// 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.
import org.ajoberstar.grgit.Grgit
import java.nio.charset.StandardCharsets
buildscript {
repositories {
mavenCentral ( )
}
apply from: "$rootDir/gradle/dependencies.gradle"
dependencies {
// For Apache Rat plugin to ignore non-Git files
classpath "org.ajoberstar.grgit:grgit-core:$versions.grgit"
}
}
plugins {
id 'com.diffplug.spotless' version '6.10.0'
id 'com.github.ben-manes.versions' version '0.42.0'
id 'idea'
id 'java-library'
id 'org.owasp.dependencycheck' version '7.1.1'
id 'org.nosphere.apache.rat' version "0.7.1"
id "com.github.spotbugs" version '5.0.9' apply false
id 'org.gradle.test-retry' version '1.4.0' apply false
id 'org.scoverage' version '7.0.0' apply false
id 'com.github.johnrengelman.shadow' version '7.1.2' apply false
id "io.swagger.core.v3.swagger-gradle-plugin" version "2.2.0"
}
spotless {
scala {
target 'streams/**/*.scala'
scalafmt ( "$versions.scalafmt" ) . configFile ( 'checkstyle/.scalafmt.conf' ) . scalaMajorVersion ( versions . baseScala )
licenseHeaderFile 'checkstyle/java.header' , 'package'
}
}
ext {
gradleVersion = versions . gradle
minJavaVersion = "8"
buildVersionFileName = "kafka-version.properties"
MINOR: Update to Gradle 6.5 and tweak build jvm config (#8751)
Gradle 6.5 includes a fix for https://github.com/gradle/gradle/pull/12866, which
affects the performance of Scala compilation.
I profiled the scalac build with async profiler and 54% of the time was on GC
even after the Gradle upgrade (it was more than 60% before), so I switched to
the throughput GC (GC latency is less important for batch builds) and it
was reduced to 38%.
I also centralized the jvm configuration in `build.gradle` and simplified it a bit
by removing the minHeapSize configuration from the test tasks.
On my desktop, the time to execute clean builds with no cached Gradle daemon
was reduced from 127 seconds to 97 seconds. With a cached daemon, it was
reduced from 120 seconds to 88 seconds. The performance regression when
we upgraded to Gradle 6.x was 27 seconds with a cached daemon
(https://github.com/apache/kafka/pull/7677#issuecomment-616271179), so it
should be fixed now.
Gradle 6.4 with no cached daemon:
```
BUILD SUCCESSFUL in 2m 7s
115 actionable tasks: 112 executed, 3 up-to-date
./gradlew clean compileScala compileJava compileTestScala compileTestJava 1.15s user 0.12s system 0% cpu 2:08.06 total
```
Gradle 6.4 with cached daemon:
```
BUILD SUCCESSFUL in 2m 0s
115 actionable tasks: 111 executed, 4 up-to-date
./gradlew clean compileScala compileJava compileTestScala compileTestJava 0.95s user 0.10s system 0% cpu 2:01.42 total
```
Gradle 6.5 with no cached daemon:
```
BUILD SUCCESSFUL in 1m 46s
115 actionable tasks: 111 executed, 4 up-to-date
./gradlew clean compileScala compileJava compileTestScala compileTestJava 1.27s user 0.12s system 1% cpu 1:47.71 total
```
Gradle 6.5 with cached daemon:
```
BUILD SUCCESSFUL in 1m 37s
115 actionable tasks: 111 executed, 4 up-to-date
./gradlew clean compileScala compileJava compileTestScala compileTestJava 1.02s user 0.10s system 1% cpu 1:38.31 total
```
This PR with no cached Gradle daemon:
```
BUILD SUCCESSFUL in 1m 37s
115 actionable tasks: 81 executed, 34 up-to-date
./gradlew clean compileScala compileJava compileTestScala compileTestJava 1.27s user 0.10s system 1% cpu 1:38.70 total
```
This PR with cached Gradle daemon:
```
BUILD SUCCESSFUL in 1m 28s
115 actionable tasks: 111 executed, 4 up-to-date
./gradlew clean compileScala compileJava compileTestScala compileTestJava 1.02s user 0.10s system 1% cpu 1:29.35 total
```
Reviewers: Manikumar Reddy <manikumar.reddy@gmail.com>, Chia-Ping Tsai <chia7712@gmail.com>
5 years ago
defaultMaxHeapSize = "2g"
defaultJvmArgs = [ "-Xss4m" , "-XX:+UseParallelGC" ]
// "JEP 403: Strongly Encapsulate JDK Internals" causes some tests to fail when they try
// to access internals (often via mocking libraries). We use `--add-opens` as a workaround
// for now and we'll fix it properly (where possible) via KAFKA-13275.
if ( JavaVersion . current ( ) . isCompatibleWith ( JavaVersion . VERSION_16 ) )
defaultJvmArgs . addAll (
"--add-opens=java.base/java.io=ALL-UNNAMED" ,
"--add-opens=java.base/java.lang=ALL-UNNAMED" ,
"--add-opens=java.base/java.nio=ALL-UNNAMED" ,
"--add-opens=java.base/java.nio.file=ALL-UNNAMED" ,
"--add-opens=java.base/java.util=ALL-UNNAMED" ,
"--add-opens=java.base/java.util.concurrent=ALL-UNNAMED" ,
"--add-opens=java.base/java.util.regex=ALL-UNNAMED" ,
"--add-opens=java.base/java.util.stream=ALL-UNNAMED" ,
"--add-opens=java.base/java.text=ALL-UNNAMED" ,
"--add-opens=java.base/java.time=ALL-UNNAMED" ,
"--add-opens=java.security.jgss/sun.security.krb5=ALL-UNNAMED"
)
MINOR: Update to Gradle 6.5 and tweak build jvm config (#8751)
Gradle 6.5 includes a fix for https://github.com/gradle/gradle/pull/12866, which
affects the performance of Scala compilation.
I profiled the scalac build with async profiler and 54% of the time was on GC
even after the Gradle upgrade (it was more than 60% before), so I switched to
the throughput GC (GC latency is less important for batch builds) and it
was reduced to 38%.
I also centralized the jvm configuration in `build.gradle` and simplified it a bit
by removing the minHeapSize configuration from the test tasks.
On my desktop, the time to execute clean builds with no cached Gradle daemon
was reduced from 127 seconds to 97 seconds. With a cached daemon, it was
reduced from 120 seconds to 88 seconds. The performance regression when
we upgraded to Gradle 6.x was 27 seconds with a cached daemon
(https://github.com/apache/kafka/pull/7677#issuecomment-616271179), so it
should be fixed now.
Gradle 6.4 with no cached daemon:
```
BUILD SUCCESSFUL in 2m 7s
115 actionable tasks: 112 executed, 3 up-to-date
./gradlew clean compileScala compileJava compileTestScala compileTestJava 1.15s user 0.12s system 0% cpu 2:08.06 total
```
Gradle 6.4 with cached daemon:
```
BUILD SUCCESSFUL in 2m 0s
115 actionable tasks: 111 executed, 4 up-to-date
./gradlew clean compileScala compileJava compileTestScala compileTestJava 0.95s user 0.10s system 0% cpu 2:01.42 total
```
Gradle 6.5 with no cached daemon:
```
BUILD SUCCESSFUL in 1m 46s
115 actionable tasks: 111 executed, 4 up-to-date
./gradlew clean compileScala compileJava compileTestScala compileTestJava 1.27s user 0.12s system 1% cpu 1:47.71 total
```
Gradle 6.5 with cached daemon:
```
BUILD SUCCESSFUL in 1m 37s
115 actionable tasks: 111 executed, 4 up-to-date
./gradlew clean compileScala compileJava compileTestScala compileTestJava 1.02s user 0.10s system 1% cpu 1:38.31 total
```
This PR with no cached Gradle daemon:
```
BUILD SUCCESSFUL in 1m 37s
115 actionable tasks: 81 executed, 34 up-to-date
./gradlew clean compileScala compileJava compileTestScala compileTestJava 1.27s user 0.10s system 1% cpu 1:38.70 total
```
This PR with cached Gradle daemon:
```
BUILD SUCCESSFUL in 1m 28s
115 actionable tasks: 111 executed, 4 up-to-date
./gradlew clean compileScala compileJava compileTestScala compileTestJava 1.02s user 0.10s system 1% cpu 1:29.35 total
```
Reviewers: Manikumar Reddy <manikumar.reddy@gmail.com>, Chia-Ping Tsai <chia7712@gmail.com>
5 years ago
maxTestForks = project . hasProperty ( 'maxParallelForks' ) ? maxParallelForks . toInteger ( ) : Runtime . runtime . availableProcessors ( )
maxScalacThreads = project . hasProperty ( 'maxScalacThreads' ) ? maxScalacThreads . toInteger ( ) :
Math . min ( Runtime . runtime . availableProcessors ( ) , 8 )
userIgnoreFailures = project . hasProperty ( 'ignoreFailures' ) ? ignoreFailures : false
userMaxTestRetries = project . hasProperty ( 'maxTestRetries' ) ? maxTestRetries . toInteger ( ) : 0
userMaxTestRetryFailures = project . hasProperty ( 'maxTestRetryFailures' ) ? maxTestRetryFailures . toInteger ( ) : 0
skipSigning = project . hasProperty ( 'skipSigning' ) & & skipSigning . toBoolean ( )
shouldSign = ! skipSigning & & ! version . endsWith ( "SNAPSHOT" )
mavenUrl = project . hasProperty ( 'mavenUrl' ) ? project . mavenUrl : ''
mavenUsername = project . hasProperty ( 'mavenUsername' ) ? project . mavenUsername : ''
mavenPassword = project . hasProperty ( 'mavenPassword' ) ? project . mavenPassword : ''
userShowStandardStreams = project . hasProperty ( "showStandardStreams" ) ? showStandardStreams : null
userTestLoggingEvents = project . hasProperty ( "testLoggingEvents" ) ? Arrays . asList ( testLoggingEvents . split ( "," ) ) : null
userEnableTestCoverage = project . hasProperty ( "enableTestCoverage" ) ? enableTestCoverage : false
MINOR: Reuse gradle daemon for scala compilation by default (#12280)
The time time to compile was reduced from 5.3 seconds to 0.9 seconds by
changing the keep alive mode from `SESSION` to `DAEMON`. We change the
default to the latter and allow the former to be set via a `keepAliveMode`
property.
Also update the Jenkins build to use `keepAliveMode="session"` instead of
`--no-daemon`.
./gradlew compileTestScala -PkeepAliveMode="daemon" --info:
> Task :streams:streams-scala:compileTestScala
> Watching 928 directories to track changes
> Caching disabled for task ':streams:streams-scala:compileTestScala' because:
> Build cache is disabled
> Task ':streams:streams-scala:compileTestScala' is not up-to-date because:
> Input property 'source' file /home/ijuma/src/kafka/streams/streams-scala/src/test/scala/org/apache/kafka/streams/scala/kstream/JoinedTest.scala has changed.
> Watching 920 directories to track changes
> Watching 919 directories to track changes
> Compiling with Zinc Scala compiler.
> Prepared Zinc Scala inputs: 0.004 secs
> compiling 16 Scala sources to /home/ijuma/src/kafka/streams/streams-scala/build/classes/scala/test ...
> done compiling
> Completed Scala compilation: 0.925 secs
./gradlew compileTestScala -PkeepAliveMode="session" --info
> Task :streams:streams-scala:compileTestScala
> Watching 928 directories to track changes
> Caching disabled for task ':streams:streams-scala:compileTestScala' because:
> Build cache is disabled
> Task ':streams:streams-scala:compileTestScala' is not up-to-date because:
> Input property 'source' file /home/ijuma/src/kafka/streams/streams-scala/src/test/scala/org/apache/kafka/streams/scala/kstream/JoinedTest.scala has changed.
> Watching 920 directories to track changes
> Watching 919 directories to track changes
> Starting process 'Gradle Worker Daemon 3'. Working directory: /home/ijuma/.gradle/workers Command: /usr/java/jdk-17.0.4.1+1/bin/java -Xss4m -XX:+UseParallelGC --add-opens=java.base/java.io=ALL-UNNAMED --add-opens=java.base/java.lang=ALL-UNNAMED --add-opens=java.base/java.nio=ALL-UNNAMED --add-opens=java.base/java.nio.file=ALL-UNNAMED --add-opens=java.base/java.util=ALL-UNNAMED --add-opens=java.base/java.util.concurrent=ALL-UNNAMED --add-opens=java.base/java.util.regex=ALL-UNNAMED --add-opens=java.base/java.util.stream=ALL-UNNAMED --add-opens=java.base/java.text=ALL-UNNAMED --add-opens=java.base/java.time=ALL-UNNAMED --add-opens=java.security.jgss/sun.security.krb5=ALL-UNNAMED --add-opens=java.base/java.util=ALL-UNNAMED --add-opens=java.base/java.lang=ALL-UNNAMED @/home/ijuma/.gradle/.tmp/gradle-worker-classpath3305983246500958050txt -Xmx2048m -Dfile.encoding=UTF-8 -Duser.country=US -Duser.language=en -Duser.variant worker.org.gradle.process.internal.worker.GradleWorkerMain 'Gradle Worker Daemon 3'
> Successfully started process 'Gradle Worker Daemon 3'
> Started Gradle worker daemon (0.244 secs) with fork options DaemonForkOptions{executable=/usr/java/jdk-17.0.4.1+1/bin/java, minHeapSize=null, maxHeapSize=2048m, jvmArgs=[-Xss4m, -XX:+UseParallelGC, --add-opens=java.base/java.io=ALL-UNNAMED, --add-opens=java.base/java.lang=ALL-UNNAMED, --add-opens=java.base/java.nio=ALL-UNNAMED, --add-opens=java.base/java.nio.file=ALL-UNNAMED, --add-opens=java.base/java.util=ALL-UNNAMED, --add-opens=java.base/java.util.concurrent=ALL-UNNAMED, --add-opens=java.base/java.util.regex=ALL-UNNAMED, --add-opens=java.base/java.util.stream=ALL-UNNAMED, --add-opens=java.base/java.text=ALL-UNNAMED, --add-opens=java.base/java.time=ALL-UNNAMED, --add-opens=java.security.jgss/sun.security.krb5=ALL-UNNAMED], keepAliveMode=SESSION}.
> Compiling with Zinc Scala compiler.
> Prepared Zinc Scala inputs: 0.187 secs
> compiling 16 Scala sources to /home/ijuma/src/kafka/streams/streams-scala/build/classes/scala/test ...
> done compiling
> Completed Scala compilation: 5.307 secs
See https://github.com/gradle/gradle/issues/20579 for more details.
Reviewers: Manikumar Reddy <manikumar.reddy@gmail.com>
2 years ago
userKeepAliveModeString = project . hasProperty ( "keepAliveMode" ) ? keepAliveMode : "daemon"
userKeepAliveMode = KeepAliveMode . values ( ) . find ( m - > m . name ( ) . toLowerCase ( ) . equals ( userKeepAliveModeString ) )
if ( userKeepAliveMode = = null ) {
def keepAliveValues = KeepAliveMode . values ( ) . collect ( m - > m . name . toLowerCase ( ) )
throw new GradleException ( "Unexpected value for keepAliveMode property. Expected one of $keepAliveValues, but received: $userKeepAliveModeString" )
}
// See README.md for details on this option and the reasoning for the default
userScalaOptimizerMode = project . hasProperty ( "scalaOptimizerMode" ) ? scalaOptimizerMode : "inline-kafka"
def scalaOptimizerValues = [ "none" , "method" , "inline-kafka" , "inline-scala" ]
if ( ! scalaOptimizerValues . contains ( userScalaOptimizerMode ) )
MINOR: Reuse gradle daemon for scala compilation by default (#12280)
The time time to compile was reduced from 5.3 seconds to 0.9 seconds by
changing the keep alive mode from `SESSION` to `DAEMON`. We change the
default to the latter and allow the former to be set via a `keepAliveMode`
property.
Also update the Jenkins build to use `keepAliveMode="session"` instead of
`--no-daemon`.
./gradlew compileTestScala -PkeepAliveMode="daemon" --info:
> Task :streams:streams-scala:compileTestScala
> Watching 928 directories to track changes
> Caching disabled for task ':streams:streams-scala:compileTestScala' because:
> Build cache is disabled
> Task ':streams:streams-scala:compileTestScala' is not up-to-date because:
> Input property 'source' file /home/ijuma/src/kafka/streams/streams-scala/src/test/scala/org/apache/kafka/streams/scala/kstream/JoinedTest.scala has changed.
> Watching 920 directories to track changes
> Watching 919 directories to track changes
> Compiling with Zinc Scala compiler.
> Prepared Zinc Scala inputs: 0.004 secs
> compiling 16 Scala sources to /home/ijuma/src/kafka/streams/streams-scala/build/classes/scala/test ...
> done compiling
> Completed Scala compilation: 0.925 secs
./gradlew compileTestScala -PkeepAliveMode="session" --info
> Task :streams:streams-scala:compileTestScala
> Watching 928 directories to track changes
> Caching disabled for task ':streams:streams-scala:compileTestScala' because:
> Build cache is disabled
> Task ':streams:streams-scala:compileTestScala' is not up-to-date because:
> Input property 'source' file /home/ijuma/src/kafka/streams/streams-scala/src/test/scala/org/apache/kafka/streams/scala/kstream/JoinedTest.scala has changed.
> Watching 920 directories to track changes
> Watching 919 directories to track changes
> Starting process 'Gradle Worker Daemon 3'. Working directory: /home/ijuma/.gradle/workers Command: /usr/java/jdk-17.0.4.1+1/bin/java -Xss4m -XX:+UseParallelGC --add-opens=java.base/java.io=ALL-UNNAMED --add-opens=java.base/java.lang=ALL-UNNAMED --add-opens=java.base/java.nio=ALL-UNNAMED --add-opens=java.base/java.nio.file=ALL-UNNAMED --add-opens=java.base/java.util=ALL-UNNAMED --add-opens=java.base/java.util.concurrent=ALL-UNNAMED --add-opens=java.base/java.util.regex=ALL-UNNAMED --add-opens=java.base/java.util.stream=ALL-UNNAMED --add-opens=java.base/java.text=ALL-UNNAMED --add-opens=java.base/java.time=ALL-UNNAMED --add-opens=java.security.jgss/sun.security.krb5=ALL-UNNAMED --add-opens=java.base/java.util=ALL-UNNAMED --add-opens=java.base/java.lang=ALL-UNNAMED @/home/ijuma/.gradle/.tmp/gradle-worker-classpath3305983246500958050txt -Xmx2048m -Dfile.encoding=UTF-8 -Duser.country=US -Duser.language=en -Duser.variant worker.org.gradle.process.internal.worker.GradleWorkerMain 'Gradle Worker Daemon 3'
> Successfully started process 'Gradle Worker Daemon 3'
> Started Gradle worker daemon (0.244 secs) with fork options DaemonForkOptions{executable=/usr/java/jdk-17.0.4.1+1/bin/java, minHeapSize=null, maxHeapSize=2048m, jvmArgs=[-Xss4m, -XX:+UseParallelGC, --add-opens=java.base/java.io=ALL-UNNAMED, --add-opens=java.base/java.lang=ALL-UNNAMED, --add-opens=java.base/java.nio=ALL-UNNAMED, --add-opens=java.base/java.nio.file=ALL-UNNAMED, --add-opens=java.base/java.util=ALL-UNNAMED, --add-opens=java.base/java.util.concurrent=ALL-UNNAMED, --add-opens=java.base/java.util.regex=ALL-UNNAMED, --add-opens=java.base/java.util.stream=ALL-UNNAMED, --add-opens=java.base/java.text=ALL-UNNAMED, --add-opens=java.base/java.time=ALL-UNNAMED, --add-opens=java.security.jgss/sun.security.krb5=ALL-UNNAMED], keepAliveMode=SESSION}.
> Compiling with Zinc Scala compiler.
> Prepared Zinc Scala inputs: 0.187 secs
> compiling 16 Scala sources to /home/ijuma/src/kafka/streams/streams-scala/build/classes/scala/test ...
> done compiling
> Completed Scala compilation: 5.307 secs
See https://github.com/gradle/gradle/issues/20579 for more details.
Reviewers: Manikumar Reddy <manikumar.reddy@gmail.com>
2 years ago
throw new GradleException ( "Unexpected value for scalaOptimizerMode property. Expected one of $scalaOptimizerValues, but received: $userScalaOptimizerMode" )
generatedDocsDir = new File ( "${project.rootDir}/docs/generated" )
commitId = determineCommitId ( )
}
allprojects {
repositories {
mavenCentral ( )
}
dependencyUpdates {
revision = "release"
resolutionStrategy {
componentSelection { rules - >
rules . all { ComponentSelection selection - >
boolean rejected = [ 'snap' , 'alpha' , 'beta' , 'rc' , 'cr' , 'm' ] . any { qualifier - >
selection . candidate . version = = ~ /(?i).*[.-]${qualifier}[.\d-]*/
}
if ( rejected ) {
selection . reject ( 'Release candidate' )
}
}
}
}
}
configurations . all {
// zinc is the Scala incremental compiler, it has a configuration for its own dependencies
// that are unrelated to the project dependencies, we should not change them
if ( name ! = "zinc" ) {
resolutionStrategy {
force (
// be explicit about the javassist dependency version instead of relying on the transitive version
libs . javassist ,
// ensure we have a single version in the classpath despite transitive dependencies
libs . scalaLibrary ,
libs . scalaReflect ,
libs . jacksonAnnotations ,
// be explicit about the Netty dependency version instead of relying on the version set by
// ZooKeeper (potentially older and containing CVEs)
libs . nettyHandler ,
libs . nettyTransportNativeEpoll
)
}
}
}
task printAllDependencies ( type: DependencyReportTask ) { }
}
def determineCommitId ( ) {
def takeFromHash = 16
if ( project . hasProperty ( 'commitId' ) ) {
commitId . take ( takeFromHash )
} else if ( file ( "$rootDir/.git/HEAD" ) . exists ( ) ) {
def headRef = file ( "$rootDir/.git/HEAD" ) . text
if ( headRef . contains ( 'ref: ' ) ) {
headRef = headRef . replaceAll ( 'ref: ' , '' ) . trim ( )
if ( file ( "$rootDir/.git/$headRef" ) . exists ( ) ) {
file ( "$rootDir/.git/$headRef" ) . text . trim ( ) . take ( takeFromHash )
}
} else {
headRef . trim ( ) . take ( takeFromHash )
}
} else {
"unknown"
}
}
apply from: file ( 'wrapper.gradle' )
if ( file ( '.git' ) . exists ( ) ) {
rat {
verbose . set ( true )
reportDir . set ( project . file ( 'build/rat' ) )
stylesheet . set ( file ( 'gradle/resources/rat-output-to-html.xsl' ) )
// Exclude everything under the directory that git should be ignoring via .gitignore or that isn't checked in. These
// restrict us only to files that are checked in or are staged.
def repo = Grgit . open ( currentDir: project . getRootDir ( ) )
excludes = new ArrayList < String > ( repo . clean ( ignore: false , directories: true , dryRun: true ) )
// And some of the files that we have checked in should also be excluded from this check
excludes . addAll ( [
'**/.git/**' ,
'**/build/**' ,
'CONTRIBUTING.md' ,
'PULL_REQUEST_TEMPLATE.md' ,
'gradlew' ,
'gradlew.bat' ,
'gradle/wrapper/gradle-wrapper.properties' ,
'TROGDOR.md' ,
'**/README.md' ,
'**/id_rsa' ,
'**/id_rsa.pub' ,
'checkstyle/suppressions.xml' ,
'streams/quickstart/java/src/test/resources/projects/basic/goal.txt' ,
'streams/streams-scala/logs/*' ,
'licenses/*' ,
'**/generated/**' ,
'clients/src/test/resources/serializedData/*'
] )
}
} else {
rat . enabled = false
}
println ( "Starting build with version $version (commit id ${commitId == null ? " null " : commitId.take(8)}) using Gradle $gradleVersion, Java ${JavaVersion.current()} and Scala ${versions.scala}" )
println ( "Build properties: maxParallelForks=$maxTestForks, maxScalacThreads=$maxScalacThreads, maxTestRetries=$userMaxTestRetries" )
subprojects {
// enable running :dependencies task recursively on all subprojects
// eg: ./gradlew allDeps
task allDeps ( type: DependencyReportTask ) { }
// enable running :dependencyInsight task recursively on all subprojects
// eg: ./gradlew allDepInsight --configuration runtime --dependency com.fasterxml.jackson.core:jackson-databind
task allDepInsight ( type: DependencyInsightReportTask ) { showingAllVariants = false } doLast { }
apply plugin: 'java-library'
apply plugin: 'checkstyle'
apply plugin: "com.github.spotbugs"
apply plugin: 'org.gradle.test-retry'
// We use the shadow plugin for the jmh-benchmarks module and the `-all` jar can get pretty large, so
// don't publish it
def shouldPublish = ! project . name . equals ( 'jmh-benchmarks' )
if ( shouldPublish ) {
apply plugin: 'maven-publish'
apply plugin: 'signing'
// Add aliases for the task names used by the maven plugin for backwards compatibility
// The maven plugin was replaced by the maven-publish plugin in Gradle 7.0
tasks . register ( 'install' ) . configure { dependsOn ( publishToMavenLocal ) }
tasks . register ( 'uploadArchives' ) . configure { dependsOn ( publish ) }
}
// apply the eclipse plugin only to subprojects that hold code. 'connect' is just a folder.
if ( ! project . name . equals ( 'connect' ) ) {
apply plugin: 'eclipse'
fineTuneEclipseClasspathFile ( eclipse , project )
}
sourceCompatibility = minJavaVersion
targetCompatibility = minJavaVersion
java {
consistentResolution {
// resolve the compileClasspath and then "inject" the result of resolution as strict constraints into the runtimeClasspath
useCompileClasspathVersions ( )
}
}
tasks . withType ( JavaCompile ) {
options . encoding = 'UTF-8'
options . compilerArgs < < "-Xlint:all"
// temporary exclusions until all the warnings are fixed
if ( ! project . path . startsWith ( ":connect" ) )
options . compilerArgs < < "-Xlint:-rawtypes"
options . compilerArgs < < "-Xlint:-serial"
options . compilerArgs < < "-Xlint:-try"
options . compilerArgs < < "-Werror"
// --release is the recommended way to select the target release, but it's only supported in Java 9 so we also
// set --source and --target via `sourceCompatibility` and `targetCompatibility`. If/when Gradle supports `--release`
// natively (https://github.com/gradle/gradle/issues/2510), we should switch to that.
if ( JavaVersion . current ( ) . isJava9Compatible ( ) )
options . compilerArgs < < "--release" < < minJavaVersion
}
if ( shouldPublish ) {
publishing {
repositories {
// To test locally, invoke gradlew with `-PmavenUrl=file:///some/local/path`
maven {
url = mavenUrl
credentials {
username = mavenUsername
password = mavenPassword
}
}
}
publications {
mavenJava ( MavenPublication ) {
from components . java
afterEvaluate {
[ "srcJar" , "javadocJar" , "scaladocJar" , "testJar" , "testSrcJar" ] . forEach { taskName - >
def task = tasks . findByName ( taskName )
if ( task ! = null )
artifact task
}
artifactId = archivesBaseName
pom {
name = 'Apache Kafka'
url = 'https://kafka.apache.org'
licenses {
license {
name = 'The Apache License, Version 2.0'
url = 'http://www.apache.org/licenses/LICENSE-2.0.txt'
distribution = 'repo'
}
}
}
}
}
}
}
if ( shouldSign ) {
signing {
sign publishing . publications . mavenJava
}
}
}
// Remove the relevant project name once it's converted to JUnit 5
def shouldUseJUnit5 = ! ( [ "runtime" ] . contains ( it . project . name ) )
def testLoggingEvents = [ "passed" , "skipped" , "failed" ]
def testShowStandardStreams = false
def testExceptionFormat = 'full'
// Gradle built-in logging only supports sending test output to stdout, which generates a lot
// of noise, especially for passing tests. We really only want output for failed tests. This
// hooks into the output and logs it (so we don't have to buffer it all in memory) and only
// saves the output for failing tests. Directory and filenames are such that you can, e.g.,
// create a Jenkins rule to collect failed test output.
def logTestStdout = {
def testId = { TestDescriptor descriptor - >
"${descriptor.className}.${descriptor.name}" . toString ( )
}
def logFiles = new HashMap < String , File > ( )
def logStreams = new HashMap < String , FileOutputStream > ( )
beforeTest { TestDescriptor td - >
def tid = testId ( td )
// truncate the file name if it's too long
def logFile = new File (
"${projectDir}/build/reports/testOutput/${tid.substring(0, Math.min(tid.size(),240))}.test.stdout"
)
logFile . parentFile . mkdirs ( )
logFiles . put ( tid , logFile )
logStreams . put ( tid , new FileOutputStream ( logFile ) )
}
onOutput { TestDescriptor td , TestOutputEvent toe - >
def tid = testId ( td )
// Some output can happen outside the context of a specific test (e.g. at the class level)
// and beforeTest/afterTest seems to not be invoked for these cases (and similarly, there's
// a TestDescriptor hierarchy that includes the thread executing the test, Gradle tasks,
// etc). We see some of these in practice and it seems like something buggy in the Gradle
// test runner since we see it *before* any tests and it is frequently not related to any
// code in the test (best guess is that it is tail output from last test). We won't have
// an output file for these, so simply ignore them. If they become critical for debugging,
// they can be seen with showStandardStreams.
if ( td . name = = td . className | | td . className = = null ) {
// silently ignore output unrelated to specific test methods
return
} else if ( logStreams . get ( tid ) = = null ) {
println "WARNING: unexpectedly got output for a test [${tid}]" +
" that we didn't previously see in the beforeTest hook." +
" Message for debugging: [" + toe . message + "]."
return
}
try {
logStreams . get ( tid ) . write ( toe . message . getBytes ( StandardCharsets . UTF_8 ) )
} catch ( Exception e ) {
println "ERROR: Failed to write output for test ${tid}"
e . printStackTrace ( )
}
}
afterTest { TestDescriptor td , TestResult tr - >
def tid = testId ( td )
try {
logStreams . get ( tid ) . close ( )
if ( tr . resultType ! = TestResult . ResultType . FAILURE ) {
logFiles . get ( tid ) . delete ( )
} else {
def file = logFiles . get ( tid )
println "${tid} failed, log available in ${file}"
}
} catch ( Exception e ) {
println "ERROR: Failed to close stdout file for ${tid}"
e . printStackTrace ( )
} finally {
logFiles . remove ( tid )
logStreams . remove ( tid )
}
}
}
// The suites are for running sets of tests in IDEs.
// Gradle will run each test class, so we exclude the suites to avoid redundantly running the tests twice.
def testsToExclude = [ '**/*Suite.class' ]
// Exclude PowerMock tests when running with Java 16 or newer until a version of PowerMock that supports the relevant versions is released
// The relevant issues are https://github.com/powermock/powermock/issues/1094 and https://github.com/powermock/powermock/issues/1099
if ( JavaVersion . current ( ) . isCompatibleWith ( JavaVersion . VERSION_16 ) ) {
testsToExclude . addAll ( [
// connect tests
"**/DistributedHerderTest.*" ,
"**/KafkaConfigBackingStoreTest.*" ,
"**/KafkaBasedLogTest.*" , "**/StandaloneHerderTest.*" ,
"**/WorkerSinkTaskTest.*" , "**/WorkerSinkTaskThreadedTest.*" ,
"**/WorkerSourceTaskTest.*" , "**/AbstractWorkerSourceTaskTest.*"
] )
}
test {
maxParallelForks = maxTestForks
ignoreFailures = userIgnoreFailures
MINOR: Update to Gradle 6.5 and tweak build jvm config (#8751)
Gradle 6.5 includes a fix for https://github.com/gradle/gradle/pull/12866, which
affects the performance of Scala compilation.
I profiled the scalac build with async profiler and 54% of the time was on GC
even after the Gradle upgrade (it was more than 60% before), so I switched to
the throughput GC (GC latency is less important for batch builds) and it
was reduced to 38%.
