Merge branch 'master' into SPARK-2669

Conflicts:
	yarn/src/main/scala/org/apache/spark/deploy/yarn/Client.scala
	yarn/src/test/scala/org/apache/spark/deploy/yarn/ClientSuite.scala

Author: Marcelo Vanzin

README.md

@@ -26,7 +26,7 @@ To build Spark and its example programs, run:
 
 (You do not need to do this if you downloaded a pre-built package.)
 More detailed documentation is available from the project site, at
-["Building Spark with Maven"](http://spark.apache.org/docs/latest/building-spark.html).
+["Building Spark"](http://spark.apache.org/docs/latest/building-spark.html).
 
 ## Interactive Scala Shell
 

assembly/pom.xml

@@ -39,16 +39,10 @@
     <deb.pkg.name>spark</deb.pkg.name>
     <deb.install.path>/usr/share/spark</deb.install.path>
     <deb.user>root</deb.user>
-    <deb.bin.filemode>744</deb.bin.filemode>
+    <deb.bin.filemode>755</deb.bin.filemode>
   </properties>
 
   <dependencies>
-    <!-- Promote Guava to compile scope in this module so it's included while shading. -->
-    <dependency>
-      <groupId>com.google.guava</groupId>
-      <artifactId>guava</artifactId>
-      <scope>compile</scope>
-    </dependency>
     <dependency>
       <groupId>org.apache.spark</groupId>
       <artifactId>spark-core_${scala.binary.version}</artifactId>
@@ -133,20 +127,6 @@
               <goal>shade</goal>
             </goals>
             <configuration>
-              <relocations>
-                <relocation>
-                  <pattern>com.google</pattern>
-                  <shadedPattern>org.spark-project.guava</shadedPattern>
-                  <includes>
-                    <include>com.google.common.**</include>
-                  </includes>
-                  <excludes>
-                    <exclude>com/google/common/base/Absent*</exclude>
-                    <exclude>com/google/common/base/Optional*</exclude>
-                    <exclude>com/google/common/base/Present*</exclude>
-                  </excludes>
-                </relocation>
-              </relocations>
               <transformers>
                 <transformer implementation="org.apache.maven.plugins.shade.resource.ServicesResourceTransformer" />
                 <transformer implementation="org.apache.maven.plugins.shade.resource.AppendingTransformer">
@@ -300,7 +280,7 @@
                         <user>${deb.user}</user>
                         <group>${deb.user}</group>
                         <prefix>${deb.install.path}/conf</prefix>
-                        <filemode>744</filemode>
+                        <filemode>${deb.bin.filemode}</filemode>
                       </mapper>
                     </data>
                     <data>
@@ -322,7 +302,7 @@
                         <user>${deb.user}</user>
                         <group>${deb.user}</group>
                         <prefix>${deb.install.path}/sbin</prefix>
-                        <filemode>744</filemode>
+                        <filemode>${deb.bin.filemode}</filemode>
                       </mapper>
                     </data>
                     <data>
@@ -333,7 +313,7 @@
                         <user>${deb.user}</user>
                         <group>${deb.user}</group>
                         <prefix>${deb.install.path}/python</prefix>
-                        <filemode>744</filemode>
+                        <filemode>${deb.bin.filemode}</filemode>
                       </mapper>
                     </data>
                   </dataSet>

bin/compute-classpath.sh

@@ -50,8 +50,8 @@ fi
 if [ -n "$SPARK_PREPEND_CLASSES" ]; then
   echo "NOTE: SPARK_PREPEND_CLASSES is set, placing locally compiled Spark"\
     "classes ahead of assembly." >&2
+  # Spark classes
   CLASSPATH="$CLASSPATH:$FWDIR/core/target/scala-$SPARK_SCALA_VERSION/classes"
-  CLASSPATH="$CLASSPATH:$FWDIR/core/target/jars/*"
   CLASSPATH="$CLASSPATH:$FWDIR/repl/target/scala-$SPARK_SCALA_VERSION/classes"
   CLASSPATH="$CLASSPATH:$FWDIR/mllib/target/scala-$SPARK_SCALA_VERSION/classes"
   CLASSPATH="$CLASSPATH:$FWDIR/bagel/target/scala-$SPARK_SCALA_VERSION/classes"
@@ -63,6 +63,8 @@ if [ -n "$SPARK_PREPEND_CLASSES" ]; then
   CLASSPATH="$CLASSPATH:$FWDIR/sql/hive/target/scala-$SPARK_SCALA_VERSION/classes"
   CLASSPATH="$CLASSPATH:$FWDIR/sql/hive-thriftserver/target/scala-$SPARK_SCALA_VERSION/classes"
   CLASSPATH="$CLASSPATH:$FWDIR/yarn/stable/target/scala-$SPARK_SCALA_VERSION/classes"
+  # Jars for shaded deps in their original form (copied here during build)
+  CLASSPATH="$CLASSPATH:$FWDIR/core/target/jars/*"
 fi
 
