From cb4ef19214332b5e9c2e0d0bfa0a72262122d04e Mon Sep 17 00:00:00 2001
From: Jey Kottalam <jey@cs.berkeley.edu>
Date: Mon, 22 Jul 2013 14:03:31 -0700
Subject: [PATCH] yarn support
---
bin/compute-classpath.cmd | 2 ++
bin/compute-classpath.sh | 2 ++
project/SparkBuild.scala | 12 ++++++------
3 files changed, 10 insertions(+), 6 deletions(-)
diff --git a/bin/compute-classpath.cmd b/bin/compute-classpath.cmd
index eb836b0ffd..9178b852e6 100644
--- a/bin/compute-classpath.cmd
+++ b/bin/compute-classpath.cmd
@@ -34,6 +34,7 @@ set EXAMPLES_DIR=%FWDIR%examples
set BAGEL_DIR=%FWDIR%bagel
set MLLIB_DIR=%FWDIR%mllib
set TOOLS_DIR=%FWDIR%tools
+set YARN_DIR=%FWDIR%yarn
set STREAMING_DIR=%FWDIR%streaming
set PYSPARK_DIR=%FWDIR%python
@@ -50,6 +51,7 @@ set CLASSPATH=%CLASSPATH%;%FWDIR%python\lib\*
set CLASSPATH=%CLASSPATH%;%BAGEL_DIR%\target\scala-%SCALA_VERSION%\classes
set CLASSPATH=%CLASSPATH%;%MLLIB_DIR%\target\scala-%SCALA_VERSION%\classes
set CLASSPATH=%CLASSPATH%;%TOOLS_DIR%\target\scala-%SCALA_VERSION%\classes
+set CLASSPATH=%CLASSPATH%;%YARN_DIR%\target\scala-%SCALA_VERSION%\classes
rem Add hadoop conf dir - else FileSystem.*, etc fail
rem Note, this assumes that there is either a HADOOP_CONF_DIR or YARN_CONF_DIR which hosts
diff --git a/bin/compute-classpath.sh b/bin/compute-classpath.sh
index e4ce1ca848..db6fc866ab 100755
--- a/bin/compute-classpath.sh
+++ b/bin/compute-classpath.sh
@@ -37,6 +37,7 @@ EXAMPLES_DIR="$FWDIR/examples"
BAGEL_DIR="$FWDIR/bagel"
MLLIB_DIR="$FWDIR/mllib"
TOOLS_DIR="$FWDIR/tools"
+YARN_DIR="$FWDIR/yarn"
STREAMING_DIR="$FWDIR/streaming"
PYSPARK_DIR="$FWDIR/python"
@@ -72,6 +73,7 @@ function dev_classpath {
CLASSPATH="$CLASSPATH:$BAGEL_DIR/target/scala-$SCALA_VERSION/classes"
CLASSPATH="$CLASSPATH:$MLLIB_DIR/target/scala-$SCALA_VERSION/classes"
CLASSPATH="$CLASSPATH:$TOOLS_DIR/target/scala-$SCALA_VERSION/classes"
+ CLASSPATH="$CLASSPATH:$YARN_DIR/target/scala-$SCALA_VERSION/classes"
for jar in `find $PYSPARK_DIR/lib -name '*jar'`; do
CLASSPATH="$CLASSPATH:$jar"
done
diff --git a/project/SparkBuild.scala b/project/SparkBuild.scala
index 99351ca935..ede49ea38b 100644
--- a/project/SparkBuild.scala
+++ b/project/SparkBuild.scala
@@ -170,7 +170,7 @@ object SparkBuild extends Build {
"org.apache.mesos" % "mesos" % "0.12.1",
"io.netty" % "netty-all" % "4.0.0.Beta2",
"org.apache.derby" % "derby" % "10.4.2.0" % "test",
- "org.apache.hadoop" % "hadoop-client" % "1.0.4",
+ "org.apache.hadoop" % "hadoop-client" % "1.0.4" excludeAll(excludeJackson, excludeNetty, excludeAsm),
"com.codahale.metrics" % "metrics-core" % "3.0.0",
"com.codahale.metrics" % "metrics-jvm" % "3.0.0",
"com.codahale.metrics" % "metrics-json" % "3.0.0",
@@ -239,12 +239,12 @@ object SparkBuild extends Build {
name := "spark-yarn",
libraryDependencies ++= Seq(
// Exclude rule required for all ?
- "org.apache.hadoop" % "hadoop-client" % "2.0.2-alpha" excludeAll(excludeJackson, excludeNetty),
- "org.apache.hadoop" % "hadoop-yarn-api" % "2.0.2-alpha" excludeAll(excludeJackson, excludeNetty),
- "org.apache.hadoop" % "hadoop-yarn-common" % "2.0.2-alpha" excludeAll(excludeJackson, excludeNetty),
- "org.apache.hadoop" % "hadoop-yarn-client" % "2.0.2-alpha" excludeAll(excludeJackson, excludeNetty)
+ "org.apache.hadoop" % "hadoop-client" % "2.0.2-alpha" excludeAll(excludeJackson, excludeNetty, excludeAsm),
+ "org.apache.hadoop" % "hadoop-yarn-api" % "2.0.2-alpha" excludeAll(excludeJackson, excludeNetty, excludeAsm),
+ "org.apache.hadoop" % "hadoop-yarn-common" % "2.0.2-alpha" excludeAll(excludeJackson, excludeNetty, excludeAsm),
+ "org.apache.hadoop" % "hadoop-yarn-client" % "2.0.2-alpha" excludeAll(excludeJackson, excludeNetty, excludeAsm)
)
- )
+ ) ++ assemblySettings ++ extraAssemblySettings
def extraAssemblySettings() = Seq(test in assembly := {}) ++ Seq(
mergeStrategy in assembly := {
--
GitLab