ableegoldman commented on a change in pull request #9615:
URL: https://github.com/apache/kafka/pull/9615#discussion_r533878767
##########
File path: streams/src/main/java/org/apache/kafka/streams/KafkaStreams.java
##########
@@ -870,43 +899,73 @@ private KafkaStreams(final InternalTopologyBuilder
internalTopologyBuilder,
cacheSizePerThread,
stateDirectory,
delegatingStateRestoreListener,
- i + 1,
+ threadIdx,
KafkaStreams.this::closeToError,
- this::defaultStreamsUncaughtExceptionHandler
- );
- threads.add(streamThread);
- threadState.put(streamThread.getId(), streamThread.state());
- storeProviders.add(new
StreamThreadStateStoreProvider(streamThread));
- }
+ streamsUncaughtExceptionHandler
+ );
+ streamThread.setStateListener(streamStateListener);
+ threads.add(streamThread);
+ threadState.put(streamThread.getId(), streamThread.state());
+ storeProviders.add(new StreamThreadStateStoreProvider(streamThread));
+ return streamThread;
+ }
- ClientMetrics.addNumAliveStreamThreadMetric(streamsMetrics,
(metricsConfig, now) ->
- Math.toIntExact(threads.stream().filter(thread ->
thread.state().isAlive()).count()));
+ /**
+ * Adds and starts a stream thread in addition to the stream threads that
are already running in this
+ * Kafka Streams client.
+ * <p>
+ * Since the number of stream threads increases, the sizes of the caches
in the new stream thread
+ * and the existing stream threads are adapted so that the sum of the
cache sizes over all stream
+ * threads does not exceed the total cache size specified in configuration
+ * {@link StreamsConfig#CACHE_MAX_BYTES_BUFFERING_CONFIG}.
+ * <p>
+ * Stream threads can only be added if this Kafka Streams client is in
state RUNNING or REBALANCING.
+ *
+ * @return name of the added stream thread or empty if a new stream thread
could not be added
+ */
+ public Optional<String> addStreamThread() {
+ if (isRunningOrRebalancing()) {
+ final int threadIdx = getNextThreadIndex();
+ final long cacheSizePerThread =
getCacheSizePerThread(threads.size() + 1);
+ resizeThreadCache(cacheSizePerThread);
+ final StreamThread streamThread =
createStreamThread(cacheSizePerThread, threadIdx);
+ synchronized (stateLock) {
+ if (isRunningOrRebalancing()) {
+ streamThread.start();
+ return Optional.of(streamThread.getName());
+ } else {
+ threads.remove(streamThread);
Review comment:
We should also shutdown the thread if it doesn't get started, otherwise
me may leak (consumer or producer) clients. But I'm actually not sure why we
don't just do everything (resize cache, create thread) inside the synchronized
block? I'm guessing it would deadlock due to locking on the `statelock` but
can't we just synchronize on something else that wouldn't interfere with the
StreamThread creation?
##########
File path:
streams/src/test/java/org/apache/kafka/streams/integration/AdjustStreamThreadCountTest.java
##########
@@ -0,0 +1,108 @@
+/*
+ * 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.serialization.Serdes;
+import org.apache.kafka.streams.KafkaStreams;
+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.processor.ThreadMetadata;
+import org.apache.kafka.test.IntegrationTest;
+import org.apache.kafka.test.StreamsTestUtils;
+import org.apache.kafka.test.TestUtils;
+import org.hamcrest.CoreMatchers;
+import org.junit.After;
+import org.junit.Before;
+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.io.IOException;
+import java.util.Optional;
+import java.util.Properties;
+
+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 AdjustStreamThreadCountTest {
+
+ @ClassRule
+ public static final EmbeddedKafkaCluster CLUSTER = new
EmbeddedKafkaCluster(1);
+
+ @Rule
+ public TestName testName = new TestName();
+
+ private static String inputTopic;
+ private static StreamsBuilder builder;
+ private static Properties properties;
+ private static String appId = "";
+
+ @Before
+ public void setup() {
+ final String testId = safeUniqueTestName(getClass(), testName);
+ appId = "appId_" + testId;
+ inputTopic = "input" + testId;
+ IntegrationTestUtils.cleanStateBeforeTest(CLUSTER, inputTopic);
+
+ builder = new StreamsBuilder();
+ builder.stream(inputTopic);
+
+ 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)
+ )
+ );
+ }
+
+ @After
+ public void teardown() throws IOException {
+ purgeLocalStreamsState(properties);
+ }
+
+ @Test
+ public void shouldAddStreamThread() throws Exception {
+ try (final KafkaStreams kafkaStreams = new
KafkaStreams(builder.build(), properties)) {
+
StreamsTestUtils.startKafkaStreamsAndWaitForRunningState(kafkaStreams);
+ final int oldThreadCount =
kafkaStreams.localThreadsMetadata().size();
+
+ final Optional<String> name = kafkaStreams.addStreamThread();
+
+ assertThat(name, CoreMatchers.not(Optional.empty()));
+ TestUtils.waitForCondition(
+ () -> kafkaStreams.localThreadsMetadata().stream().sequential()
+ .map(ThreadMetadata::threadName).anyMatch(t ->
t.equals(name.orElse(""))),
+ "Wait for the thread to be added"
+ );
+ assertThat(kafkaStreams.localThreadsMetadata().size(),
equalTo(oldThreadCount + 1));
+ }
Review comment:
Can we also assert that the state gets to `RUNNING` after the new thread
has joined
----------------------------------------------------------------
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