I also centralized the jvm configuration in `build.gradle` and simplified it a bit
by removing the minHeapSize configuration from the test tasks.
On my desktop, the time to execute clean builds with no cached Gradle daemon
was reduced from 127 seconds to 97 seconds. With a cached daemon, it was
reduced from 120 seconds to 88 seconds. The performance regression when
we upgraded to Gradle 6.x was 27 seconds with a cached daemon
(https://github.com/apache/kafka/pull/7677#issuecomment-616271179), so it
should be fixed now.
Gradle 6.4 with no cached daemon:
```
BUILD SUCCESSFUL in 2m 7s
115 actionable tasks: 112 executed, 3 up-to-date
./gradlew clean compileScala compileJava compileTestScala compileTestJava 1.15s user 0.12s system 0% cpu 2:08.06 total
```
Gradle 6.4 with cached daemon:
```
BUILD SUCCESSFUL in 2m 0s
115 actionable tasks: 111 executed, 4 up-to-date
./gradlew clean compileScala compileJava compileTestScala compileTestJava 0.95s user 0.10s system 0% cpu 2:01.42 total
```
Gradle 6.5 with no cached daemon:
```
BUILD SUCCESSFUL in 1m 46s
115 actionable tasks: 111 executed, 4 up-to-date
./gradlew clean compileScala compileJava compileTestScala compileTestJava 1.27s user 0.12s system 1% cpu 1:47.71 total
```
Gradle 6.5 with cached daemon:
```
BUILD SUCCESSFUL in 1m 37s
115 actionable tasks: 111 executed, 4 up-to-date
./gradlew clean compileScala compileJava compileTestScala compileTestJava 1.02s user 0.10s system 1% cpu 1:38.31 total
```
This PR with no cached Gradle daemon:
```
BUILD SUCCESSFUL in 1m 37s
115 actionable tasks: 81 executed, 34 up-to-date
./gradlew clean compileScala compileJava compileTestScala compileTestJava 1.27s user 0.10s system 1% cpu 1:38.70 total
```
This PR with cached Gradle daemon:
```
BUILD SUCCESSFUL in 1m 28s
115 actionable tasks: 111 executed, 4 up-to-date
./gradlew clean compileScala compileJava compileTestScala compileTestJava 1.02s user 0.10s system 1% cpu 1:29.35 total
```
Reviewers: Manikumar Reddy <manikumar.reddy@gmail.com>, Chia-Ping Tsai <chia7712@gmail.com>
5 years ago
maxHeapSize = defaultMaxHeapSize
jvmArgs = defaultJvmArgs
testLogging {
events = userTestLoggingEvents ? : testLoggingEvents
showStandardStreams = userShowStandardStreams ? : testShowStandardStreams
exceptionFormat = testExceptionFormat
displayGranularity = 0
}
logTestStdout . rehydrate ( delegate , owner , this ) ( )
exclude testsToExclude
if ( shouldUseJUnit5 )
useJUnitPlatform ( )
retry {
maxRetries = userMaxTestRetries
maxFailures = userMaxTestRetryFailures
}
// Allows devs to run tests in a loop to debug flaky tests. See README.
if ( project . hasProperty ( "rerun-tests" ) ) {
outputs . upToDateWhen { false }
}
}
task integrationTest ( type: Test , dependsOn: compileJava ) {
maxParallelForks = maxTestForks
ignoreFailures = userIgnoreFailures
// Increase heap size for integration tests
maxHeapSize = "2560m"
MINOR: Update to Gradle 6.5 and tweak build jvm config (#8751)
Gradle 6.5 includes a fix for https://github.com/gradle/gradle/pull/12866, which
affects the performance of Scala compilation.
I profiled the scalac build with async profiler and 54% of the time was on GC
even after the Gradle upgrade (it was more than 60% before), so I switched to
the throughput GC (GC latency is less important for batch builds) and it
was reduced to 38%.
I also centralized the jvm configuration in `build.gradle` and simplified it a bit
by removing the minHeapSize configuration from the test tasks.
On my desktop, the time to execute clean builds with no cached Gradle daemon
was reduced from 127 seconds to 97 seconds. With a cached daemon, it was
reduced from 120 seconds to 88 seconds. The performance regression when
we upgraded to Gradle 6.x was 27 seconds with a cached daemon
(https://github.com/apache/kafka/pull/7677#issuecomment-616271179), so it
should be fixed now.
Gradle 6.4 with no cached daemon:
```
BUILD SUCCESSFUL in 2m 7s
115 actionable tasks: 112 executed, 3 up-to-date
./gradlew clean compileScala compileJava compileTestScala compileTestJava 1.15s user 0.12s system 0% cpu 2:08.06 total
```
Gradle 6.4 with cached daemon:
```
BUILD SUCCESSFUL in 2m 0s
115 actionable tasks: 111 executed, 4 up-to-date
./gradlew clean compileScala compileJava compileTestScala compileTestJava 0.95s user 0.10s system 0% cpu 2:01.42 total
```
Gradle 6.5 with no cached daemon:
```
BUILD SUCCESSFUL in 1m 46s
115 actionable tasks: 111 executed, 4 up-to-date
./gradlew clean compileScala compileJava compileTestScala compileTestJava 1.27s user 0.12s system 1% cpu 1:47.71 total
```
Gradle 6.5 with cached daemon:
```
BUILD SUCCESSFUL in 1m 37s
115 actionable tasks: 111 executed, 4 up-to-date
./gradlew clean compileScala compileJava compileTestScala compileTestJava 1.02s user 0.10s system 1% cpu 1:38.31 total
```
This PR with no cached Gradle daemon:
```
BUILD SUCCESSFUL in 1m 37s
115 actionable tasks: 81 executed, 34 up-to-date
./gradlew clean compileScala compileJava compileTestScala compileTestJava 1.27s user 0.10s system 1% cpu 1:38.70 total
```
This PR with cached Gradle daemon:
```
BUILD SUCCESSFUL in 1m 28s
115 actionable tasks: 111 executed, 4 up-to-date
./gradlew clean compileScala compileJava compileTestScala compileTestJava 1.02s user 0.10s system 1% cpu 1:29.35 total
```
Reviewers: Manikumar Reddy <manikumar.reddy@gmail.com>, Chia-Ping Tsai <chia7712@gmail.com>
5 years ago
jvmArgs = defaultJvmArgs
testLogging {
events = userTestLoggingEvents ? : testLoggingEvents
showStandardStreams = userShowStandardStreams ? : testShowStandardStreams
exceptionFormat = testExceptionFormat
displayGranularity = 0
}
logTestStdout . rehydrate ( delegate , owner , this ) ( )
exclude testsToExclude
if ( shouldUseJUnit5 ) {
if ( project . name = = 'streams' ) {
useJUnitPlatform {
includeTags "integration"
includeTags "org.apache.kafka.test.IntegrationTest"
// Both engines are needed to run JUnit 4 tests alongside JUnit 5 tests.
// junit-vintage (JUnit 4) can be removed once the JUnit 4 migration is complete.
includeEngines "junit-vintage" , "junit-jupiter"
}
} else {
useJUnitPlatform {
includeTags "integration"
}
}
} else {
useJUnit {
includeCategories 'org.apache.kafka.test.IntegrationTest'
}
}
retry {
maxRetries = userMaxTestRetries
maxFailures = userMaxTestRetryFailures
}
// Allows devs to run tests in a loop to debug flaky tests. See README.
if ( project . hasProperty ( "rerun-tests" ) ) {
outputs . upToDateWhen { false }
}
}
task unitTest ( type: Test , dependsOn: compileJava ) {
maxParallelForks = maxTestForks
ignoreFailures = userIgnoreFailures
MINOR: Update to Gradle 6.5 and tweak build jvm config (#8751)
Gradle 6.5 includes a fix for https://github.com/gradle/gradle/pull/12866, which
affects the performance of Scala compilation.
I profiled the scalac build with async profiler and 54% of the time was on GC
even after the Gradle upgrade (it was more than 60% before), so I switched to
the throughput GC (GC latency is less important for batch builds) and it
was reduced to 38%.
I also centralized the jvm configuration in `build.gradle` and simplified it a bit
by removing the minHeapSize configuration from the test tasks.
On my desktop, the time to execute clean builds with no cached Gradle daemon
was reduced from 127 seconds to 97 seconds. With a cached daemon, it was
reduced from 120 seconds to 88 seconds. The performance regression when
we upgraded to Gradle 6.x was 27 seconds with a cached daemon
(https://github.com/apache/kafka/pull/7677#issuecomment-616271179), so it
should be fixed now.
Gradle 6.4 with no cached daemon:
```
BUILD SUCCESSFUL in 2m 7s
115 actionable tasks: 112 executed, 3 up-to-date
./gradlew clean compileScala compileJava compileTestScala compileTestJava 1.15s user 0.12s system 0% cpu 2:08.06 total
```
Gradle 6.4 with cached daemon:
```
BUILD SUCCESSFUL in 2m 0s
115 actionable tasks: 111 executed, 4 up-to-date
./gradlew clean compileScala compileJava compileTestScala compileTestJava 0.95s user 0.10s system 0% cpu 2:01.42 total
```
Gradle 6.5 with no cached daemon:
```
BUILD SUCCESSFUL in 1m 46s
115 actionable tasks: 111 executed, 4 up-to-date
./gradlew clean compileScala compileJava compileTestScala compileTestJava 1.27s user 0.12s system 1% cpu 1:47.71 total
```
Gradle 6.5 with cached daemon:
```
BUILD SUCCESSFUL in 1m 37s
115 actionable tasks: 111 executed, 4 up-to-date
./gradlew clean compileScala compileJava compileTestScala compileTestJava 1.02s user 0.10s system 1% cpu 1:38.31 total
```
This PR with no cached Gradle daemon:
```
BUILD SUCCESSFUL in 1m 37s
115 actionable tasks: 81 executed, 34 up-to-date
./gradlew clean compileScala compileJava compileTestScala compileTestJava 1.27s user 0.10s system 1% cpu 1:38.70 total
```
This PR with cached Gradle daemon:
```
BUILD SUCCESSFUL in 1m 28s
115 actionable tasks: 111 executed, 4 up-to-date
./gradlew clean compileScala compileJava compileTestScala compileTestJava 1.02s user 0.10s system 1% cpu 1:29.35 total
```
Reviewers: Manikumar Reddy <manikumar.reddy@gmail.com>, Chia-Ping Tsai <chia7712@gmail.com>
5 years ago
maxHeapSize = defaultMaxHeapSize
jvmArgs = defaultJvmArgs
testLogging {
events = userTestLoggingEvents ? : testLoggingEvents
showStandardStreams = userShowStandardStreams ? : testShowStandardStreams
exceptionFormat = testExceptionFormat
displayGranularity = 0
}
logTestStdout . rehydrate ( delegate , owner , this ) ( )
exclude testsToExclude
if ( shouldUseJUnit5 ) {
if ( project . name = = 'streams' ) {
useJUnitPlatform {
excludeTags "integration"
excludeTags "org.apache.kafka.test.IntegrationTest"
// Both engines are needed to run JUnit 4 tests alongside JUnit 5 tests.
// junit-vintage (JUnit 4) can be removed once the JUnit 4 migration is complete.
includeEngines "junit-vintage" , "junit-jupiter"
}
} else {
useJUnitPlatform {
excludeTags "integration"
}
}
} else {
useJUnit {
excludeCategories 'org.apache.kafka.test.IntegrationTest'
}
}
retry {
maxRetries = userMaxTestRetries
maxFailures = userMaxTestRetryFailures
}
}
// remove test output from all test types
tasks . withType ( Test ) . all { t - >
cleanTest {
delete t . reports . junitXml . outputLocation
delete t . reports . html . outputLocation
}
}
jar {
from "$rootDir/LICENSE"
from "$rootDir/NOTICE"
}
task srcJar ( type: Jar ) {
archiveClassifier = 'sources'
from "$rootDir/LICENSE"
from "$rootDir/NOTICE"
from sourceSets . main . allSource
}
task javadocJar ( type: Jar , dependsOn: javadoc ) {
archiveClassifier = 'javadoc'
from "$rootDir/LICENSE"
from "$rootDir/NOTICE"
from javadoc . destinationDir
}
task docsJar ( dependsOn: javadocJar )
javadoc {
options . charSet = 'UTF-8'
options . docEncoding = 'UTF-8'
options . encoding = 'UTF-8'
// Turn off doclint for now, see https://blog.joda.org/2014/02/turning-off-doclint-in-jdk-8-javadoc.html for rationale
options . addStringOption ( 'Xdoclint:none' , '-quiet' )
// The URL structure was changed to include the locale after Java 8
if ( JavaVersion . current ( ) . isJava11Compatible ( ) )
options . links "https://docs.oracle.com/en/java/javase/${JavaVersion.current().majorVersion}/docs/api/"
else
options . links "https://docs.oracle.com/javase/8/docs/api/"
}
task systemTestLibs ( dependsOn: jar )
if ( ! sourceSets . test . allSource . isEmpty ( ) ) {
task testJar ( type: Jar ) {
archiveClassifier = 'test'
from "$rootDir/LICENSE"
from "$rootDir/NOTICE"
from sourceSets . test . output
}
task testSrcJar ( type: Jar , dependsOn: testJar ) {
archiveClassifier = 'test-sources'
from "$rootDir/LICENSE"
from "$rootDir/NOTICE"
from sourceSets . test . allSource
}
}
plugins . withType ( ScalaPlugin ) {
scala {
zincVersion = versions . zinc
}
task scaladocJar ( type: Jar , dependsOn: scaladoc ) {
archiveClassifier = 'scaladoc'
from "$rootDir/LICENSE"
from "$rootDir/NOTICE"
from scaladoc . destinationDir
}
//documentation task should also trigger building scala doc jar
docsJar . dependsOn scaladocJar
}
tasks . withType ( ScalaCompile ) {
MINOR: Reuse gradle daemon for scala compilation by default (#12280)
The time time to compile was reduced from 5.3 seconds to 0.9 seconds by
changing the keep alive mode from `SESSION` to `DAEMON`. We change the
default to the latter and allow the former to be set via a `keepAliveMode`
property.
Also update the Jenkins build to use `keepAliveMode="session"` instead of
`--no-daemon`.
./gradlew compileTestScala -PkeepAliveMode="daemon" --info:
> Task :streams:streams-scala:compileTestScala
> Watching 928 directories to track changes
> Caching disabled for task ':streams:streams-scala:compileTestScala' because:
> Build cache is disabled
> Task ':streams:streams-scala:compileTestScala' is not up-to-date because:
> Input property 'source' file /home/ijuma/src/kafka/streams/streams-scala/src/test/scala/org/apache/kafka/streams/scala/kstream/JoinedTest.scala has changed.
> Watching 920 directories to track changes
> Watching 919 directories to track changes
> Compiling with Zinc Scala compiler.
> Prepared Zinc Scala inputs: 0.004 secs
> compiling 16 Scala sources to /home/ijuma/src/kafka/streams/streams-scala/build/classes/scala/test ...
> done compiling
> Completed Scala compilation: 0.925 secs
./gradlew compileTestScala -PkeepAliveMode="session" --info
> Task :streams:streams-scala:compileTestScala
> Watching 928 directories to track changes
> Caching disabled for task ':streams:streams-scala:compileTestScala' because:
> Build cache is disabled
> Task ':streams:streams-scala:compileTestScala' is not up-to-date because:
> Input property 'source' file /home/ijuma/src/kafka/streams/streams-scala/src/test/scala/org/apache/kafka/streams/scala/kstream/JoinedTest.scala has changed.
> Watching 920 directories to track changes
> Watching 919 directories to track changes
> Starting process 'Gradle Worker Daemon 3'. Working directory: /home/ijuma/.gradle/workers Command: /usr/java/jdk-17.0.4.1+1/bin/java -Xss4m -XX:+UseParallelGC --add-opens=java.base/java.io=ALL-UNNAMED --add-opens=java.base/java.lang=ALL-UNNAMED --add-opens=java.base/java.nio=ALL-UNNAMED --add-opens=java.base/java.nio.file=ALL-UNNAMED --add-opens=java.base/java.util=ALL-UNNAMED --add-opens=java.base/java.util.concurrent=ALL-UNNAMED --add-opens=java.base/java.util.regex=ALL-UNNAMED --add-opens=java.base/java.util.stream=ALL-UNNAMED --add-opens=java.base/java.text=ALL-UNNAMED --add-opens=java.base/java.time=ALL-UNNAMED --add-opens=java.security.jgss/sun.security.krb5=ALL-UNNAMED --add-opens=java.base/java.util=ALL-UNNAMED --add-opens=java.base/java.lang=ALL-UNNAMED @/home/ijuma/.gradle/.tmp/gradle-worker-classpath3305983246500958050txt -Xmx2048m -Dfile.encoding=UTF-8 -Duser.country=US -Duser.language=en -Duser.variant worker.org.gradle.process.internal.worker.GradleWorkerMain 'Gradle Worker Daemon 3'
> Successfully started process 'Gradle Worker Daemon 3'
> Started Gradle worker daemon (0.244 secs) with fork options DaemonForkOptions{executable=/usr/java/jdk-17.0.4.1+1/bin/java, minHeapSize=null, maxHeapSize=2048m, jvmArgs=[-Xss4m, -XX:+UseParallelGC, --add-opens=java.base/java.io=ALL-UNNAMED, --add-opens=java.base/java.lang=ALL-UNNAMED, --add-opens=java.base/java.nio=ALL-UNNAMED, --add-opens=java.base/java.nio.file=ALL-UNNAMED, --add-opens=java.base/java.util=ALL-UNNAMED, --add-opens=java.base/java.util.concurrent=ALL-UNNAMED, --add-opens=java.base/java.util.regex=ALL-UNNAMED, --add-opens=java.base/java.util.stream=ALL-UNNAMED, --add-opens=java.base/java.text=ALL-UNNAMED, --add-opens=java.base/java.time=ALL-UNNAMED, --add-opens=java.security.jgss/sun.security.krb5=ALL-UNNAMED], keepAliveMode=SESSION}.
> Compiling with Zinc Scala compiler.
> Prepared Zinc Scala inputs: 0.187 secs
> compiling 16 Scala sources to /home/ijuma/src/kafka/streams/streams-scala/build/classes/scala/test ...
> done compiling
> Completed Scala compilation: 5.307 secs
See https://github.com/gradle/gradle/issues/20579 for more details.
Reviewers: Manikumar Reddy <manikumar.reddy@gmail.com>
2 years ago
scalaCompileOptions . keepAliveMode = userKeepAliveMode
scalaCompileOptions . additionalParameters = [
"-deprecation" ,
"-unchecked" ,
"-encoding" , "utf8" ,
"-Xlog-reflective-calls" ,
"-feature" ,
"-language:postfixOps" ,
"-language:implicitConversions" ,
"-language:existentials" ,
"-Ybackend-parallelism" , maxScalacThreads . toString ( ) ,
"-Xlint:constant" ,
"-Xlint:delayedinit-select" ,
"-Xlint:doc-detached" ,
"-Xlint:missing-interpolator" ,
"-Xlint:nullary-unit" ,
"-Xlint:option-implicit" ,
"-Xlint:package-object-classes" ,
"-Xlint:poly-implicit-overload" ,
"-Xlint:private-shadow" ,
"-Xlint:stars-align" ,
"-Xlint:type-parameter-shadow" ,
"-Xlint:unused"
]
// See README.md for details on this option and the meaning of each value
if ( userScalaOptimizerMode . equals ( "method" ) )
scalaCompileOptions . additionalParameters + = [ "-opt:l:method" ]
else if ( userScalaOptimizerMode . startsWith ( "inline-" ) ) {
List < String > inlineFrom = [ "-opt-inline-from:org.apache.kafka.**" ]
if ( project . name . equals ( 'core' ) )
inlineFrom . add ( "-opt-inline-from:kafka.**" )
if ( userScalaOptimizerMode . equals ( "inline-scala" ) )
inlineFrom . add ( "-opt-inline-from:scala.**" )
scalaCompileOptions . additionalParameters + = [ "-opt:l:inline" ]
scalaCompileOptions . additionalParameters + = inlineFrom
}
if ( versions . baseScala ! = '2.12' ) {
scalaCompileOptions . additionalParameters + = [ "-opt-warnings" , "-Xlint:strict-unsealed-patmat" ]
// Scala 2.13.2 introduces compiler warnings suppression, which is a pre-requisite for -Xfatal-warnings
scalaCompileOptions . additionalParameters + = [ "-Xfatal-warnings" ]
}
// these options are valid for Scala versions < 2.13 only
// Scala 2.13 removes them, see https://github.com/scala/scala/pull/6502 and https://github.com/scala/scala/pull/5969
if ( versions . baseScala = = '2.12' ) {
scalaCompileOptions . additionalParameters + = [
"-Xlint:by-name-right-associative" ,
"-Xlint:nullary-override" ,
"-Xlint:unsound-match"
]
}
// Scalac's `-release` requires Java 9 or higher
if ( JavaVersion . current ( ) . isJava9Compatible ( ) )
scalaCompileOptions . additionalParameters + = [ "-release" , minJavaVersion ]
configure ( scalaCompileOptions . forkOptions ) {
MINOR: Update to Gradle 6.5 and tweak build jvm config (#8751)
Gradle 6.5 includes a fix for https://github.com/gradle/gradle/pull/12866, which
affects the performance of Scala compilation.
I profiled the scalac build with async profiler and 54% of the time was on GC
even after the Gradle upgrade (it was more than 60% before), so I switched to
the throughput GC (GC latency is less important for batch builds) and it
was reduced to 38%.
I also centralized the jvm configuration in `build.gradle` and simplified it a bit
by removing the minHeapSize configuration from the test tasks.
On my desktop, the time to execute clean builds with no cached Gradle daemon
was reduced from 127 seconds to 97 seconds. With a cached daemon, it was
reduced from 120 seconds to 88 seconds. The performance regression when
we upgraded to Gradle 6.x was 27 seconds with a cached daemon
(https://github.com/apache/kafka/pull/7677#issuecomment-616271179), so it
should be fixed now.
Gradle 6.4 with no cached daemon:
```
BUILD SUCCESSFUL in 2m 7s
115 actionable tasks: 112 executed, 3 up-to-date
./gradlew clean compileScala compileJava compileTestScala compileTestJava 1.15s user 0.12s system 0% cpu 2:08.06 total
```
Gradle 6.4 with cached daemon:
```
BUILD SUCCESSFUL in 2m 0s
115 actionable tasks: 111 executed, 4 up-to-date
./gradlew clean compileScala compileJava compileTestScala compileTestJava 0.95s user 0.10s system 0% cpu 2:01.42 total
```
Gradle 6.5 with no cached daemon:
```
BUILD SUCCESSFUL in 1m 46s
115 actionable tasks: 111 executed, 4 up-to-date
./gradlew clean compileScala compileJava compileTestScala compileTestJava 1.27s user 0.12s system 1% cpu 1:47.71 total
```
Gradle 6.5 with cached daemon:
```
BUILD SUCCESSFUL in 1m 37s
115 actionable tasks: 111 executed, 4 up-to-date
./gradlew clean compileScala compileJava compileTestScala compileTestJava 1.02s user 0.10s system 1% cpu 1:38.31 total
```
This PR with no cached Gradle daemon:
```
BUILD SUCCESSFUL in 1m 37s
115 actionable tasks: 81 executed, 34 up-to-date
./gradlew clean compileScala compileJava compileTestScala compileTestJava 1.27s user 0.10s system 1% cpu 1:38.70 total
```
This PR with cached Gradle daemon:
```
BUILD SUCCESSFUL in 1m 28s
115 actionable tasks: 111 executed, 4 up-to-date
./gradlew clean compileScala compileJava compileTestScala compileTestJava 1.02s user 0.10s system 1% cpu 1:29.35 total
```
Reviewers: Manikumar Reddy <manikumar.reddy@gmail.com>, Chia-Ping Tsai <chia7712@gmail.com>
5 years ago
memoryMaximumSize = defaultMaxHeapSize
jvmArgs = defaultJvmArgs
}
}
checkstyle {
configFile = new File ( rootDir , "checkstyle/checkstyle.xml" )
configProperties = checkstyleConfigProperties ( "import-control.xml" )
toolVersion = versions . checkstyle
}
configure ( checkstyleMain ) {
group = 'Verification'
description = 'Run checkstyle on all main Java sources'
}
configure ( checkstyleTest ) {
group = 'Verification'
description = 'Run checkstyle on all test Java sources'
}
test . dependsOn ( 'checkstyleMain' , 'checkstyleTest' )
spotbugs {
toolVersion = versions . spotbugs
excludeFilter = file ( "$rootDir/gradle/spotbugs-exclude.xml" )
ignoreFailures = false
}
test . dependsOn ( 'spotbugsMain' )
tasks . withType ( com . github . spotbugs . snom . SpotBugsTask ) {
reports {
// Continue supporting `xmlFindBugsReport` for compatibility
xml . enabled ( project . hasProperty ( 'xmlSpotBugsReport' ) | | project . hasProperty ( 'xmlFindBugsReport' ) )
html . enabled ( ! project . hasProperty ( 'xmlSpotBugsReport' ) & & ! project . hasProperty ( 'xmlFindBugsReport' ) )
}
MINOR: Update to Gradle 6.5 and tweak build jvm config (#8751)
Gradle 6.5 includes a fix for https://github.com/gradle/gradle/pull/12866, which
affects the performance of Scala compilation.
I profiled the scalac build with async profiler and 54% of the time was on GC
even after the Gradle upgrade (it was more than 60% before), so I switched to
the throughput GC (GC latency is less important for batch builds) and it
was reduced to 38%.
I also centralized the jvm configuration in `build.gradle` and simplified it a bit
by removing the minHeapSize configuration from the test tasks.
On my desktop, the time to execute clean builds with no cached Gradle daemon
was reduced from 127 seconds to 97 seconds. With a cached daemon, it was
reduced from 120 seconds to 88 seconds. The performance regression when
we upgraded to Gradle 6.x was 27 seconds with a cached daemon
(https://github.com/apache/kafka/pull/7677#issuecomment-616271179), so it
should be fixed now.
Gradle 6.4 with no cached daemon:
```
BUILD SUCCESSFUL in 2m 7s
115 actionable tasks: 112 executed, 3 up-to-date
./gradlew clean compileScala compileJava compileTestScala compileTestJava 1.15s user 0.12s system 0% cpu 2:08.06 total
```
Gradle 6.4 with cached daemon:
```
BUILD SUCCESSFUL in 2m 0s
115 actionable tasks: 111 executed, 4 up-to-date
./gradlew clean compileScala compileJava compileTestScala compileTestJava 0.95s user 0.10s system 0% cpu 2:01.42 total
```
Gradle 6.5 with no cached daemon:
```
BUILD SUCCESSFUL in 1m 46s
115 actionable tasks: 111 executed, 4 up-to-date
./gradlew clean compileScala compileJava compileTestScala compileTestJava 1.27s user 0.12s system 1% cpu 1:47.71 total
```
Gradle 6.5 with cached daemon:
```
BUILD SUCCESSFUL in 1m 37s
115 actionable tasks: 111 executed, 4 up-to-date
./gradlew clean compileScala compileJava compileTestScala compileTestJava 1.02s user 0.10s system 1% cpu 1:38.31 total
```
This PR with no cached Gradle daemon:
```
BUILD SUCCESSFUL in 1m 37s
115 actionable tasks: 81 executed, 34 up-to-date
./gradlew clean compileScala compileJava compileTestScala compileTestJava 1.27s user 0.10s system 1% cpu 1:38.70 total
```
This PR with cached Gradle daemon:
```
BUILD SUCCESSFUL in 1m 28s
115 actionable tasks: 111 executed, 4 up-to-date
./gradlew clean compileScala compileJava compileTestScala compileTestJava 1.02s user 0.10s system 1% cpu 1:29.35 total
```
Reviewers: Manikumar Reddy <manikumar.reddy@gmail.com>, Chia-Ping Tsai <chia7712@gmail.com>
5 years ago
maxHeapSize = defaultMaxHeapSize
jvmArgs = defaultJvmArgs
}
// Ignore core since its a scala project
if ( it . path ! = ':core' ) {
if ( userEnableTestCoverage ) {
apply plugin: "jacoco"
jacoco {
toolVersion = versions . jacoco
}
// NOTE: Jacoco Gradle plugin does not support "offline instrumentation" this means that classes mocked by PowerMock
// may report 0 coverage, since the source was modified after initial instrumentation.
// See https://github.com/jacoco/jacoco/issues/51
jacocoTestReport {
dependsOn tasks . test
sourceSets sourceSets . main
reports {
html . enabled = true
xml . enabled = true
csv . enabled = false
}
}
}
}
if ( userEnableTestCoverage ) {
def coverageGen = it . path = = ':core' ? 'reportScoverage' : 'jacocoTestReport'
task reportCoverage ( dependsOn: [ coverageGen ] )
}
}
gradle . taskGraph . whenReady { taskGraph - >
taskGraph . getAllTasks ( ) . findAll { it . name . contains ( 'spotbugsScoverage' ) | | it . name . contains ( 'spotbugsTest' ) } . each { task - >
task . enabled = false
}
}
def fineTuneEclipseClasspathFile ( eclipse , project ) {
eclipse . classpath . file {
beforeMerged { cp - >
cp . entries . clear ( )
// for the core project add the directories defined under test/scala as separate source directories
if ( project . name . equals ( 'core' ) ) {
cp . entries . add ( new org . gradle . plugins . ide . eclipse . model . SourceFolder ( "src/test/scala/integration" , null ) )
cp . entries . add ( new org . gradle . plugins . ide . eclipse . model . SourceFolder ( "src/test/scala/other" , null ) )
cp . entries . add ( new org . gradle . plugins . ide . eclipse . model . SourceFolder ( "src/test/scala/unit" , null ) )
}
}
whenMerged { cp - >
// for the core project exclude the separate sub-directories defined under test/scala. These are added as source dirs above
if ( project . name . equals ( 'core' ) ) {
cp . entries . findAll { it . kind = = "src" & & it . path . equals ( "src/test/scala" ) } * . excludes = [ "integration/" , "other/" , "unit/" ]
}
/ *
* Set all eclipse build output to go to 'build_eclipse' directory . This is to ensure that gradle and eclipse use different
* build output directories , and also avoid using the eclpise default of 'bin' which clashes with some of our script directories .
* https: //discuss.gradle.org/t/eclipse-generated-files-should-be-put-in-the-same-place-as-the-gradle-generated-files/6986/2
* /
cp . entries . findAll { it . kind = = "output" } * . path = "build_eclipse"
/ *
* Some projects have explicitly added test output dependencies . These are required for the gradle build but not required
* in Eclipse since the dependent projects are added as dependencies . So clean up these from the generated classpath .
