Repository: spark Updated Branches: refs/heads/branch-1.2 233f0377a -> f50c0881b
[SPARK-4281][Build] Package Yarn shuffle service into its own jar This is another addendum to #3082, which added the Yarn shuffle service to run inside the NM. This PR makes the feature much more usable by packaging enough dependencies into the jar to run the service inside an NM. After these changes, the user can run `./make-distribution.sh` and find a `spark-network-yarn*.jar` in their `lib` directory. The equivalent change is done in SBT by making the `network-yarn` module an assembly project. Author: Andrew Or <[email protected]> Closes #3147 from andrewor14/yarn-shuffle-build and squashes the following commits: bda58d0 [Andrew Or] Fix line too long 81e9705 [Andrew Or] Merge branch 'master' of github.com:apache/spark into yarn-shuffle-build fb7f398 [Andrew Or] Rename jar to spark-{VERSION}-yarn-shuffle.jar 65db822 [Andrew Or] Actually mark slf4j as provided abcefd1 [Andrew Or] Do the same for SBT c653028 [Andrew Or] Package network-yarn and its dependencies (cherry picked from commit aa43a8da012cf0dac7c7fcccde5f028a942599f0) Signed-off-by: Andrew Or <[email protected]> Project: http://git-wip-us.apache.org/repos/asf/spark/repo Commit: http://git-wip-us.apache.org/repos/asf/spark/commit/f50c0881 Tree: http://git-wip-us.apache.org/repos/asf/spark/tree/f50c0881 Diff: http://git-wip-us.apache.org/repos/asf/spark/diff/f50c0881 Branch: refs/heads/branch-1.2 Commit: f50c0881be943d8df98a88cc73d163b16169874e Parents: 233f037 Author: Andrew Or <[email protected]> Authored: Wed Nov 12 13:39:45 2014 -0800 Committer: Andrew Or <[email protected]> Committed: Wed Nov 12 13:39:54 2014 -0800 ---------------------------------------------------------------------- make-distribution.sh | 1 + network/common/pom.xml | 5 +++-- network/shuffle/pom.xml | 5 +++-- network/yarn/pom.xml | 33 +++++++++++++++++++++++++++++++++ project/SparkBuild.scala | 19 +++++++++++++------ 5 files changed, 53 insertions(+), 10 deletions(-) ---------------------------------------------------------------------- http://git-wip-us.apache.org/repos/asf/spark/blob/f50c0881/make-distribution.sh ---------------------------------------------------------------------- diff --git a/make-distribution.sh b/make-distribution.sh index d46edbc..55cbdc1 100755 --- a/make-distribution.sh +++ b/make-distribution.sh @@ -181,6 +181,7 @@ echo "Spark $VERSION$GITREVSTRING built for Hadoop $SPARK_HADOOP_VERSION" > "$DI # Copy jars cp "$FWDIR"/assembly/target/scala*/*assembly*hadoop*.jar "$DISTDIR/lib/" cp "$FWDIR"/examples/target/scala*/spark-examples*.jar "$DISTDIR/lib/" +cp "$FWDIR"/network/yarn/target/scala*/spark-*-yarn-shuffle.jar "$DISTDIR/lib/" # Copy example sources (needed for python and SQL) mkdir -p "$DISTDIR/examples/src/main" http://git-wip-us.apache.org/repos/asf/spark/blob/f50c0881/network/common/pom.xml ---------------------------------------------------------------------- diff --git a/network/common/pom.xml b/network/common/pom.xml index 8b24ebf..a6bee7e 100644 --- a/network/common/pom.xml +++ b/network/common/pom.xml @@ -41,12 +41,13 @@ <groupId>io.netty</groupId> <artifactId>netty-all</artifactId> </dependency> + + <!-- Provided dependencies --> <dependency> <groupId>org.slf4j</groupId> <artifactId>slf4j-api</artifactId> + <scope>provided</scope> </dependency> - - <!-- Provided dependencies --> <dependency> <groupId>com.google.guava</groupId> <artifactId>guava</artifactId> http://git-wip-us.apache.org/repos/asf/spark/blob/f50c0881/network/shuffle/pom.xml ---------------------------------------------------------------------- diff --git a/network/shuffle/pom.xml b/network/shuffle/pom.xml index a180a5e..be78331 100644 --- a/network/shuffle/pom.xml +++ b/network/shuffle/pom.xml @@ -42,12 +42,13 @@ <artifactId>spark-network-common_${scala.binary.version}</artifactId> <version>${project.version}</version> </dependency> + + <!