Savonitar commented on code in PR #322: URL: https://github.com/apache/flink-connector-kafka/pull/322#discussion_r4054529411
########## flink-connector-kafka/src/test/java/org/apache/flink/connector/kafka/sink/KafkaSinkRecoveryITCase.java: ########## @@ -0,0 +1,537 @@ +/* + * 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.flink.connector.kafka.sink; + +import org.apache.flink.api.common.eventtime.WatermarkStrategy; +import org.apache.flink.api.common.functions.MapFunction; +import org.apache.flink.api.common.serialization.SerializationSchema; +import org.apache.flink.api.common.state.ListState; +import org.apache.flink.api.common.state.ListStateDescriptor; +import org.apache.flink.api.common.typeinfo.BasicTypeInfo; +import org.apache.flink.api.common.typeutils.SimpleTypeSerializerSnapshot; +import org.apache.flink.api.common.typeutils.TypeSerializerSnapshot; +import org.apache.flink.api.common.typeutils.base.TypeSerializerSingleton; +import org.apache.flink.api.connector.source.lib.NumberSequenceSource.NumberSequenceSplit; +import org.apache.flink.api.connector.source.util.ratelimit.RateLimiter; +import org.apache.flink.configuration.CheckpointingOptions; +import org.apache.flink.configuration.Configuration; +import org.apache.flink.configuration.CoreOptions; +import org.apache.flink.configuration.ExternalizedCheckpointRetention; +import org.apache.flink.configuration.RestartStrategyOptions; +import org.apache.flink.connector.base.DeliveryGuarantee; +import org.apache.flink.connector.datagen.source.DataGeneratorSource; +import org.apache.flink.connector.kafka.sink.internal.KafkaCommitter; +import org.apache.flink.connector.kafka.sink.internal.TransactionalIdFactory; +import org.apache.flink.connector.kafka.testutils.KafkaUtil; +import org.apache.flink.connector.kafka.testutils.TestKafkaContainer; +import org.apache.flink.connector.kafka.util.AdminUtils; +import org.apache.flink.core.execution.JobClient; +import org.apache.flink.core.memory.DataInputView; +import org.apache.flink.core.memory.DataOutputView; +import org.apache.flink.runtime.minicluster.MiniCluster; +import org.apache.flink.runtime.state.FunctionInitializationContext; +import org.apache.flink.runtime.state.FunctionSnapshotContext; +import org.apache.flink.runtime.testutils.MiniClusterResourceConfiguration; +import org.apache.flink.streaming.api.checkpoint.CheckpointedFunction; +import org.apache.flink.streaming.api.environment.StreamExecutionEnvironment; +import org.apache.flink.test.junit5.InjectMiniCluster; +import org.apache.flink.test.junit5.MiniClusterExtension; +import org.apache.flink.testutils.junit.SharedObjectsExtension; +import org.apache.flink.testutils.junit.SharedReference; +import org.apache.flink.util.IOUtils; + +import org.apache.kafka.clients.admin.AdminClient; +import org.apache.kafka.clients.admin.TransactionListing; +import org.apache.kafka.clients.consumer.ConsumerRecord; +import org.apache.kafka.clients.consumer.KafkaConsumer; +import org.apache.kafka.common.TopicPartition; +import org.apache.kafka.common.serialization.ByteArrayDeserializer; +import org.junit.jupiter.api.AfterEach; +import org.junit.jupiter.api.Test; +import org.junit.jupiter.api.extension.RegisterExtension; +import org.junit.jupiter.api.io.TempDir; +import org.testcontainers.junit.jupiter.Container; +import org.testcontainers.junit.jupiter.Testcontainers; + +import javax.annotation.Nullable; + +import java.io.IOException; +import java.nio.ByteBuffer; +import java.nio.file.Path; +import java.time.Duration; +import java.util.ArrayList; +import java.util.Collections; +import java.util.List; +import java.util.Properties; +import java.util.UUID; +import java.util.concurrent.BlockingQueue; +import java.util.concurrent.CompletableFuture; +import java.util.concurrent.CompletionStage; +import java.util.concurrent.CountDownLatch; +import java.util.concurrent.ExecutionException; +import java.util.concurrent.LinkedBlockingQueue; +import java.util.concurrent.TimeUnit; +import java.util.concurrent.atomic.AtomicLong; +import java.util.stream.Collectors; + +import static org.apache.flink.configuration.StateRecoveryOptions.SAVEPOINT_PATH; +import static org.assertj.core.api.Assertions.assertThat; + +/** + * Exercises transactional id reuse across checkpoint recovery with a real sink pipeline. + * + * <p>C1 completes and commits its transaction. C2's asynchronous snapshot is blocked rather than + * failed so processing can continue through C3, which precommits a transaction reusing C1's + * transactional id, while C1 remains the latest completed checkpoint. The job is then cancelled and + * restored from C1 with the same transactional id prefix and operator identities. + * + * <p>This exercises the recovery fencing scenario described in {@link + * KafkaCommitter#logFencedRequest}. The restored job must replay the uncheckpointed records and Review Comment: I switched to `@link` because, with `@code`, IntelliJ treated the method name as plain text: I couldn’t navigate to it via hotkeys/mouse. My intention was to make the reference navigable. It is convenient if people read java docs "manually". Maybe a little bit out of dated approach in AI era though :-) linking to KafkaCommitter#commit sounds like a good alternative, agree, will fix it in a hotfix commit. -- 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]