* /
cp . entries . removeAll { it . kind = = "lib" & & it . path . matches ( ".*/build/(classes|resources)/test" ) }
}
}
}
def checkstyleConfigProperties ( configFileName ) {
[ importControlFile: "$rootDir/checkstyle/$configFileName" ,
suppressionsFile: "$rootDir/checkstyle/suppressions.xml" ,
headerFile: "$rootDir/checkstyle/java.header" ]
}
// Aggregates all jacoco results into the root project directory
if ( userEnableTestCoverage ) {
task jacocoRootReport ( type: org . gradle . testing . jacoco . tasks . JacocoReport ) {
def javaProjects = subprojects . findAll { it . path ! = ':core' }
description = 'Generates an aggregate report from all subprojects'
dependsOn ( javaProjects . test )
additionalSourceDirs . from = javaProjects . sourceSets . main . allSource . srcDirs
sourceDirectories . from = javaProjects . sourceSets . main . allSource . srcDirs
classDirectories . from = javaProjects . sourceSets . main . output
executionData . from = javaProjects . jacocoTestReport . executionData
reports {
html . enabled = true
xml . enabled = true
}
// workaround to ignore projects that don't have any tests at all
onlyIf = { true }
doFirst {
executionData = files ( executionData . findAll { it . exists ( ) } )
}
}
}
if ( userEnableTestCoverage ) {
task reportCoverage ( dependsOn: [ 'jacocoRootReport' , 'core:reportCoverage' ] )
}
def connectPkgs = [
'connect:api' ,
'connect:basic-auth-extension' ,
'connect:file' ,
'connect:json' ,
'connect:runtime' ,
KAFKA-7500: MirrorMaker 2.0 (KIP-382)
Implementation of [KIP-382 "MirrorMaker 2.0"](https://cwiki.apache.org/confluence/display/KAFKA/KIP-382%3A+MirrorMaker+2.0)
Author: Ryanne Dolan <ryannedolan@gmail.com>
Author: Arun Mathew <arunmathew88@gmail.com>
Author: In Park <inpark@cloudera.com>
Author: Andre Price <obsoleted@users.noreply.github.com>
Author: christian.hagel@rio.cloud <christian.hagel@rio.cloud>
Reviewers: Eno Thereska <eno.thereska@gmail.com>, William Hammond <william.t.hammond@gmail.com>, Viktor Somogyi <viktorsomogyi@gmail.com>, Jakub Korzeniowski, Tim Carey-Smith, Kamal Chandraprakash <kamal.chandraprakash@gmail.com>, Arun Mathew, Jeremy-l-ford, vpernin, Oleg Kasian <oleg.kasian@gmail.com>, Mickael Maison <mickael.maison@gmail.com>, Qihong Chen, Sriharsha Chintalapani <sriharsha@apache.org>, Jun Rao <junrao@gmail.com>, Randall Hauch <rhauch@gmail.com>, Manikumar Reddy <manikumar.reddy@gmail.com>, Ismael Juma <ismael@juma.me.uk>
Closes #6295 from ryannedolan/KIP-382
5 years ago
'connect:transforms' ,
'connect:mirror' ,
'connect:mirror-client'
]
tasks . create ( name: "jarConnect" , dependsOn: connectPkgs . collect { it + ":jar" } ) { }
tasks . create ( name: "testConnect" , dependsOn: connectPkgs . collect { it + ":test" } ) { }
project ( ':core' ) {
apply plugin: 'scala'
// scaladoc generation is configured at the sub-module level with an artifacts
// block (cf. see streams-scala). If scaladoc generation is invoked explicitly
// for the `core` module, this ensures the generated jar doesn't include scaladoc
// files since the `core` module doesn't include public APIs.
scaladoc {
enabled = false
}
if ( userEnableTestCoverage )
apply plugin: "org.scoverage"
archivesBaseName = "kafka_${versions.baseScala}"
configurations {
generator
}
dependencies {
// `core` is often used in users' tests, define the following dependencies as `api` for backwards compatibility
// even though the `core` module doesn't expose any public API
api project ( ':clients' )
api libs . scalaLibrary
implementation project ( ':server-common' )
implementation project ( ':group-coordinator' )
implementation project ( ':metadata' )
[KAFKA-13369] Follower fetch protocol changes for tiered storage. (#11390)
This PR implements the follower fetch protocol as mentioned in KIP-405.
Added a new version for ListOffsets protocol to receive local log start offset on the leader replica. This is used by follower replicas to find the local log star offset on the leader.
Added a new version for FetchRequest protocol to receive OffsetMovedToTieredStorageException error. This is part of the enhanced fetch protocol as described in KIP-405.
We introduced a new field locaLogStartOffset to maintain the log start offset in the local logs. Existing logStartOffset will continue to be the log start offset of the effective log that includes the segments in remote storage.
When a follower receives OffsetMovedToTieredStorage, then it tries to build the required state from the leader and remote storage so that it can be ready to move to fetch state.
Introduced RemoteLogManager which is responsible for
initializing RemoteStorageManager and RemoteLogMetadataManager instances.
receives any leader and follower replica events and partition stop events and act on them
also provides APIs to fetch indexes, metadata about remote log segments.
Followup PRs will add more functionality like copying segments to tiered storage, retention checks to clean local and remote log segments. This will change the local log start offset and make sure the follower fetch protocol works fine for several cases.
You can look at the detailed protocol changes in KIP: https://cwiki.apache.org/confluence/display/KAFKA/KIP-405%3A+Kafka+Tiered+Storage#KIP405:KafkaTieredStorage-FollowerReplication
Co-authors: satishd@apache.org, kamal.chandraprakash@gmail.com, yingz@uber.com
Reviewers: Kowshik Prakasam <kprakasam@confluent.io>, Cong Ding <cong@ccding.com>, Tirtha Chatterjee <tirtha.p.chatterjee@gmail.com>, Yaodong Yang <yangyaodong88@gmail.com>, Divij Vaidya <diviv@amazon.com>, Luke Chen <showuon@gmail.com>, Jun Rao <junrao@gmail.com>
2 years ago
implementation project ( ':storage:api' )
implementation project ( ':raft' )
implementation project ( ':storage' )
implementation libs . argparse4j
implementation libs . jacksonDatabind
implementation libs . jacksonModuleScala
implementation libs . jacksonDataformatCsv
implementation libs . jacksonJDK8Datatypes
implementation libs . joptSimple
implementation libs . jose4j
implementation libs . metrics
implementation libs . scalaCollectionCompat
implementation libs . scalaJava8Compat
// only needed transitively, but set it explicitly to ensure it has the same version as scala-library
implementation libs . scalaReflect
implementation libs . scalaLogging
implementation libs . slf4jApi
implementation ( libs . zookeeper ) {
// Dropwizard Metrics are required by ZooKeeper as of v3.6.0,
// but the library should *not* be used in Kafka code
implementation libs . dropwizardMetrics
exclude module: 'slf4j-log4j12'
exclude module: 'log4j'
}
// ZooKeeperMain depends on commons-cli but declares the dependency as `provided`
implementation libs . commonsCli
compileOnly libs . log4j
testImplementation project ( ':clients' ) . sourceSets . test . output
testImplementation project ( ':group-coordinator' ) . sourceSets . test . output
testImplementation project ( ':metadata' ) . sourceSets . test . output
testImplementation project ( ':raft' ) . sourceSets . test . output
KAFKA-14124: improve quorum controller fault handling (#12447)
Before trying to commit a batch of records to the __cluster_metadata log, the active controller
should try to apply them to its current in-memory state. If this application process fails, the
active controller process should exit, allowing another node to take leadership. This will prevent
most bad metadata records from ending up in the log and help to surface errors during testing.
Similarly, if the active controller attempts to renounce leadership, and the renunciation process
itself fails, the process should exit. This will help avoid bugs where the active controller
continues in an undefined state.
In contrast, standby controllers that experience metadata application errors should continue on, in
order to avoid a scenario where a bad record brings down the whole controller cluster. The
intended effect of these changes is to make it harder to commit a bad record to the metadata log,
but to continue to ride out the bad record as well as possible if such a record does get committed.
This PR introduces the FaultHandler interface to implement these concepts. In junit tests, we use a
FaultHandler implementation which does not exit the process. This allows us to avoid terminating
the gradle test runner, which would be very disruptive. It also allows us to ensure that the test
surfaces these exceptions, which we previously were not doing (the mock fault handler stores the
exception).
In addition to the above, this PR fixes a bug where RaftClient#resign was not being called from the
renounce() function. This bug could have resulted in the raft layer not being informed of an active
controller resigning.
Reviewers: David Arthur <mumrah@gmail.com>
2 years ago
testImplementation project ( ':server-common' ) . sourceSets . test . output
[KAFKA-13369] Follower fetch protocol changes for tiered storage. (#11390)
This PR implements the follower fetch protocol as mentioned in KIP-405.
Added a new version for ListOffsets protocol to receive local log start offset on the leader replica. This is used by follower replicas to find the local log star offset on the leader.
Added a new version for FetchRequest protocol to receive OffsetMovedToTieredStorageException error. This is part of the enhanced fetch protocol as described in KIP-405.
We introduced a new field locaLogStartOffset to maintain the log start offset in the local logs. Existing logStartOffset will continue to be the log start offset of the effective log that includes the segments in remote storage.
When a follower receives OffsetMovedToTieredStorage, then it tries to build the required state from the leader and remote storage so that it can be ready to move to fetch state.
Introduced RemoteLogManager which is responsible for
initializing RemoteStorageManager and RemoteLogMetadataManager instances.
receives any leader and follower replica events and partition stop events and act on them
also provides APIs to fetch indexes, metadata about remote log segments.
Followup PRs will add more functionality like copying segments to tiered storage, retention checks to clean local and remote log segments. This will change the local log start offset and make sure the follower fetch protocol works fine for several cases.
You can look at the detailed protocol changes in KIP: https://cwiki.apache.org/confluence/display/KAFKA/KIP-405%3A+Kafka+Tiered+Storage#KIP405:KafkaTieredStorage-FollowerReplication
Co-authors: satishd@apache.org, kamal.chandraprakash@gmail.com, yingz@uber.com
Reviewers: Kowshik Prakasam <kprakasam@confluent.io>, Cong Ding <cong@ccding.com>, Tirtha Chatterjee <tirtha.p.chatterjee@gmail.com>, Yaodong Yang <yangyaodong88@gmail.com>, Divij Vaidya <diviv@amazon.com>, Luke Chen <showuon@gmail.com>, Jun Rao <junrao@gmail.com>
2 years ago
testImplementation project ( ':storage:api' ) . sourceSets . test . output
testImplementation libs . bcpkix
testImplementation libs . mockitoCore
testImplementation ( libs . apacheda ) {
exclude group: 'xml-apis' , module: 'xml-apis'
// `mina-core` is a transitive dependency for `apacheds` and `apacheda`.
// It is safer to use from `apacheds` since that is the implementation.
exclude module: 'mina-core'
}
testImplementation libs . apachedsCoreApi
testImplementation libs . apachedsInterceptorKerberos
testImplementation libs . apachedsProtocolShared
testImplementation libs . apachedsProtocolKerberos
testImplementation libs . apachedsProtocolLdap
testImplementation libs . apachedsLdifPartition
testImplementation libs . apachedsMavibotPartition
testImplementation libs . apachedsJdbmPartition
testImplementation libs . junitJupiter
testImplementation libs . slf4jlog4j
testImplementation ( libs . jfreechart ) {
exclude group: 'junit' , module: 'junit'
}
generator project ( ':generator' )
}
if ( userEnableTestCoverage ) {
scoverage {
scoverageVersion = versions . scoverage
reportDir = file ( "${rootProject.buildDir}/scoverage" )
highlighting = false
minimumRate = 0.0
}
}
configurations {
// manually excludes some unnecessary dependencies
implementation . exclude module: 'javax'
implementation . exclude module: 'jline'
implementation . exclude module: 'jms'
implementation . exclude module: 'jmxri'
implementation . exclude module: 'jmxtools'
implementation . exclude module: 'mail'
// To prevent a UniqueResourceException due the same resource existing in both
// org.apache.directory.api/api-all and org.apache.directory.api/api-ldap-schema-data
testImplementation . exclude module: 'api-ldap-schema-data'
}
tasks . create ( name: "copyDependantLibs" , type: Copy ) {
from ( configurations . testRuntimeClasspath ) {
include ( 'slf4j-log4j12*' )
include ( 'reload4j*jar' )
}
from ( configurations . runtimeClasspath ) {
exclude ( 'kafka-clients*' )
}
into "$buildDir/dependant-libs-${versions.scala}"
duplicatesStrategy 'exclude'
}
task processMessages ( type: JavaExec ) {
mainClass = "org.apache.kafka.message.MessageGenerator"
classpath = configurations . generator
args = [ "-p" , "kafka.internals.generated" ,
"-o" , "src/generated/java/kafka/internals/generated" ,
"-i" , "src/main/resources/common/message" ,
"-m" , "MessageDataGenerator"
]
inputs . dir ( "src/main/resources/common/message" )
. withPropertyName ( "messages" )
. withPathSensitivity ( PathSensitivity . RELATIVE )
outputs . cacheIf { true }
outputs . dir ( "src/generated/java/kafka/internals/generated" )
}
compileJava . dependsOn 'processMessages'
task genProtocolErrorDocs ( type: JavaExec ) {
classpath = sourceSets . main . runtimeClasspath
mainClass = 'org.apache.kafka.common.protocol.Errors'
if ( ! generatedDocsDir . exists ( ) ) { generatedDocsDir . mkdirs ( ) }
standardOutput = new File ( generatedDocsDir , "protocol_errors.html" ) . newOutputStream ( )
}
task genProtocolTypesDocs ( type: JavaExec ) {
classpath = sourceSets . main . runtimeClasspath
mainClass = 'org.apache.kafka.common.protocol.types.Type'
if ( ! generatedDocsDir . exists ( ) ) { generatedDocsDir . mkdirs ( ) }
standardOutput = new File ( generatedDocsDir , "protocol_types.html" ) . newOutputStream ( )
}
task genProtocolApiKeyDocs ( type: JavaExec ) {
classpath = sourceSets . main . runtimeClasspath
mainClass = 'org.apache.kafka.common.protocol.ApiKeys'
if ( ! generatedDocsDir . exists ( ) ) { generatedDocsDir . mkdirs ( ) }
standardOutput = new File ( generatedDocsDir , "protocol_api_keys.html" ) . newOutputStream ( )
}
task genProtocolMessageDocs ( type: JavaExec ) {
classpath = sourceSets . main . runtimeClasspath
mainClass = 'org.apache.kafka.common.protocol.Protocol'
if ( ! generatedDocsDir . exists ( ) ) { generatedDocsDir . mkdirs ( ) }
standardOutput = new File ( generatedDocsDir , "protocol_messages.html" ) . newOutputStream ( )
}
task genAdminClientConfigDocs ( type: JavaExec ) {
classpath = sourceSets . main . runtimeClasspath
mainClass = 'org.apache.kafka.clients.admin.AdminClientConfig'
if ( ! generatedDocsDir . exists ( ) ) { generatedDocsDir . mkdirs ( ) }
standardOutput = new File ( generatedDocsDir , "admin_client_config.html" ) . newOutputStream ( )
}
task genProducerConfigDocs ( type: JavaExec ) {
classpath = sourceSets . main . runtimeClasspath
mainClass = 'org.apache.kafka.clients.producer.ProducerConfig'
if ( ! generatedDocsDir . exists ( ) ) { generatedDocsDir . mkdirs ( ) }
standardOutput = new File ( generatedDocsDir , "producer_config.html" ) . newOutputStream ( )
}
task genConsumerConfigDocs ( type: JavaExec ) {
classpath = sourceSets . main . runtimeClasspath
mainClass = 'org.apache.kafka.clients.consumer.ConsumerConfig'
if ( ! generatedDocsDir . exists ( ) ) { generatedDocsDir . mkdirs ( ) }
standardOutput = new File ( generatedDocsDir , "consumer_config.html" ) . newOutputStream ( )
}
task genKafkaConfigDocs ( type: JavaExec ) {
classpath = sourceSets . main . runtimeClasspath
mainClass = 'kafka.server.KafkaConfig'
if ( ! generatedDocsDir . exists ( ) ) { generatedDocsDir . mkdirs ( ) }
standardOutput = new File ( generatedDocsDir , "kafka_config.html" ) . newOutputStream ( )
}
KAFKA-3809: Auto-generate documentation for topic-level configuration
ijuma said that it would make sense to split out this work from KAFKA-3234, since KAFKA-3234 had both a mechanical change (generating docs) as well as a change requiring discussion (deprecating/renaming config options).
jjkoshy, I hope you don't mind that I took over this work. It's been 3 months since the last activity on KAFKA-3234, so I thought it would be okay to take over.
This work is essentially is the first 5-6 commits from Joel's https://github.com/apache/kafka/pull/907. However, since I'm not very experienced with git, I didn't do a direct merge/rebase, but instead largely hand-merged it. I did some minor cleanup. All credit goes to Joel, all blame goes to me. :)
For reference, I attached the auto-generated configuration.html file (as a PDF, because github won't let me attache html).
[configuration.pdf](https://github.com/apache/kafka/files/323901/configuration.pdf)
This is my first time writing Scala, so let me know if there are any changes needed.
I don't know who is the right person to review this. ijuma, can you help me redirect this to the appropriate person? Thanks.
Author: James Cheng <jylcheng@yahoo.com>
Reviewers: Ismael Juma <ismael@juma.me.uk>, Joel Koshy <jjkoshy@gmail.com>, Ewen Cheslack-Postava <ewen@confluent.io>
Closes #1527 from wushujames/generate_topic_docs
8 years ago
task genTopicConfigDocs ( type: JavaExec ) {
classpath = sourceSets . main . runtimeClasspath
mainClass = 'org.apache.kafka.server.log.internals.LogConfig'
KAFKA-3809: Auto-generate documentation for topic-level configuration
ijuma said that it would make sense to split out this work from KAFKA-3234, since KAFKA-3234 had both a mechanical change (generating docs) as well as a change requiring discussion (deprecating/renaming config options).
jjkoshy, I hope you don't mind that I took over this work. It's been 3 months since the last activity on KAFKA-3234, so I thought it would be okay to take over.
This work is essentially is the first 5-6 commits from Joel's https://github.com/apache/kafka/pull/907. However, since I'm not very experienced with git, I didn't do a direct merge/rebase, but instead largely hand-merged it. I did some minor cleanup. All credit goes to Joel, all blame goes to me. :)
For reference, I attached the auto-generated configuration.html file (as a PDF, because github won't let me attache html).
[configuration.pdf](https://github.com/apache/kafka/files/323901/configuration.pdf)
This is my first time writing Scala, so let me know if there are any changes needed.
I don't know who is the right person to review this. ijuma, can you help me redirect this to the appropriate person? Thanks.
Author: James Cheng <jylcheng@yahoo.com>
Reviewers: Ismael Juma <ismael@juma.me.uk>, Joel Koshy <jjkoshy@gmail.com>, Ewen Cheslack-Postava <ewen@confluent.io>
Closes #1527 from wushujames/generate_topic_docs
8 years ago
if ( ! generatedDocsDir . exists ( ) ) { generatedDocsDir . mkdirs ( ) }
standardOutput = new File ( generatedDocsDir , "topic_config.html" ) . newOutputStream ( )
}
task genConsumerMetricsDocs ( type: JavaExec ) {
classpath = sourceSets . test . runtimeClasspath
mainClass = 'org.apache.kafka.clients.consumer.internals.ConsumerMetrics'
if ( ! generatedDocsDir . exists ( ) ) { generatedDocsDir . mkdirs ( ) }
standardOutput = new File ( generatedDocsDir , "consumer_metrics.html" ) . newOutputStream ( )
}
task genProducerMetricsDocs ( type: JavaExec ) {
classpath = sourceSets . test . runtimeClasspath
mainClass = 'org.apache.kafka.clients.producer.internals.ProducerMetrics'
if ( ! generatedDocsDir . exists ( ) ) { generatedDocsDir . mkdirs ( ) }
standardOutput = new File ( generatedDocsDir , "producer_metrics.html" ) . newOutputStream ( )
}
task siteDocsTar ( dependsOn: [ 'genProtocolErrorDocs' , 'genProtocolTypesDocs' , 'genProtocolApiKeyDocs' , 'genProtocolMessageDocs' ,
'genAdminClientConfigDocs' , 'genProducerConfigDocs' , 'genConsumerConfigDocs' ,
'genKafkaConfigDocs' , 'genTopicConfigDocs' ,
':connect:runtime:genConnectConfigDocs' , ':connect:runtime:genConnectTransformationDocs' ,
':connect:runtime:genConnectPredicateDocs' ,
':connect:runtime:genSinkConnectorConfigDocs' , ':connect:runtime:genSourceConnectorConfigDocs' ,
':streams:genStreamsConfigDocs' , 'genConsumerMetricsDocs' , 'genProducerMetricsDocs' ,
':connect:runtime:genConnectMetricsDocs' , ':connect:runtime:genConnectOpenAPIDocs' ,
':connect:mirror:genMirrorSourceConfigDocs' , ':connect:mirror:genMirrorCheckpointConfigDocs' ,
':connect:mirror:genMirrorHeartbeatConfigDocs' ] , type: Tar ) {
archiveClassifier = 'site-docs'
compression = Compression . GZIP
from project . file ( "$rootDir/docs" )
into 'site-docs'
duplicatesStrategy 'exclude'
}
tasks . create ( name: "releaseTarGz" , dependsOn: configurations . archives . artifacts , type: Tar ) {
into "kafka_${versions.baseScala}-${archiveVersion.get()}"
compression = Compression . GZIP
from ( project . file ( "$rootDir/bin" ) ) { into "bin/" }
from ( project . file ( "$rootDir/config" ) ) { into "config/" }
from ( project . file ( "$rootDir/licenses" ) ) { into "licenses/" }
from "$rootDir/LICENSE-binary" rename { String filename - > filename . replace ( "-binary" , "" ) }
from "$rootDir/NOTICE-binary" rename { String filename - > filename . replace ( "-binary" , "" ) }
from ( configurations . runtimeClasspath ) { into ( "libs/" ) }
from ( configurations . archives . artifacts . files ) { into ( "libs/" ) }
from ( project . siteDocsTar ) { into ( "site-docs/" ) }
from ( project ( ':tools' ) . jar ) { into ( "libs/" ) }
from ( project ( ':tools' ) . configurations . runtimeClasspath ) { into ( "libs/" ) }
from ( project ( ':trogdor' ) . jar ) { into ( "libs/" ) }
from ( project ( ':trogdor' ) . configurations . runtimeClasspath ) { into ( "libs/" ) }
from ( project ( ':shell' ) . jar ) { into ( "libs/" ) }
from ( project ( ':shell' ) . configurations . runtimeClasspath ) { into ( "libs/" ) }
from ( project ( ':connect:api' ) . jar ) { into ( "libs/" ) }
from ( project ( ':connect:api' ) . configurations . runtimeClasspath ) { into ( "libs/" ) }
from ( project ( ':connect:runtime' ) . jar ) { into ( "libs/" ) }
from ( project ( ':connect:runtime' ) . configurations . runtimeClasspath ) { into ( "libs/" ) }
from ( project ( ':connect:transforms' ) . jar ) { into ( "libs/" ) }
from ( project ( ':connect:transforms' ) . configurations . runtimeClasspath ) { into ( "libs/" ) }
from ( project ( ':connect:json' ) . jar ) { into ( "libs/" ) }
from ( project ( ':connect:json' ) . configurations . runtimeClasspath ) { into ( "libs/" ) }
from ( project ( ':connect:file' ) . jar ) { into ( "libs/" ) }
from ( project ( ':connect:file' ) . configurations . runtimeClasspath ) { into ( "libs/" ) }
from ( project ( ':connect:basic-auth-extension' ) . jar ) { into ( "libs/" ) }
from ( project ( ':connect:basic-auth-extension' ) . configurations . runtimeClasspath ) { into ( "libs/" ) }
KAFKA-7500: MirrorMaker 2.0 (KIP-382)
Implementation of [KIP-382 "MirrorMaker 2.0"](https://cwiki.apache.org/confluence/display/KAFKA/KIP-382%3A+MirrorMaker+2.0)
Author: Ryanne Dolan <ryannedolan@gmail.com>
Author: Arun Mathew <arunmathew88@gmail.com>
Author: In Park <inpark@cloudera.com>
Author: Andre Price <obsoleted@users.noreply.github.com>
Author: christian.hagel@rio.cloud <christian.hagel@rio.cloud>
Reviewers: Eno Thereska <eno.thereska@gmail.com>, William Hammond <william.t.hammond@gmail.com>, Viktor Somogyi <viktorsomogyi@gmail.com>, Jakub Korzeniowski, Tim Carey-Smith, Kamal Chandraprakash <kamal.chandraprakash@gmail.com>, Arun Mathew, Jeremy-l-ford, vpernin, Oleg Kasian <oleg.kasian@gmail.com>, Mickael Maison <mickael.maison@gmail.com>, Qihong Chen, Sriharsha Chintalapani <sriharsha@apache.org>, Jun Rao <junrao@gmail.com>, Randall Hauch <rhauch@gmail.com>, Manikumar Reddy <manikumar.reddy@gmail.com>, Ismael Juma <ismael@juma.me.uk>
Closes #6295 from ryannedolan/KIP-382
5 years ago
from ( project ( ':connect:mirror' ) . jar ) { into ( "libs/" ) }
from ( project ( ':connect:mirror' ) . configurations . runtimeClasspath ) { into ( "libs/" ) }
KAFKA-7500: MirrorMaker 2.0 (KIP-382)
Implementation of [KIP-382 "MirrorMaker 2.0"](https://cwiki.apache.org/confluence/display/KAFKA/KIP-382%3A+MirrorMaker+2.0)
Author: Ryanne Dolan <ryannedolan@gmail.com>
Author: Arun Mathew <arunmathew88@gmail.com>
Author: In Park <inpark@cloudera.com>
Author: Andre Price <obsoleted@users.noreply.github.com>
Author: christian.hagel@rio.cloud <christian.hagel@rio.cloud>
Reviewers: Eno Thereska <eno.thereska@gmail.com>, William Hammond <william.t.hammond@gmail.com>, Viktor Somogyi <viktorsomogyi@gmail.com>, Jakub Korzeniowski, Tim Carey-Smith, Kamal Chandraprakash <kamal.chandraprakash@gmail.com>, Arun Mathew, Jeremy-l-ford, vpernin, Oleg Kasian <oleg.kasian@gmail.com>, Mickael Maison <mickael.maison@gmail.com>, Qihong Chen, Sriharsha Chintalapani <sriharsha@apache.org>, Jun Rao <junrao@gmail.com>, Randall Hauch <rhauch@gmail.com>, Manikumar Reddy <manikumar.reddy@gmail.com>, Ismael Juma <ismael@juma.me.uk>
Closes #6295 from ryannedolan/KIP-382
5 years ago
from ( project ( ':connect:mirror-client' ) . jar ) { into ( "libs/" ) }
from ( project ( ':connect:mirror-client' ) . configurations . runtimeClasspath ) { into ( "libs/" ) }
from ( project ( ':streams' ) . jar ) { into ( "libs/" ) }
from ( project ( ':streams' ) . configurations . runtimeClasspath ) { into ( "libs/" ) }
from ( project ( ':streams:streams-scala' ) . jar ) { into ( "libs/" ) }
from ( project ( ':streams:streams-scala' ) . configurations . runtimeClasspath ) { into ( "libs/" ) }
from ( project ( ':streams:test-utils' ) . jar ) { into ( "libs/" ) }
from ( project ( ':streams:test-utils' ) . configurations . runtimeClasspath ) { into ( "libs/" ) }
from ( project ( ':streams:examples' ) . jar ) { into ( "libs/" ) }
from ( project ( ':streams:examples' ) . configurations . runtimeClasspath ) { into ( "libs/" ) }
duplicatesStrategy 'exclude'
}
jar {
dependsOn ( 'copyDependantLibs' )
}
jar . manifest {
attributes (
'Version' : "${version}"
)
}
tasks . create ( name: "copyDependantTestLibs" , type: Copy ) {
from ( configurations . testRuntimeClasspath ) {
include ( '*.jar' )
}
into "$buildDir/dependant-testlibs"
//By default gradle does not handle test dependencies between the sub-projects
//This line is to include clients project test jar to dependant-testlibs
from ( project ( ':clients' ) . testJar ) { "$buildDir/dependant-testlibs" }
duplicatesStrategy 'exclude'
}
systemTestLibs . dependsOn ( 'jar' , 'testJar' , 'copyDependantTestLibs' )
checkstyle {
configProperties = checkstyleConfigProperties ( "import-control-core.xml" )
}
sourceSets {
// Set java/scala source folders in the `scala` block to enable joint compilation
main {
java {
srcDirs = [ ]
}
scala {
srcDirs = [ "src/generated/java" , "src/main/java" , "src/main/scala" ]
}
}
test {
java {
srcDirs = [ ]
}
scala {
srcDirs = [ "src/test/java" , "src/test/scala" ]
}
}
}
}
project ( ':metadata' ) {
archivesBaseName = "kafka-metadata"
configurations {
generator
}
dependencies {
implementation project ( ':server-common' )
implementation project ( ':clients' )
implementation project ( ':raft' )
implementation libs . jacksonDatabind
implementation libs . jacksonJDK8Datatypes
implementation libs . metrics
compileOnly libs . log4j
testImplementation libs . junitJupiter
testImplementation libs . jqwik
testImplementation libs . hamcrest
testImplementation libs . mockitoCore
testImplementation libs . mockitoInline
testImplementation libs . slf4jlog4j
testImplementation project ( ':clients' ) . sourceSets . test . output
testImplementation project ( ':raft' ) . sourceSets . test . output
KAFKA-14124: improve quorum controller fault handling (#12447)
Before trying to commit a batch of records to the __cluster_metadata log, the active controller
should try to apply them to its current in-memory state. If this application process fails, the
active controller process should exit, allowing another node to take leadership. This will prevent
most bad metadata records from ending up in the log and help to surface errors during testing.
Similarly, if the active controller attempts to renounce leadership, and the renunciation process
itself fails, the process should exit. This will help avoid bugs where the active controller
continues in an undefined state.
In contrast, standby controllers that experience metadata application errors should continue on, in
order to avoid a scenario where a bad record brings down the whole controller cluster. The
intended effect of these changes is to make it harder to commit a bad record to the metadata log,
but to continue to ride out the bad record as well as possible if such a record does get committed.
This PR introduces the FaultHandler interface to implement these concepts. In junit tests, we use a
FaultHandler implementation which does not exit the process. This allows us to avoid terminating
the gradle test runner, which would be very disruptive. It also allows us to ensure that the test
surfaces these exceptions, which we previously were not doing (the mock fault handler stores the
exception).
In addition to the above, this PR fixes a bug where RaftClient#resign was not being called from the
renounce() function. This bug could have resulted in the raft layer not being informed of an active
controller resigning.