-- Provided dependencies --> <dependency> <groupId>org.slf4j</groupId> <artifactId>slf4j-api</artifactId> + <scope>provided</scope> </dependency> - - <!-- Provided dependencies --> <dependency> <groupId>com.google.guava</groupId> <artifactId>guava</artifactId> http://git-wip-us.apache.org/repos/asf/spark/blob/f50c0881/network/yarn/pom.xml ---------------------------------------------------------------------- diff --git a/network/yarn/pom.xml b/network/yarn/pom.xml index 85960eb..7845011 100644 --- a/network/yarn/pom.xml +++ b/network/yarn/pom.xml @@ -54,5 +54,38 @@ <build> <outputDirectory>target/scala-${scala.binary.version}/classes</outputDirectory> <testOutputDirectory>target/scala-${scala.binary.version}/test-classes</testOutputDirectory> + <plugins> + <plugin> + <groupId>org.apache.maven.plugins</groupId> + <artifactId>maven-shade-plugin</artifactId> + <configuration> + <shadedArtifactAttached>false</shadedArtifactAttached> + <outputFile>${project.build.directory}/scala-${scala.binary.version}/spark-${project.version}-yarn-shuffle.jar</outputFile> + <artifactSet> + <includes> + <include>*:*</include> + </includes> + </artifactSet> + <filters> + <filter> + <artifact>*:*</artifact> + <excludes> + <exclude>META-INF/*.SF</exclude> + <exclude>META-INF/*.DSA</exclude> + <exclude>META-INF/*.RSA</exclude> + </excludes> + </filter> + </filters> + </configuration> + <executions> + <execution> + <phase>package</phase> + <goals> + <goal>shade</goal> + </goals> + </execution> + </executions> + </plugin> + </plugins> </build> </project> http://git-wip-us.apache.org/repos/asf/spark/blob/f50c0881/project/SparkBuild.scala ---------------------------------------------------------------------- diff --git a/project/SparkBuild.scala b/project/SparkBuild.scala index 492607d..bbba642 100644 --- a/project/SparkBuild.scala +++ b/project/SparkBuild.scala @@ -38,12 +38,12 @@ object BuildCommons { "streaming-flume", "streaming-kafka", "streaming-mqtt", "streaming-twitter", "streaming-zeromq").map(ProjectRef(buildLocation, _)) - val optionallyEnabledProjects@Seq(yarn, yarnStable, yarnAlpha, networkYarn, java8Tests, - sparkGangliaLgpl, sparkKinesisAsl) = Seq("yarn", "yarn-stable", "yarn-alpha", "network-yarn", + val optionallyEnabledProjects@Seq(yarn, yarnStable, yarnAlpha, java8Tests, + sparkGangliaLgpl, sparkKinesisAsl) = Seq("yarn", "yarn-stable", "yarn-alpha", "java8-tests", "ganglia-lgpl", "kinesis-asl").map(ProjectRef(buildLocation, _)) - val assemblyProjects@Seq(assembly, examples) = Seq("assembly", "examples") - .map(ProjectRef(buildLocation, _)) + val assemblyProjects@Seq(assembly, examples, networkYarn) = + Seq("assembly", "examples", "network-yarn").map(ProjectRef(buildLocation, _)) val tools = ProjectRef(buildLocation, "tools") // Root project. @@ -289,8 +289,15 @@ object Assembly { lazy val settings = assemblySettings ++ Seq( test in assembly := {}, - jarName in assembly <<= (version, moduleName) map { (v, mName) => mName + "-"+v + "-hadoop" + - Option(System.getProperty("hadoop.version")).getOrElse("1.0.4") + ".jar" }, + jarName in assembly <<= (version, moduleName) map { (v, mName) => + if (mName.contains("network-yarn")) { + // This must match the same name used in maven (see network/yarn/pom.xml) + "spark-" + v + "-yarn-shuffle.jar" + } else { + mName + "-" + v + "-hadoop" + + Option(System.getProperty("hadoop.version")).getOrElse("1.0.4") + ".jar" + } + }, mergeStrategy in assembly := { case PathList("org", "datanucleus", xs @ _*) => MergeStrategy.discard case m if m.toLowerCase.endsWith("manifest.mf") => MergeStrategy.discard --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
