From 53cd50c0699efc8733518658100c62426b425de2 Mon Sep 17 00:00:00 2001 From: Matei Zaharia Date: Fri, 23 Aug 2013 23:30:17 -0700 Subject: Change build and run instructions to use assemblies This commit makes Spark invocation saner by using an assembly JAR to find all of Spark's dependencies instead of adding all the JARs in lib_managed. It also packages the examples into an assembly and uses that as SPARK_EXAMPLES_JAR. Finally, it replaces the old "run" script with two better-named scripts: "run-examples" for examples, and "spark-class" for Spark internal classes (e.g. REPL, master, etc). This is also designed to minimize the confusion people have in trying to use "run" to run their own classes; it's not meant to do that, but now at least if they look at it, they can modify run-examples to do a decent job for them. As part of this, Bagel's examples are also now properly moved to the examples package instead of bagel. --- project/SparkBuild.scala | 52 +++++++++++++++++++++++++++++------------------- 1 file changed, 32 insertions(+), 20 deletions(-) (limited to 'project/SparkBuild.scala') diff --git a/project/SparkBuild.scala b/project/SparkBuild.scala index 5fdcf19b62..b3bf3ef89b 100644 --- a/project/SparkBuild.scala +++ b/project/SparkBuild.scala @@ -26,30 +26,35 @@ import AssemblyKeys._ object SparkBuild extends Build { // Hadoop version to build against. For example, "1.0.4" for Apache releases, or // "2.0.0-mr1-cdh4.2.0" for Cloudera Hadoop. Note that these variables can be set - // through the environment variables SPARK_HADOOP_VERSION and SPARK_WITH_YARN. + // through the environment variables SPARK_HADOOP_VERSION and SPARK_YARN. val DEFAULT_HADOOP_VERSION = "1.0.4" - val DEFAULT_WITH_YARN = false + val DEFAULT_YARN = false // HBase version; set as appropriate. val HBASE_VERSION = "0.94.6" - lazy val root = Project("root", file("."), settings = rootSettings) aggregate(allProjects:_*) + lazy val root = Project("root", file("."), settings = rootSettings) aggregate(allProjects: _*) lazy val core = Project("core", file("core"), settings = coreSettings) - lazy val repl = Project("repl", file("repl"), settings = replSettings) dependsOn(core) dependsOn(bagel) dependsOn(mllib) dependsOn(maybeYarn:_*) + lazy val repl = Project("repl", file("repl"), settings = replSettings) + .dependsOn(core, bagel, mllib) dependsOn(maybeYarn: _*) - lazy val examples = Project("examples", file("examples"), settings = examplesSettings) dependsOn (core) dependsOn (streaming) dependsOn(mllib) + lazy val examples = Project("examples", file("examples"), settings = examplesSettings) + .dependsOn(core, mllib, bagel, streaming) - lazy val tools = Project("tools", file("tools"), settings = examplesSettings) dependsOn (core) dependsOn (streaming) + lazy val tools = Project("tools", file("tools"), settings = toolsSettings) dependsOn(core) dependsOn(streaming) - lazy val bagel = Project("bagel", file("bagel"), settings = bagelSettings) dependsOn (core) + lazy val bagel = Project("bagel", file("bagel"), settings = bagelSettings) dependsOn(core) - lazy val streaming = Project("streaming", file("streaming"), settings = streamingSettings) dependsOn (core) + lazy val streaming = Project("streaming", file("streaming"), settings = streamingSettings) dependsOn(core) - lazy val mllib = Project("mllib", file("mllib"), settings = mllibSettings) dependsOn (core) + lazy val mllib = Project("mllib", file("mllib"), settings = mllibSettings) dependsOn(core) - lazy val yarn = Project("yarn", file("yarn"), settings = yarnSettings) dependsOn (core) + lazy val yarn = Project("yarn", file("yarn"), settings = yarnSettings) dependsOn(core) + + lazy val assemblyProj = Project("assembly", file("assembly"), settings = assemblyProjSettings) + .dependsOn(core, bagel, mllib, repl, streaming) dependsOn(maybeYarn: _*) // A configuration to set an alternative publishLocalConfiguration lazy val MavenCompile = config("m2r") extend(Compile) @@ -57,15 +62,16 @@ object SparkBuild extends Build { // Allows build configuration to be set through environment variables lazy val hadoopVersion = scala.util.Properties.envOrElse("SPARK_HADOOP_VERSION", DEFAULT_HADOOP_VERSION) - lazy val isYarnEnabled = scala.util.Properties.envOrNone("SPARK_WITH_YARN") match { - case None => DEFAULT_WITH_YARN + lazy val isYarnEnabled = scala.util.Properties.envOrNone("SPARK_YARN") match { + case None => DEFAULT_YARN case Some(v) => v.toBoolean } // Conditionally include the yarn sub-project lazy val maybeYarn = if(isYarnEnabled) Seq[ClasspathDependency](yarn) else Seq[ClasspathDependency]() lazy val maybeYarnRef = if(isYarnEnabled) Seq[ProjectReference](yarn) else Seq[ProjectReference]() - lazy val allProjects = Seq[ProjectReference](core, repl, examples, bagel, streaming, mllib, tools) ++ maybeYarnRef + lazy val allProjects = Seq[ProjectReference]( + core, repl, examples, bagel, streaming, mllib, tools, assemblyProj) ++ maybeYarnRef def sharedSettings = Defaults.defaultSettings ++ Seq( organization := "org.spark-project", @@ -100,8 +106,8 @@ object SparkBuild extends Build { http://spark-project.org/ - BSD License - https://github.com/mesos/spark/blob/master/LICENSE + Apache 2.0 License + http://www.apache.org/licenses/LICENSE-2.0.html repo @@ -195,7 +201,7 @@ object SparkBuild extends Build { "com.twitter" % "chill_2.9.3" % "0.3.1", "com.twitter" % "chill-java" % "0.3.1" ) - ) ++ assemblySettings ++ extraAssemblySettings + ) def rootSettings = sharedSettings ++ Seq( publish := {} @@ -204,7 +210,7 @@ object SparkBuild extends Build { def replSettings = sharedSettings ++ Seq( name := "spark-repl", libraryDependencies <+= scalaVersion("org.scala-lang" % "scala-compiler" % _) - ) ++ assemblySettings ++ extraAssemblySettings + ) def examplesSettings = sharedSettings ++ Seq( name := "spark-examples", @@ -223,7 +229,7 @@ object SparkBuild extends Build { exclude("org.apache.cassandra.deps", "avro") excludeAll(excludeSnappy) ) - ) + ) ++ assemblySettings ++ extraAssemblySettings def toolsSettings = sharedSettings ++ Seq( name := "spark-tools" @@ -251,7 +257,7 @@ object SparkBuild extends Build { "org.twitter4j" % "twitter4j-stream" % "3.0.3" excludeAll(excludeNetty), "com.typesafe.akka" % "akka-zeromq" % "2.0.5" excludeAll(excludeNetty) ) - ) ++ assemblySettings ++ extraAssemblySettings + ) def yarnSettings = sharedSettings ++ Seq( name := "spark-yarn" @@ -271,7 +277,13 @@ object SparkBuild extends Build { ) ) - def extraAssemblySettings() = Seq(test in assembly := {}) ++ Seq( + def assemblyProjSettings = sharedSettings ++ Seq( + name := "spark-assembly", + jarName in assembly <<= version map { v => "spark-assembly-" + v + "-hadoop" + hadoopVersion + ".jar" } + ) ++ assemblySettings ++ extraAssemblySettings + + def extraAssemblySettings() = Seq( + test in assembly := {}, mergeStrategy in assembly := { case m if m.toLowerCase.endsWith("manifest.mf") => MergeStrategy.discard case m if m.toLowerCase.matches("meta-inf.*\\.sf$") => MergeStrategy.discard -- cgit v1.2.3