C0urante commented on code in PR #13776: URL: https://github.com/apache/kafka/pull/13776#discussion_r1212118898
########## jmh-benchmarks/src/main/java/org/apache/kafka/jmh/connect/ReplaceFieldBenchmark.java: ########## @@ -0,0 +1,78 @@ +/* + * 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.connect; + +import org.apache.kafka.connect.source.SourceRecord; +import org.apache.kafka.connect.transforms.ReplaceField; +import org.openjdk.jmh.annotations.Benchmark; +import org.openjdk.jmh.annotations.BenchmarkMode; +import org.openjdk.jmh.annotations.Fork; +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.util.HashMap; +import java.util.Map; +import java.util.concurrent.TimeUnit; +import java.util.stream.Collectors; +import java.util.stream.IntStream; + + +/** + * This benchmark tests the performance of the {@link ReplaceField} {@link org.apache.kafka.connect.transforms.Transformation SMT} + * when configured with a large number of include and exclude fields and applied on a {@link SourceRecord} containing a similarly + * large number of fields. + */ +@State(Scope.Benchmark) +@Fork(value = 1) +@Warmup(iterations = 3) +@Measurement(iterations = 5) +@BenchmarkMode(Mode.AverageTime) +@OutputTimeUnit(TimeUnit.NANOSECONDS) +public class ReplaceFieldBenchmark { + + @Param({"100", "1000", "10000"}) + private int fieldCount; + private ReplaceField<SourceRecord> replaceFieldSmt; + private SourceRecord record; + + @Setup + public void setup() { + this.replaceFieldSmt = new ReplaceField.Value<>(); + Map<String, String> replaceFieldConfigs = new HashMap<>(); + replaceFieldConfigs.put("exclude", + IntStream.range(0, fieldCount).filter(x -> (x & 1) == 0).mapToObj(x -> "Field-" + x).collect(Collectors.joining(","))); + replaceFieldConfigs.put("include", + IntStream.range(0, fieldCount).filter(x -> (x & 1) == 1).mapToObj(x -> "Field-" + x).collect(Collectors.joining(","))); Review Comment: Object lookup in a hash set usually involves both computing its hash and performing an equality check, since multiple objects may occupy the same bucket. Lookup in a single-element list may theoretically be faster if it only involves a single equality check. I think it's worth including in the benchmark for a few reasons: - Saves people the trouble of having to look up this PR discussion - Covers a more-common case (it's much more likely that someone configures this SMT with 1 field than 10,000) - Guards against performance regressions if we change things in the future But if it's too much work then we can merge as-is. @yashmayya let me know what your decision is. -- 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. To unsubscribe, e-mail: jira-unsubscr...@kafka.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org
