aokolnychyi commented on code in PR #6371: URL: https://github.com/apache/iceberg/pull/6371#discussion_r1042643130
########## spark/v3.3/spark/src/test/java/org/apache/iceberg/spark/sql/TestStoragePartitionedJoins.java: ########## @@ -0,0 +1,585 @@ +/* + * 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.sql; + +import java.util.List; +import java.util.Map; +import java.util.concurrent.atomic.AtomicReference; +import org.apache.commons.lang3.StringUtils; +import org.apache.iceberg.Schema; +import org.apache.iceberg.Table; +import org.apache.iceberg.TableProperties; +import org.apache.iceberg.expressions.Expressions; +import org.apache.iceberg.relocated.com.google.common.collect.ImmutableMap; +import org.apache.iceberg.relocated.com.google.common.collect.Lists; +import org.apache.iceberg.spark.SparkSQLProperties; +import org.apache.iceberg.spark.SparkSchemaUtil; +import org.apache.iceberg.spark.SparkTestBaseWithCatalog; +import org.apache.iceberg.spark.SparkWriteOptions; +import org.apache.iceberg.spark.data.RandomData; +import org.apache.spark.api.java.JavaRDD; +import org.apache.spark.sql.Dataset; +import org.apache.spark.sql.Row; +import org.apache.spark.sql.catalyst.InternalRow; +import org.apache.spark.sql.catalyst.analysis.NoSuchTableException; +import org.apache.spark.sql.internal.SQLConf; +import org.apache.spark.sql.types.StructType; +import org.junit.After; +import org.junit.Assert; +import org.junit.BeforeClass; +import org.junit.Test; + +public class TestStoragePartitionedJoins extends SparkTestBaseWithCatalog { + + 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 String TABLE_PROPERTIES = + String.format( + "'%s' = 16777216, '%s' = 16777216", + TableProperties.SPLIT_SIZE, TableProperties.SPLIT_OPEN_FILE_COST); + + private static final Map<String, String> SPJ_ON_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"); + + private static final Map<String, String> SPJ_OFF_SQL_CONF = + ImmutableMap.of( + SQLConf.V2_BUCKETING_ENABLED().key(), + "false", + 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"); + + @BeforeClass + public static void setupSparkConf() { + spark.conf().set("spark.sql.shuffle.partitions", "4"); + } + + @After + public void removeTables() { + sql("DROP TABLE IF EXISTS %s", tableName); + sql("DROP TABLE IF EXISTS %s", tableName(OTHER_TABLE_NAME)); + } + + // TODO: add tests for truncate transforms once SPARK-40295 is released + // TODO: add tests for cases when one side contains a subset of keys once Spark supports this + Review Comment: We will definitely need to support distributing the other side using the Iceberg function catalog. A common use case for this is MERGE. The incoming relation may be a view, which will never be distributed in a compatible way with Iceberg tables. I hope Spark would be smart enough to shuffle just the smaller relation using the reported partitioning from the target table. Unfortunately, it does not work even if I distribute the incoming data manually using the Iceberg function catalog. We must have `KeyGroupPartitioning` on both sides, which can only be reported by data sources. -- 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
