SPARK-1843: Replace assemble-deps with env variable.

(This change is actually small, I moved some logic into
compute-classpath that was previously in spark-class).

Assemble deps has existed for a while to allow developers to
run local code with new changes quickly. When I'm developing I
typically use a simpler approach which just prepends the Spark
classes to the classpath before the assembly jar. This is well
defined in the JVM and the Spark classes take predece over those
in the assembly.

This approach is portable across both builds which is the main reason I'd
like to switch to it. It's also faster than creating a new assembly.

Author: pwendell

bin/compute-classpath.sh

@@ -38,8 +38,10 @@ else
   JAR_CMD="jar"
 fi
 
-# First check if we have a dependencies jar. If so, include binary classes with the deps jar
-if [ -f "$ASSEMBLY_DIR"/spark-assembly*hadoop*-deps.jar ]; then
+# A developer option to prepend more recently compiled Spark classes
+if [ -n "$SPARK_PREPEND_CLASSES" ]; then
+  echo "NOTE: SPARK_PREPEND_CLASSES is set, placing locally compiled Spark"\
+    "classes ahead of assembly." >&2
   CLASSPATH="$CLASSPATH:$FWDIR/core/target/scala-$SCALA_VERSION/classes"
   CLASSPATH="$CLASSPATH:$FWDIR/repl/target/scala-$SCALA_VERSION/classes"
   CLASSPATH="$CLASSPATH:$FWDIR/mllib/target/scala-$SCALA_VERSION/classes"
@@ -51,17 +53,31 @@ if [ -f "$ASSEMBLY_DIR"/spark-assembly*hadoop*-deps.jar ]; then
   CLASSPATH="$CLASSPATH:$FWDIR/sql/core/target/scala-$SCALA_VERSION/classes"
   CLASSPATH="$CLASSPATH:$FWDIR/sql/hive/target/scala-$SCALA_VERSION/classes"
   CLASSPATH="$CLASSPATH:$FWDIR/yarn/stable/target/scala-$SCALA_VERSION/classes"
+fi
 
-  ASSEMBLY_JAR=$(ls "$ASSEMBLY_DIR"/spark-assembly*hadoop*-deps.jar 2>/dev/null)
+# Use spark-assembly jar from either RELEASE or assembly directory
+if [ -f "$FWDIR/RELEASE" ]; then
+  assembly_folder="$FWDIR"/lib
 else
-  # Else use spark-assembly jar from either RELEASE or assembly directory
-  if [ -f "$FWDIR/RELEASE" ]; then
-    ASSEMBLY_JAR=$(ls "$FWDIR"/lib/spark-assembly*hadoop*.jar 2>/dev/null)
-  else
-    ASSEMBLY_JAR=$(ls "$ASSEMBLY_DIR"/spark-assembly*hadoop*.jar 2>/dev/null)
-  fi
+  assembly_folder="$ASSEMBLY_DIR"
 fi
 
+num_jars=$(ls "$assembly_folder" | grep "spark-assembly.*hadoop.*.jar" | wc -l)
+if [ "$num_jars" -eq "0" ]; then
+  echo "Failed to find Spark assembly in $assembly_folder"
+  echo "You need to build Spark before running this program."
+  exit 1
+fi
+if [ "$num_jars" -gt "1" ]; then
+  jars_list=$(ls "$assembly_folder" | grep "spark-assembly.*hadoop.*.jar")
+  echo "Found multiple Spark assembly jars in $assembly_folder:"
+  echo "$jars_list"
+  echo "Please remove all but one jar."
+  exit 1
+fi
+
+ASSEMBLY_JAR=$(ls "$assembly_folder"/spark-assembly*hadoop*.jar 2>/dev/null)
+
 # Verify that versions of java used to build the jars and run Spark are compatible
 jar_error_check=$("$JAR_CMD" -tf "$ASSEMBLY_JAR" nonexistent/class/path 2>&1)
 if [[ "$jar_error_check" =~ "invalid CEN header" ]]; then

bin/spark-class

@@ -108,23 +108,6 @@ fi
 export JAVA_OPTS
 # Attention: when changing the way the JAVA_OPTS are assembled, the change must be reflected in CommandUtils.scala!
 
-if [ ! -f "$FWDIR/RELEASE" ]; then
-  # Exit if the user hasn't compiled Spark
-  num_jars=$(ls "$FWDIR"/assembly/target/scala-$SCALA_VERSION/ | grep "spark-assembly.*hadoop.*.jar" | wc -l)
-  jars_list=$(ls "$FWDIR"/assembly/target/scala-$SCALA_VERSION/ | grep "spark-assembly.*hadoop.*.jar")
-  if [ "$num_jars" -eq "0" ]; then
-    echo "Failed to find Spark assembly in $FWDIR/assembly/target/scala-$SCALA_VERSION/" >&2
-    echo "You need to build Spark before running this program." >&2
-    exit 1
-  fi
-  if [ "$num_jars" -gt "1" ]; then
-    echo "Found multiple Spark assembly jars in $FWDIR/assembly/target/scala-$SCALA_VERSION:" >&2
-    echo "$jars_list"
-    echo "Please remove all but one jar."
-    exit 1
-  fi
-fi
-
 TOOLS_DIR="$FWDIR"/tools
 SPARK_TOOLS_JAR=""
 if [ -e "$TOOLS_DIR"/target/scala-$SCALA_VERSION/*assembly*[0-9Tg].jar ]; then

core/src/main/scala/org/apache/spark/SparkContext.scala

@@ -290,6 +290,9 @@ class SparkContext(config: SparkConf) extends Logging {
     value <- Option(System.getenv(envKey)).orElse(Option(System.getProperty(propKey)))} {
     executorEnvs(envKey) = value
   }
+  Option(System.getenv("SPARK_PREPEND_CLASSES")).foreach { v => 
+    executorEnvs("SPARK_PREPEND_CLASSES") = v
+  }
   // The Mesos scheduler backend relies on this environment variable to set executor memory.
   // TODO: Set this only in the Mesos scheduler.
   executorEnvs("SPARK_EXECUTOR_MEMORY") = executorMemory + "m"

project/SparkBuild.scala

@@ -84,8 +84,6 @@ object SparkBuild extends Build {
   lazy val assemblyProj = Project("assembly", file("assembly"), settings = assemblyProjSettings)
     .dependsOn(core, graphx, bagel, mllib, streaming, repl, sql) dependsOn(maybeYarn: _*) dependsOn(maybeHive: _*) dependsOn(maybeGanglia: _*)
 
-  lazy val assembleDeps = TaskKey[Unit]("assemble-deps", "Build assembly of dependencies and packages Spark projects")
-
   // A configuration to set an alternative publishLocalConfiguration
   lazy val MavenCompile = config("m2r") extend(Compile)
   lazy val publishLocalBoth = TaskKey[Unit]("publish-local", "publish local for m2 and ivy")
@@ -574,7 +572,6 @@ object SparkBuild extends Build {
 
   def assemblyProjSettings = sharedSettings ++ Seq(
     name := "spark-assembly",
-    assembleDeps in Compile <<= (packageProjects.map(packageBin in Compile in _) ++ Seq(packageDependency in Compile)).dependOn,
     jarName in assembly <<= version map { v => "spark-assembly-" + v + "-hadoop" + hadoopVersion + ".jar" },
     jarName in packageDependency <<= version map { v => "spark-assembly-" + v + "-hadoop" + hadoopVersion + "-deps.jar" }
   ) ++ assemblySettings ++ extraAssemblySettings