chore: add jmh benchmarks module

Include a new module to host JMH benchmarks from TS plugin components.

.gitignore

@@ -9,3 +9,5 @@ build/
 rpm/
 rpmbuild/
 *.sh
+# ignore benchmark outputs
+io.aiven.kafka.tieredstorage*/

Makefile

@@ -63,3 +63,8 @@ docker_image: build
 .PHONY: docker_push
 docker_push:
 	docker push $(IMAGE_TAG)
+
+# Prepare kernel to capture CPU events
+async_profiler_cpu_kernel-prep:
+	sudo sh -c 'echo 1 >/proc/sys/kernel/perf_event_paranoid'
+	sudo sh -c 'echo 0 >/proc/sys/kernel/kptr_restrict'

benchmarks/README.md

@@ -0,0 +1,121 @@
+### Benchmarks module
+
+> Borrowed from https://github.com/apache/kafka/blob/trunk/jmh-benchmarks
+
+This module contains benchmarks written using [JMH](https://openjdk.java.net/projects/code-tools/jmh/) from OpenJDK.
+
+### Running benchmarks
+
+If you want to set specific JMH flags or only run certain benchmarks, passing arguments via
+gradle tasks is cumbersome. These are simplified by the provided `jmh.sh` script.
+
+The default behavior is to run all benchmarks:
+
+    ./benchmarks/jmh.sh
+
+Pass a pattern or name after the command to select the benchmarks:
+
+    ./benchmarks/jmh.sh TransformBench
+
+Check which benchmarks that match the provided pattern:
+
+    ./benchmarks/jmh.sh -l TransformBench
+
+Run a specific test and override the number of forks, iterations and warm-up iteration to `2`:
+
+    ./benchmarks/jmh.sh -f 2 -i 2 -wi 2 TransformBench
+
+Run a specific test with async and GC profilers on Linux and flame graph output:
+
+    ./benchmarks/jmh.sh -prof gc -prof async:libPath=/path/to/libasyncProfiler.so\;output=flamegraph TransformBench
+
+The following sections cover async profiler and GC profilers in more detail.
+
+### Using JMH with async profiler
+
+It's good practice to check profiler output for micro-benchmarks in order to verify that they represent the expected
+application behavior and measure what you expect to measure. Some example pitfalls include the use of expensive mocks
+or accidental inclusion of test setup code in the benchmarked code. JMH includes
+[async-profiler](https://github.com/jvm-profiling-tools/async-profiler) integration that makes this easy:
+
+    ./benchmarks/jmh.sh -prof async:libPath=/path/to/libasyncProfiler.so
+
+or if having async-profiler on environment variable `export LD_LIBRARY_PATH=/opt/async-profiler-2.9-linux-x64/build/`
+
+    ./benchmarks/jmh.sh -prof async
+
+With flame graph output (the semicolon is escaped to ensure it is not treated as a command separator):
+
+    ./benchmarks/jmh.sh -prof async:libPath=/path/to/libasyncProfiler.so\;output=flamegraph
+
+Simultaneous cpu, allocation and lock profiling with async profiler 2.0 and jfr output (the semicolon is
+escaped to ensure it is not treated as a command separator):
+
+    ./benchmarks/jmh.sh -prof async:libPath=/path/to/libasyncProfiler.so\;output=jfr\;alloc\;lock TransformBench
+
+A number of arguments can be passed to configure async profiler, run the following for a description:
+
+    ./benchmarks/jmh.sh -prof async:help
+
+### Using JMH GC profiler
+
+It's good practice to run your benchmark with `-prof gc` to measure its allocation rate:
+
+    ./benchmarks/jmh.sh -prof gc
+
+Of particular importance is the `norm` alloc rates, which measure the allocations per operation rather than allocations
+per second which can increase when you have make your code faster.
+
+### Running JMH outside gradle
+
+The JMH benchmarks can be run outside gradle as you would with any executable jar file:
+
+    java -jar ./benchmarks/build/libs/kafka-benchmarks-*.jar -f2 TransformBench
+
+### Gradle Tasks
+
+If no benchmark mode is specified, the default is used which is throughput. It is assumed that users run
+the gradle tasks with `./gradlew` from the root of the Kafka project.
+
+* `benchmarks:shadowJar` - creates the uber jar required to run the benchmarks.
+
+* `benchmarks:jmh` - runs the `clean` and `shadowJar` tasks followed by all the benchmarks.
+
+### JMH Options
+Some common JMH options are:
+
+```text
+
+   -e <regexp+>                Benchmarks to exclude from the run. 
+
+   -f <int>                    How many times to fork a single benchmark. Use 0 to 
+                               disable forking altogether. Warning: disabling 
+                               forking may have detrimental impact on benchmark 
+                               and infrastructure reliability, you might want 
+                               to use different warmup mode instead.
+
+   -i <int>                    Number of measurement iterations to do. Measurement
+                               iterations are counted towards the benchmark score.
+                               (default: 1 for SingleShotTime, and 5 for all other
+                               modes)
+
+   -l                          List the benchmarks that match a filter, and exit.
+
+   -lprof                      List profilers, and exit.
+
+   -o <filename>               Redirect human-readable output to a given file. 
+
+   -prof <profiler>            Use profilers to collect additional benchmark data. 
+                               Some profilers are not available on all JVMs and/or 
+                               all OSes. Please see the list of available profilers 
+                               with -lprof.
+
+   -v <mode>                   Verbosity mode. Available modes are: [SILENT, NORMAL,
+                               EXTRA]
+
+   -wi <int>                   Number of warmup iterations to do. Warmup iterations
+                               are not counted towards the benchmark score. (default:
+                               0 for SingleShotTime, and 5 for all other modes)
+```
+
+To view all options run jmh with the -h flag. 

