 MB to produce a split per file + private static final Map<String, String> COMMON_TABLE_PROPERTIES = + ImmutableMap.of( + TableProperties.FORMAT_VERSION, + "2", + TableProperties.SPLIT_SIZE, + "16777216", + TableProperties.SPLIT_OPEN_FILE_COST, + "16777216"); + + // only v2 bucketing and preserve data grouping properties have to be enabled to trigger SPJ + // other properties are only to simplify testing and validation + private static final Map<String, String> ENABLED_SPJ_SQL_CONF = + ImmutableMap.of( + SQLConf.V2_BUCKETING_ENABLED().key(), + "true", + SQLConf.REQUIRE_ALL_CLUSTER_KEYS_FOR_CO_PARTITION().key(), + "false", + SQLConf.ADAPTIVE_EXECUTION_ENABLED().key(), + "false", + SQLConf.AUTO_BROADCASTJOIN_THRESHOLD().key(), + "-1", + SparkSQLProperties.PRESERVE_DATA_GROUPING, + "true"); + + @Parameterized.Parameters(name = "catalogName = {0}, implementation = {1}, config = {2}") + public static Object[][] parameters() { + return new Object[][] { + { + SparkCatalogConfig.HIVE.catalogName(), + SparkCatalogConfig.HIVE.implementation(), + SparkCatalogConfig.HIVE.properties() + } + }; + } + + public TestStoragePartitionedJoinsInRowLevelOperations( + String catalogName, String implementation, Map<String, String> config) { + super(catalogName, implementation, config); + } + + @After + public void removeTables() { + sql("DROP TABLE IF EXISTS %s", tableName); + sql("DROP TABLE IF EXISTS %s", tableName(OTHER_TABLE_NAME)); + } + + @Test + public void testCopyOnWriteDeleteWithoutShuffles() { + checkDelete(COPY_ON_WRITE); + } + + @Test + public void testMergeOnReadDeleteWithoutShuffles() { + checkDelete(MERGE_ON_READ); + } + + private void checkDelete(RowLevelOperationMode mode) { + String createTableStmt = + "CREATE TABLE %s (id INT, salary INT, dep STRING)" + + "USING iceberg " + + "PARTITIONED BY (dep) " + + "TBLPROPERTIES (%s)"; + + sql(createTableStmt, tableName, tablePropsAsString(COMMON_TABLE_PROPERTIES)); + + append(tableName, "{ \"id\": 1, \"salary\": 100, \"dep\": \"hr\" }"); + append(tableName, "{ \"id\": 2, \"salary\": 200, \"dep\": \"hr\" }"); + append(tableName, "{ \"id\": 3, \"salary\": 300, \"dep\": \"hr\" }"); + append(tableName, "{ \"id\": 4, \"salary\": 400, \"dep\": \"hardware\" }"); + + sql(createTableStmt, tableName(OTHER_TABLE_NAME), tablePropsAsString(COMMON_TABLE_PROPERTIES)); + + append(tableName(OTHER_TABLE_NAME), "{ \"id\": 1, \"salary\": 110, \"dep\": \"hr\" }"); + append(tableName(OTHER_TABLE_NAME), "{ \"id\": 5, \"salary\": 500, \"dep\": \"hr\" }"); + + Map<String, String> deleteTableProps = + ImmutableMap.of( + TableProperties.DELETE_MODE, + mode.modeName(), + TableProperties.DELETE_DISTRIBUTION_MODE, + "none"); + + sql("ALTER TABLE %s SET TBLPROPERTIES(%s)", tableName, tablePropsAsString(deleteTableProps)); + + withSQLConf( + ENABLED_SPJ_SQL_CONF, + () -> { + SparkPlan plan = + executeAndKeepPlan( + "DELETE FROM %s t WHERE " + + "EXISTS (SELECT 1 FROM %s s WHERE t.id = s.id AND t.dep = s.dep) AND " + + "dep = 'hr'", Review Comment: Why restrict this to just `hr`? It seems like that could cause everything to fit in a single task, which Spark handles specially in some cases. If we were to test a delete in both departments, then I think this would be more likely to test what we want in Spark. -- 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: issues-unsubscr...@iceberg.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@iceberg.apache.org For additional commands, e-mail: issues-h...@iceberg.apache.org