Reviewers: David Arthur <mumrah@gmail.com>
2 years ago
testImplementation project ( ':server-common' ) . sourceSets . test . output
generator project ( ':generator' )
}
task processMessages ( type: JavaExec ) {
mainClass = "org.apache.kafka.message.MessageGenerator"
classpath = configurations . generator
args = [ "-p" , "org.apache.kafka.common.metadata" ,
"-o" , "src/generated/java/org/apache/kafka/common/metadata" ,
"-i" , "src/main/resources/common/metadata" ,
"-m" , "MessageDataGenerator" , "JsonConverterGenerator" ,
"-t" , "MetadataRecordTypeGenerator" , "MetadataJsonConvertersGenerator"
]
inputs . dir ( "src/main/resources/common/metadata" )
. withPropertyName ( "messages" )
. withPathSensitivity ( PathSensitivity . RELATIVE )
outputs . cacheIf { true }
outputs . dir ( "src/generated/java/org/apache/kafka/common/metadata" )
}
compileJava . dependsOn 'processMessages'
sourceSets {
main {
java {
srcDirs = [ "src/generated/java" , "src/main/java" ]
}
}
test {
java {
srcDirs = [ "src/generated/java" , "src/test/java" ]
}
}
}
javadoc {
enabled = false
}
}
project ( ':group-coordinator' ) {
archivesBaseName = "kafka-group-coordinator"
dependencies {
implementation project ( ':server-common' )
implementation project ( ':clients' )
implementation libs . slf4jApi
testImplementation project ( ':clients' ) . sourceSets . test . output
testImplementation project ( ':server-common' ) . sourceSets . test . output
testImplementation libs . junitJupiter
testImplementation libs . mockitoCore
testRuntimeOnly libs . slf4jlog4j
}
sourceSets {
main {
java {
srcDirs = [ "src/generated/java" , "src/main/java" ]
}
}
test {
java {
srcDirs = [ "src/generated/java" , "src/test/java" ]
}
}
}
javadoc {
enabled = false
}
}
project ( ':examples' ) {
archivesBaseName = "kafka-examples"
dependencies {
implementation project ( ':clients' )
implementation project ( ':core' )
}
javadoc {
enabled = false
}
checkstyle {
configProperties = checkstyleConfigProperties ( "import-control-core.xml" )
}
}
project ( ':generator' ) {
dependencies {
implementation libs . argparse4j
implementation libs . jacksonDatabind
implementation libs . jacksonJDK8Datatypes
implementation libs . jacksonJaxrsJsonProvider
testImplementation libs . junitJupiter
}
javadoc {
enabled = false
}
}
project ( ':clients' ) {
archivesBaseName = "kafka-clients"
configurations {
generator
}
dependencies {
implementation libs . zstd
implementation libs . lz4
implementation libs . snappy
implementation libs . slf4jApi
compileOnly libs . jacksonDatabind // for SASL/OAUTHBEARER bearer token parsing
compileOnly libs . jacksonJDK8Datatypes
compileOnly libs . jose4j // for SASL/OAUTHBEARER JWT validation; only used by broker
testImplementation libs . bcpkix
testImplementation libs . jacksonJaxrsJsonProvider
testImplementation libs . jose4j
testImplementation libs . junitJupiter
testImplementation libs . log4j
testImplementation libs . mockitoInline
testRuntimeOnly libs . slf4jlog4j
testRuntimeOnly libs . jacksonDatabind
testRuntimeOnly libs . jacksonJDK8Datatypes
generator project ( ':generator' )
}
task createVersionFile ( ) {
def receiptFile = file ( "$buildDir/kafka/$buildVersionFileName" )
inputs . property "commitId" , commitId
inputs . property "version" , version
outputs . file receiptFile
doLast {
def data = [
commitId: commitId ,
version: version ,
]
receiptFile . parentFile . mkdirs ( )
def content = data . entrySet ( ) . collect { "$it.key=$it.value" } . sort ( ) . join ( "\n" )
receiptFile . setText ( content , "ISO-8859-1" )
}
}
jar {
dependsOn createVersionFile
from ( "$buildDir" ) {
include "kafka/$buildVersionFileName"
}
}
clean . doFirst {
delete "$buildDir/kafka/"
}
task processMessages ( type: JavaExec ) {
mainClass = "org.apache.kafka.message.MessageGenerator"
classpath = configurations . generator
args = [ "-p" , "org.apache.kafka.common.message" ,
"-o" , "src/generated/java/org/apache/kafka/common/message" ,
"-i" , "src/main/resources/common/message" ,
"-t" , "ApiMessageTypeGenerator" ,
"-m" , "MessageDataGenerator" , "JsonConverterGenerator"
]
inputs . dir ( "src/main/resources/common/message" )
. withPropertyName ( "messages" )
. withPathSensitivity ( PathSensitivity . RELATIVE )
outputs . cacheIf { true }
outputs . dir ( "src/generated/java/org/apache/kafka/common/message" )
}
task processTestMessages ( type: JavaExec ) {
mainClass = "org.apache.kafka.message.MessageGenerator"
classpath = configurations . generator
args = [ "-p" , "org.apache.kafka.common.message" ,
"-o" , "src/generated-test/java/org/apache/kafka/common/message" ,
"-i" , "src/test/resources/common/message" ,
"-m" , "MessageDataGenerator" , "JsonConverterGenerator"
]
inputs . dir ( "src/test/resources/common/message" )
. withPropertyName ( "testMessages" )
. withPathSensitivity ( PathSensitivity . RELATIVE )
outputs . cacheIf { true }
outputs . dir ( "src/generated-test/java/org/apache/kafka/common/message" )
}
sourceSets {
main {
java {
srcDirs = [ "src/generated/java" , "src/main/java" ]
}
}
test {
java {
srcDirs = [ "src/generated-test/java" , "src/test/java" ]
}
}
}
compileJava . dependsOn 'processMessages'
compileTestJava . dependsOn 'processTestMessages'
javadoc {
include "**/org/apache/kafka/clients/admin/*"
include "**/org/apache/kafka/clients/consumer/*"
include "**/org/apache/kafka/clients/producer/*"
include "**/org/apache/kafka/common/*"
include "**/org/apache/kafka/common/acl/*"
include "**/org/apache/kafka/common/annotation/*"
include "**/org/apache/kafka/common/errors/*"
include "**/org/apache/kafka/common/header/*"
include "**/org/apache/kafka/common/metrics/*"
include "**/org/apache/kafka/common/metrics/stats/*"
include "**/org/apache/kafka/common/quota/*"
include "**/org/apache/kafka/common/resource/*"
include "**/org/apache/kafka/common/serialization/*"
include "**/org/apache/kafka/common/config/*"
include "**/org/apache/kafka/common/config/provider/*"
include "**/org/apache/kafka/common/security/auth/*"
include "**/org/apache/kafka/common/security/plain/*"
include "**/org/apache/kafka/common/security/scram/*"
include "**/org/apache/kafka/common/security/token/delegation/*"
include "**/org/apache/kafka/common/security/oauthbearer/*"
include "**/org/apache/kafka/common/security/oauthbearer/secured/*"
include "**/org/apache/kafka/server/authorizer/*"
include "**/org/apache/kafka/server/policy/*"
include "**/org/apache/kafka/server/quota/*"
}
}
project ( ':raft' ) {
archivesBaseName = "kafka-raft"
configurations {
generator
}
dependencies {
implementation project ( ':server-common' )
implementation project ( ':clients' )
implementation libs . slf4jApi
implementation libs . jacksonDatabind
testImplementation project ( ':server-common' )
testImplementation project ( ':clients' )
testImplementation project ( ':clients' ) . sourceSets . test . output
testImplementation libs . junitJupiter
testImplementation libs . mockitoCore
testImplementation libs . jqwik
testRuntimeOnly libs . slf4jlog4j
generator project ( ':generator' )
}
task createVersionFile ( ) {
def receiptFile = file ( "$buildDir/kafka/$buildVersionFileName" )
inputs . property "commitId" , commitId
inputs . property "version" , version
outputs . file receiptFile
doLast {
def data = [
commitId: commitId ,
version: version ,
]
receiptFile . parentFile . mkdirs ( )
def content = data . entrySet ( ) . collect { "$it.key=$it.value" } . sort ( ) . join ( "\n" )
receiptFile . setText ( content , "ISO-8859-1" )
}
}
task processMessages ( type: JavaExec ) {
mainClass = "org.apache.kafka.message.MessageGenerator"
classpath = configurations . generator
args = [ "-p" , "org.apache.kafka.raft.generated" ,
"-o" , "src/generated/java/org/apache/kafka/raft/generated" ,
"-i" , "src/main/resources/common/message" ,
"-m" , "MessageDataGenerator" , "JsonConverterGenerator" ]
inputs . dir ( "src/main/resources/common/message" )
. withPropertyName ( "messages" )
. withPathSensitivity ( PathSensitivity . RELATIVE )
outputs . cacheIf { true }
outputs . dir ( "src/generated/java/org/apache/kafka/raft/generated" )
}
sourceSets {
main {
java {
srcDirs = [ "src/generated/java" , "src/main/java" ]
}
}
test {
java {
srcDirs = [ "src/generated/java" , "src/test/java" ]
}
}
}
compileJava . dependsOn 'processMessages'
jar {
dependsOn createVersionFile
from ( "$buildDir" ) {
include "kafka/$buildVersionFileName"
}
}
test {
useJUnitPlatform {
includeEngines 'jqwik' , 'junit-jupiter'
}
}
clean . doFirst {
delete "$buildDir/kafka/"
}
javadoc {
enabled = false
}
}
project ( ':server-common' ) {
archivesBaseName = "kafka-server-common"
dependencies {
api project ( ':clients' )
implementation libs . slf4jApi
implementation libs . metrics
implementation libs . joptSimple
testImplementation project ( ':clients' )
testImplementation project ( ':clients' ) . sourceSets . test . output
testImplementation libs . junitJupiter
testImplementation libs . mockitoCore
testImplementation libs . hamcrest
testRuntimeOnly libs . slf4jlog4j
}
task createVersionFile ( ) {
def receiptFile = file ( "$buildDir/kafka/$buildVersionFileName" )
inputs . property "commitId" , commitId
inputs . property "version" , version
outputs . file receiptFile
doLast {
def data = [
commitId: commitId ,
version: version ,
]
receiptFile . parentFile . mkdirs ( )
def content = data . entrySet ( ) . collect { "$it.key=$it.value" } . sort ( ) . join ( "\n" )
receiptFile . setText ( content , "ISO-8859-1" )
}
}
sourceSets {
main {
java {
srcDirs = [ "src/main/java" ]
}
}
test {
java {
srcDirs = [ "src/test/java" ]
}
}
}
jar {
dependsOn createVersionFile
from ( "$buildDir" ) {
include "kafka/$buildVersionFileName"
}
}
clean . doFirst {
delete "$buildDir/kafka/"
}
}
project ( ':storage:api' ) {
archivesBaseName = "kafka-storage-api"
dependencies {
implementation project ( ':clients' )
implementation libs . slf4jApi
testImplementation project ( ':clients' )
testImplementation project ( ':clients' ) . sourceSets . test . output
testImplementation libs . junitJupiter
testImplementation libs . mockitoCore
testRuntimeOnly libs . slf4jlog4j
}
task createVersionFile ( ) {
def receiptFile = file ( "$buildDir/kafka/$buildVersionFileName" )
inputs . property "commitId" , commitId
inputs . property "version" , version
outputs . file receiptFile
doLast {
def data = [
commitId: commitId ,
version: version ,
]
receiptFile . parentFile . mkdirs ( )
def content = data . entrySet ( ) . collect { "$it.key=$it.value" } . sort ( ) . join ( "\n" )
receiptFile . setText ( content , "ISO-8859-1" )
}
}
sourceSets {
main {
java {
srcDirs = [ "src/main/java" ]
}
}
test {
java {
srcDirs = [ "src/test/java" ]
}
}
}
jar {
dependsOn createVersionFile
from ( "$buildDir" ) {
include "kafka/$buildVersionFileName"
}
}
clean . doFirst {
delete "$buildDir/kafka/"
}
javadoc {
include "**/org/apache/kafka/server/log/remote/storage/*"
}
}
project ( ':storage' ) {
archivesBaseName = "kafka-storage"
configurations {
generator
}
dependencies {
implementation project ( ':storage:api' )
implementation project ( ':server-common' )
implementation project ( ':clients' )
implementation libs . slf4jApi
implementation libs . jacksonDatabind
testImplementation project ( ':clients' )
testImplementation project ( ':clients' ) . sourceSets . test . output
testImplementation project ( ':core' )
testImplementation project ( ':core' ) . sourceSets . test . output
testImplementation project ( ':server-common' )
testImplementation project ( ':server-common' ) . sourceSets . test . output
testImplementation libs . junitJupiter
testImplementation libs . mockitoCore
testImplementation libs . bcpkix
testRuntimeOnly libs . slf4jlog4j
generator project ( ':generator' )
}
task createVersionFile ( ) {
def receiptFile = file ( "$buildDir/kafka/$buildVersionFileName" )
inputs . property "commitId" , commitId
inputs . property "version" , version
outputs . file receiptFile
doLast {
def data = [
commitId: commitId ,
version: version ,
]
receiptFile . parentFile . mkdirs ( )
def content = data . entrySet ( ) . collect { "$it.key=$it.value" } . sort ( ) . join ( "\n" )
receiptFile . setText ( content , "ISO-8859-1" )
}
}
task processMessages ( type: JavaExec ) {
mainClass = "org.apache.kafka.message.MessageGenerator"
classpath = configurations . generator
args = [ "-p" , " org.apache.kafka.server.log.remote.metadata.storage.generated" ,
"-o" , "src/generated/java/org/apache/kafka/server/log/remote/metadata/storage/generated" ,
"-i" , "src/main/resources/message" ,
"-m" , "MessageDataGenerator" , "JsonConverterGenerator" ,
"-t" , "MetadataRecordTypeGenerator" , "MetadataJsonConvertersGenerator" ]
inputs . dir ( "src/main/resources/message" )
. withPropertyName ( "messages" )
. withPathSensitivity ( PathSensitivity . RELATIVE )
outputs . cacheIf { true }
outputs . dir ( "src/generated/java/org/apache/kafka/server/log/remote/metadata/storage/generated" )
}
sourceSets {
main {
java {
srcDirs = [ "src/generated/java" , "src/main/java" ]
}
}
test {
java {
srcDirs = [ "src/generated/java" , "src/test/java" ]
}
}
}
compileJava . dependsOn 'processMessages'
jar {
dependsOn createVersionFile
from ( "$buildDir" ) {
include "kafka/$buildVersionFileName"
}
}
test {
useJUnitPlatform {
includeEngines 'junit-jupiter'
}
}
clean . doFirst {
delete "$buildDir/kafka/"
}
javadoc {
enabled = false
}
}
project ( ':tools' ) {
archivesBaseName = "kafka-tools"
dependencies {
implementation project ( ':clients' )
implementation project ( ':server-common' )
implementation project ( ':log4j-appender' )
implementation libs . argparse4j
implementation libs . jacksonDatabind
implementation libs . jacksonJDK8Datatypes
implementation libs . slf4jApi
implementation libs . log4j
implementation libs . joptSimple
implementation libs . jose4j // for SASL/OAUTHBEARER JWT validation
implementation libs . jacksonJaxrsJsonProvider
testImplementation project ( ':clients' )
testImplementation project ( ':clients' ) . sourceSets . test . output
testImplementation project ( ':core' )
testImplementation project ( ':core' ) . sourceSets . test . output
testImplementation project ( ':server-common' )
testImplementation project ( ':server-common' ) . sourceSets . test . output
testImplementation libs . junitJupiter
testImplementation libs . mockitoInline // supports mocking static methods, final classes, etc.
testImplementation libs . mockitoJunitJupiter // supports MockitoExtension
testImplementation libs . bcpkix // required by the clients test module, but we have to specify it explicitly as gradle does not include the transitive test dependency automatically
testRuntimeOnly libs . slf4jlog4j
}
javadoc {
enabled = false
}
tasks . create ( name: "copyDependantLibs" , type: Copy ) {
from ( configurations . testRuntimeClasspath ) {
include ( 'slf4j-log4j12*' )
include ( 'reload4j*jar' )
}
from ( configurations . runtimeClasspath ) {
exclude ( 'kafka-clients*' )
}
into "$buildDir/dependant-libs-${versions.scala}"
duplicatesStrategy 'exclude'
}
jar {
dependsOn 'copyDependantLibs'
}
}
project ( ':trogdor' ) {
archivesBaseName = "trogdor"
dependencies {
implementation project ( ':clients' )
implementation project ( ':log4j-appender' )
implementation libs . argparse4j
implementation libs . jacksonDatabind
implementation libs . jacksonJDK8Datatypes
implementation libs . slf4jApi
implementation libs . log4j
implementation libs . jacksonJaxrsJsonProvider
implementation libs . jerseyContainerServlet
implementation libs . jerseyHk2
implementation libs . jaxbApi // Jersey dependency that was available in the JDK before Java 9
implementation libs . activation // Jersey dependency that was available in the JDK before Java 9
implementation libs . jettyServer
implementation libs . jettyServlet
implementation libs . jettyServlets
testImplementation project ( ':clients' )
testImplementation libs . junitJupiter
testImplementation project ( ':clients' ) . sourceSets . test . output
testImplementation libs . mockitoInline // supports mocking static methods, final classes, etc.
testRuntimeOnly libs . slf4jlog4j
}
javadoc {
enabled = false
}
tasks . create ( name: "copyDependantLibs" , type: Copy ) {
from ( configurations . testRuntimeClasspath ) {
include ( 'slf4j-log4j12*' )
include ( 'reload4j*jar' )
}
from ( configurations . runtimeClasspath ) {
exclude ( 'kafka-clients*' )
}
into "$buildDir/dependant-libs-${versions.scala}"
duplicatesStrategy 'exclude'
}
jar {
dependsOn 'copyDependantLibs'
}
}
project ( ':shell' ) {
archivesBaseName = "kafka-shell"
dependencies {
implementation libs . argparse4j
implementation libs . jacksonDatabind
implementation libs . jacksonJDK8Datatypes
implementation libs . jline
implementation libs . slf4jApi
implementation project ( ':server-common' )
implementation project ( ':clients' )
implementation project ( ':core' )
implementation project ( ':log4j-appender' )
implementation project ( ':metadata' )
implementation project ( ':raft' )
implementation libs . jose4j // for SASL/OAUTHBEARER JWT validation
implementation libs . jacksonJaxrsJsonProvider
testImplementation project ( ':clients' )
testImplementation libs . junitJupiter
testRuntimeOnly libs . slf4jlog4j
}
javadoc {
enabled = false
}
tasks . create ( name: "copyDependantLibs" , type: Copy ) {
from ( configurations . testRuntimeClasspath ) {
include ( 'jline-*jar' )
}
from ( configurations . runtimeClasspath ) {
include ( 'jline-*jar' )
}
into "$buildDir/dependant-libs-${versions.scala}"
duplicatesStrategy 'exclude'
}
jar {
dependsOn 'copyDependantLibs'
}
}
project ( ':streams' ) {
archivesBaseName = "kafka-streams"
ext . buildStreamsVersionFileName = "kafka-streams-version.properties"
configurations {
generator
}
dependencies {
api project ( ':clients' )
// `org.rocksdb.Options` is part of Kafka Streams public api via `RocksDBConfigSetter`
api libs . rocksDBJni
implementation libs . slf4jApi
implementation libs . jacksonAnnotations
implementation libs . jacksonDatabind
// testCompileOnly prevents streams from exporting a dependency on test-utils, which would cause a dependency cycle
testCompileOnly project ( ':streams:test-utils' )
testImplementation project ( ':clients' ) . sourceSets . test . output
testImplementation project ( ':core' )
testImplementation project ( ':core' ) . sourceSets . test . output
testImplementation project ( ':server-common' ) . sourceSets . test . output
testImplementation libs . log4j
testImplementation libs . junitJupiter
testImplementation libs . junitVintageEngine
testImplementation libs . easymock
testImplementation libs . powermockJunit4
testImplementation libs . powermockEasymock
testImplementation libs . bcpkix
testImplementation libs . hamcrest
testImplementation libs . mockitoInline // supports mocking static methods, final classes, etc.
testRuntimeOnly project ( ':streams:test-utils' )
testRuntimeOnly libs . slf4jlog4j
generator project ( ':generator' )
}
KAFKA-8868: Generate SubscriptionInfo protocol message (#7248)
Rather than maintain hand coded protocol serialization code, Streams could use the same code-generation framework as Clients/Core.
There isn't a perfect match, since the code generation framework includes an assumption that you're generating "protocol messages", rather than just arbitrary blobs, but I think it's close enough to justify using it, and improving it over time.
Using the code generation allows us to drop a lot of detail-oriented, brittle, and hard-to-maintain serialization logic in favor of a schema spec.
Reviewers: Colin P. McCabe <cmccabe@apache.org>, Boyang Chen <boyang@confluent.io>, Bill Bejeck <bill@confluent.io>, Guozhang Wang <wangguoz@gmail.com>
5 years ago
task processMessages ( type: JavaExec ) {
mainClass = "org.apache.kafka.message.MessageGenerator"
classpath = configurations . generator
args = [ "-p" , "org.apache.kafka.streams.internals.generated" ,
"-o" , "src/generated/java/org/apache/kafka/streams/internals/generated" ,
"-i" , "src/main/resources/common/message" ,
"-m" , "MessageDataGenerator"
]
KAFKA-8868: Generate SubscriptionInfo protocol message (#7248)
Rather than maintain hand coded protocol serialization code, Streams could use the same code-generation framework as Clients/Core.
There isn't a perfect match, since the code generation framework includes an assumption that you're generating "protocol messages", rather than just arbitrary blobs, but I think it's close enough to justify using it, and improving it over time.
Using the code generation allows us to drop a lot of detail-oriented, brittle, and hard-to-maintain serialization logic in favor of a schema spec.
Reviewers: Colin P. McCabe <cmccabe@apache.org>, Boyang Chen <boyang@confluent.io>, Bill Bejeck <bill@confluent.io>, Guozhang Wang <wangguoz@gmail.com>
5 years ago
inputs . dir ( "src/main/resources/common/message" )
. withPropertyName ( "messages" )
. withPathSensitivity ( PathSensitivity . RELATIVE )
outputs . cacheIf { true }
KAFKA-8868: Generate SubscriptionInfo protocol message (#7248)
Rather than maintain hand coded protocol serialization code, Streams could use the same code-generation framework as Clients/Core.
There isn't a perfect match, since the code generation framework includes an assumption that you're generating "protocol messages", rather than just arbitrary blobs, but I think it's close enough to justify using it, and improving it over time.
Using the code generation allows us to drop a lot of detail-oriented, brittle, and hard-to-maintain serialization logic in favor of a schema spec.
Reviewers: Colin P. McCabe <cmccabe@apache.org>, Boyang Chen <boyang@confluent.io>, Bill Bejeck <bill@confluent.io>, Guozhang Wang <wangguoz@gmail.com>
5 years ago
outputs . dir ( "src/generated/java/org/apache/kafka/streams/internals/generated" )
}
sourceSets {
main {
java {
srcDirs = [ "src/generated/java" , "src/main/java" ]
}
}
test {
java {
srcDirs = [ "src/generated/java" , "src/test/java" ]
}
}
}
compileJava . dependsOn 'processMessages'
javadoc {
include "**/org/apache/kafka/streams/**"
exclude "**/org/apache/kafka/streams/internals/**" , "**/org/apache/kafka/streams/**/internals/**"
}
tasks . create ( name: "copyDependantLibs" , type: Copy ) {
from ( configurations . runtimeClasspath ) {
exclude ( 'kafka-clients*' )
}
into "$buildDir/dependant-libs-${versions.scala}"
duplicatesStrategy 'exclude'
}
task createStreamsVersionFile ( ) {
def receiptFile = file ( "$buildDir/kafka/$buildStreamsVersionFileName" )
inputs . property "commitId" , commitId
inputs . property "version" , version
outputs . file receiptFile
doLast {
def data = [
commitId: commitId ,
version: version ,
]
receiptFile . parentFile . mkdirs ( )
def content = data . entrySet ( ) . collect { "$it.key=$it.value" } . sort ( ) . join ( "\n" )
receiptFile . setText ( content , "ISO-8859-1" )
}
}
jar {
dependsOn 'createStreamsVersionFile'
from ( "$buildDir" ) {
include "kafka/$buildStreamsVersionFileName"
}
dependsOn 'copyDependantLibs'
}
systemTestLibs {
dependsOn testJar
}
task genStreamsConfigDocs ( type: JavaExec ) {
classpath = sourceSets . main . runtimeClasspath
mainClass = 'org.apache.kafka.streams.StreamsConfig'
if ( ! generatedDocsDir . exists ( ) ) { generatedDocsDir . mkdirs ( ) }
standardOutput = new File ( generatedDocsDir , "streams_config.html" ) . newOutputStream ( )
}
task testAll (
dependsOn: [
':streams:test' ,
':streams:test-utils:test' ,
':streams:streams-scala:test' ,
':streams:upgrade-system-tests-0100:test' ,
':streams:upgrade-system-tests-0101:test' ,
':streams:upgrade-system-tests-0102:test' ,
':streams:upgrade-system-tests-0110:test' ,
':streams:upgrade-system-tests-10:test' ,
':streams:upgrade-system-tests-11:test' ,
':streams:upgrade-system-tests-20:test' ,
':streams:upgrade-system-tests-21:test' ,
':streams:upgrade-system-tests-22:test' ,
':streams:upgrade-system-tests-23:test' ,
':streams:upgrade-system-tests-24:test' ,
':streams:upgrade-system-tests-25:test' ,
':streams:upgrade-system-tests-26:test' ,
':streams:upgrade-system-tests-27:test' ,
':streams:upgrade-system-tests-28:test' ,
':streams:upgrade-system-tests-30:test' ,
':streams:upgrade-system-tests-31:test' ,
':streams:upgrade-system-tests-32:test' ,
':streams:upgrade-system-tests-33:test' ,
':streams:examples:test'
]
)
}
project ( ':streams:streams-scala' ) {
apply plugin: 'scala'
archivesBaseName = "kafka-streams-scala_${versions.baseScala}"
dependencies {
api project ( ':streams' )
api libs . scalaLibrary
api libs . scalaCollectionCompat
testImplementation project ( ':core' )
testImplementation project ( ':core' ) . sourceSets . test . output
testImplementation project ( ':server-common' ) . sourceSets . test . output
testImplementation project ( ':streams' ) . sourceSets . test . output
testImplementation project ( ':clients' ) . sourceSets . test . output
testImplementation project ( ':streams:test-utils' )
testImplementation libs . junitJupiter
testImplementation libs . easymock
testImplementation libs . hamcrest
testRuntimeOnly libs . slf4jlog4j
}
javadoc {
include "**/org/apache/kafka/streams/scala/**"
}
scaladoc {
scalaDocOptions . additionalParameters = [ "-no-link-warnings" ]
}
tasks . create ( name: "copyDependantLibs" , type: Copy ) {
from ( configurations . runtimeClasspath ) {
exclude ( 'kafka-streams*' )
}
into "$buildDir/dependant-libs-${versions.scala}"
duplicatesStrategy 'exclude'
}
jar {
dependsOn 'copyDependantLibs'
}
test . dependsOn ( ':spotlessScalaCheck' )
}
project ( ':streams:test-utils' ) {
archivesBaseName = "kafka-streams-test-utils"
dependencies {
api project ( ':streams' )
api project ( ':clients' )
implementation libs . slf4jApi
testImplementation project ( ':clients' ) . sourceSets . test . output
testImplementation libs . junitJupiter
testImplementation libs . mockitoCore
testImplementation libs . hamcrest
testRuntimeOnly libs . slf4jlog4j
}
javadoc {
include "**/org/apache/kafka/streams/test/**"
}
tasks . create ( name: "copyDependantLibs" , type: Copy ) {
from ( configurations . runtimeClasspath ) {
exclude ( 'kafka-streams*' )
}
into "$buildDir/dependant-libs-${versions.scala}"
duplicatesStrategy 'exclude'
}
jar {
dependsOn 'copyDependantLibs'
}
}
project ( ':streams:examples' ) {
archivesBaseName = "kafka-streams-examples"
dependencies {
// this dependency should be removed after we unify data API
implementation ( project ( ':connect:json' ) ) {
// this transitive dependency is not used in Streams, and it breaks SBT builds
exclude module: 'javax.ws.rs-api'
}
implementation project ( ':streams' )
implementation libs . slf4jlog4j
testImplementation project ( ':streams:test-utils' )
testImplementation project ( ':clients' ) . sourceSets . test . output // for org.apache.kafka.test.IntegrationTest
testImplementation libs . junitJupiter
testImplementation libs . hamcrest
}
javadoc {
enabled = false
}
tasks . create ( name: "copyDependantLibs" , type: Copy ) {
from ( configurations . runtimeClasspath ) {
exclude ( 'kafka-streams*' )
}
into "$buildDir/dependant-libs-${versions.scala}"
duplicatesStrategy 'exclude'
}
jar {
dependsOn 'copyDependantLibs'
}
}
project ( ':streams:upgrade-system-tests-0100' ) {
archivesBaseName = "kafka-streams-upgrade-system-tests-0100"
dependencies {
testImplementation ( libs . kafkaStreams_0100 ) {
exclude group: 'org.slf4j' , module: 'slf4j-log4j12'
exclude group: 'log4j' , module: 'log4j'
}
testRuntimeOnly libs . junitJupiter
}
systemTestLibs {
dependsOn testJar
}
}
project ( ':streams:upgrade-system-tests-0101' ) {
archivesBaseName = "kafka-streams-upgrade-system-tests-0101"
dependencies {
testImplementation ( libs . kafkaStreams_0101 ) {
exclude group: 'org.slf4j' , module: 'slf4j-log4j12'
exclude group: 'log4j' , module: 'log4j'
}
testRuntimeOnly libs . junitJupiter
}
systemTestLibs {
dependsOn testJar
}
}
project ( ':streams:upgrade-system-tests-0102' ) {
archivesBaseName = "kafka-streams-upgrade-system-tests-0102"
dependencies {
testImplementation libs . kafkaStreams_0102
testRuntimeOnly libs . junitJupiter
}
systemTestLibs {
dependsOn testJar
}
}
project ( ':streams:upgrade-system-tests-0110' ) {
archivesBaseName = "kafka-streams-upgrade-system-tests-0110"
dependencies {
testImplementation libs . kafkaStreams_0110
testRuntimeOnly libs . junitJupiter
}
systemTestLibs {
dependsOn testJar
}
}
project ( ':streams:upgrade-system-tests-10' ) {
archivesBaseName = "kafka-streams-upgrade-system-tests-10"
dependencies {
testImplementation libs . kafkaStreams_10
testRuntimeOnly libs . junitJupiter
}
systemTestLibs {
dependsOn testJar
}
}
project ( ':streams:upgrade-system-tests-11' ) {
archivesBaseName = "kafka-streams-upgrade-system-tests-11"
dependencies {
testImplementation libs . kafkaStreams_11
testRuntimeOnly libs . junitJupiter
}
systemTestLibs {
dependsOn testJar
}
}
MINOR: Enable ignored upgrade system tests - trunk (#5605)
Removed ignore annotations from the upgrade tests. This PR includes the following changes for updating the upgrade tests:
* Uploaded new versions 0.10.2.2, 0.11.0.3, 1.0.2, 1.1.1, and 2.0.0 (in the associated scala versions) to kafka-packages
* Update versions in version.py, Dockerfile, base.sh
* Added new versions to StreamsUpgradeTest.test_upgrade_downgrade_brokers including version 2.0.0
* Added new versions StreamsUpgradeTest.test_simple_upgrade_downgrade test excluding version 2.0.0
* Version 2.0.0 is excluded from the streams upgrade/downgrade test as StreamsConfig needs an update for the new version, requiring a KIP. Once the community votes the KIP in, a minor follow-up PR can be pushed to add the 2.0.0 version to the upgrade test.
* Fixed minor bug in kafka-run-class.sh for classpath in upgrade/downgrade tests across versions.
* Follow on PRs for 0.10.2x, 0.11.0x, 1.0.x, 1.1.x, and 2.0.x will be pushed soon with the same updates required for the specific version.
Reviewers: Eno Thereska <eno.thereska@gmail.com>, John Roesler <vvcephei@users.noreply.github.com>, Guozhang Wang <wangguoz@gmail.com>, Matthias J. Sax <matthias@confluent.io>
6 years ago
project ( ':streams:upgrade-system-tests-20' ) {
archivesBaseName = "kafka-streams-upgrade-system-tests-20"
dependencies {
testImplementation libs . kafkaStreams_20
testRuntimeOnly libs . junitJupiter
MINOR: Enable ignored upgrade system tests - trunk (#5605)
Removed ignore annotations from the upgrade tests. This PR includes the following changes for updating the upgrade tests:
* Uploaded new versions 0.10.2.2, 0.11.0.3, 1.0.2, 1.1.1, and 2.0.0 (in the associated scala versions) to kafka-packages
* Update versions in version.py, Dockerfile, base.sh
* Added new versions to StreamsUpgradeTest.test_upgrade_downgrade_brokers including version 2.0.0
* Added new versions StreamsUpgradeTest.test_simple_upgrade_downgrade test excluding version 2.0.0
* Version 2.0.0 is excluded from the streams upgrade/downgrade test as StreamsConfig needs an update for the new version, requiring a KIP. Once the community votes the KIP in, a minor follow-up PR can be pushed to add the 2.0.0 version to the upgrade test.
* Fixed minor bug in kafka-run-class.sh for classpath in upgrade/downgrade tests across versions.
* Follow on PRs for 0.10.2x, 0.11.0x, 1.0.x, 1.1.x, and 2.0.x will be pushed soon with the same updates required for the specific version.
