RussellSpitzer commented on code in PR #7607: URL: https://github.com/apache/iceberg/pull/7607#discussion_r1282439133
########## spark/v3.4/spark-extensions/src/test/java/org/apache/iceberg/spark/extensions/TestCopyOnWriteMergeAPI.java: ########## @@ -0,0 +1,214 @@ +/* + * 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 java.lang.String.format; +import static org.apache.iceberg.TableProperties.MERGE_ISOLATION_LEVEL; +import static org.apache.spark.sql.functions.lit; + +import java.util.Collections; +import java.util.HashMap; +import java.util.Map; +import java.util.concurrent.ExecutionException; +import java.util.concurrent.ExecutorService; +import java.util.concurrent.Executors; +import java.util.concurrent.Future; +import java.util.concurrent.ThreadPoolExecutor; +import java.util.concurrent.TimeUnit; +import java.util.concurrent.atomic.AtomicBoolean; +import java.util.concurrent.atomic.AtomicInteger; +import org.apache.iceberg.DataFile; +import org.apache.iceberg.RowLevelOperationMode; +import org.apache.iceberg.Snapshot; +import org.apache.iceberg.Table; +import org.apache.iceberg.TableProperties; +import org.apache.iceberg.data.GenericRecord; +import org.apache.iceberg.relocated.com.google.common.collect.ImmutableList; +import org.apache.iceberg.relocated.com.google.common.collect.ImmutableMap; +import org.apache.iceberg.relocated.com.google.common.collect.Iterables; +import org.apache.iceberg.relocated.com.google.common.util.concurrent.MoreExecutors; +import org.apache.iceberg.spark.Spark3Util; +import org.apache.iceberg.spark.SparkSQLProperties; +import org.apache.iceberg.util.SnapshotUtil; +import org.apache.spark.sql.Column; +import org.apache.spark.sql.Dataset; +import org.apache.spark.sql.Encoders; +import org.apache.spark.sql.Row; +import org.apache.spark.sql.internal.SQLConf; +import org.assertj.core.api.Assertions; +import org.junit.Assert; +import org.junit.Assume; +import org.junit.Test; + +public class TestCopyOnWriteMergeAPI extends TestMergeAPI { + + public TestCopyOnWriteMergeAPI( + String catalogName, + String implementation, + Map<String, String> config, + String fileFormat, + boolean vectorized, + String distributionMode, + String branch) { + super(catalogName, implementation, config, fileFormat, vectorized, distributionMode, branch); + } + + @Override + protected Map<String, String> extraTableProperties() { + return ImmutableMap.of( + TableProperties.MERGE_MODE, RowLevelOperationMode.COPY_ON_WRITE.modeName()); + } + + @Test + public synchronized void testMergeWithConcurrentTableRefresh() throws Exception { + // this test can only be run with Hive tables as it requires a reliable lock + // also, the table cache must be enabled so that the same table instance can be reused + Assume.assumeTrue(catalogName.equalsIgnoreCase("testhive")); + + createAndInitTable("id INT, dep STRING"); + Dataset<Row> source = spark.createDataset(Collections.singletonList(1), Encoders.INT()).toDF(); + + sql( + "ALTER TABLE %s SET TBLPROPERTIES('%s' '%s')", + tableName, MERGE_ISOLATION_LEVEL, "snapshot"); + + sql("INSERT INTO TABLE %s VALUES (1, 'hr')", tableName); + createBranchIfNeeded(); + + Table table = Spark3Util.loadIcebergTable(spark, tableName); + + ExecutorService executorService = + MoreExecutors.getExitingExecutorService( + (ThreadPoolExecutor) Executors.newFixedThreadPool(2)); + + AtomicInteger barrier = new AtomicInteger(0); + AtomicBoolean shouldAppend = new AtomicBoolean(true); + + // merge thread + Future<?> mergeFuture = + executorService.submit( + () -> { + for (int numOperations = 0; numOperations < Integer.MAX_VALUE; numOperations++) { + while (barrier.get() < numOperations * 2) { + sleep(10); + } + IcebergMergeInto.apply(tableName) + .using(source.as("source")) + .when(format("%s.id = source.value", tableName)) + .whenMatched() + .update( + new HashMap<String, Column>() { + { + put("dep", lit("x")); + } + }) + .merge(); + barrier.incrementAndGet(); + } + }); + + // append thread + Future<?> appendFuture = + executorService.submit( + () -> { + GenericRecord record = GenericRecord.create(table.schema()); + record.set(0, 1); // id + record.set(1, "hr"); // dep + + for (int numOperations = 0; numOperations < Integer.MAX_VALUE; numOperations++) { + while (shouldAppend.get() && barrier.get() < numOperations * 2) { + sleep(10); + } + + if (!shouldAppend.get()) { + return; + } + + for (int numAppends = 0; numAppends < 5; numAppends++) { + DataFile dataFile = writeDataFile(table, ImmutableList.of(record)); + table.newFastAppend().appendFile(dataFile).commit(); + sleep(10); + } + + barrier.incrementAndGet(); + } + }); + + try { + Assertions.assertThatThrownBy(mergeFuture::get) + .isInstanceOf(ExecutionException.class) + .cause() + .isInstanceOf(IllegalStateException.class) + .hasMessageContaining("the table has been concurrently modified"); + } finally { + shouldAppend.set(false); + appendFuture.cancel(true); + } + + executorService.shutdown(); + Assert.assertTrue("Timeout", executorService.awaitTermination(2, TimeUnit.MINUTES)); Review Comment: we probably don't want to add in 2 minute tests if we can help it -- 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] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
