pvary commented on code in PR #8553: URL: https://github.com/apache/iceberg/pull/8553#discussion_r1399328620
########## flink/v1.17/flink/src/test/java/org/apache/iceberg/flink/source/TestIcebergSourceWithWatermarkExtractor.java: ########## @@ -0,0 +1,375 @@ +/* + * 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.flink.source; + +import static org.apache.flink.connector.testframe.utils.ConnectorTestConstants.DEFAULT_COLLECT_DATA_TIMEOUT; +import static org.assertj.core.api.AssertionsForClassTypes.assertThat; + +import java.io.Serializable; +import java.time.Duration; +import java.time.Instant; +import java.time.LocalDateTime; +import java.time.ZoneId; +import java.util.List; +import java.util.Optional; +import java.util.Set; +import java.util.UUID; +import java.util.concurrent.CompletableFuture; +import java.util.concurrent.TimeUnit; +import java.util.stream.Collectors; +import org.apache.flink.api.common.JobID; +import org.apache.flink.api.common.eventtime.SerializableTimestampAssigner; +import org.apache.flink.api.common.eventtime.WatermarkStrategy; +import org.apache.flink.api.common.typeinfo.TypeInformation; +import org.apache.flink.api.common.typeutils.TypeSerializer; +import org.apache.flink.configuration.Configuration; +import org.apache.flink.core.execution.JobClient; +import org.apache.flink.metrics.Gauge; +import org.apache.flink.runtime.metrics.MetricNames; +import org.apache.flink.runtime.minicluster.RpcServiceSharing; +import org.apache.flink.runtime.testutils.InMemoryReporter; +import org.apache.flink.runtime.testutils.MiniClusterResourceConfiguration; +import org.apache.flink.streaming.api.datastream.DataStream; +import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment; +import org.apache.flink.streaming.api.functions.windowing.AllWindowFunction; +import org.apache.flink.streaming.api.operators.collect.CollectResultIterator; +import org.apache.flink.streaming.api.operators.collect.CollectSinkOperator; +import org.apache.flink.streaming.api.operators.collect.CollectSinkOperatorFactory; +import org.apache.flink.streaming.api.operators.collect.CollectStreamSink; +import org.apache.flink.streaming.api.windowing.assigners.TumblingEventTimeWindows; +import org.apache.flink.streaming.api.windowing.time.Time; +import org.apache.flink.streaming.api.windowing.windows.TimeWindow; +import org.apache.flink.table.data.RowData; +import org.apache.flink.test.util.MiniClusterWithClientResource; +import org.apache.flink.util.Collector; +import org.apache.iceberg.FileFormat; +import org.apache.iceberg.data.GenericAppenderHelper; +import org.apache.iceberg.data.GenericRecord; +import org.apache.iceberg.data.RandomGenericData; +import org.apache.iceberg.data.Record; +import org.apache.iceberg.flink.HadoopTableResource; +import org.apache.iceberg.flink.RowDataConverter; +import org.apache.iceberg.flink.TestFixtures; +import org.apache.iceberg.relocated.com.google.common.collect.ImmutableList; +import org.apache.iceberg.relocated.com.google.common.collect.Lists; +import org.apache.iceberg.relocated.com.google.common.collect.Sets; +import org.apache.iceberg.types.Comparators; +import org.apache.iceberg.util.StructLikeWrapper; +import org.awaitility.Awaitility; +import org.junit.Assert; +import org.junit.ClassRule; +import org.junit.Rule; +import org.junit.Test; +import org.junit.rules.TemporaryFolder; + +public class TestIcebergSourceWithWatermarkExtractor implements Serializable { + private static final InMemoryReporter reporter = InMemoryReporter.createWithRetainedMetrics(); + private static final int PARALLELISM = 4; + private static final String SOURCE_NAME = "IcebergSource"; + private static final int RECORD_NUM_FOR_2_SPLITS = 200; + + @ClassRule public static final TemporaryFolder TEMPORARY_FOLDER = new TemporaryFolder(); + + @Rule + public final MiniClusterWithClientResource miniClusterResource = + new MiniClusterWithClientResource( + new MiniClusterResourceConfiguration.Builder() + .setNumberTaskManagers(1) + .setNumberSlotsPerTaskManager(PARALLELISM) + .setRpcServiceSharing(RpcServiceSharing.DEDICATED) + .setConfiguration(reporter.addToConfiguration(new Configuration())) + .withHaLeadershipControl() + .build()); + + @Rule + public final HadoopTableResource sourceTableResource = + new HadoopTableResource( + TEMPORARY_FOLDER, TestFixtures.DATABASE, TestFixtures.TABLE, TestFixtures.TS_SCHEMA); + + @Test + public void testWindowing() throws Exception { Review Comment: > * d lateness to 20, make sure 3 splits with target split size > * slow down the processing of file 1 and 2 with some sleep. make sure the watermark advanced to 50 before processing file 3. The `testThrottling` does something similar. We use the `findAlignmentDriftMetric` to validate that the watermarks is as we expect it. > * test A: use sequence number ordered assigner and allowed lateness. the records from file 3 should have been dropped and not in the final output The watermarks are generally handled on task manager level. If the 3rd split (with watermark 10) is assigned to the task manager which read the 1st split (watermark 1), then they will not be late records. If it is assigned to the task manager which read the 2nd split (watermark 50), they will be late records. There is no easy way to ensure the scheduling happens on the task manager which we prefer. > * test B: enable watermark alignment. records from all 3 files should be kept in the final output For testing the ordering I will add a separate test class. -- 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