Reviewers: Eno Thereska <eno.thereska@gmail.com>, John Roesler <vvcephei@users.noreply.github.com>, Guozhang Wang <wangguoz@gmail.com>, Matthias J. Sax <matthias@confluent.io>
6 years ago
}
systemTestLibs {
dependsOn testJar
}
}
project ( ':streams:upgrade-system-tests-21' ) {
archivesBaseName = "kafka-streams-upgrade-system-tests-21"
dependencies {
testImplementation libs . kafkaStreams_21
testRuntimeOnly libs . junitJupiter
}
systemTestLibs {
dependsOn testJar
}
}
project ( ':streams:upgrade-system-tests-22' ) {
archivesBaseName = "kafka-streams-upgrade-system-tests-22"
dependencies {
testImplementation libs . kafkaStreams_22
testRuntimeOnly libs . junitJupiter
}
systemTestLibs {
dependsOn testJar
}
}
project ( ':streams:upgrade-system-tests-23' ) {
archivesBaseName = "kafka-streams-upgrade-system-tests-23"
dependencies {
testImplementation libs . kafkaStreams_23
testRuntimeOnly libs . junitJupiter
}
systemTestLibs {
dependsOn testJar
}
}
project ( ':streams:upgrade-system-tests-24' ) {
archivesBaseName = "kafka-streams-upgrade-system-tests-24"
dependencies {
testImplementation libs . kafkaStreams_24
testRuntimeOnly libs . junitJupiter
}
systemTestLibs {
dependsOn testJar
}
}
project ( ':streams:upgrade-system-tests-25' ) {
archivesBaseName = "kafka-streams-upgrade-system-tests-25"
dependencies {
testImplementation libs . kafkaStreams_25
testRuntimeOnly libs . junitJupiter
}
systemTestLibs {
dependsOn testJar
}
}
project ( ':streams:upgrade-system-tests-26' ) {
archivesBaseName = "kafka-streams-upgrade-system-tests-26"
dependencies {
testImplementation libs . kafkaStreams_26
testRuntimeOnly libs . junitJupiter
}
systemTestLibs {
dependsOn testJar
}
}
project ( ':streams:upgrade-system-tests-27' ) {
archivesBaseName = "kafka-streams-upgrade-system-tests-27"
dependencies {
testImplementation libs . kafkaStreams_27
testRuntimeOnly libs . junitJupiter
}
systemTestLibs {
dependsOn testJar
}
}
project ( ':streams:upgrade-system-tests-28' ) {
archivesBaseName = "kafka-streams-upgrade-system-tests-28"
dependencies {
testImplementation libs . kafkaStreams_28
testRuntimeOnly libs . junitJupiter
}
systemTestLibs {
dependsOn testJar
}
}
project ( ':streams:upgrade-system-tests-30' ) {
archivesBaseName = "kafka-streams-upgrade-system-tests-30"
dependencies {
testImplementation libs . kafkaStreams_30
testRuntimeOnly libs . junitJupiter
}
systemTestLibs {
dependsOn testJar
}
}
project ( ':streams:upgrade-system-tests-31' ) {
archivesBaseName = "kafka-streams-upgrade-system-tests-31"
dependencies {
testImplementation libs . kafkaStreams_31
testRuntimeOnly libs . junitJupiter
}
systemTestLibs {
dependsOn testJar
}
}
project ( ':streams:upgrade-system-tests-32' ) {
archivesBaseName = "kafka-streams-upgrade-system-tests-32"
dependencies {
testImplementation libs . kafkaStreams_32
testRuntimeOnly libs . junitJupiter
}
systemTestLibs {
dependsOn testJar
}
}
project ( ':streams:upgrade-system-tests-33' ) {
archivesBaseName = "kafka-streams-upgrade-system-tests-33"
dependencies {
testImplementation libs . kafkaStreams_33
testRuntimeOnly libs . junitJupiter
}
systemTestLibs {
dependsOn testJar
}
}
project ( ':jmh-benchmarks' ) {
apply plugin: 'com.github.johnrengelman.shadow'
shadowJar {
archiveBaseName = 'kafka-jmh-benchmarks'
}
dependencies {
implementation ( project ( ':core' ) ) {
// jmh requires jopt 4.x while `core` depends on 5.0, they are not binary compatible
exclude group: 'net.sf.jopt-simple' , module: 'jopt-simple'
}
implementation project ( ':server-common' )
implementation project ( ':clients' )
implementation project ( ':group-coordinator' )
implementation project ( ':metadata' )
implementation project ( ':storage' )
implementation project ( ':streams' )
implementation project ( ':core' )
implementation project ( ':clients' ) . sourceSets . test . output
implementation project ( ':core' ) . sourceSets . test . output
implementation libs . jmhCore
annotationProcessor libs . jmhGeneratorAnnProcess
implementation libs . jmhCoreBenchmarks
implementation libs . jacksonDatabind
implementation libs . metrics
implementation libs . mockitoCore
implementation libs . slf4jlog4j
implementation libs . scalaLibrary
implementation libs . scalaJava8Compat
}
tasks . withType ( JavaCompile ) {
// Suppress warning caused by code generated by jmh: `warning: [cast] redundant cast to long`
options . compilerArgs < < "-Xlint:-cast"
}
jar {
manifest {
attributes "Main-Class" : "org.openjdk.jmh.Main"
}
}
KAFKA-8841; Reduce overhead of ReplicaManager.updateFollowerFetchState (#7324)
This PR makes two changes to code in the ReplicaManager.updateFollowerFetchState path, which is in the hot path for follower fetches. Although calling ReplicaManager.updateFollowerFetch state is inexpensive on its own, it is called once for each partition every time a follower fetch occurs.
1. updateFollowerFetchState no longer calls maybeExpandIsr when the follower is already in the ISR. This avoid repeated expansion checks.
2. Partition.maybeIncrementLeaderHW is also in the hot path for ReplicaManager.updateFollowerFetchState. Partition.maybeIncrementLeaderHW calls Partition.remoteReplicas four times each iteration, and it performs a toSet conversion. maybeIncrementLeaderHW now avoids generating any intermediate collections when updating the HWM.
**Benchmark results for Partition.updateFollowerFetchState on a r5.xlarge:**
Old:
```
1288.633 ±(99.9%) 1.170 ns/op [Average]
(min, avg, max) = (1287.343, 1288.633, 1290.398), stdev = 1.037
CI (99.9%): [1287.463, 1289.802] (assumes normal distribution)
```
New (when follower fetch offset is updated):
```
261.727 ±(99.9%) 0.122 ns/op [Average]
(min, avg, max) = (261.565, 261.727, 261.937), stdev = 0.114
CI (99.9%): [261.605, 261.848] (assumes normal distribution)
```
New (when follower fetch offset is the same):
```
68.484 ±(99.9%) 0.025 ns/op [Average]
(min, avg, max) = (68.446, 68.484, 68.520), stdev = 0.023
CI (99.9%): [68.460, 68.509] (assumes normal distribution)
```
Reviewers: Ismael Juma <ismael@juma.me.uk>, Jason Gustafson <jason@confluent.io>
5 years ago
checkstyle {
configProperties = checkstyleConfigProperties ( "import-control-jmh-benchmarks.xml" )
}
task jmh ( type: JavaExec , dependsOn: [ ':jmh-benchmarks:clean' , ':jmh-benchmarks:shadowJar' ] ) {
mainClass = "-jar"
doFirst {
if ( System . getProperty ( "jmhArgs" ) ) {
args System . getProperty ( "jmhArgs" ) . split ( ' ' )
}
args = [ shadowJar . archivePath , * args ]
}
}
javadoc {
enabled = false
}
}
project ( ':log4j-appender' ) {
archivesBaseName = "kafka-log4j-appender"
dependencies {
implementation project ( ':clients' )
implementation libs . slf4jlog4j
testImplementation project ( ':clients' ) . sourceSets . test . output
testImplementation libs . junitJupiter
testImplementation libs . hamcrest
testImplementation libs . mockitoCore
}
javadoc {
enabled = false
}
}
KAFKA-2366; Initial patch for Copycat
This is an initial patch implementing the basics of Copycat for KIP-26.
The intent here is to start a review of the key pieces of the core API and get a reasonably functional, baseline, non-distributed implementation of Copycat in place to get things rolling. The current patch has a number of known issues that need to be addressed before a final version:
* Some build-related issues. Specifically, requires some locally-installed dependencies (see below), ignores checkstyle for the runtime data library because it's lifted from Avro currently and likely won't last in its current form, and some Gradle task dependencies aren't quite right because I haven't gotten rid of the dependency on `core` (which should now be an easy patch since new consumer groups are in a much better state).
* This patch currently depends on some Confluent trunk code because I prototyped with our Avro serializers w/ schema-registry support. We need to figure out what we want to provide as an example built-in set of serializers. Unlike core Kafka where we could ignore the issue, providing only ByteArray or String serializers, this is pretty central to how Copycat works.
* This patch uses a hacked up version of Avro as its runtime data format. Not sure if we want to go through the entire API discussion just to get some basic code committed, so I filed KAFKA-2367 to handle that separately. The core connector APIs and the runtime data APIs are entirely orthogonal.
* This patch needs some updates to get aligned with recent new consumer changes (specifically, I'm aware of the ConcurrentModificationException issue on exit). More generally, the new consumer is in flux but Copycat depends on it, so there are likely to be some negative interactions.
* The layout feels a bit awkward to me right now because I ported it from a Maven layout. We don't have nearly the same level of granularity in Kafka currently (core and clients, plus the mostly ignored examples, log4j-appender, and a couple of contribs). We might want to reorganize, although keeping data+api separate from runtime and connector plugins is useful for minimizing dependencies.
* There are a variety of other things (e.g., I'm not happy with the exception hierarchy/how they are currently handled, TopicPartition doesn't really need to be duplicated unless we want Copycat entirely isolated from the Kafka APIs, etc), but I expect those we'll cover in the review.
Before commenting on the patch, it's probably worth reviewing https://issues.apache.org/jira/browse/KAFKA-2365 and https://issues.apache.org/jira/browse/KAFKA-2366 to get an idea of what I had in mind for a) what we ultimately want with all the Copycat patches and b) what we aim to cover in this initial patch. My hope is that we can use a WIP patch (after the current obvious deficiencies are addressed) while recognizing that we want to make iterative progress with a bunch of subsequent PRs.
Author: Ewen Cheslack-Postava <me@ewencp.org>
Reviewers: Ismael Juma, Gwen Shapira
Closes #99 from ewencp/copycat and squashes the following commits:
a3a47a6 [Ewen Cheslack-Postava] Simplify Copycat exceptions, make them a subclass of KafkaException.
8c108b0 [Ewen Cheslack-Postava] Rename Coordinator to Herder to avoid confusion with the consumer coordinator.
7bf8075 [Ewen Cheslack-Postava] Make Copycat CLI speific to standalone mode, clean up some config and get rid of config storage in standalone mode.
656a003 [Ewen Cheslack-Postava] Clarify and expand the explanation of the Copycat Coordinator interface.
c0e5fdc [Ewen Cheslack-Postava] Merge remote-tracking branch 'origin/trunk' into copycat
0fa7a36 [Ewen Cheslack-Postava] Mark Copycat classes as unstable and reduce visibility of some classes where possible.
d55d31e [Ewen Cheslack-Postava] Reorganize Copycat code to put it all under one top-level directory.
b29cb2c [Ewen Cheslack-Postava] Merge remote-tracking branch 'origin/trunk' into copycat
d713a21 [Ewen Cheslack-Postava] Address Gwen's review comments.
6787a85 [Ewen Cheslack-Postava] Make Converter generic to match serializers since some serialization formats do not require a base class of Object; update many other classes to have generic key and value class type parameters to match this change.
b194c73 [Ewen Cheslack-Postava] Split Copycat converter option into two options for key and value.
0b5a1a0 [Ewen Cheslack-Postava] Normalize naming to use partition for both source and Kafka, adjusting naming in CopycatRecord classes to clearly differentiate.
e345142 [Ewen Cheslack-Postava] Remove Copycat reflection utils, use existing Utils and ConfigDef functionality from clients package.
be5c387 [Ewen Cheslack-Postava] Minor cleanup
122423e [Ewen Cheslack-Postava] Style cleanup
6ba87de [Ewen Cheslack-Postava] Remove most of the Avro-based mock runtime data API, only preserving enough schema functionality to support basic primitive types for an initial patch.
4674d13 [Ewen Cheslack-Postava] Address review comments, clean up some code styling.
25b5739 [Ewen Cheslack-Postava] Fix sink task offset commit concurrency issue by moving it to the worker thread and waking up the consumer to ensure it exits promptly.
0aefe21 [Ewen Cheslack-Postava] Add log4j settings for Copycat.
220e42d [Ewen Cheslack-Postava] Replace Avro serializer with JSON serializer.
1243a7c [Ewen Cheslack-Postava] Merge remote-tracking branch 'origin/trunk' into copycat
5a618c6 [Ewen Cheslack-Postava] Remove offset serializers, instead reusing the existing serializers and removing schema projection support.
e849e10 [Ewen Cheslack-Postava] Remove duplicated TopicPartition implementation.
dec1379 [Ewen Cheslack-Postava] Switch to using new consumer coordinator instead of manually assigning partitions. Remove dependency of copycat-runtime on core.
4a9b4f3 [Ewen Cheslack-Postava] Add some helpful Copycat-specific build and test targets that cover all Copycat packages.
31cd1ca [Ewen Cheslack-Postava] Add CLI tools for Copycat.
e14942c [Ewen Cheslack-Postava] Add Copycat file connector.
0233456 [Ewen Cheslack-Postava] Add copycat-avro and copycat-runtime
11981d2 [Ewen Cheslack-Postava] Add copycat-data and copycat-api
9 years ago
project ( ':connect:api' ) {
archivesBaseName = "connect-api"
KAFKA-2366; Initial patch for Copycat
This is an initial patch implementing the basics of Copycat for KIP-26.
The intent here is to start a review of the key pieces of the core API and get a reasonably functional, baseline, non-distributed implementation of Copycat in place to get things rolling. The current patch has a number of known issues that need to be addressed before a final version:
* Some build-related issues. Specifically, requires some locally-installed dependencies (see below), ignores checkstyle for the runtime data library because it's lifted from Avro currently and likely won't last in its current form, and some Gradle task dependencies aren't quite right because I haven't gotten rid of the dependency on `core` (which should now be an easy patch since new consumer groups are in a much better state).
* This patch currently depends on some Confluent trunk code because I prototyped with our Avro serializers w/ schema-registry support. We need to figure out what we want to provide as an example built-in set of serializers. Unlike core Kafka where we could ignore the issue, providing only ByteArray or String serializers, this is pretty central to how Copycat works.
* This patch uses a hacked up version of Avro as its runtime data format. Not sure if we want to go through the entire API discussion just to get some basic code committed, so I filed KAFKA-2367 to handle that separately. The core connector APIs and the runtime data APIs are entirely orthogonal.
* This patch needs some updates to get aligned with recent new consumer changes (specifically, I'm aware of the ConcurrentModificationException issue on exit). More generally, the new consumer is in flux but Copycat depends on it, so there are likely to be some negative interactions.
* The layout feels a bit awkward to me right now because I ported it from a Maven layout. We don't have nearly the same level of granularity in Kafka currently (core and clients, plus the mostly ignored examples, log4j-appender, and a couple of contribs). We might want to reorganize, although keeping data+api separate from runtime and connector plugins is useful for minimizing dependencies.
* There are a variety of other things (e.g., I'm not happy with the exception hierarchy/how they are currently handled, TopicPartition doesn't really need to be duplicated unless we want Copycat entirely isolated from the Kafka APIs, etc), but I expect those we'll cover in the review.
Before commenting on the patch, it's probably worth reviewing https://issues.apache.org/jira/browse/KAFKA-2365 and https://issues.apache.org/jira/browse/KAFKA-2366 to get an idea of what I had in mind for a) what we ultimately want with all the Copycat patches and b) what we aim to cover in this initial patch. My hope is that we can use a WIP patch (after the current obvious deficiencies are addressed) while recognizing that we want to make iterative progress with a bunch of subsequent PRs.
Author: Ewen Cheslack-Postava <me@ewencp.org>
Reviewers: Ismael Juma, Gwen Shapira
Closes #99 from ewencp/copycat and squashes the following commits:
a3a47a6 [Ewen Cheslack-Postava] Simplify Copycat exceptions, make them a subclass of KafkaException.
8c108b0 [Ewen Cheslack-Postava] Rename Coordinator to Herder to avoid confusion with the consumer coordinator.
7bf8075 [Ewen Cheslack-Postava] Make Copycat CLI speific to standalone mode, clean up some config and get rid of config storage in standalone mode.
656a003 [Ewen Cheslack-Postava] Clarify and expand the explanation of the Copycat Coordinator interface.
c0e5fdc [Ewen Cheslack-Postava] Merge remote-tracking branch 'origin/trunk' into copycat
0fa7a36 [Ewen Cheslack-Postava] Mark Copycat classes as unstable and reduce visibility of some classes where possible.
d55d31e [Ewen Cheslack-Postava] Reorganize Copycat code to put it all under one top-level directory.
b29cb2c [Ewen Cheslack-Postava] Merge remote-tracking branch 'origin/trunk' into copycat
d713a21 [Ewen Cheslack-Postava] Address Gwen's review comments.
6787a85 [Ewen Cheslack-Postava] Make Converter generic to match serializers since some serialization formats do not require a base class of Object; update many other classes to have generic key and value class type parameters to match this change.
b194c73 [Ewen Cheslack-Postava] Split Copycat converter option into two options for key and value.
0b5a1a0 [Ewen Cheslack-Postava] Normalize naming to use partition for both source and Kafka, adjusting naming in CopycatRecord classes to clearly differentiate.
e345142 [Ewen Cheslack-Postava] Remove Copycat reflection utils, use existing Utils and ConfigDef functionality from clients package.
be5c387 [Ewen Cheslack-Postava] Minor cleanup
122423e [Ewen Cheslack-Postava] Style cleanup
6ba87de [Ewen Cheslack-Postava] Remove most of the Avro-based mock runtime data API, only preserving enough schema functionality to support basic primitive types for an initial patch.
4674d13 [Ewen Cheslack-Postava] Address review comments, clean up some code styling.
25b5739 [Ewen Cheslack-Postava] Fix sink task offset commit concurrency issue by moving it to the worker thread and waking up the consumer to ensure it exits promptly.
0aefe21 [Ewen Cheslack-Postava] Add log4j settings for Copycat.
220e42d [Ewen Cheslack-Postava] Replace Avro serializer with JSON serializer.
1243a7c [Ewen Cheslack-Postava] Merge remote-tracking branch 'origin/trunk' into copycat
5a618c6 [Ewen Cheslack-Postava] Remove offset serializers, instead reusing the existing serializers and removing schema projection support.
e849e10 [Ewen Cheslack-Postava] Remove duplicated TopicPartition implementation.
dec1379 [Ewen Cheslack-Postava] Switch to using new consumer coordinator instead of manually assigning partitions. Remove dependency of copycat-runtime on core.
4a9b4f3 [Ewen Cheslack-Postava] Add some helpful Copycat-specific build and test targets that cover all Copycat packages.
31cd1ca [Ewen Cheslack-Postava] Add CLI tools for Copycat.
e14942c [Ewen Cheslack-Postava] Add Copycat file connector.
0233456 [Ewen Cheslack-Postava] Add copycat-avro and copycat-runtime
11981d2 [Ewen Cheslack-Postava] Add copycat-data and copycat-api
9 years ago
dependencies {
api project ( ':clients' )
implementation libs . slf4jApi
implementation libs . jaxrsApi
testImplementation libs . junitJupiter
testRuntimeOnly libs . slf4jlog4j
testImplementation project ( ':clients' ) . sourceSets . test . output
KAFKA-2366; Initial patch for Copycat
This is an initial patch implementing the basics of Copycat for KIP-26.
The intent here is to start a review of the key pieces of the core API and get a reasonably functional, baseline, non-distributed implementation of Copycat in place to get things rolling. The current patch has a number of known issues that need to be addressed before a final version:
* Some build-related issues. Specifically, requires some locally-installed dependencies (see below), ignores checkstyle for the runtime data library because it's lifted from Avro currently and likely won't last in its current form, and some Gradle task dependencies aren't quite right because I haven't gotten rid of the dependency on `core` (which should now be an easy patch since new consumer groups are in a much better state).
* This patch currently depends on some Confluent trunk code because I prototyped with our Avro serializers w/ schema-registry support. We need to figure out what we want to provide as an example built-in set of serializers. Unlike core Kafka where we could ignore the issue, providing only ByteArray or String serializers, this is pretty central to how Copycat works.
* This patch uses a hacked up version of Avro as its runtime data format. Not sure if we want to go through the entire API discussion just to get some basic code committed, so I filed KAFKA-2367 to handle that separately. The core connector APIs and the runtime data APIs are entirely orthogonal.
* This patch needs some updates to get aligned with recent new consumer changes (specifically, I'm aware of the ConcurrentModificationException issue on exit). More generally, the new consumer is in flux but Copycat depends on it, so there are likely to be some negative interactions.
* The layout feels a bit awkward to me right now because I ported it from a Maven layout. We don't have nearly the same level of granularity in Kafka currently (core and clients, plus the mostly ignored examples, log4j-appender, and a couple of contribs). We might want to reorganize, although keeping data+api separate from runtime and connector plugins is useful for minimizing dependencies.
* There are a variety of other things (e.g., I'm not happy with the exception hierarchy/how they are currently handled, TopicPartition doesn't really need to be duplicated unless we want Copycat entirely isolated from the Kafka APIs, etc), but I expect those we'll cover in the review.
Before commenting on the patch, it's probably worth reviewing https://issues.apache.org/jira/browse/KAFKA-2365 and https://issues.apache.org/jira/browse/KAFKA-2366 to get an idea of what I had in mind for a) what we ultimately want with all the Copycat patches and b) what we aim to cover in this initial patch. My hope is that we can use a WIP patch (after the current obvious deficiencies are addressed) while recognizing that we want to make iterative progress with a bunch of subsequent PRs.
Author: Ewen Cheslack-Postava <me@ewencp.org>
Reviewers: Ismael Juma, Gwen Shapira
Closes #99 from ewencp/copycat and squashes the following commits:
a3a47a6 [Ewen Cheslack-Postava] Simplify Copycat exceptions, make them a subclass of KafkaException.
8c108b0 [Ewen Cheslack-Postava] Rename Coordinator to Herder to avoid confusion with the consumer coordinator.
7bf8075 [Ewen Cheslack-Postava] Make Copycat CLI speific to standalone mode, clean up some config and get rid of config storage in standalone mode.
656a003 [Ewen Cheslack-Postava] Clarify and expand the explanation of the Copycat Coordinator interface.
c0e5fdc [Ewen Cheslack-Postava] Merge remote-tracking branch 'origin/trunk' into copycat
0fa7a36 [Ewen Cheslack-Postava] Mark Copycat classes as unstable and reduce visibility of some classes where possible.
d55d31e [Ewen Cheslack-Postava] Reorganize Copycat code to put it all under one top-level directory.
b29cb2c [Ewen Cheslack-Postava] Merge remote-tracking branch 'origin/trunk' into copycat
d713a21 [Ewen Cheslack-Postava] Address Gwen's review comments.
6787a85 [Ewen Cheslack-Postava] Make Converter generic to match serializers since some serialization formats do not require a base class of Object; update many other classes to have generic key and value class type parameters to match this change.
b194c73 [Ewen Cheslack-Postava] Split Copycat converter option into two options for key and value.
0b5a1a0 [Ewen Cheslack-Postava] Normalize naming to use partition for both source and Kafka, adjusting naming in CopycatRecord classes to clearly differentiate.
e345142 [Ewen Cheslack-Postava] Remove Copycat reflection utils, use existing Utils and ConfigDef functionality from clients package.
be5c387 [Ewen Cheslack-Postava] Minor cleanup
122423e [Ewen Cheslack-Postava] Style cleanup
6ba87de [Ewen Cheslack-Postava] Remove most of the Avro-based mock runtime data API, only preserving enough schema functionality to support basic primitive types for an initial patch.
4674d13 [Ewen Cheslack-Postava] Address review comments, clean up some code styling.
25b5739 [Ewen Cheslack-Postava] Fix sink task offset commit concurrency issue by moving it to the worker thread and waking up the consumer to ensure it exits promptly.
0aefe21 [Ewen Cheslack-Postava] Add log4j settings for Copycat.
220e42d [Ewen Cheslack-Postava] Replace Avro serializer with JSON serializer.
1243a7c [Ewen Cheslack-Postava] Merge remote-tracking branch 'origin/trunk' into copycat
5a618c6 [Ewen Cheslack-Postava] Remove offset serializers, instead reusing the existing serializers and removing schema projection support.
e849e10 [Ewen Cheslack-Postava] Remove duplicated TopicPartition implementation.
dec1379 [Ewen Cheslack-Postava] Switch to using new consumer coordinator instead of manually assigning partitions. Remove dependency of copycat-runtime on core.
4a9b4f3 [Ewen Cheslack-Postava] Add some helpful Copycat-specific build and test targets that cover all Copycat packages.
31cd1ca [Ewen Cheslack-Postava] Add CLI tools for Copycat.
e14942c [Ewen Cheslack-Postava] Add Copycat file connector.
0233456 [Ewen Cheslack-Postava] Add copycat-avro and copycat-runtime
11981d2 [Ewen Cheslack-Postava] Add copycat-data and copycat-api
9 years ago
}
javadoc {
include "**/org/apache/kafka/connect/**" // needed for the `aggregatedJavadoc` task
KAFKA-2366; Initial patch for Copycat
This is an initial patch implementing the basics of Copycat for KIP-26.
The intent here is to start a review of the key pieces of the core API and get a reasonably functional, baseline, non-distributed implementation of Copycat in place to get things rolling. The current patch has a number of known issues that need to be addressed before a final version:
* Some build-related issues. Specifically, requires some locally-installed dependencies (see below), ignores checkstyle for the runtime data library because it's lifted from Avro currently and likely won't last in its current form, and some Gradle task dependencies aren't quite right because I haven't gotten rid of the dependency on `core` (which should now be an easy patch since new consumer groups are in a much better state).
* This patch currently depends on some Confluent trunk code because I prototyped with our Avro serializers w/ schema-registry support. We need to figure out what we want to provide as an example built-in set of serializers. Unlike core Kafka where we could ignore the issue, providing only ByteArray or String serializers, this is pretty central to how Copycat works.
* This patch uses a hacked up version of Avro as its runtime data format. Not sure if we want to go through the entire API discussion just to get some basic code committed, so I filed KAFKA-2367 to handle that separately. The core connector APIs and the runtime data APIs are entirely orthogonal.
* This patch needs some updates to get aligned with recent new consumer changes (specifically, I'm aware of the ConcurrentModificationException issue on exit). More generally, the new consumer is in flux but Copycat depends on it, so there are likely to be some negative interactions.
* The layout feels a bit awkward to me right now because I ported it from a Maven layout. We don't have nearly the same level of granularity in Kafka currently (core and clients, plus the mostly ignored examples, log4j-appender, and a couple of contribs). We might want to reorganize, although keeping data+api separate from runtime and connector plugins is useful for minimizing dependencies.
* There are a variety of other things (e.g., I'm not happy with the exception hierarchy/how they are currently handled, TopicPartition doesn't really need to be duplicated unless we want Copycat entirely isolated from the Kafka APIs, etc), but I expect those we'll cover in the review.
Before commenting on the patch, it's probably worth reviewing https://issues.apache.org/jira/browse/KAFKA-2365 and https://issues.apache.org/jira/browse/KAFKA-2366 to get an idea of what I had in mind for a) what we ultimately want with all the Copycat patches and b) what we aim to cover in this initial patch. My hope is that we can use a WIP patch (after the current obvious deficiencies are addressed) while recognizing that we want to make iterative progress with a bunch of subsequent PRs.
Author: Ewen Cheslack-Postava <me@ewencp.org>
Reviewers: Ismael Juma, Gwen Shapira
Closes #99 from ewencp/copycat and squashes the following commits:
a3a47a6 [Ewen Cheslack-Postava] Simplify Copycat exceptions, make them a subclass of KafkaException.
8c108b0 [Ewen Cheslack-Postava] Rename Coordinator to Herder to avoid confusion with the consumer coordinator.
7bf8075 [Ewen Cheslack-Postava] Make Copycat CLI speific to standalone mode, clean up some config and get rid of config storage in standalone mode.
656a003 [Ewen Cheslack-Postava] Clarify and expand the explanation of the Copycat Coordinator interface.
c0e5fdc [Ewen Cheslack-Postava] Merge remote-tracking branch 'origin/trunk' into copycat
0fa7a36 [Ewen Cheslack-Postava] Mark Copycat classes as unstable and reduce visibility of some classes where possible.
d55d31e [Ewen Cheslack-Postava] Reorganize Copycat code to put it all under one top-level directory.
b29cb2c [Ewen Cheslack-Postava] Merge remote-tracking branch 'origin/trunk' into copycat
d713a21 [Ewen Cheslack-Postava] Address Gwen's review comments.
6787a85 [Ewen Cheslack-Postava] Make Converter generic to match serializers since some serialization formats do not require a base class of Object; update many other classes to have generic key and value class type parameters to match this change.
b194c73 [Ewen Cheslack-Postava] Split Copycat converter option into two options for key and value.
0b5a1a0 [Ewen Cheslack-Postava] Normalize naming to use partition for both source and Kafka, adjusting naming in CopycatRecord classes to clearly differentiate.
e345142 [Ewen Cheslack-Postava] Remove Copycat reflection utils, use existing Utils and ConfigDef functionality from clients package.
be5c387 [Ewen Cheslack-Postava] Minor cleanup
122423e [Ewen Cheslack-Postava] Style cleanup
6ba87de [Ewen Cheslack-Postava] Remove most of the Avro-based mock runtime data API, only preserving enough schema functionality to support basic primitive types for an initial patch.
4674d13 [Ewen Cheslack-Postava] Address review comments, clean up some code styling.
25b5739 [Ewen Cheslack-Postava] Fix sink task offset commit concurrency issue by moving it to the worker thread and waking up the consumer to ensure it exits promptly.
0aefe21 [Ewen Cheslack-Postava] Add log4j settings for Copycat.
220e42d [Ewen Cheslack-Postava] Replace Avro serializer with JSON serializer.
1243a7c [Ewen Cheslack-Postava] Merge remote-tracking branch 'origin/trunk' into copycat
5a618c6 [Ewen Cheslack-Postava] Remove offset serializers, instead reusing the existing serializers and removing schema projection support.
e849e10 [Ewen Cheslack-Postava] Remove duplicated TopicPartition implementation.
dec1379 [Ewen Cheslack-Postava] Switch to using new consumer coordinator instead of manually assigning partitions. Remove dependency of copycat-runtime on core.
4a9b4f3 [Ewen Cheslack-Postava] Add some helpful Copycat-specific build and test targets that cover all Copycat packages.
31cd1ca [Ewen Cheslack-Postava] Add CLI tools for Copycat.
e14942c [Ewen Cheslack-Postava] Add Copycat file connector.
0233456 [Ewen Cheslack-Postava] Add copycat-avro and copycat-runtime
11981d2 [Ewen Cheslack-Postava] Add copycat-data and copycat-api
9 years ago
}
tasks . create ( name: "copyDependantLibs" , type: Copy ) {
from ( configurations . testRuntimeClasspath ) {
include ( 'slf4j-log4j12*' )
include ( 'reload4j*jar' )
}
from ( configurations . runtimeClasspath ) {
exclude ( 'kafka-clients*' )
exclude ( 'connect-*' )
}
into "$buildDir/dependant-libs"
duplicatesStrategy 'exclude'
}
jar {
dependsOn copyDependantLibs
}
KAFKA-2366; Initial patch for Copycat
This is an initial patch implementing the basics of Copycat for KIP-26.
The intent here is to start a review of the key pieces of the core API and get a reasonably functional, baseline, non-distributed implementation of Copycat in place to get things rolling. The current patch has a number of known issues that need to be addressed before a final version:
* Some build-related issues. Specifically, requires some locally-installed dependencies (see below), ignores checkstyle for the runtime data library because it's lifted from Avro currently and likely won't last in its current form, and some Gradle task dependencies aren't quite right because I haven't gotten rid of the dependency on `core` (which should now be an easy patch since new consumer groups are in a much better state).
