[GitHub] [kafka] wcarlson5 commented on a change in pull request #10634: KAFKA-12754: Improve endOffsets for TaskMetadata
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 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
[GitHub] [kafka] wcarlson5 commented on a change in pull request #10634: KAFKA-12754: Improve endOffsets for TaskMetadata
wcarlson5 commented on a change in pull request #10634:
URL: https://github.com/apache/kafka/pull/10634#discussion_r629609542
##
File path:
streams/src/main/java/org/apache/kafka/streams/processor/internals/StreamThread.java
##
@@ -900,6 +902,14 @@ private long pollPhase() {
final int numRecords = records.count();
+for (final TopicPartition topicPartition: records.partitions()) {
+records
+.records(topicPartition)
+.stream()
+.max(Comparator.comparing(ConsumerRecord::offset))
+.ifPresent(t ->
taskManager.updateTaskEndMetadata(topicPartition, t.offset()));
Review comment:
It was intended to be the highest offset that the client knows is in the
topic. In order to make that the case I am looking the most recent pull now.
I will add the java docs to the TaskMetadata getters
--
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
[GitHub] [kafka] wcarlson5 commented on a change in pull request #10634: KAFKA-12754: Improve endOffsets for TaskMetadata
wcarlson5 commented on a change in pull request #10634:
URL: https://github.com/apache/kafka/pull/10634#discussion_r629604506
##
File path:
streams/src/main/java/org/apache/kafka/streams/processor/internals/TaskManager.java
##
@@ -1162,6 +1162,15 @@ private void updateTaskMetadata(final
Map all
}
}
+public void updateTaskEndMetadata(final TopicPartition topicPartition,
final Long offset) {
+for (final Task task: tasks.activeTasks()) {
Review comment:
Thanks for pointing that out. I think I can fix a lot of these sort of
methods that way
--
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
[GitHub] [kafka] wcarlson5 commented on a change in pull request #10634: KAFKA-12754: Improve endOffsets for TaskMetadata
wcarlson5 commented on a change in pull request #10634:
URL: https://github.com/apache/kafka/pull/10634#discussion_r629603915
##
File path:
streams/src/main/java/org/apache/kafka/streams/processor/internals/StandbyTask.java
##
@@ -302,6 +302,11 @@ public void updateCommittedOffsets(final TopicPartition
topicPartition, final Lo
}
+@Override
+public void updateEndOffsets(final TopicPartition topicPartition, final
Long offset) {
+
Review comment:
I agree
--
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
[GitHub] [kafka] wcarlson5 commented on a change in pull request #10634: KAFKA-12754: Improve endOffsets for TaskMetadata
wcarlson5 commented on a change in pull request #10634:
URL: https://github.com/apache/kafka/pull/10634#discussion_r629599232
##
File path:
streams/src/main/java/org/apache/kafka/streams/processor/internals/StreamTask.java
##
@@ -1193,6 +1196,11 @@ public void updateCommittedOffsets(final TopicPartition
topicPartition, final Lo
committedOffsets.put(topicPartition, offset);
}
+@Override
+public void updateEndOffsets(final TopicPartition topicPartition, final
Long offset) {
+highWatermark.put(topicPartition, offset);
Review comment:
StreamThread#updateThreadMetadata does not actually update the map what
it does is link a object reference to the map in the Task to the TaskMetadata.
This makes it so that whenever the TaskMetadata is fetched it has the most up
to date maps. For that to matter we need to update the map more frequently
--
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
[GitHub] [kafka] wcarlson5 commented on a change in pull request #10634: KAFKA-12754: Improve endOffsets for TaskMetadata
wcarlson5 commented on a change in pull request #10634:
URL: https://github.com/apache/kafka/pull/10634#discussion_r629595406
##
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 = "";
+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 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() {
+
[GitHub] [kafka] wcarlson5 commented on a change in pull request #10634: KAFKA-12754: Improve endOffsets for TaskMetadata
wcarlson5 commented on a change in pull request #10634:
URL: https://github.com/apache/kafka/pull/10634#discussion_r629592700
##
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 = "";
+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);
Review comment:
process makes more sense to me, because the flag controls the processing
as well
--
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
