lbradstreet commented on a change in pull request #9008: URL: https://github.com/apache/kafka/pull/9008#discussion_r455518434
########## File path: jmh-benchmarks/src/main/java/org/apache/kafka/jmh/common/FetchRequestBenchmark.java ########## @@ -0,0 +1,93 @@ +/* + * 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.jmh.common; + +import org.apache.kafka.common.TopicPartition; +import org.apache.kafka.common.network.Send; +import org.apache.kafka.common.protocol.ApiKeys; +import org.apache.kafka.common.requests.ByteBufferChannel; +import org.apache.kafka.common.requests.FetchRequest; +import org.apache.kafka.common.requests.RequestHeader; +import org.openjdk.jmh.annotations.Benchmark; +import org.openjdk.jmh.annotations.BenchmarkMode; +import org.openjdk.jmh.annotations.Fork; +import org.openjdk.jmh.annotations.Level; +import org.openjdk.jmh.annotations.Measurement; +import org.openjdk.jmh.annotations.Mode; +import org.openjdk.jmh.annotations.OutputTimeUnit; +import org.openjdk.jmh.annotations.Param; +import org.openjdk.jmh.annotations.Scope; +import org.openjdk.jmh.annotations.Setup; +import org.openjdk.jmh.annotations.State; +import org.openjdk.jmh.annotations.Warmup; + +import java.io.IOException; +import java.util.HashMap; +import java.util.Map; +import java.util.Optional; +import java.util.concurrent.TimeUnit; + +@State(Scope.Benchmark) +@Fork(value = 1) +@Warmup(iterations = 5) +@Measurement(iterations = 15) +@BenchmarkMode(Mode.AverageTime) +@OutputTimeUnit(TimeUnit.NANOSECONDS) +public class FetchRequestBenchmark { + @Param({"1000"}) + private int topicCount; + + @Param({"20"}) + private int partitionCount; + + Map<TopicPartition, FetchRequest.PartitionData> fetchData; + + RequestHeader header; + + FetchRequest request; + + + @Setup(Level.Trial) + public void setup() { + this.fetchData = new HashMap<>(); + for (int topicIdx = 0; topicIdx < topicCount; topicIdx++) { + for (int partitionId = 0; partitionId < partitionCount; partitionId++) { + FetchRequest.PartitionData partitionData = new FetchRequest.PartitionData( + 0, 0, 4096, Optional.empty()); + fetchData.put(new TopicPartition(String.format("topic-%04d", topicIdx), partitionId), partitionData); + } + } + + this.header = new RequestHeader(ApiKeys.FETCH, ApiKeys.FETCH.latestVersion(), "jmh-benchmark", 100); + this.request = FetchRequest.Builder.forConsumer(0, 0, fetchData).build(ApiKeys.FETCH.latestVersion()); Review comment: Changing our hashCode method massively improves the benchmark times so I think the current benchmark results aren't really representative. ``` --- a/clients/src/main/java/org/apache/kafka/common/TopicPartition.java +++ b/clients/src/main/java/org/apache/kafka/common/TopicPartition.java @@ -46,10 +46,7 @@ public final class TopicPartition implements Serializable { public int hashCode() { if (hash != 0) return hash; - final int prime = 31; - int result = 1; - result = prime * result + partition; - result = prime * result + Objects.hashCode(topic); + int result = Objects.hash(topic, partition); this.hash = result; return result; } ``` Edit: it looks like the main difference here is ordering by topic and then partition which seems to avoid the collisions for this reasonably pathological case. Maybe we can just change the test case. ---------------------------------------------------------------- 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