* This patch currently depends on some Confluent trunk code because I prototyped with our Avro serializers w/ schema-registry support. We need to figure out what we want to provide as an example built-in set of serializers. Unlike core Kafka where we could ignore the issue, providing only ByteArray or String serializers, this is pretty central to how Copycat works.
* This patch uses a hacked up version of Avro as its runtime data format. Not sure if we want to go through the entire API discussion just to get some basic code committed, so I filed KAFKA-2367 to handle that separately. The core connector APIs and the runtime data APIs are entirely orthogonal.
* This patch needs some updates to get aligned with recent new consumer changes (specifically, I'm aware of the ConcurrentModificationException issue on exit). More generally, the new consumer is in flux but Copycat depends on it, so there are likely to be some negative interactions.
* The layout feels a bit awkward to me right now because I ported it from a Maven layout. We don't have nearly the same level of granularity in Kafka currently (core and clients, plus the mostly ignored examples, log4j-appender, and a couple of contribs). We might want to reorganize, although keeping data+api separate from runtime and connector plugins is useful for minimizing dependencies.
* There are a variety of other things (e.g., I'm not happy with the exception hierarchy/how they are currently handled, TopicPartition doesn't really need to be duplicated unless we want Copycat entirely isolated from the Kafka APIs, etc), but I expect those we'll cover in the review.
Before commenting on the patch, it's probably worth reviewing https://issues.apache.org/jira/browse/KAFKA-2365 and https://issues.apache.org/jira/browse/KAFKA-2366 to get an idea of what I had in mind for a) what we ultimately want with all the Copycat patches and b) what we aim to cover in this initial patch. My hope is that we can use a WIP patch (after the current obvious deficiencies are addressed) while recognizing that we want to make iterative progress with a bunch of subsequent PRs.
Author: Ewen Cheslack-Postava <me@ewencp.org>
Reviewers: Ismael Juma, Gwen Shapira
Closes #99 from ewencp/copycat and squashes the following commits:
a3a47a6 [Ewen Cheslack-Postava] Simplify Copycat exceptions, make them a subclass of KafkaException.
8c108b0 [Ewen Cheslack-Postava] Rename Coordinator to Herder to avoid confusion with the consumer coordinator.
7bf8075 [Ewen Cheslack-Postava] Make Copycat CLI speific to standalone mode, clean up some config and get rid of config storage in standalone mode.
656a003 [Ewen Cheslack-Postava] Clarify and expand the explanation of the Copycat Coordinator interface.
c0e5fdc [Ewen Cheslack-Postava] Merge remote-tracking branch 'origin/trunk' into copycat
0fa7a36 [Ewen Cheslack-Postava] Mark Copycat classes as unstable and reduce visibility of some classes where possible.
d55d31e [Ewen Cheslack-Postava] Reorganize Copycat code to put it all under one top-level directory.
b29cb2c [Ewen Cheslack-Postava] Merge remote-tracking branch 'origin/trunk' into copycat
d713a21 [Ewen Cheslack-Postava] Address Gwen's review comments.
6787a85 [Ewen Cheslack-Postava] Make Converter generic to match serializers since some serialization formats do not require a base class of Object; update many other classes to have generic key and value class type parameters to match this change.
b194c73 [Ewen Cheslack-Postava] Split Copycat converter option into two options for key and value.
0b5a1a0 [Ewen Cheslack-Postava] Normalize naming to use partition for both source and Kafka, adjusting naming in CopycatRecord classes to clearly differentiate.
e345142 [Ewen Cheslack-Postava] Remove Copycat reflection utils, use existing Utils and ConfigDef functionality from clients package.
be5c387 [Ewen Cheslack-Postava] Minor cleanup
122423e [Ewen Cheslack-Postava] Style cleanup
6ba87de [Ewen Cheslack-Postava] Remove most of the Avro-based mock runtime data API, only preserving enough schema functionality to support basic primitive types for an initial patch.
4674d13 [Ewen Cheslack-Postava] Address review comments, clean up some code styling.
25b5739 [Ewen Cheslack-Postava] Fix sink task offset commit concurrency issue by moving it to the worker thread and waking up the consumer to ensure it exits promptly.
0aefe21 [Ewen Cheslack-Postava] Add log4j settings for Copycat.
220e42d [Ewen Cheslack-Postava] Replace Avro serializer with JSON serializer.
1243a7c [Ewen Cheslack-Postava] Merge remote-tracking branch 'origin/trunk' into copycat
5a618c6 [Ewen Cheslack-Postava] Remove offset serializers, instead reusing the existing serializers and removing schema projection support.
e849e10 [Ewen Cheslack-Postava] Remove duplicated TopicPartition implementation.
dec1379 [Ewen Cheslack-Postava] Switch to using new consumer coordinator instead of manually assigning partitions. Remove dependency of copycat-runtime on core.
4a9b4f3 [Ewen Cheslack-Postava] Add some helpful Copycat-specific build and test targets that cover all Copycat packages.
31cd1ca [Ewen Cheslack-Postava] Add CLI tools for Copycat.
e14942c [Ewen Cheslack-Postava] Add Copycat file connector.
0233456 [Ewen Cheslack-Postava] Add copycat-avro and copycat-runtime
11981d2 [Ewen Cheslack-Postava] Add copycat-data and copycat-api
9 years ago
}
project ( ':connect:transforms' ) {
archivesBaseName = "connect-transforms"
dependencies {
api project ( ':connect:api' )
implementation libs . slf4jApi
testImplementation libs . easymock
testImplementation libs . junitJupiter
testRuntimeOnly libs . slf4jlog4j
testImplementation project ( ':clients' ) . sourceSets . test . output
}
javadoc {
enabled = false
}
tasks . create ( name: "copyDependantLibs" , type: Copy ) {
from ( configurations . testRuntimeClasspath ) {
include ( 'slf4j-log4j12*' )
include ( 'reload4j*jar' )
}
from ( configurations . runtimeClasspath ) {
exclude ( 'kafka-clients*' )
exclude ( 'connect-*' )
}
into "$buildDir/dependant-libs"
duplicatesStrategy 'exclude'
}
jar {
dependsOn copyDependantLibs
}
}
project ( ':connect:json' ) {
archivesBaseName = "connect-json"
KAFKA-2366; Initial patch for Copycat
This is an initial patch implementing the basics of Copycat for KIP-26.
The intent here is to start a review of the key pieces of the core API and get a reasonably functional, baseline, non-distributed implementation of Copycat in place to get things rolling. The current patch has a number of known issues that need to be addressed before a final version:
* Some build-related issues. Specifically, requires some locally-installed dependencies (see below), ignores checkstyle for the runtime data library because it's lifted from Avro currently and likely won't last in its current form, and some Gradle task dependencies aren't quite right because I haven't gotten rid of the dependency on `core` (which should now be an easy patch since new consumer groups are in a much better state).
* This patch currently depends on some Confluent trunk code because I prototyped with our Avro serializers w/ schema-registry support. We need to figure out what we want to provide as an example built-in set of serializers. Unlike core Kafka where we could ignore the issue, providing only ByteArray or String serializers, this is pretty central to how Copycat works.
* This patch uses a hacked up version of Avro as its runtime data format. Not sure if we want to go through the entire API discussion just to get some basic code committed, so I filed KAFKA-2367 to handle that separately. The core connector APIs and the runtime data APIs are entirely orthogonal.
* This patch needs some updates to get aligned with recent new consumer changes (specifically, I'm aware of the ConcurrentModificationException issue on exit). More generally, the new consumer is in flux but Copycat depends on it, so there are likely to be some negative interactions.
* The layout feels a bit awkward to me right now because I ported it from a Maven layout. We don't have nearly the same level of granularity in Kafka currently (core and clients, plus the mostly ignored examples, log4j-appender, and a couple of contribs). We might want to reorganize, although keeping data+api separate from runtime and connector plugins is useful for minimizing dependencies.
* There are a variety of other things (e.g., I'm not happy with the exception hierarchy/how they are currently handled, TopicPartition doesn't really need to be duplicated unless we want Copycat entirely isolated from the Kafka APIs, etc), but I expect those we'll cover in the review.
Before commenting on the patch, it's probably worth reviewing https://issues.apache.org/jira/browse/KAFKA-2365 and https://issues.apache.org/jira/browse/KAFKA-2366 to get an idea of what I had in mind for a) what we ultimately want with all the Copycat patches and b) what we aim to cover in this initial patch. My hope is that we can use a WIP patch (after the current obvious deficiencies are addressed) while recognizing that we want to make iterative progress with a bunch of subsequent PRs.
Author: Ewen Cheslack-Postava <me@ewencp.org>
Reviewers: Ismael Juma, Gwen Shapira
Closes #99 from ewencp/copycat and squashes the following commits:
a3a47a6 [Ewen Cheslack-Postava] Simplify Copycat exceptions, make them a subclass of KafkaException.
8c108b0 [Ewen Cheslack-Postava] Rename Coordinator to Herder to avoid confusion with the consumer coordinator.
7bf8075 [Ewen Cheslack-Postava] Make Copycat CLI speific to standalone mode, clean up some config and get rid of config storage in standalone mode.
656a003 [Ewen Cheslack-Postava] Clarify and expand the explanation of the Copycat Coordinator interface.
c0e5fdc [Ewen Cheslack-Postava] Merge remote-tracking branch 'origin/trunk' into copycat
0fa7a36 [Ewen Cheslack-Postava] Mark Copycat classes as unstable and reduce visibility of some classes where possible.
d55d31e [Ewen Cheslack-Postava] Reorganize Copycat code to put it all under one top-level directory.
b29cb2c [Ewen Cheslack-Postava] Merge remote-tracking branch 'origin/trunk' into copycat
d713a21 [Ewen Cheslack-Postava] Address Gwen's review comments.
6787a85 [Ewen Cheslack-Postava] Make Converter generic to match serializers since some serialization formats do not require a base class of Object; update many other classes to have generic key and value class type parameters to match this change.
b194c73 [Ewen Cheslack-Postava] Split Copycat converter option into two options for key and value.
0b5a1a0 [Ewen Cheslack-Postava] Normalize naming to use partition for both source and Kafka, adjusting naming in CopycatRecord classes to clearly differentiate.
e345142 [Ewen Cheslack-Postava] Remove Copycat reflection utils, use existing Utils and ConfigDef functionality from clients package.
be5c387 [Ewen Cheslack-Postava] Minor cleanup
122423e [Ewen Cheslack-Postava] Style cleanup
6ba87de [Ewen Cheslack-Postava] Remove most of the Avro-based mock runtime data API, only preserving enough schema functionality to support basic primitive types for an initial patch.
4674d13 [Ewen Cheslack-Postava] Address review comments, clean up some code styling.
25b5739 [Ewen Cheslack-Postava] Fix sink task offset commit concurrency issue by moving it to the worker thread and waking up the consumer to ensure it exits promptly.
0aefe21 [Ewen Cheslack-Postava] Add log4j settings for Copycat.
220e42d [Ewen Cheslack-Postava] Replace Avro serializer with JSON serializer.
1243a7c [Ewen Cheslack-Postava] Merge remote-tracking branch 'origin/trunk' into copycat
5a618c6 [Ewen Cheslack-Postava] Remove offset serializers, instead reusing the existing serializers and removing schema projection support.
e849e10 [Ewen Cheslack-Postava] Remove duplicated TopicPartition implementation.
dec1379 [Ewen Cheslack-Postava] Switch to using new consumer coordinator instead of manually assigning partitions. Remove dependency of copycat-runtime on core.
4a9b4f3 [Ewen Cheslack-Postava] Add some helpful Copycat-specific build and test targets that cover all Copycat packages.
31cd1ca [Ewen Cheslack-Postava] Add CLI tools for Copycat.
e14942c [Ewen Cheslack-Postava] Add Copycat file connector.
0233456 [Ewen Cheslack-Postava] Add copycat-avro and copycat-runtime
11981d2 [Ewen Cheslack-Postava] Add copycat-data and copycat-api
9 years ago
dependencies {
api project ( ':connect:api' )
KAFKA-2366; Initial patch for Copycat
This is an initial patch implementing the basics of Copycat for KIP-26.
The intent here is to start a review of the key pieces of the core API and get a reasonably functional, baseline, non-distributed implementation of Copycat in place to get things rolling. The current patch has a number of known issues that need to be addressed before a final version:
* Some build-related issues. Specifically, requires some locally-installed dependencies (see below), ignores checkstyle for the runtime data library because it's lifted from Avro currently and likely won't last in its current form, and some Gradle task dependencies aren't quite right because I haven't gotten rid of the dependency on `core` (which should now be an easy patch since new consumer groups are in a much better state).
* This patch currently depends on some Confluent trunk code because I prototyped with our Avro serializers w/ schema-registry support. We need to figure out what we want to provide as an example built-in set of serializers. Unlike core Kafka where we could ignore the issue, providing only ByteArray or String serializers, this is pretty central to how Copycat works.
* This patch uses a hacked up version of Avro as its runtime data format. Not sure if we want to go through the entire API discussion just to get some basic code committed, so I filed KAFKA-2367 to handle that separately. The core connector APIs and the runtime data APIs are entirely orthogonal.
* This patch needs some updates to get aligned with recent new consumer changes (specifically, I'm aware of the ConcurrentModificationException issue on exit). More generally, the new consumer is in flux but Copycat depends on it, so there are likely to be some negative interactions.
* The layout feels a bit awkward to me right now because I ported it from a Maven layout. We don't have nearly the same level of granularity in Kafka currently (core and clients, plus the mostly ignored examples, log4j-appender, and a couple of contribs). We might want to reorganize, although keeping data+api separate from runtime and connector plugins is useful for minimizing dependencies.
* There are a variety of other things (e.g., I'm not happy with the exception hierarchy/how they are currently handled, TopicPartition doesn't really need to be duplicated unless we want Copycat entirely isolated from the Kafka APIs, etc), but I expect those we'll cover in the review.
Before commenting on the patch, it's probably worth reviewing https://issues.apache.org/jira/browse/KAFKA-2365 and https://issues.apache.org/jira/browse/KAFKA-2366 to get an idea of what I had in mind for a) what we ultimately want with all the Copycat patches and b) what we aim to cover in this initial patch. My hope is that we can use a WIP patch (after the current obvious deficiencies are addressed) while recognizing that we want to make iterative progress with a bunch of subsequent PRs.
Author: Ewen Cheslack-Postava <me@ewencp.org>
Reviewers: Ismael Juma, Gwen Shapira
Closes #99 from ewencp/copycat and squashes the following commits:
a3a47a6 [Ewen Cheslack-Postava] Simplify Copycat exceptions, make them a subclass of KafkaException.
8c108b0 [Ewen Cheslack-Postava] Rename Coordinator to Herder to avoid confusion with the consumer coordinator.
7bf8075 [Ewen Cheslack-Postava] Make Copycat CLI speific to standalone mode, clean up some config and get rid of config storage in standalone mode.
656a003 [Ewen Cheslack-Postava] Clarify and expand the explanation of the Copycat Coordinator interface.
c0e5fdc [Ewen Cheslack-Postava] Merge remote-tracking branch 'origin/trunk' into copycat
0fa7a36 [Ewen Cheslack-Postava] Mark Copycat classes as unstable and reduce visibility of some classes where possible.
d55d31e [Ewen Cheslack-Postava] Reorganize Copycat code to put it all under one top-level directory.
b29cb2c [Ewen Cheslack-Postava] Merge remote-tracking branch 'origin/trunk' into copycat
d713a21 [Ewen Cheslack-Postava] Address Gwen's review comments.
6787a85 [Ewen Cheslack-Postava] Make Converter generic to match serializers since some serialization formats do not require a base class of Object; update many other classes to have generic key and value class type parameters to match this change.
b194c73 [Ewen Cheslack-Postava] Split Copycat converter option into two options for key and value.
0b5a1a0 [Ewen Cheslack-Postava] Normalize naming to use partition for both source and Kafka, adjusting naming in CopycatRecord classes to clearly differentiate.
e345142 [Ewen Cheslack-Postava] Remove Copycat reflection utils, use existing Utils and ConfigDef functionality from clients package.
be5c387 [Ewen Cheslack-Postava] Minor cleanup
122423e [Ewen Cheslack-Postava] Style cleanup
6ba87de [Ewen Cheslack-Postava] Remove most of the Avro-based mock runtime data API, only preserving enough schema functionality to support basic primitive types for an initial patch.
4674d13 [Ewen Cheslack-Postava] Address review comments, clean up some code styling.
25b5739 [Ewen Cheslack-Postava] Fix sink task offset commit concurrency issue by moving it to the worker thread and waking up the consumer to ensure it exits promptly.
0aefe21 [Ewen Cheslack-Postava] Add log4j settings for Copycat.
220e42d [Ewen Cheslack-Postava] Replace Avro serializer with JSON serializer.
1243a7c [Ewen Cheslack-Postava] Merge remote-tracking branch 'origin/trunk' into copycat
5a618c6 [Ewen Cheslack-Postava] Remove offset serializers, instead reusing the existing serializers and removing schema projection support.
e849e10 [Ewen Cheslack-Postava] Remove duplicated TopicPartition implementation.
dec1379 [Ewen Cheslack-Postava] Switch to using new consumer coordinator instead of manually assigning partitions. Remove dependency of copycat-runtime on core.
4a9b4f3 [Ewen Cheslack-Postava] Add some helpful Copycat-specific build and test targets that cover all Copycat packages.
31cd1ca [Ewen Cheslack-Postava] Add CLI tools for Copycat.
e14942c [Ewen Cheslack-Postava] Add Copycat file connector.
0233456 [Ewen Cheslack-Postava] Add copycat-avro and copycat-runtime
11981d2 [Ewen Cheslack-Postava] Add copycat-data and copycat-api
9 years ago
api libs . jacksonDatabind
api libs . jacksonJDK8Datatypes
implementation libs . slf4jApi
testImplementation libs . easymock
testImplementation libs . junitJupiter
testRuntimeOnly libs . slf4jlog4j
testImplementation project ( ':clients' ) . sourceSets . test . output
KAFKA-2366; Initial patch for Copycat
This is an initial patch implementing the basics of Copycat for KIP-26.
The intent here is to start a review of the key pieces of the core API and get a reasonably functional, baseline, non-distributed implementation of Copycat in place to get things rolling. The current patch has a number of known issues that need to be addressed before a final version:
* Some build-related issues. Specifically, requires some locally-installed dependencies (see below), ignores checkstyle for the runtime data library because it's lifted from Avro currently and likely won't last in its current form, and some Gradle task dependencies aren't quite right because I haven't gotten rid of the dependency on `core` (which should now be an easy patch since new consumer groups are in a much better state).
* This patch currently depends on some Confluent trunk code because I prototyped with our Avro serializers w/ schema-registry support. We need to figure out what we want to provide as an example built-in set of serializers. Unlike core Kafka where we could ignore the issue, providing only ByteArray or String serializers, this is pretty central to how Copycat works.
* This patch uses a hacked up version of Avro as its runtime data format. Not sure if we want to go through the entire API discussion just to get some basic code committed, so I filed KAFKA-2367 to handle that separately. The core connector APIs and the runtime data APIs are entirely orthogonal.
* This patch needs some updates to get aligned with recent new consumer changes (specifically, I'm aware of the ConcurrentModificationException issue on exit). More generally, the new consumer is in flux but Copycat depends on it, so there are likely to be some negative interactions.
* The layout feels a bit awkward to me right now because I ported it from a Maven layout. We don't have nearly the same level of granularity in Kafka currently (core and clients, plus the mostly ignored examples, log4j-appender, and a couple of contribs). We might want to reorganize, although keeping data+api separate from runtime and connector plugins is useful for minimizing dependencies.
* There are a variety of other things (e.g., I'm not happy with the exception hierarchy/how they are currently handled, TopicPartition doesn't really need to be duplicated unless we want Copycat entirely isolated from the Kafka APIs, etc), but I expect those we'll cover in the review.
Before commenting on the patch, it's probably worth reviewing https://issues.apache.org/jira/browse/KAFKA-2365 and https://issues.apache.org/jira/browse/KAFKA-2366 to get an idea of what I had in mind for a) what we ultimately want with all the Copycat patches and b) what we aim to cover in this initial patch. My hope is that we can use a WIP patch (after the current obvious deficiencies are addressed) while recognizing that we want to make iterative progress with a bunch of subsequent PRs.
Author: Ewen Cheslack-Postava <me@ewencp.org>
Reviewers: Ismael Juma, Gwen Shapira
Closes #99 from ewencp/copycat and squashes the following commits:
a3a47a6 [Ewen Cheslack-Postava] Simplify Copycat exceptions, make them a subclass of KafkaException.
8c108b0 [Ewen Cheslack-Postava] Rename Coordinator to Herder to avoid confusion with the consumer coordinator.
7bf8075 [Ewen Cheslack-Postava] Make Copycat CLI speific to standalone mode, clean up some config and get rid of config storage in standalone mode.
656a003 [Ewen Cheslack-Postava] Clarify and expand the explanation of the Copycat Coordinator interface.
c0e5fdc [Ewen Cheslack-Postava] Merge remote-tracking branch 'origin/trunk' into copycat
0fa7a36 [Ewen Cheslack-Postava] Mark Copycat classes as unstable and reduce visibility of some classes where possible.
d55d31e [Ewen Cheslack-Postava] Reorganize Copycat code to put it all under one top-level directory.
b29cb2c [Ewen Cheslack-Postava] Merge remote-tracking branch 'origin/trunk' into copycat
d713a21 [Ewen Cheslack-Postava] Address Gwen's review comments.
6787a85 [Ewen Cheslack-Postava] Make Converter generic to match serializers since some serialization formats do not require a base class of Object; update many other classes to have generic key and value class type parameters to match this change.
b194c73 [Ewen Cheslack-Postava] Split Copycat converter option into two options for key and value.
0b5a1a0 [Ewen Cheslack-Postava] Normalize naming to use partition for both source and Kafka, adjusting naming in CopycatRecord classes to clearly differentiate.
e345142 [Ewen Cheslack-Postava] Remove Copycat reflection utils, use existing Utils and ConfigDef functionality from clients package.
be5c387 [Ewen Cheslack-Postava] Minor cleanup
122423e [Ewen Cheslack-Postava] Style cleanup
6ba87de [Ewen Cheslack-Postava] Remove most of the Avro-based mock runtime data API, only preserving enough schema functionality to support basic primitive types for an initial patch.
4674d13 [Ewen Cheslack-Postava] Address review comments, clean up some code styling.
25b5739 [Ewen Cheslack-Postava] Fix sink task offset commit concurrency issue by moving it to the worker thread and waking up the consumer to ensure it exits promptly.
0aefe21 [Ewen Cheslack-Postava] Add log4j settings for Copycat.
220e42d [Ewen Cheslack-Postava] Replace Avro serializer with JSON serializer.
1243a7c [Ewen Cheslack-Postava] Merge remote-tracking branch 'origin/trunk' into copycat
5a618c6 [Ewen Cheslack-Postava] Remove offset serializers, instead reusing the existing serializers and removing schema projection support.
e849e10 [Ewen Cheslack-Postava] Remove duplicated TopicPartition implementation.
dec1379 [Ewen Cheslack-Postava] Switch to using new consumer coordinator instead of manually assigning partitions. Remove dependency of copycat-runtime on core.
4a9b4f3 [Ewen Cheslack-Postava] Add some helpful Copycat-specific build and test targets that cover all Copycat packages.
31cd1ca [Ewen Cheslack-Postava] Add CLI tools for Copycat.
e14942c [Ewen Cheslack-Postava] Add Copycat file connector.
0233456 [Ewen Cheslack-Postava] Add copycat-avro and copycat-runtime
11981d2 [Ewen Cheslack-Postava] Add copycat-data and copycat-api
9 years ago
}
javadoc {
enabled = false
KAFKA-2366; Initial patch for Copycat
This is an initial patch implementing the basics of Copycat for KIP-26.
The intent here is to start a review of the key pieces of the core API and get a reasonably functional, baseline, non-distributed implementation of Copycat in place to get things rolling. The current patch has a number of known issues that need to be addressed before a final version:
* Some build-related issues. Specifically, requires some locally-installed dependencies (see below), ignores checkstyle for the runtime data library because it's lifted from Avro currently and likely won't last in its current form, and some Gradle task dependencies aren't quite right because I haven't gotten rid of the dependency on `core` (which should now be an easy patch since new consumer groups are in a much better state).
* This patch currently depends on some Confluent trunk code because I prototyped with our Avro serializers w/ schema-registry support. We need to figure out what we want to provide as an example built-in set of serializers. Unlike core Kafka where we could ignore the issue, providing only ByteArray or String serializers, this is pretty central to how Copycat works.
* This patch uses a hacked up version of Avro as its runtime data format. Not sure if we want to go through the entire API discussion just to get some basic code committed, so I filed KAFKA-2367 to handle that separately. The core connector APIs and the runtime data APIs are entirely orthogonal.
* This patch needs some updates to get aligned with recent new consumer changes (specifically, I'm aware of the ConcurrentModificationException issue on exit). More generally, the new consumer is in flux but Copycat depends on it, so there are likely to be some negative interactions.
* The layout feels a bit awkward to me right now because I ported it from a Maven layout. We don't have nearly the same level of granularity in Kafka currently (core and clients, plus the mostly ignored examples, log4j-appender, and a couple of contribs). We might want to reorganize, although keeping data+api separate from runtime and connector plugins is useful for minimizing dependencies.
* There are a variety of other things (e.g., I'm not happy with the exception hierarchy/how they are currently handled, TopicPartition doesn't really need to be duplicated unless we want Copycat entirely isolated from the Kafka APIs, etc), but I expect those we'll cover in the review.
Before commenting on the patch, it's probably worth reviewing https://issues.apache.org/jira/browse/KAFKA-2365 and https://issues.apache.org/jira/browse/KAFKA-2366 to get an idea of what I had in mind for a) what we ultimately want with all the Copycat patches and b) what we aim to cover in this initial patch. My hope is that we can use a WIP patch (after the current obvious deficiencies are addressed) while recognizing that we want to make iterative progress with a bunch of subsequent PRs.
Author: Ewen Cheslack-Postava <me@ewencp.org>
Reviewers: Ismael Juma, Gwen Shapira
Closes #99 from ewencp/copycat and squashes the following commits:
a3a47a6 [Ewen Cheslack-Postava] Simplify Copycat exceptions, make them a subclass of KafkaException.
8c108b0 [Ewen Cheslack-Postava] Rename Coordinator to Herder to avoid confusion with the consumer coordinator.
7bf8075 [Ewen Cheslack-Postava] Make Copycat CLI speific to standalone mode, clean up some config and get rid of config storage in standalone mode.
656a003 [Ewen Cheslack-Postava] Clarify and expand the explanation of the Copycat Coordinator interface.
c0e5fdc [Ewen Cheslack-Postava] Merge remote-tracking branch 'origin/trunk' into copycat
0fa7a36 [Ewen Cheslack-Postava] Mark Copycat classes as unstable and reduce visibility of some classes where possible.
d55d31e [Ewen Cheslack-Postava] Reorganize Copycat code to put it all under one top-level directory.
b29cb2c [Ewen Cheslack-Postava] Merge remote-tracking branch 'origin/trunk' into copycat
d713a21 [Ewen Cheslack-Postava] Address Gwen's review comments.
6787a85 [Ewen Cheslack-Postava] Make Converter generic to match serializers since some serialization formats do not require a base class of Object; update many other classes to have generic key and value class type parameters to match this change.
b194c73 [Ewen Cheslack-Postava] Split Copycat converter option into two options for key and value.
0b5a1a0 [Ewen Cheslack-Postava] Normalize naming to use partition for both source and Kafka, adjusting naming in CopycatRecord classes to clearly differentiate.
e345142 [Ewen Cheslack-Postava] Remove Copycat reflection utils, use existing Utils and ConfigDef functionality from clients package.
be5c387 [Ewen Cheslack-Postava] Minor cleanup
122423e [Ewen Cheslack-Postava] Style cleanup
6ba87de [Ewen Cheslack-Postava] Remove most of the Avro-based mock runtime data API, only preserving enough schema functionality to support basic primitive types for an initial patch.
4674d13 [Ewen Cheslack-Postava] Address review comments, clean up some code styling.
25b5739 [Ewen Cheslack-Postava] Fix sink task offset commit concurrency issue by moving it to the worker thread and waking up the consumer to ensure it exits promptly.
0aefe21 [Ewen Cheslack-Postava] Add log4j settings for Copycat.
220e42d [Ewen Cheslack-Postava] Replace Avro serializer with JSON serializer.
1243a7c [Ewen Cheslack-Postava] Merge remote-tracking branch 'origin/trunk' into copycat
5a618c6 [Ewen Cheslack-Postava] Remove offset serializers, instead reusing the existing serializers and removing schema projection support.
e849e10 [Ewen Cheslack-Postava] Remove duplicated TopicPartition implementation.
dec1379 [Ewen Cheslack-Postava] Switch to using new consumer coordinator instead of manually assigning partitions. Remove dependency of copycat-runtime on core.
4a9b4f3 [Ewen Cheslack-Postava] Add some helpful Copycat-specific build and test targets that cover all Copycat packages.
31cd1ca [Ewen Cheslack-Postava] Add CLI tools for Copycat.
e14942c [Ewen Cheslack-Postava] Add Copycat file connector.
0233456 [Ewen Cheslack-Postava] Add copycat-avro and copycat-runtime
11981d2 [Ewen Cheslack-Postava] Add copycat-data and copycat-api
9 years ago
}
tasks . create ( name: "copyDependantLibs" , type: Copy ) {
from ( configurations . testRuntimeClasspath ) {
include ( 'slf4j-log4j12*' )
include ( 'reload4j*jar' )
}
from ( configurations . runtimeClasspath ) {
exclude ( 'kafka-clients*' )
exclude ( 'connect-*' )
}
into "$buildDir/dependant-libs"
duplicatesStrategy 'exclude'
}
jar {
dependsOn copyDependantLibs
}
KAFKA-2366; Initial patch for Copycat
This is an initial patch implementing the basics of Copycat for KIP-26.
The intent here is to start a review of the key pieces of the core API and get a reasonably functional, baseline, non-distributed implementation of Copycat in place to get things rolling. The current patch has a number of known issues that need to be addressed before a final version:
* Some build-related issues. Specifically, requires some locally-installed dependencies (see below), ignores checkstyle for the runtime data library because it's lifted from Avro currently and likely won't last in its current form, and some Gradle task dependencies aren't quite right because I haven't gotten rid of the dependency on `core` (which should now be an easy patch since new consumer groups are in a much better state).
* This patch currently depends on some Confluent trunk code because I prototyped with our Avro serializers w/ schema-registry support. We need to figure out what we want to provide as an example built-in set of serializers. Unlike core Kafka where we could ignore the issue, providing only ByteArray or String serializers, this is pretty central to how Copycat works.
* This patch uses a hacked up version of Avro as its runtime data format. Not sure if we want to go through the entire API discussion just to get some basic code committed, so I filed KAFKA-2367 to handle that separately. The core connector APIs and the runtime data APIs are entirely orthogonal.
* This patch needs some updates to get aligned with recent new consumer changes (specifically, I'm aware of the ConcurrentModificationException issue on exit). More generally, the new consumer is in flux but Copycat depends on it, so there are likely to be some negative interactions.
* The layout feels a bit awkward to me right now because I ported it from a Maven layout. We don't have nearly the same level of granularity in Kafka currently (core and clients, plus the mostly ignored examples, log4j-appender, and a couple of contribs). We might want to reorganize, although keeping data+api separate from runtime and connector plugins is useful for minimizing dependencies.
* There are a variety of other things (e.g., I'm not happy with the exception hierarchy/how they are currently handled, TopicPartition doesn't really need to be duplicated unless we want Copycat entirely isolated from the Kafka APIs, etc), but I expect those we'll cover in the review.
Before commenting on the patch, it's probably worth reviewing https://issues.apache.org/jira/browse/KAFKA-2365 and https://issues.apache.org/jira/browse/KAFKA-2366 to get an idea of what I had in mind for a) what we ultimately want with all the Copycat patches and b) what we aim to cover in this initial patch. My hope is that we can use a WIP patch (after the current obvious deficiencies are addressed) while recognizing that we want to make iterative progress with a bunch of subsequent PRs.
