wcarlson5 commented on a change in pull request #10634: URL: https://github.com/apache/kafka/pull/10634#discussion_r632637377
########## File path: streams/src/test/java/org/apache/kafka/streams/integration/TaskMetadataIntegrationTest.java ########## @@ -0,0 +1,200 @@ +/* + * 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.kafka.streams.integration; + +import org.apache.kafka.common.TopicPartition; +import org.apache.kafka.common.serialization.Serdes; +import org.apache.kafka.common.serialization.StringSerializer; +import org.apache.kafka.streams.KafkaStreams; +import org.apache.kafka.streams.KeyValue; +import org.apache.kafka.streams.StreamsBuilder; +import org.apache.kafka.streams.StreamsConfig; +import org.apache.kafka.streams.integration.utils.EmbeddedKafkaCluster; +import org.apache.kafka.streams.integration.utils.IntegrationTestUtils; +import org.apache.kafka.streams.kstream.KStream; +import org.apache.kafka.streams.processor.AbstractProcessor; +import org.apache.kafka.streams.processor.TaskMetadata; +import org.apache.kafka.test.IntegrationTest; +import org.apache.kafka.test.TestUtils; +import org.junit.After; +import org.junit.AfterClass; +import org.junit.Before; +import org.junit.BeforeClass; +import org.junit.Rule; +import org.junit.Test; +import org.junit.experimental.categories.Category; +import org.junit.rules.TestName; + +import java.io.IOException; +import java.time.Duration; +import java.util.Collections; +import java.util.List; +import java.util.Properties; +import java.util.concurrent.atomic.AtomicBoolean; +import java.util.stream.Collectors; + +import static org.apache.kafka.common.utils.Utils.mkEntry; +import static org.apache.kafka.common.utils.Utils.mkMap; +import static org.apache.kafka.common.utils.Utils.mkObjectProperties; +import static org.apache.kafka.streams.integration.utils.IntegrationTestUtils.purgeLocalStreamsState; +import static org.apache.kafka.streams.integration.utils.IntegrationTestUtils.safeUniqueTestName; +import static org.hamcrest.CoreMatchers.equalTo; +import static org.hamcrest.MatcherAssert.assertThat; + +@Category(IntegrationTest.class) +public class TaskMetadataIntegrationTest { + + public static final EmbeddedKafkaCluster CLUSTER = new EmbeddedKafkaCluster(1, new Properties(), 0L, 0L); + + @BeforeClass + public static void startCluster() throws IOException { + CLUSTER.start(); + } + + @AfterClass + public static void closeCluster() { + CLUSTER.stop(); + } + public static final Duration DEFAULT_DURATION = Duration.ofSeconds(30); + + @Rule + public TestName testName = new TestName(); + + private String inputTopic; + private static StreamsBuilder builder; + private static Properties properties; + private static String appId = "TaskMetadataTest_"; + private AtomicBoolean process; + private AtomicBoolean commit; + + @Before + public void setup() { + final String testId = safeUniqueTestName(getClass(), testName); + appId = appId + testId; + inputTopic = "input" + testId; + IntegrationTestUtils.cleanStateBeforeTest(CLUSTER, inputTopic); + + builder = new StreamsBuilder(); + + process = new AtomicBoolean(true); + commit = new AtomicBoolean(true); + + final KStream<String, String> stream = builder.stream(inputTopic); + stream.process(PauseProcessor::new); + + properties = mkObjectProperties( + mkMap( + mkEntry(StreamsConfig.BOOTSTRAP_SERVERS_CONFIG, CLUSTER.bootstrapServers()), + mkEntry(StreamsConfig.APPLICATION_ID_CONFIG, appId), + mkEntry(StreamsConfig.STATE_DIR_CONFIG, TestUtils.tempDirectory().getPath()), + mkEntry(StreamsConfig.NUM_STREAM_THREADS_CONFIG, 2), + mkEntry(StreamsConfig.DEFAULT_KEY_SERDE_CLASS_CONFIG, Serdes.StringSerde.class), + mkEntry(StreamsConfig.DEFAULT_VALUE_SERDE_CLASS_CONFIG, Serdes.StringSerde.class), + mkEntry(StreamsConfig.COMMIT_INTERVAL_MS_CONFIG, 1L) + ) + ); + } + + @Test + public void shouldReportCorrectCommittedOffsetInformation() { + try (final KafkaStreams kafkaStreams = new KafkaStreams(builder.build(), properties)) { + IntegrationTestUtils.startApplicationAndWaitUntilRunning(Collections.singletonList(kafkaStreams), DEFAULT_DURATION); + final TaskMetadata taskMetadata = getTaskMetadata(kafkaStreams); + assertThat(taskMetadata.committedOffsets().size(), equalTo(1)); + final TopicPartition topicPartition = new TopicPartition(inputTopic, 0); + + produceMessages(0L, inputTopic, "test"); + TestUtils.waitForCondition(() -> !process.get(), "the record was processed"); + TestUtils.waitForCondition(() -> taskMetadata.committedOffsets().get(topicPartition) == 1L, "the record was processed"); + process.set(true); + + produceMessages(0L, inputTopic, "test1"); Review comment: not really, I wrote the process gate first before I wanted to have more than one at a time. I think it makes the consumer have to poll multiple times as it alternates between the pollPhase and processing but I am not sure if that actually improves the test. -- 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. For queries about this service, please contact Infrastructure at: us...@infra.apache.org