benchmarks/build.gradle

@@ -0,0 +1,64 @@
+/*
+ * Copyright 2021 Aiven Oy
+ *
+ * Licensed 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.
+ */
+
+// JMH execution borrowed from https://github.com/apache/kafka/blob/trunk/jmh-benchmarks
+
+
+apply plugin: 'com.github.johnrengelman.shadow'
+
+shadowJar {
+    archiveBaseName = 'kafka-ts-benchmarks'
+}
+
+ext {
+    jmhVersion = "1.36"
+}
+
+dependencies {
+    implementation project(':core')
+    implementation group: "org.apache.kafka", name: "kafka-storage-api", version: kafkaVersion
+    implementation group: "org.apache.kafka", name: "kafka-clients", version: kafkaVersion
+
+    implementation "org.openjdk.jmh:jmh-core:$jmhVersion"
+    implementation "org.openjdk.jmh:jmh-core-benchmarks:$jmhVersion"
+    annotationProcessor "org.openjdk.jmh:jmh-generator-annprocess:$jmhVersion"
+
+    implementation "org.slf4j:slf4j-log4j12:1.7.36"
+}
+
+jar {
+    manifest {
+        attributes "Main-Class": "org.openjdk.jmh.Main"
+    }
+}
+
+tasks.register('jmh', JavaExec) {
+    dependsOn ':benchmarks:clean'
+    dependsOn ':benchmarks:shadowJar'
+
+    mainClass = "-jar"
+
+    doFirst {
+        if (System.getProperty("jmhArgs")) {
+            args System.getProperty("jmhArgs").split(' ')
+        }
+        args = [shadowJar.getArchiveFile(), *args]
+    }
+}
+
+javadoc {
+    enabled = false
+}

benchmarks/src/main/resources/log4j.properties

@@ -0,0 +1,21 @@
+#
+# Copyright 2023 Aiven Oy
+#
+# Licensed 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.
+#
+
+log4j.rootLogger=WARN, stdout
+
+log4j.appender.stdout=org.apache.log4j.ConsoleAppender
+log4j.appender.stdout.layout=org.apache.log4j.PatternLayout
+log4j.appender.stdout.layout.ConversionPattern=[%d] %p %m (%c:%L)%n

build.gradle

@@ -24,6 +24,7 @@ plugins {
     id 'info.solidsoft.pitest' version '1.15.0' apply false
     id "java-library"
     id "distribution"
+    id 'com.github.johnrengelman.shadow' version '8.1.1' apply false
 }
 
 apply plugin: 'info.solidsoft.pitest.aggregator'

checkstyle/suppressions.xml

@@ -21,6 +21,7 @@
     <suppress checks="AbbreviationAsWordInName" files="DataKeyAndAADEqualsTest"/>
     <suppress checks="ClassDataAbstractionCoupling" files=".*Test\.java"/>
     <suppress checks="ClassFanOutComplexity" files=".*Test\.java"/>
+    <suppress checks="ClassFanOutComplexity" files=".*Bench\.java"/>
     <suppress checks="ClassFanOutComplexity" files="RemoteStorageManager.java"/>
     <suppress checks="ClassFanOutComplexity" files="ChunkCache.java"/>
     <suppress checks="ClassFanOutComplexity" files="AzureBlobStorage.java"/>
@@ -30,6 +31,7 @@
     <suppress checks="ClassDataAbstractionCoupling" files="Metrics.java"/>
     <suppress checks="ClassDataAbstractionCoupling" files="MetricCollector.java"/>
     <suppress checks="ClassDataAbstractionCoupling" files="AzureBlobStorage.java"/>
+    <suppress checks="ClassDataAbstractionCoupling" files=".*Bench\.java"/>
     <suppress checks="CyclomaticComplexity" files="MetricCollector.java"/>
     <suppress checks="CyclomaticComplexity" files="SegmentIndexesV1Builder.java"/>
     <suppress checks="CyclomaticComplexity" files="SingleBrokerTest.java"/>

settings.gradle

@@ -24,3 +24,4 @@ include 'storage:gcs'
 include 'storage:s3'
 include 'e2e'
 include 'commons'
+include 'benchmarks'