Author: Ewen Cheslack-Postava <me@ewencp.org>
Reviewers: Ismael Juma, Gwen Shapira
Closes #99 from ewencp/copycat and squashes the following commits:
a3a47a6 [Ewen Cheslack-Postava] Simplify Copycat exceptions, make them a subclass of KafkaException.
8c108b0 [Ewen Cheslack-Postava] Rename Coordinator to Herder to avoid confusion with the consumer coordinator.
7bf8075 [Ewen Cheslack-Postava] Make Copycat CLI speific to standalone mode, clean up some config and get rid of config storage in standalone mode.
656a003 [Ewen Cheslack-Postava] Clarify and expand the explanation of the Copycat Coordinator interface.
c0e5fdc [Ewen Cheslack-Postava] Merge remote-tracking branch 'origin/trunk' into copycat
0fa7a36 [Ewen Cheslack-Postava] Mark Copycat classes as unstable and reduce visibility of some classes where possible.
d55d31e [Ewen Cheslack-Postava] Reorganize Copycat code to put it all under one top-level directory.
b29cb2c [Ewen Cheslack-Postava] Merge remote-tracking branch 'origin/trunk' into copycat
d713a21 [Ewen Cheslack-Postava] Address Gwen's review comments.
6787a85 [Ewen Cheslack-Postava] Make Converter generic to match serializers since some serialization formats do not require a base class of Object; update many other classes to have generic key and value class type parameters to match this change.
b194c73 [Ewen Cheslack-Postava] Split Copycat converter option into two options for key and value.
0b5a1a0 [Ewen Cheslack-Postava] Normalize naming to use partition for both source and Kafka, adjusting naming in CopycatRecord classes to clearly differentiate.
e345142 [Ewen Cheslack-Postava] Remove Copycat reflection utils, use existing Utils and ConfigDef functionality from clients package.
be5c387 [Ewen Cheslack-Postava] Minor cleanup
122423e [Ewen Cheslack-Postava] Style cleanup
6ba87de [Ewen Cheslack-Postava] Remove most of the Avro-based mock runtime data API, only preserving enough schema functionality to support basic primitive types for an initial patch.
4674d13 [Ewen Cheslack-Postava] Address review comments, clean up some code styling.
25b5739 [Ewen Cheslack-Postava] Fix sink task offset commit concurrency issue by moving it to the worker thread and waking up the consumer to ensure it exits promptly.
0aefe21 [Ewen Cheslack-Postava] Add log4j settings for Copycat.
220e42d [Ewen Cheslack-Postava] Replace Avro serializer with JSON serializer.
1243a7c [Ewen Cheslack-Postava] Merge remote-tracking branch 'origin/trunk' into copycat
5a618c6 [Ewen Cheslack-Postava] Remove offset serializers, instead reusing the existing serializers and removing schema projection support.
e849e10 [Ewen Cheslack-Postava] Remove duplicated TopicPartition implementation.
dec1379 [Ewen Cheslack-Postava] Switch to using new consumer coordinator instead of manually assigning partitions. Remove dependency of copycat-runtime on core.
4a9b4f3 [Ewen Cheslack-Postava] Add some helpful Copycat-specific build and test targets that cover all Copycat packages.
31cd1ca [Ewen Cheslack-Postava] Add CLI tools for Copycat.
e14942c [Ewen Cheslack-Postava] Add Copycat file connector.
0233456 [Ewen Cheslack-Postava] Add copycat-avro and copycat-runtime
11981d2 [Ewen Cheslack-Postava] Add copycat-data and copycat-api
9 years ago
}
project ( ':connect:runtime' ) {
configurations {
swagger
}
archivesBaseName = "connect-runtime"
KAFKA-2366; Initial patch for Copycat
This is an initial patch implementing the basics of Copycat for KIP-26.
The intent here is to start a review of the key pieces of the core API and get a reasonably functional, baseline, non-distributed implementation of Copycat in place to get things rolling. The current patch has a number of known issues that need to be addressed before a final version:
* Some build-related issues. Specifically, requires some locally-installed dependencies (see below), ignores checkstyle for the runtime data library because it's lifted from Avro currently and likely won't last in its current form, and some Gradle task dependencies aren't quite right because I haven't gotten rid of the dependency on `core` (which should now be an easy patch since new consumer groups are in a much better state).
* This patch currently depends on some Confluent trunk code because I prototyped with our Avro serializers w/ schema-registry support. We need to figure out what we want to provide as an example built-in set of serializers. Unlike core Kafka where we could ignore the issue, providing only ByteArray or String serializers, this is pretty central to how Copycat works.
* This patch uses a hacked up version of Avro as its runtime data format. Not sure if we want to go through the entire API discussion just to get some basic code committed, so I filed KAFKA-2367 to handle that separately. The core connector APIs and the runtime data APIs are entirely orthogonal.
* This patch needs some updates to get aligned with recent new consumer changes (specifically, I'm aware of the ConcurrentModificationException issue on exit). More generally, the new consumer is in flux but Copycat depends on it, so there are likely to be some negative interactions.
* The layout feels a bit awkward to me right now because I ported it from a Maven layout. We don't have nearly the same level of granularity in Kafka currently (core and clients, plus the mostly ignored examples, log4j-appender, and a couple of contribs). We might want to reorganize, although keeping data+api separate from runtime and connector plugins is useful for minimizing dependencies.
* There are a variety of other things (e.g., I'm not happy with the exception hierarchy/how they are currently handled, TopicPartition doesn't really need to be duplicated unless we want Copycat entirely isolated from the Kafka APIs, etc), but I expect those we'll cover in the review.
Before commenting on the patch, it's probably worth reviewing https://issues.apache.org/jira/browse/KAFKA-2365 and https://issues.apache.org/jira/browse/KAFKA-2366 to get an idea of what I had in mind for a) what we ultimately want with all the Copycat patches and b) what we aim to cover in this initial patch. My hope is that we can use a WIP patch (after the current obvious deficiencies are addressed) while recognizing that we want to make iterative progress with a bunch of subsequent PRs.
Author: Ewen Cheslack-Postava <me@ewencp.org>
Reviewers: Ismael Juma, Gwen Shapira
Closes #99 from ewencp/copycat and squashes the following commits:
a3a47a6 [Ewen Cheslack-Postava] Simplify Copycat exceptions, make them a subclass of KafkaException.
8c108b0 [Ewen Cheslack-Postava] Rename Coordinator to Herder to avoid confusion with the consumer coordinator.
7bf8075 [Ewen Cheslack-Postava] Make Copycat CLI speific to standalone mode, clean up some config and get rid of config storage in standalone mode.
656a003 [Ewen Cheslack-Postava] Clarify and expand the explanation of the Copycat Coordinator interface.
c0e5fdc [Ewen Cheslack-Postava] Merge remote-tracking branch 'origin/trunk' into copycat
0fa7a36 [Ewen Cheslack-Postava] Mark Copycat classes as unstable and reduce visibility of some classes where possible.
d55d31e [Ewen Cheslack-Postava] Reorganize Copycat code to put it all under one top-level directory.
b29cb2c [Ewen Cheslack-Postava] Merge remote-tracking branch 'origin/trunk' into copycat
d713a21 [Ewen Cheslack-Postava] Address Gwen's review comments.
6787a85 [Ewen Cheslack-Postava] Make Converter generic to match serializers since some serialization formats do not require a base class of Object; update many other classes to have generic key and value class type parameters to match this change.
b194c73 [Ewen Cheslack-Postava] Split Copycat converter option into two options for key and value.
0b5a1a0 [Ewen Cheslack-Postava] Normalize naming to use partition for both source and Kafka, adjusting naming in CopycatRecord classes to clearly differentiate.
e345142 [Ewen Cheslack-Postava] Remove Copycat reflection utils, use existing Utils and ConfigDef functionality from clients package.
be5c387 [Ewen Cheslack-Postava] Minor cleanup
122423e [Ewen Cheslack-Postava] Style cleanup
6ba87de [Ewen Cheslack-Postava] Remove most of the Avro-based mock runtime data API, only preserving enough schema functionality to support basic primitive types for an initial patch.
4674d13 [Ewen Cheslack-Postava] Address review comments, clean up some code styling.
25b5739 [Ewen Cheslack-Postava] Fix sink task offset commit concurrency issue by moving it to the worker thread and waking up the consumer to ensure it exits promptly.
0aefe21 [Ewen Cheslack-Postava] Add log4j settings for Copycat.
220e42d [Ewen Cheslack-Postava] Replace Avro serializer with JSON serializer.
1243a7c [Ewen Cheslack-Postava] Merge remote-tracking branch 'origin/trunk' into copycat
5a618c6 [Ewen Cheslack-Postava] Remove offset serializers, instead reusing the existing serializers and removing schema projection support.
e849e10 [Ewen Cheslack-Postava] Remove duplicated TopicPartition implementation.
dec1379 [Ewen Cheslack-Postava] Switch to using new consumer coordinator instead of manually assigning partitions. Remove dependency of copycat-runtime on core.
4a9b4f3 [Ewen Cheslack-Postava] Add some helpful Copycat-specific build and test targets that cover all Copycat packages.
31cd1ca [Ewen Cheslack-Postava] Add CLI tools for Copycat.
e14942c [Ewen Cheslack-Postava] Add Copycat file connector.
0233456 [Ewen Cheslack-Postava] Add copycat-avro and copycat-runtime
11981d2 [Ewen Cheslack-Postava] Add copycat-data and copycat-api
9 years ago
dependencies {
// connect-runtime is used in tests, use `api` for modules below for backwards compatibility even though
// applications should generally not depend on `connect-runtime`
api project ( ':connect:api' )
api project ( ':clients' )
api project ( ':connect:json' )
api project ( ':connect:transforms' )
implementation project ( ':tools' )
implementation libs . slf4jApi
implementation libs . log4j
implementation libs . jose4j // for SASL/OAUTHBEARER JWT validation
implementation libs . jacksonAnnotations
implementation libs . jacksonJaxrsJsonProvider
implementation libs . jerseyContainerServlet
implementation libs . jerseyHk2
implementation libs . jaxbApi // Jersey dependency that was available in the JDK before Java 9
implementation libs . activation // Jersey dependency that was available in the JDK before Java 9
implementation libs . jettyServer
implementation libs . jettyServlet
implementation libs . jettyServlets
implementation libs . jettyClient
implementation libs . reflections
implementation libs . mavenArtifact
implementation libs . swaggerAnnotations
// We use this library to generate OpenAPI docs for the REST API, but we don't want or need it at compile
// or run time. So, we add it to a separate configuration, which we use later on during docs generation
swagger libs . swaggerJaxrs2
testImplementation project ( ':clients' ) . sourceSets . test . output
testImplementation project ( ':core' )
testImplementation project ( ':metadata' )
testImplementation project ( ':core' ) . sourceSets . test . output
testImplementation libs . easymock
testImplementation libs . junitJupiterApi
testImplementation libs . junitVintageEngine
testImplementation libs . powermockJunit4
testImplementation libs . powermockEasymock
testImplementation libs . mockitoInline
testImplementation libs . httpclient
testRuntimeOnly libs . slf4jlog4j
testRuntimeOnly libs . bcpkix
KAFKA-2366; Initial patch for Copycat
This is an initial patch implementing the basics of Copycat for KIP-26.
The intent here is to start a review of the key pieces of the core API and get a reasonably functional, baseline, non-distributed implementation of Copycat in place to get things rolling. The current patch has a number of known issues that need to be addressed before a final version:
* Some build-related issues. Specifically, requires some locally-installed dependencies (see below), ignores checkstyle for the runtime data library because it's lifted from Avro currently and likely won't last in its current form, and some Gradle task dependencies aren't quite right because I haven't gotten rid of the dependency on `core` (which should now be an easy patch since new consumer groups are in a much better state).
* This patch currently depends on some Confluent trunk code because I prototyped with our Avro serializers w/ schema-registry support. We need to figure out what we want to provide as an example built-in set of serializers. Unlike core Kafka where we could ignore the issue, providing only ByteArray or String serializers, this is pretty central to how Copycat works.
* This patch uses a hacked up version of Avro as its runtime data format. Not sure if we want to go through the entire API discussion just to get some basic code committed, so I filed KAFKA-2367 to handle that separately. The core connector APIs and the runtime data APIs are entirely orthogonal.
* This patch needs some updates to get aligned with recent new consumer changes (specifically, I'm aware of the ConcurrentModificationException issue on exit). More generally, the new consumer is in flux but Copycat depends on it, so there are likely to be some negative interactions.
* The layout feels a bit awkward to me right now because I ported it from a Maven layout. We don't have nearly the same level of granularity in Kafka currently (core and clients, plus the mostly ignored examples, log4j-appender, and a couple of contribs). We might want to reorganize, although keeping data+api separate from runtime and connector plugins is useful for minimizing dependencies.
* There are a variety of other things (e.g., I'm not happy with the exception hierarchy/how they are currently handled, TopicPartition doesn't really need to be duplicated unless we want Copycat entirely isolated from the Kafka APIs, etc), but I expect those we'll cover in the review.
Before commenting on the patch, it's probably worth reviewing https://issues.apache.org/jira/browse/KAFKA-2365 and https://issues.apache.org/jira/browse/KAFKA-2366 to get an idea of what I had in mind for a) what we ultimately want with all the Copycat patches and b) what we aim to cover in this initial patch. My hope is that we can use a WIP patch (after the current obvious deficiencies are addressed) while recognizing that we want to make iterative progress with a bunch of subsequent PRs.
Author: Ewen Cheslack-Postava <me@ewencp.org>
Reviewers: Ismael Juma, Gwen Shapira
Closes #99 from ewencp/copycat and squashes the following commits:
a3a47a6 [Ewen Cheslack-Postava] Simplify Copycat exceptions, make them a subclass of KafkaException.
8c108b0 [Ewen Cheslack-Postava] Rename Coordinator to Herder to avoid confusion with the consumer coordinator.
7bf8075 [Ewen Cheslack-Postava] Make Copycat CLI speific to standalone mode, clean up some config and get rid of config storage in standalone mode.
656a003 [Ewen Cheslack-Postava] Clarify and expand the explanation of the Copycat Coordinator interface.
c0e5fdc [Ewen Cheslack-Postava] Merge remote-tracking branch 'origin/trunk' into copycat
0fa7a36 [Ewen Cheslack-Postava] Mark Copycat classes as unstable and reduce visibility of some classes where possible.
d55d31e [Ewen Cheslack-Postava] Reorganize Copycat code to put it all under one top-level directory.
b29cb2c [Ewen Cheslack-Postava] Merge remote-tracking branch 'origin/trunk' into copycat
d713a21 [Ewen Cheslack-Postava] Address Gwen's review comments.
6787a85 [Ewen Cheslack-Postava] Make Converter generic to match serializers since some serialization formats do not require a base class of Object; update many other classes to have generic key and value class type parameters to match this change.
b194c73 [Ewen Cheslack-Postava] Split Copycat converter option into two options for key and value.
0b5a1a0 [Ewen Cheslack-Postava] Normalize naming to use partition for both source and Kafka, adjusting naming in CopycatRecord classes to clearly differentiate.
e345142 [Ewen Cheslack-Postava] Remove Copycat reflection utils, use existing Utils and ConfigDef functionality from clients package.
be5c387 [Ewen Cheslack-Postava] Minor cleanup
122423e [Ewen Cheslack-Postava] Style cleanup
6ba87de [Ewen Cheslack-Postava] Remove most of the Avro-based mock runtime data API, only preserving enough schema functionality to support basic primitive types for an initial patch.
4674d13 [Ewen Cheslack-Postava] Address review comments, clean up some code styling.
25b5739 [Ewen Cheslack-Postava] Fix sink task offset commit concurrency issue by moving it to the worker thread and waking up the consumer to ensure it exits promptly.
0aefe21 [Ewen Cheslack-Postava] Add log4j settings for Copycat.
220e42d [Ewen Cheslack-Postava] Replace Avro serializer with JSON serializer.
1243a7c [Ewen Cheslack-Postava] Merge remote-tracking branch 'origin/trunk' into copycat
5a618c6 [Ewen Cheslack-Postava] Remove offset serializers, instead reusing the existing serializers and removing schema projection support.
e849e10 [Ewen Cheslack-Postava] Remove duplicated TopicPartition implementation.
dec1379 [Ewen Cheslack-Postava] Switch to using new consumer coordinator instead of manually assigning partitions. Remove dependency of copycat-runtime on core.
4a9b4f3 [Ewen Cheslack-Postava] Add some helpful Copycat-specific build and test targets that cover all Copycat packages.
31cd1ca [Ewen Cheslack-Postava] Add CLI tools for Copycat.
e14942c [Ewen Cheslack-Postava] Add Copycat file connector.
0233456 [Ewen Cheslack-Postava] Add copycat-avro and copycat-runtime
11981d2 [Ewen Cheslack-Postava] Add copycat-data and copycat-api
9 years ago
}
javadoc {
enabled = false
KAFKA-2366; Initial patch for Copycat
This is an initial patch implementing the basics of Copycat for KIP-26.
The intent here is to start a review of the key pieces of the core API and get a reasonably functional, baseline, non-distributed implementation of Copycat in place to get things rolling. The current patch has a number of known issues that need to be addressed before a final version:
* Some build-related issues. Specifically, requires some locally-installed dependencies (see below), ignores checkstyle for the runtime data library because it's lifted from Avro currently and likely won't last in its current form, and some Gradle task dependencies aren't quite right because I haven't gotten rid of the dependency on `core` (which should now be an easy patch since new consumer groups are in a much better state).
* This patch currently depends on some Confluent trunk code because I prototyped with our Avro serializers w/ schema-registry support. We need to figure out what we want to provide as an example built-in set of serializers. Unlike core Kafka where we could ignore the issue, providing only ByteArray or String serializers, this is pretty central to how Copycat works.
* This patch uses a hacked up version of Avro as its runtime data format. Not sure if we want to go through the entire API discussion just to get some basic code committed, so I filed KAFKA-2367 to handle that separately. The core connector APIs and the runtime data APIs are entirely orthogonal.
* This patch needs some updates to get aligned with recent new consumer changes (specifically, I'm aware of the ConcurrentModificationException issue on exit). More generally, the new consumer is in flux but Copycat depends on it, so there are likely to be some negative interactions.
* The layout feels a bit awkward to me right now because I ported it from a Maven layout. We don't have nearly the same level of granularity in Kafka currently (core and clients, plus the mostly ignored examples, log4j-appender, and a couple of contribs). We might want to reorganize, although keeping data+api separate from runtime and connector plugins is useful for minimizing dependencies.
* There are a variety of other things (e.g., I'm not happy with the exception hierarchy/how they are currently handled, TopicPartition doesn't really need to be duplicated unless we want Copycat entirely isolated from the Kafka APIs, etc), but I expect those we'll cover in the review.
Before commenting on the patch, it's probably worth reviewing https://issues.apache.org/jira/browse/KAFKA-2365 and https://issues.apache.org/jira/browse/KAFKA-2366 to get an idea of what I had in mind for a) what we ultimately want with all the Copycat patches and b) what we aim to cover in this initial patch. My hope is that we can use a WIP patch (after the current obvious deficiencies are addressed) while recognizing that we want to make iterative progress with a bunch of subsequent PRs.
Author: Ewen Cheslack-Postava <me@ewencp.org>
Reviewers: Ismael Juma, Gwen Shapira
Closes #99 from ewencp/copycat and squashes the following commits:
a3a47a6 [Ewen Cheslack-Postava] Simplify Copycat exceptions, make them a subclass of KafkaException.
8c108b0 [Ewen Cheslack-Postava] Rename Coordinator to Herder to avoid confusion with the consumer coordinator.
7bf8075 [Ewen Cheslack-Postava] Make Copycat CLI speific to standalone mode, clean up some config and get rid of config storage in standalone mode.
656a003 [Ewen Cheslack-Postava] Clarify and expand the explanation of the Copycat Coordinator interface.
c0e5fdc [Ewen Cheslack-Postava] Merge remote-tracking branch 'origin/trunk' into copycat
0fa7a36 [Ewen Cheslack-Postava] Mark Copycat classes as unstable and reduce visibility of some classes where possible.
d55d31e [Ewen Cheslack-Postava] Reorganize Copycat code to put it all under one top-level directory.
b29cb2c [Ewen Cheslack-Postava] Merge remote-tracking branch 'origin/trunk' into copycat
d713a21 [Ewen Cheslack-Postava] Address Gwen's review comments.
6787a85 [Ewen Cheslack-Postava] Make Converter generic to match serializers since some serialization formats do not require a base class of Object; update many other classes to have generic key and value class type parameters to match this change.
b194c73 [Ewen Cheslack-Postava] Split Copycat converter option into two options for key and value.
0b5a1a0 [Ewen Cheslack-Postava] Normalize naming to use partition for both source and Kafka, adjusting naming in CopycatRecord classes to clearly differentiate.
e345142 [Ewen Cheslack-Postava] Remove Copycat reflection utils, use existing Utils and ConfigDef functionality from clients package.
be5c387 [Ewen Cheslack-Postava] Minor cleanup
122423e [Ewen Cheslack-Postava] Style cleanup
6ba87de [Ewen Cheslack-Postava] Remove most of the Avro-based mock runtime data API, only preserving enough schema functionality to support basic primitive types for an initial patch.
4674d13 [Ewen Cheslack-Postava] Address review comments, clean up some code styling.
25b5739 [Ewen Cheslack-Postava] Fix sink task offset commit concurrency issue by moving it to the worker thread and waking up the consumer to ensure it exits promptly.
0aefe21 [Ewen Cheslack-Postava] Add log4j settings for Copycat.
220e42d [Ewen Cheslack-Postava] Replace Avro serializer with JSON serializer.
1243a7c [Ewen Cheslack-Postava] Merge remote-tracking branch 'origin/trunk' into copycat
5a618c6 [Ewen Cheslack-Postava] Remove offset serializers, instead reusing the existing serializers and removing schema projection support.
e849e10 [Ewen Cheslack-Postava] Remove duplicated TopicPartition implementation.
dec1379 [Ewen Cheslack-Postava] Switch to using new consumer coordinator instead of manually assigning partitions. Remove dependency of copycat-runtime on core.
4a9b4f3 [Ewen Cheslack-Postava] Add some helpful Copycat-specific build and test targets that cover all Copycat packages.
31cd1ca [Ewen Cheslack-Postava] Add CLI tools for Copycat.
e14942c [Ewen Cheslack-Postava] Add Copycat file connector.
0233456 [Ewen Cheslack-Postava] Add copycat-avro and copycat-runtime
11981d2 [Ewen Cheslack-Postava] Add copycat-data and copycat-api
9 years ago
}
tasks . create ( name: "copyDependantLibs" , type: Copy ) {
from ( configurations . testRuntimeClasspath ) {
// No need to copy log4j since the module has an explicit dependency on that
include ( 'slf4j-log4j12*' )
}
from ( configurations . runtimeClasspath ) {
exclude ( 'kafka-clients*' )
exclude ( 'connect-*' )
}
into "$buildDir/dependant-libs"
duplicatesStrategy 'exclude'
}
jar {
dependsOn copyDependantLibs
}
task genConnectConfigDocs ( type: JavaExec ) {
classpath = sourceSets . main . runtimeClasspath
mainClass = 'org.apache.kafka.connect.runtime.distributed.DistributedConfig'
if ( ! generatedDocsDir . exists ( ) ) { generatedDocsDir . mkdirs ( ) }
standardOutput = new File ( generatedDocsDir , "connect_config.html" ) . newOutputStream ( )
}
task genSinkConnectorConfigDocs ( type: JavaExec ) {
classpath = sourceSets . main . runtimeClasspath
mainClass = 'org.apache.kafka.connect.runtime.SinkConnectorConfig'
if ( ! generatedDocsDir . exists ( ) ) { generatedDocsDir . mkdirs ( ) }
standardOutput = new File ( generatedDocsDir , "sink_connector_config.html" ) . newOutputStream ( )
}
task genSourceConnectorConfigDocs ( type: JavaExec ) {
classpath = sourceSets . main . runtimeClasspath
mainClass = 'org.apache.kafka.connect.runtime.SourceConnectorConfig'
if ( ! generatedDocsDir . exists ( ) ) { generatedDocsDir . mkdirs ( ) }
standardOutput = new File ( generatedDocsDir , "source_connector_config.html" ) . newOutputStream ( )
}
task genConnectTransformationDocs ( type: JavaExec ) {
classpath = sourceSets . main . runtimeClasspath
mainClass = 'org.apache.kafka.connect.tools.TransformationDoc'
if ( ! generatedDocsDir . exists ( ) ) { generatedDocsDir . mkdirs ( ) }
standardOutput = new File ( generatedDocsDir , "connect_transforms.html" ) . newOutputStream ( )
}
task genConnectPredicateDocs ( type: JavaExec ) {
classpath = sourceSets . main . runtimeClasspath
mainClass = 'org.apache.kafka.connect.tools.PredicateDoc'
if ( ! generatedDocsDir . exists ( ) ) { generatedDocsDir . mkdirs ( ) }
standardOutput = new File ( generatedDocsDir , "connect_predicates.html" ) . newOutputStream ( )
}
task genConnectMetricsDocs ( type: JavaExec ) {
classpath = sourceSets . test . runtimeClasspath
mainClass = 'org.apache.kafka.connect.runtime.ConnectMetrics'
if ( ! generatedDocsDir . exists ( ) ) { generatedDocsDir . mkdirs ( ) }
standardOutput = new File ( generatedDocsDir , "connect_metrics.html" ) . newOutputStream ( )
}
task setVersionInOpenAPISpec ( type: Copy ) {
from "$rootDir/gradle/openapi.template"
into "$buildDir/resources/docs"
rename ( 'openapi.template' , 'openapi.yaml' )
expand ( kafkaVersion: "$rootProject.version" )
}
task genConnectOpenAPIDocs ( type: io . swagger . v3 . plugins . gradle . tasks . ResolveTask , dependsOn: setVersionInOpenAPISpec ) {
classpath = sourceSets . main . runtimeClasspath
buildClasspath = classpath + configurations . swagger . asCollection ( )
outputFileName = 'connect_rest'
outputFormat = 'YAML'
prettyPrint = 'TRUE'
sortOutput = 'TRUE'
openApiFile = file ( "$buildDir/resources/docs/openapi.yaml" )
resourcePackages = [ 'org.apache.kafka.connect.runtime.rest.resources' ]
if ( ! generatedDocsDir . exists ( ) ) { generatedDocsDir . mkdirs ( ) }
outputDir = file ( generatedDocsDir )
}
KAFKA-2366; Initial patch for Copycat
This is an initial patch implementing the basics of Copycat for KIP-26.
The intent here is to start a review of the key pieces of the core API and get a reasonably functional, baseline, non-distributed implementation of Copycat in place to get things rolling. The current patch has a number of known issues that need to be addressed before a final version:
* Some build-related issues. Specifically, requires some locally-installed dependencies (see below), ignores checkstyle for the runtime data library because it's lifted from Avro currently and likely won't last in its current form, and some Gradle task dependencies aren't quite right because I haven't gotten rid of the dependency on `core` (which should now be an easy patch since new consumer groups are in a much better state).
* This patch currently depends on some Confluent trunk code because I prototyped with our Avro serializers w/ schema-registry support. We need to figure out what we want to provide as an example built-in set of serializers. Unlike core Kafka where we could ignore the issue, providing only ByteArray or String serializers, this is pretty central to how Copycat works.
* This patch uses a hacked up version of Avro as its runtime data format. Not sure if we want to go through the entire API discussion just to get some basic code committed, so I filed KAFKA-2367 to handle that separately. The core connector APIs and the runtime data APIs are entirely orthogonal.
* This patch needs some updates to get aligned with recent new consumer changes (specifically, I'm aware of the ConcurrentModificationException issue on exit). More generally, the new consumer is in flux but Copycat depends on it, so there are likely to be some negative interactions.
* The layout feels a bit awkward to me right now because I ported it from a Maven layout. We don't have nearly the same level of granularity in Kafka currently (core and clients, plus the mostly ignored examples, log4j-appender, and a couple of contribs). We might want to reorganize, although keeping data+api separate from runtime and connector plugins is useful for minimizing dependencies.
* There are a variety of other things (e.g., I'm not happy with the exception hierarchy/how they are currently handled, TopicPartition doesn't really need to be duplicated unless we want Copycat entirely isolated from the Kafka APIs, etc), but I expect those we'll cover in the review.
Before commenting on the patch, it's probably worth reviewing https://issues.apache.org/jira/browse/KAFKA-2365 and https://issues.apache.org/jira/browse/KAFKA-2366 to get an idea of what I had in mind for a) what we ultimately want with all the Copycat patches and b) what we aim to cover in this initial patch. My hope is that we can use a WIP patch (after the current obvious deficiencies are addressed) while recognizing that we want to make iterative progress with a bunch of subsequent PRs.
Author: Ewen Cheslack-Postava <me@ewencp.org>
Reviewers: Ismael Juma, Gwen Shapira
Closes #99 from ewencp/copycat and squashes the following commits:
a3a47a6 [Ewen Cheslack-Postava] Simplify Copycat exceptions, make them a subclass of KafkaException.
8c108b0 [Ewen Cheslack-Postava] Rename Coordinator to Herder to avoid confusion with the consumer coordinator.
7bf8075 [Ewen Cheslack-Postava] Make Copycat CLI speific to standalone mode, clean up some config and get rid of config storage in standalone mode.
656a003 [Ewen Cheslack-Postava] Clarify and expand the explanation of the Copycat Coordinator interface.
c0e5fdc [Ewen Cheslack-Postava] Merge remote-tracking branch 'origin/trunk' into copycat
0fa7a36 [Ewen Cheslack-Postava] Mark Copycat classes as unstable and reduce visibility of some classes where possible.
d55d31e [Ewen Cheslack-Postava] Reorganize Copycat code to put it all under one top-level directory.
b29cb2c [Ewen Cheslack-Postava] Merge remote-tracking branch 'origin/trunk' into copycat
d713a21 [Ewen Cheslack-Postava] Address Gwen's review comments.
6787a85 [Ewen Cheslack-Postava] Make Converter generic to match serializers since some serialization formats do not require a base class of Object; update many other classes to have generic key and value class type parameters to match this change.
b194c73 [Ewen Cheslack-Postava] Split Copycat converter option into two options for key and value.
0b5a1a0 [Ewen Cheslack-Postava] Normalize naming to use partition for both source and Kafka, adjusting naming in CopycatRecord classes to clearly differentiate.
e345142 [Ewen Cheslack-Postava] Remove Copycat reflection utils, use existing Utils and ConfigDef functionality from clients package.
be5c387 [Ewen Cheslack-Postava] Minor cleanup
122423e [Ewen Cheslack-Postava] Style cleanup
6ba87de [Ewen Cheslack-Postava] Remove most of the Avro-based mock runtime data API, only preserving enough schema functionality to support basic primitive types for an initial patch.
4674d13 [Ewen Cheslack-Postava] Address review comments, clean up some code styling.
25b5739 [Ewen Cheslack-Postava] Fix sink task offset commit concurrency issue by moving it to the worker thread and waking up the consumer to ensure it exits promptly.
0aefe21 [Ewen Cheslack-Postava] Add log4j settings for Copycat.
220e42d [Ewen Cheslack-Postava] Replace Avro serializer with JSON serializer.
1243a7c [Ewen Cheslack-Postava] Merge remote-tracking branch 'origin/trunk' into copycat
5a618c6 [Ewen Cheslack-Postava] Remove offset serializers, instead reusing the existing serializers and removing schema projection support.
e849e10 [Ewen Cheslack-Postava] Remove duplicated TopicPartition implementation.
dec1379 [Ewen Cheslack-Postava] Switch to using new consumer coordinator instead of manually assigning partitions. Remove dependency of copycat-runtime on core.
4a9b4f3 [Ewen Cheslack-Postava] Add some helpful Copycat-specific build and test targets that cover all Copycat packages.
