vvcephei commented on a change in pull request #8818: URL: https://github.com/apache/kafka/pull/8818#discussion_r438421521
########## File path: streams/src/test/java/org/apache/kafka/streams/integration/HighAvailabilityTaskAssignorIntegrationTest.java ########## @@ -0,0 +1,266 @@ +/* + * 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.clients.consumer.Consumer; +import org.apache.kafka.clients.consumer.ConsumerConfig; +import org.apache.kafka.clients.consumer.KafkaConsumer; +import org.apache.kafka.clients.producer.KafkaProducer; +import org.apache.kafka.clients.producer.Producer; +import org.apache.kafka.clients.producer.ProducerConfig; +import org.apache.kafka.clients.producer.ProducerRecord; +import org.apache.kafka.common.TopicPartition; +import org.apache.kafka.common.serialization.StringDeserializer; +import org.apache.kafka.common.serialization.StringSerializer; +import org.apache.kafka.common.utils.Bytes; +import org.apache.kafka.streams.KafkaStreams; +import org.apache.kafka.streams.StreamsBuilder; +import org.apache.kafka.streams.StreamsConfig; +import org.apache.kafka.streams.Topology; +import org.apache.kafka.streams.integration.utils.EmbeddedKafkaCluster; +import org.apache.kafka.streams.integration.utils.IntegrationTestUtils; +import org.apache.kafka.streams.kstream.Materialized; +import org.apache.kafka.streams.processor.StateRestoreListener; +import org.apache.kafka.streams.processor.internals.assignment.AssignorConfiguration.AssignmentListener; +import org.apache.kafka.streams.processor.internals.assignment.HighAvailabilityTaskAssignor; +import org.apache.kafka.streams.state.KeyValueStore; +import org.apache.kafka.streams.state.Stores; +import org.apache.kafka.test.IntegrationTest; +import org.apache.kafka.test.TestUtils; +import org.junit.ClassRule; +import org.junit.Rule; +import org.junit.Test; +import org.junit.experimental.categories.Category; +import org.junit.rules.TestName; + +import java.util.Collection; +import java.util.Properties; +import java.util.Set; +import java.util.concurrent.CountDownLatch; +import java.util.concurrent.atomic.AtomicBoolean; +import java.util.concurrent.atomic.AtomicInteger; +import java.util.concurrent.atomic.AtomicLong; +import java.util.concurrent.locks.ReentrantLock; +import java.util.function.Function; + +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.common.utils.Utils.mkProperties; +import static org.apache.kafka.common.utils.Utils.mkSet; +import static org.apache.kafka.streams.integration.utils.IntegrationTestUtils.safeUniqueTestName; +import static org.hamcrest.MatcherAssert.assertThat; +import static org.hamcrest.Matchers.is; + +@Category(IntegrationTest.class) +public class HighAvailabilityTaskAssignorIntegrationTest { + @ClassRule + public static final EmbeddedKafkaCluster CLUSTER = new EmbeddedKafkaCluster(1); + + @Rule + public TestName testName = new TestName(); + + @Test + public void shouldScaleOutWithWarmupTasksAndInMemoryStores() throws InterruptedException { + // NB: this test takes at least a minute to run, because it needs a probing rebalance, and the minimum + // value is one minute + shouldScaleOutWithWarmupTasks(storeName -> Materialized.as(Stores.inMemoryKeyValueStore(storeName))); + } + + @Test + public void shouldScaleOutWithWarmupTasksAndPersistentStores() throws InterruptedException { + // NB: this test takes at least a minute to run, because it needs a probing rebalance, and the minimum + // value is one minute + shouldScaleOutWithWarmupTasks(storeName -> Materialized.as(Stores.persistentKeyValueStore(storeName))); + } + + private void shouldScaleOutWithWarmupTasks(final Function<String, Materialized<Object, Object, KeyValueStore<Bytes, byte[]>>> materializedFunction) throws InterruptedException { + final String testId = safeUniqueTestName(getClass(), testName); + final String appId = "appId_" + System.currentTimeMillis() + "_" + testId; + final String inputTopic = "input" + testId; + final String storeName = "store" + testId; + final String storeChangelog = appId + "-store" + testId + "-changelog"; + final Set<TopicPartition> changelogTopicPartitions = mkSet( + new TopicPartition(storeChangelog, 0), + new TopicPartition(storeChangelog, 1) + ); + + IntegrationTestUtils.cleanStateBeforeTest(CLUSTER, 2, inputTopic, storeChangelog); + + final ReentrantLock assignmentLock = new ReentrantLock(); + final AtomicInteger assignmentsCompleted = new AtomicInteger(0); + final AtomicBoolean assignmentStable = new AtomicBoolean(false); + final AssignmentListener assignmentListener = + stable -> { + assignmentLock.lock(); + try { + assignmentsCompleted.incrementAndGet(); + assignmentStable.set(stable); + } finally { + assignmentLock.unlock(); + } + }; + + final StreamsBuilder builder = new StreamsBuilder(); + builder.table(inputTopic, materializedFunction.apply(storeName)); + final Topology topology = builder.build(); + + final Properties producerProperties = mkProperties( + mkMap( + mkEntry(ProducerConfig.BOOTSTRAP_SERVERS_CONFIG, CLUSTER.bootstrapServers()), + mkEntry(ProducerConfig.ACKS_CONFIG, "all"), + mkEntry(ProducerConfig.RETRIES_CONFIG, "0"), Review comment: I just copied this config, maybe this particular setting is not necessary. ---------------------------------------------------------------- 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