31cd1ca [Ewen Cheslack-Postava] Add CLI tools for Copycat.
e14942c [Ewen Cheslack-Postava] Add Copycat file connector.
0233456 [Ewen Cheslack-Postava] Add copycat-avro and copycat-runtime
11981d2 [Ewen Cheslack-Postava] Add copycat-data and copycat-api
9 years ago
}
project ( ':connect:file' ) {
archivesBaseName = "connect-file"
KAFKA-2366; Initial patch for Copycat
This is an initial patch implementing the basics of Copycat for KIP-26.
The intent here is to start a review of the key pieces of the core API and get a reasonably functional, baseline, non-distributed implementation of Copycat in place to get things rolling. The current patch has a number of known issues that need to be addressed before a final version:
* Some build-related issues. Specifically, requires some locally-installed dependencies (see below), ignores checkstyle for the runtime data library because it's lifted from Avro currently and likely won't last in its current form, and some Gradle task dependencies aren't quite right because I haven't gotten rid of the dependency on `core` (which should now be an easy patch since new consumer groups are in a much better state).
* This patch currently depends on some Confluent trunk code because I prototyped with our Avro serializers w/ schema-registry support. We need to figure out what we want to provide as an example built-in set of serializers. Unlike core Kafka where we could ignore the issue, providing only ByteArray or String serializers, this is pretty central to how Copycat works.
* This patch uses a hacked up version of Avro as its runtime data format. Not sure if we want to go through the entire API discussion just to get some basic code committed, so I filed KAFKA-2367 to handle that separately. The core connector APIs and the runtime data APIs are entirely orthogonal.
* This patch needs some updates to get aligned with recent new consumer changes (specifically, I'm aware of the ConcurrentModificationException issue on exit). More generally, the new consumer is in flux but Copycat depends on it, so there are likely to be some negative interactions.
* The layout feels a bit awkward to me right now because I ported it from a Maven layout. We don't have nearly the same level of granularity in Kafka currently (core and clients, plus the mostly ignored examples, log4j-appender, and a couple of contribs). We might want to reorganize, although keeping data+api separate from runtime and connector plugins is useful for minimizing dependencies.
* There are a variety of other things (e.g., I'm not happy with the exception hierarchy/how they are currently handled, TopicPartition doesn't really need to be duplicated unless we want Copycat entirely isolated from the Kafka APIs, etc), but I expect those we'll cover in the review.
Before commenting on the patch, it's probably worth reviewing https://issues.apache.org/jira/browse/KAFKA-2365 and https://issues.apache.org/jira/browse/KAFKA-2366 to get an idea of what I had in mind for a) what we ultimately want with all the Copycat patches and b) what we aim to cover in this initial patch. My hope is that we can use a WIP patch (after the current obvious deficiencies are addressed) while recognizing that we want to make iterative progress with a bunch of subsequent PRs.
Author: Ewen Cheslack-Postava <me@ewencp.org>
Reviewers: Ismael Juma, Gwen Shapira
Closes #99 from ewencp/copycat and squashes the following commits:
a3a47a6 [Ewen Cheslack-Postava] Simplify Copycat exceptions, make them a subclass of KafkaException.
8c108b0 [Ewen Cheslack-Postava] Rename Coordinator to Herder to avoid confusion with the consumer coordinator.
7bf8075 [Ewen Cheslack-Postava] Make Copycat CLI speific to standalone mode, clean up some config and get rid of config storage in standalone mode.
656a003 [Ewen Cheslack-Postava] Clarify and expand the explanation of the Copycat Coordinator interface.
c0e5fdc [Ewen Cheslack-Postava] Merge remote-tracking branch 'origin/trunk' into copycat
0fa7a36 [Ewen Cheslack-Postava] Mark Copycat classes as unstable and reduce visibility of some classes where possible.
d55d31e [Ewen Cheslack-Postava] Reorganize Copycat code to put it all under one top-level directory.
b29cb2c [Ewen Cheslack-Postava] Merge remote-tracking branch 'origin/trunk' into copycat
d713a21 [Ewen Cheslack-Postava] Address Gwen's review comments.
6787a85 [Ewen Cheslack-Postava] Make Converter generic to match serializers since some serialization formats do not require a base class of Object; update many other classes to have generic key and value class type parameters to match this change.
b194c73 [Ewen Cheslack-Postava] Split Copycat converter option into two options for key and value.
0b5a1a0 [Ewen Cheslack-Postava] Normalize naming to use partition for both source and Kafka, adjusting naming in CopycatRecord classes to clearly differentiate.
e345142 [Ewen Cheslack-Postava] Remove Copycat reflection utils, use existing Utils and ConfigDef functionality from clients package.
be5c387 [Ewen Cheslack-Postava] Minor cleanup
122423e [Ewen Cheslack-Postava] Style cleanup
6ba87de [Ewen Cheslack-Postava] Remove most of the Avro-based mock runtime data API, only preserving enough schema functionality to support basic primitive types for an initial patch.
4674d13 [Ewen Cheslack-Postava] Address review comments, clean up some code styling.
25b5739 [Ewen Cheslack-Postava] Fix sink task offset commit concurrency issue by moving it to the worker thread and waking up the consumer to ensure it exits promptly.
0aefe21 [Ewen Cheslack-Postava] Add log4j settings for Copycat.
220e42d [Ewen Cheslack-Postava] Replace Avro serializer with JSON serializer.
1243a7c [Ewen Cheslack-Postava] Merge remote-tracking branch 'origin/trunk' into copycat
5a618c6 [Ewen Cheslack-Postava] Remove offset serializers, instead reusing the existing serializers and removing schema projection support.
e849e10 [Ewen Cheslack-Postava] Remove duplicated TopicPartition implementation.
dec1379 [Ewen Cheslack-Postava] Switch to using new consumer coordinator instead of manually assigning partitions. Remove dependency of copycat-runtime on core.
4a9b4f3 [Ewen Cheslack-Postava] Add some helpful Copycat-specific build and test targets that cover all Copycat packages.
31cd1ca [Ewen Cheslack-Postava] Add CLI tools for Copycat.
e14942c [Ewen Cheslack-Postava] Add Copycat file connector.
0233456 [Ewen Cheslack-Postava] Add copycat-avro and copycat-runtime
11981d2 [Ewen Cheslack-Postava] Add copycat-data and copycat-api
9 years ago
dependencies {
implementation project ( ':connect:api' )
implementation libs . slf4jApi
testImplementation libs . junitJupiter
testImplementation libs . mockitoCore
testRuntimeOnly libs . slf4jlog4j
testImplementation project ( ':clients' ) . sourceSets . test . output
}
javadoc {
enabled = false
}
tasks . create ( name: "copyDependantLibs" , type: Copy ) {
from ( configurations . testRuntimeClasspath ) {
include ( 'slf4j-log4j12*' )
include ( 'reload4j*jar' )
}
from ( configurations . runtimeClasspath ) {
exclude ( 'kafka-clients*' )
exclude ( 'connect-*' )
}
into "$buildDir/dependant-libs"
duplicatesStrategy 'exclude'
}
jar {
dependsOn copyDependantLibs
}
}
project ( ':connect:basic-auth-extension' ) {
archivesBaseName = "connect-basic-auth-extension"
dependencies {
implementation project ( ':connect:api' )
implementation libs . slf4jApi
implementation libs . jaxrsApi
implementation libs . jaxAnnotationApi
testImplementation libs . bcpkix
testImplementation libs . mockitoCore
testImplementation libs . junitJupiter
testImplementation project ( ':clients' ) . sourceSets . test . output
testRuntimeOnly libs . slf4jlog4j
testRuntimeOnly libs . jerseyContainerServlet
}
javadoc {
enabled = false
}
KAFKA-7500: MirrorMaker 2.0 (KIP-382)
Implementation of [KIP-382 "MirrorMaker 2.0"](https://cwiki.apache.org/confluence/display/KAFKA/KIP-382%3A+MirrorMaker+2.0)
Author: Ryanne Dolan <ryannedolan@gmail.com>
Author: Arun Mathew <arunmathew88@gmail.com>
Author: In Park <inpark@cloudera.com>
Author: Andre Price <obsoleted@users.noreply.github.com>
Author: christian.hagel@rio.cloud <christian.hagel@rio.cloud>
Reviewers: Eno Thereska <eno.thereska@gmail.com>, William Hammond <william.t.hammond@gmail.com>, Viktor Somogyi <viktorsomogyi@gmail.com>, Jakub Korzeniowski, Tim Carey-Smith, Kamal Chandraprakash <kamal.chandraprakash@gmail.com>, Arun Mathew, Jeremy-l-ford, vpernin, Oleg Kasian <oleg.kasian@gmail.com>, Mickael Maison <mickael.maison@gmail.com>, Qihong Chen, Sriharsha Chintalapani <sriharsha@apache.org>, Jun Rao <junrao@gmail.com>, Randall Hauch <rhauch@gmail.com>, Manikumar Reddy <manikumar.reddy@gmail.com>, Ismael Juma <ismael@juma.me.uk>
Closes #6295 from ryannedolan/KIP-382
5 years ago
tasks . create ( name: "copyDependantLibs" , type: Copy ) {
from ( configurations . testRuntimeClasspath ) {
KAFKA-7500: MirrorMaker 2.0 (KIP-382)
Implementation of [KIP-382 "MirrorMaker 2.0"](https://cwiki.apache.org/confluence/display/KAFKA/KIP-382%3A+MirrorMaker+2.0)
Author: Ryanne Dolan <ryannedolan@gmail.com>
Author: Arun Mathew <arunmathew88@gmail.com>
Author: In Park <inpark@cloudera.com>
Author: Andre Price <obsoleted@users.noreply.github.com>
Author: christian.hagel@rio.cloud <christian.hagel@rio.cloud>
Reviewers: Eno Thereska <eno.thereska@gmail.com>, William Hammond <william.t.hammond@gmail.com>, Viktor Somogyi <viktorsomogyi@gmail.com>, Jakub Korzeniowski, Tim Carey-Smith, Kamal Chandraprakash <kamal.chandraprakash@gmail.com>, Arun Mathew, Jeremy-l-ford, vpernin, Oleg Kasian <oleg.kasian@gmail.com>, Mickael Maison <mickael.maison@gmail.com>, Qihong Chen, Sriharsha Chintalapani <sriharsha@apache.org>, Jun Rao <junrao@gmail.com>, Randall Hauch <rhauch@gmail.com>, Manikumar Reddy <manikumar.reddy@gmail.com>, Ismael Juma <ismael@juma.me.uk>
Closes #6295 from ryannedolan/KIP-382
5 years ago
include ( 'slf4j-log4j12*' )
include ( 'reload4j*jar' )
KAFKA-7500: MirrorMaker 2.0 (KIP-382)
Implementation of [KIP-382 "MirrorMaker 2.0"](https://cwiki.apache.org/confluence/display/KAFKA/KIP-382%3A+MirrorMaker+2.0)
Author: Ryanne Dolan <ryannedolan@gmail.com>
Author: Arun Mathew <arunmathew88@gmail.com>
Author: In Park <inpark@cloudera.com>
Author: Andre Price <obsoleted@users.noreply.github.com>
Author: christian.hagel@rio.cloud <christian.hagel@rio.cloud>
Reviewers: Eno Thereska <eno.thereska@gmail.com>, William Hammond <william.t.hammond@gmail.com>, Viktor Somogyi <viktorsomogyi@gmail.com>, Jakub Korzeniowski, Tim Carey-Smith, Kamal Chandraprakash <kamal.chandraprakash@gmail.com>, Arun Mathew, Jeremy-l-ford, vpernin, Oleg Kasian <oleg.kasian@gmail.com>, Mickael Maison <mickael.maison@gmail.com>, Qihong Chen, Sriharsha Chintalapani <sriharsha@apache.org>, Jun Rao <junrao@gmail.com>, Randall Hauch <rhauch@gmail.com>, Manikumar Reddy <manikumar.reddy@gmail.com>, Ismael Juma <ismael@juma.me.uk>
Closes #6295 from ryannedolan/KIP-382
5 years ago
}
from ( configurations . runtimeClasspath ) {
KAFKA-7500: MirrorMaker 2.0 (KIP-382)
Implementation of [KIP-382 "MirrorMaker 2.0"](https://cwiki.apache.org/confluence/display/KAFKA/KIP-382%3A+MirrorMaker+2.0)
Author: Ryanne Dolan <ryannedolan@gmail.com>
Author: Arun Mathew <arunmathew88@gmail.com>
Author: In Park <inpark@cloudera.com>
Author: Andre Price <obsoleted@users.noreply.github.com>
Author: christian.hagel@rio.cloud <christian.hagel@rio.cloud>
Reviewers: Eno Thereska <eno.thereska@gmail.com>, William Hammond <william.t.hammond@gmail.com>, Viktor Somogyi <viktorsomogyi@gmail.com>, Jakub Korzeniowski, Tim Carey-Smith, Kamal Chandraprakash <kamal.chandraprakash@gmail.com>, Arun Mathew, Jeremy-l-ford, vpernin, Oleg Kasian <oleg.kasian@gmail.com>, Mickael Maison <mickael.maison@gmail.com>, Qihong Chen, Sriharsha Chintalapani <sriharsha@apache.org>, Jun Rao <junrao@gmail.com>, Randall Hauch <rhauch@gmail.com>, Manikumar Reddy <manikumar.reddy@gmail.com>, Ismael Juma <ismael@juma.me.uk>
Closes #6295 from ryannedolan/KIP-382
5 years ago
exclude ( 'kafka-clients*' )
exclude ( 'connect-*' )
}
into "$buildDir/dependant-libs"
duplicatesStrategy 'exclude'
}
jar {
dependsOn copyDependantLibs
}
}
project ( ':connect:mirror' ) {
archivesBaseName = "connect-mirror"
dependencies {
implementation project ( ':connect:api' )
implementation project ( ':connect:runtime' )
implementation project ( ':connect:mirror-client' )
implementation project ( ':clients' )
KAFKA-7500: MirrorMaker 2.0 (KIP-382)
Implementation of [KIP-382 "MirrorMaker 2.0"](https://cwiki.apache.org/confluence/display/KAFKA/KIP-382%3A+MirrorMaker+2.0)
Author: Ryanne Dolan <ryannedolan@gmail.com>
Author: Arun Mathew <arunmathew88@gmail.com>
Author: In Park <inpark@cloudera.com>
Author: Andre Price <obsoleted@users.noreply.github.com>
Author: christian.hagel@rio.cloud <christian.hagel@rio.cloud>
Reviewers: Eno Thereska <eno.thereska@gmail.com>, William Hammond <william.t.hammond@gmail.com>, Viktor Somogyi <viktorsomogyi@gmail.com>, Jakub Korzeniowski, Tim Carey-Smith, Kamal Chandraprakash <kamal.chandraprakash@gmail.com>, Arun Mathew, Jeremy-l-ford, vpernin, Oleg Kasian <oleg.kasian@gmail.com>, Mickael Maison <mickael.maison@gmail.com>, Qihong Chen, Sriharsha Chintalapani <sriharsha@apache.org>, Jun Rao <junrao@gmail.com>, Randall Hauch <rhauch@gmail.com>, Manikumar Reddy <manikumar.reddy@gmail.com>, Ismael Juma <ismael@juma.me.uk>
Closes #6295 from ryannedolan/KIP-382
5 years ago
implementation libs . argparse4j
implementation libs . jacksonAnnotations
implementation libs . slf4jApi
KAFKA-7500: MirrorMaker 2.0 (KIP-382)
Implementation of [KIP-382 "MirrorMaker 2.0"](https://cwiki.apache.org/confluence/display/KAFKA/KIP-382%3A+MirrorMaker+2.0)
Author: Ryanne Dolan <ryannedolan@gmail.com>
Author: Arun Mathew <arunmathew88@gmail.com>
Author: In Park <inpark@cloudera.com>
Author: Andre Price <obsoleted@users.noreply.github.com>
Author: christian.hagel@rio.cloud <christian.hagel@rio.cloud>
Reviewers: Eno Thereska <eno.thereska@gmail.com>, William Hammond <william.t.hammond@gmail.com>, Viktor Somogyi <viktorsomogyi@gmail.com>, Jakub Korzeniowski, Tim Carey-Smith, Kamal Chandraprakash <kamal.chandraprakash@gmail.com>, Arun Mathew, Jeremy-l-ford, vpernin, Oleg Kasian <oleg.kasian@gmail.com>, Mickael Maison <mickael.maison@gmail.com>, Qihong Chen, Sriharsha Chintalapani <sriharsha@apache.org>, Jun Rao <junrao@gmail.com>, Randall Hauch <rhauch@gmail.com>, Manikumar Reddy <manikumar.reddy@gmail.com>, Ismael Juma <ismael@juma.me.uk>
Closes #6295 from ryannedolan/KIP-382
5 years ago
testImplementation libs . junitJupiter
testImplementation libs . mockitoCore
testImplementation project ( ':clients' ) . sourceSets . test . output
testImplementation project ( ':connect:runtime' ) . sourceSets . test . output
testImplementation project ( ':core' )
testImplementation project ( ':core' ) . sourceSets . test . output
testRuntimeOnly project ( ':connect:runtime' )
testRuntimeOnly libs . slf4jlog4j
testRuntimeOnly libs . bcpkix
KAFKA-7500: MirrorMaker 2.0 (KIP-382)
Implementation of [KIP-382 "MirrorMaker 2.0"](https://cwiki.apache.org/confluence/display/KAFKA/KIP-382%3A+MirrorMaker+2.0)
Author: Ryanne Dolan <ryannedolan@gmail.com>
Author: Arun Mathew <arunmathew88@gmail.com>
Author: In Park <inpark@cloudera.com>
Author: Andre Price <obsoleted@users.noreply.github.com>
Author: christian.hagel@rio.cloud <christian.hagel@rio.cloud>
Reviewers: Eno Thereska <eno.thereska@gmail.com>, William Hammond <william.t.hammond@gmail.com>, Viktor Somogyi <viktorsomogyi@gmail.com>, Jakub Korzeniowski, Tim Carey-Smith, Kamal Chandraprakash <kamal.chandraprakash@gmail.com>, Arun Mathew, Jeremy-l-ford, vpernin, Oleg Kasian <oleg.kasian@gmail.com>, Mickael Maison <mickael.maison@gmail.com>, Qihong Chen, Sriharsha Chintalapani <sriharsha@apache.org>, Jun Rao <junrao@gmail.com>, Randall Hauch <rhauch@gmail.com>, Manikumar Reddy <manikumar.reddy@gmail.com>, Ismael Juma <ismael@juma.me.uk>
Closes #6295 from ryannedolan/KIP-382
5 years ago
}
javadoc {
enabled = false
}
tasks . create ( name: "copyDependantLibs" , type: Copy ) {
from ( configurations . testRuntimeClasspath ) {
KAFKA-7500: MirrorMaker 2.0 (KIP-382)
Implementation of [KIP-382 "MirrorMaker 2.0"](https://cwiki.apache.org/confluence/display/KAFKA/KIP-382%3A+MirrorMaker+2.0)
Author: Ryanne Dolan <ryannedolan@gmail.com>
Author: Arun Mathew <arunmathew88@gmail.com>
Author: In Park <inpark@cloudera.com>
Author: Andre Price <obsoleted@users.noreply.github.com>
Author: christian.hagel@rio.cloud <christian.hagel@rio.cloud>
Reviewers: Eno Thereska <eno.thereska@gmail.com>, William Hammond <william.t.hammond@gmail.com>, Viktor Somogyi <viktorsomogyi@gmail.com>, Jakub Korzeniowski, Tim Carey-Smith, Kamal Chandraprakash <kamal.chandraprakash@gmail.com>, Arun Mathew, Jeremy-l-ford, vpernin, Oleg Kasian <oleg.kasian@gmail.com>, Mickael Maison <mickael.maison@gmail.com>, Qihong Chen, Sriharsha Chintalapani <sriharsha@apache.org>, Jun Rao <junrao@gmail.com>, Randall Hauch <rhauch@gmail.com>, Manikumar Reddy <manikumar.reddy@gmail.com>, Ismael Juma <ismael@juma.me.uk>
Closes #6295 from ryannedolan/KIP-382
5 years ago
include ( 'slf4j-log4j12*' )
include ( 'reload4j*jar' )
KAFKA-7500: MirrorMaker 2.0 (KIP-382)
Implementation of [KIP-382 "MirrorMaker 2.0"](https://cwiki.apache.org/confluence/display/KAFKA/KIP-382%3A+MirrorMaker+2.0)
Author: Ryanne Dolan <ryannedolan@gmail.com>
Author: Arun Mathew <arunmathew88@gmail.com>
Author: In Park <inpark@cloudera.com>
Author: Andre Price <obsoleted@users.noreply.github.com>
Author: christian.hagel@rio.cloud <christian.hagel@rio.cloud>
Reviewers: Eno Thereska <eno.thereska@gmail.com>, William Hammond <william.t.hammond@gmail.com>, Viktor Somogyi <viktorsomogyi@gmail.com>, Jakub Korzeniowski, Tim Carey-Smith, Kamal Chandraprakash <kamal.chandraprakash@gmail.com>, Arun Mathew, Jeremy-l-ford, vpernin, Oleg Kasian <oleg.kasian@gmail.com>, Mickael Maison <mickael.maison@gmail.com>, Qihong Chen, Sriharsha Chintalapani <sriharsha@apache.org>, Jun Rao <junrao@gmail.com>, Randall Hauch <rhauch@gmail.com>, Manikumar Reddy <manikumar.reddy@gmail.com>, Ismael Juma <ismael@juma.me.uk>
Closes #6295 from ryannedolan/KIP-382
5 years ago
}
from ( configurations . runtimeClasspath ) {
KAFKA-7500: MirrorMaker 2.0 (KIP-382)
Implementation of [KIP-382 "MirrorMaker 2.0"](https://cwiki.apache.org/confluence/display/KAFKA/KIP-382%3A+MirrorMaker+2.0)
Author: Ryanne Dolan <ryannedolan@gmail.com>
Author: Arun Mathew <arunmathew88@gmail.com>
Author: In Park <inpark@cloudera.com>
Author: Andre Price <obsoleted@users.noreply.github.com>
Author: christian.hagel@rio.cloud <christian.hagel@rio.cloud>
Reviewers: Eno Thereska <eno.thereska@gmail.com>, William Hammond <william.t.hammond@gmail.com>, Viktor Somogyi <viktorsomogyi@gmail.com>, Jakub Korzeniowski, Tim Carey-Smith, Kamal Chandraprakash <kamal.chandraprakash@gmail.com>, Arun Mathew, Jeremy-l-ford, vpernin, Oleg Kasian <oleg.kasian@gmail.com>, Mickael Maison <mickael.maison@gmail.com>, Qihong Chen, Sriharsha Chintalapani <sriharsha@apache.org>, Jun Rao <junrao@gmail.com>, Randall Hauch <rhauch@gmail.com>, Manikumar Reddy <manikumar.reddy@gmail.com>, Ismael Juma <ismael@juma.me.uk>
Closes #6295 from ryannedolan/KIP-382
5 years ago
exclude ( 'kafka-clients*' )
exclude ( 'connect-*' )
}
into "$buildDir/dependant-libs"
duplicatesStrategy 'exclude'
}
task genMirrorSourceConfigDocs ( type: JavaExec ) {
classpath = sourceSets . main . runtimeClasspath
mainClass = 'org.apache.kafka.connect.mirror.MirrorSourceConfig'
if ( ! generatedDocsDir . exists ( ) ) { generatedDocsDir . mkdirs ( ) }
standardOutput = new File ( generatedDocsDir , "mirror_source_config.html" ) . newOutputStream ( )
}
task genMirrorCheckpointConfigDocs ( type: JavaExec ) {
classpath = sourceSets . main . runtimeClasspath
mainClass = 'org.apache.kafka.connect.mirror.MirrorCheckpointConfig'
if ( ! generatedDocsDir . exists ( ) ) { generatedDocsDir . mkdirs ( ) }
standardOutput = new File ( generatedDocsDir , "mirror_checkpoint_config.html" ) . newOutputStream ( )
}
task genMirrorHeartbeatConfigDocs ( type: JavaExec ) {
classpath = sourceSets . main . runtimeClasspath
mainClass = 'org.apache.kafka.connect.mirror.MirrorHeartbeatConfig'
if ( ! generatedDocsDir . exists ( ) ) { generatedDocsDir . mkdirs ( ) }
standardOutput = new File ( generatedDocsDir , "mirror_heartbeat_config.html" ) . newOutputStream ( )
}
KAFKA-7500: MirrorMaker 2.0 (KIP-382)
Implementation of [KIP-382 "MirrorMaker 2.0"](https://cwiki.apache.org/confluence/display/KAFKA/KIP-382%3A+MirrorMaker+2.0)
Author: Ryanne Dolan <ryannedolan@gmail.com>
Author: Arun Mathew <arunmathew88@gmail.com>
Author: In Park <inpark@cloudera.com>
Author: Andre Price <obsoleted@users.noreply.github.com>
Author: christian.hagel@rio.cloud <christian.hagel@rio.cloud>
Reviewers: Eno Thereska <eno.thereska@gmail.com>, William Hammond <william.t.hammond@gmail.com>, Viktor Somogyi <viktorsomogyi@gmail.com>, Jakub Korzeniowski, Tim Carey-Smith, Kamal Chandraprakash <kamal.chandraprakash@gmail.com>, Arun Mathew, Jeremy-l-ford, vpernin, Oleg Kasian <oleg.kasian@gmail.com>, Mickael Maison <mickael.maison@gmail.com>, Qihong Chen, Sriharsha Chintalapani <sriharsha@apache.org>, Jun Rao <junrao@gmail.com>, Randall Hauch <rhauch@gmail.com>, Manikumar Reddy <manikumar.reddy@gmail.com>, Ismael Juma <ismael@juma.me.uk>
Closes #6295 from ryannedolan/KIP-382
5 years ago
jar {
dependsOn copyDependantLibs
}
}
project ( ':connect:mirror-client' ) {
archivesBaseName = "connect-mirror-client"
dependencies {
implementation project ( ':clients' )
implementation libs . slf4jApi
KAFKA-7500: MirrorMaker 2.0 (KIP-382)
Implementation of [KIP-382 "MirrorMaker 2.0"](https://cwiki.apache.org/confluence/display/KAFKA/KIP-382%3A+MirrorMaker+2.0)
Author: Ryanne Dolan <ryannedolan@gmail.com>
Author: Arun Mathew <arunmathew88@gmail.com>
Author: In Park <inpark@cloudera.com>
Author: Andre Price <obsoleted@users.noreply.github.com>
Author: christian.hagel@rio.cloud <christian.hagel@rio.cloud>
Reviewers: Eno Thereska <eno.thereska@gmail.com>, William Hammond <william.t.hammond@gmail.com>, Viktor Somogyi <viktorsomogyi@gmail.com>, Jakub Korzeniowski, Tim Carey-Smith, Kamal Chandraprakash <kamal.chandraprakash@gmail.com>, Arun Mathew, Jeremy-l-ford, vpernin, Oleg Kasian <oleg.kasian@gmail.com>, Mickael Maison <mickael.maison@gmail.com>, Qihong Chen, Sriharsha Chintalapani <sriharsha@apache.org>, Jun Rao <junrao@gmail.com>, Randall Hauch <rhauch@gmail.com>, Manikumar Reddy <manikumar.reddy@gmail.com>, Ismael Juma <ismael@juma.me.uk>
Closes #6295 from ryannedolan/KIP-382
5 years ago
testImplementation libs . junitJupiter
testImplementation project ( ':clients' ) . sourceSets . test . output
KAFKA-7500: MirrorMaker 2.0 (KIP-382)
Implementation of [KIP-382 "MirrorMaker 2.0"](https://cwiki.apache.org/confluence/display/KAFKA/KIP-382%3A+MirrorMaker+2.0)
Author: Ryanne Dolan <ryannedolan@gmail.com>
Author: Arun Mathew <arunmathew88@gmail.com>
Author: In Park <inpark@cloudera.com>
Author: Andre Price <obsoleted@users.noreply.github.com>
Author: christian.hagel@rio.cloud <christian.hagel@rio.cloud>
Reviewers: Eno Thereska <eno.thereska@gmail.com>, William Hammond <william.t.hammond@gmail.com>, Viktor Somogyi <viktorsomogyi@gmail.com>, Jakub Korzeniowski, Tim Carey-Smith, Kamal Chandraprakash <kamal.chandraprakash@gmail.com>, Arun Mathew, Jeremy-l-ford, vpernin, Oleg Kasian <oleg.kasian@gmail.com>, Mickael Maison <mickael.maison@gmail.com>, Qihong Chen, Sriharsha Chintalapani <sriharsha@apache.org>, Jun Rao <junrao@gmail.com>, Randall Hauch <rhauch@gmail.com>, Manikumar Reddy <manikumar.reddy@gmail.com>, Ismael Juma <ismael@juma.me.uk>
Closes #6295 from ryannedolan/KIP-382
5 years ago
testRuntimeOnly libs . slf4jlog4j
KAFKA-7500: MirrorMaker 2.0 (KIP-382)
Implementation of [KIP-382 "MirrorMaker 2.0"](https://cwiki.apache.org/confluence/display/KAFKA/KIP-382%3A+MirrorMaker+2.0)
Author: Ryanne Dolan <ryannedolan@gmail.com>
Author: Arun Mathew <arunmathew88@gmail.com>
Author: In Park <inpark@cloudera.com>
Author: Andre Price <obsoleted@users.noreply.github.com>
Author: christian.hagel@rio.cloud <christian.hagel@rio.cloud>
Reviewers: Eno Thereska <eno.thereska@gmail.com>, William Hammond <william.t.hammond@gmail.com>, Viktor Somogyi <viktorsomogyi@gmail.com>, Jakub Korzeniowski, Tim Carey-Smith, Kamal Chandraprakash <kamal.chandraprakash@gmail.com>, Arun Mathew, Jeremy-l-ford, vpernin, Oleg Kasian <oleg.kasian@gmail.com>, Mickael Maison <mickael.maison@gmail.com>, Qihong Chen, Sriharsha Chintalapani <sriharsha@apache.org>, Jun Rao <junrao@gmail.com>, Randall Hauch <rhauch@gmail.com>, Manikumar Reddy <manikumar.reddy@gmail.com>, Ismael Juma <ismael@juma.me.uk>
Closes #6295 from ryannedolan/KIP-382
5 years ago
}
javadoc {
enabled = true
}
tasks . create ( name: "copyDependantLibs" , type: Copy ) {
from ( configurations . testRuntimeClasspath ) {
include ( 'slf4j-log4j12*' )
include ( 'reload4j*jar' )
}
from ( configurations . runtimeClasspath ) {
exclude ( 'kafka-clients*' )
exclude ( 'connect-*' )
}
into "$buildDir/dependant-libs"
duplicatesStrategy 'exclude'
}
jar {
dependsOn copyDependantLibs
}
}
task aggregatedJavadoc ( type: Javadoc , dependsOn: compileJava ) {
def projectsWithJavadoc = subprojects . findAll { it . javadoc . enabled }
source = projectsWithJavadoc . collect { it . sourceSets . main . allJava }
classpath = files ( projectsWithJavadoc . collect { it . sourceSets . main . compileClasspath } )
includes = projectsWithJavadoc . collectMany { it . javadoc . getIncludes ( ) }
excludes = projectsWithJavadoc . collectMany { it . javadoc . getExcludes ( ) }
options . charSet = 'UTF-8'
options . docEncoding = 'UTF-8'
options . encoding = 'UTF-8'
// Turn off doclint for now, see https://blog.joda.org/2014/02/turning-off-doclint-in-jdk-8-javadoc.html for rationale
options . addStringOption ( 'Xdoclint:none' , '-quiet' )
// The URL structure was changed to include the locale after Java 8
if ( JavaVersion . current ( ) . isJava11Compatible ( ) )
options . links "https://docs.oracle.com/en/java/javase/${JavaVersion.current().majorVersion}/docs/api/"
else
options . links "https://docs.oracle.com/javase/8/docs/api/"
}