 # Use spark-assembly jar from either RELEASE or assembly directory

bin/spark-class

@@ -29,6 +29,7 @@ FWDIR="$(cd "`dirname "$0"`"/..; pwd)"
 
 # Export this as SPARK_HOME
 export SPARK_HOME="$FWDIR"
+export SPARK_CONF_DIR="${SPARK_CONF_DIR:-"$SPARK_HOME/conf"}"
 
 . "$FWDIR"/bin/load-spark-env.sh
 
@@ -120,8 +121,8 @@ fi
 JAVA_OPTS="$JAVA_OPTS -Xms$OUR_JAVA_MEM -Xmx$OUR_JAVA_MEM"
 
 # Load extra JAVA_OPTS from conf/java-opts, if it exists
-if [ -e "$FWDIR/conf/java-opts" ] ; then
-  JAVA_OPTS="$JAVA_OPTS `cat "$FWDIR"/conf/java-opts`"
+if [ -e "$SPARK_CONF_DIR/java-opts" ] ; then
+  JAVA_OPTS="$JAVA_OPTS `cat "$SPARK_CONF_DIR"/java-opts`"
 fi
 
 # Attention: when changing the way the JAVA_OPTS are assembled, the change must be reflected in CommandUtils.scala!

bin/spark-shell.cmd

@@ -25,7 +25,7 @@ set ORIG_ARGS=%*
 rem Reset the values of all variables used
 set SPARK_SUBMIT_DEPLOY_MODE=client
 
-if not defined %SPARK_CONF_DIR% (
+if [%SPARK_CONF_DIR%] == [] (
   set SPARK_CONF_DIR=%SPARK_HOME%\conf
 )
 set SPARK_SUBMIT_PROPERTIES_FILE=%SPARK_CONF_DIR%\spark-defaults.conf

bin/spark-submit2.cmd

@@ -26,14 +26,14 @@ function gatherSparkSubmitOpts() {
     exit 1
   fi
 
-  # NOTE: If you add or remove spark-sumbmit options,
+  # NOTE: If you add or remove spark-submit options,
   # modify NOT ONLY this script but also SparkSubmitArgument.scala
   SUBMISSION_OPTS=()
   APPLICATION_OPTS=()
   while (($#)); do
     case "$1" in
-      --master | --deploy-mode | --class | --name | --jars | --py-files | --files | \
-      --conf | --properties-file | --driver-memory | --driver-java-options | \
+      --master | --deploy-mode | --class | --name | --jars | --packages | --py-files | --files | \
+      --conf | --repositories | --properties-file | --driver-memory | --driver-java-options | \
       --driver-library-path | --driver-class-path | --executor-memory | --driver-cores | \
       --total-executor-cores | --executor-cores | --queue | --num-executors | --archives)
         if [[ $# -lt 2 ]]; then

bin/utils.sh

@@ -32,7 +32,7 @@ SET opts="\<--master\> \<--deploy-mode\> \<--class\> \<--name\> \<--jars\> \<--p
 SET opts="%opts:~1,-1% \<--conf\> \<--properties-file\> \<--driver-memory\> \<--driver-java-options\>"
 SET opts="%opts:~1,-1% \<--driver-library-path\> \<--driver-class-path\> \<--executor-memory\>"
 SET opts="%opts:~1,-1% \<--driver-cores\> \<--total-executor-cores\> \<--executor-cores\> \<--queue\>"
-SET opts="%opts:~1,-1% \<--num-executors\> \<--archives\>"
+SET opts="%opts:~1,-1% \<--num-executors\> \<--archives\> \<--packages\> \<--repositories\>"
 
 echo %1 | findstr %opts% >nul
 if %ERRORLEVEL% equ 0 (

bin/windows-utils.cmd

@@ -34,25 +34,25 @@ install_app() {
   local binary="${_DIR}/$3"
 
   # setup `curl` and `wget` silent options if we're running on Jenkins
-  local curl_opts=""
+  local curl_opts="-L"
   local wget_opts=""
   if [ -n "$AMPLAB_JENKINS" ]; then
-    curl_opts="-s"
-    wget_opts="--quiet"
+    curl_opts="-s ${curl_opts}"
+    wget_opts="--quiet ${wget_opts}"
   else
-    curl_opts="--progress-bar"
-    wget_opts="--progress=bar:force"
+    curl_opts="--progress-bar ${curl_opts}"
+    wget_opts="--progress=bar:force ${wget_opts}"
   fi
 
   if [ -z "$3" -o ! -f "$binary" ]; then
     # check if we already have the tarball
     # check if we have curl installed
     # download application
-    [ ! -f "${local_tarball}" ] && [ -n "`which curl 2>/dev/null`" ] && \
+    [ ! -f "${local_tarball}" ] && [ $(command -v curl) ] && \
       echo "exec: curl ${curl_opts} ${remote_tarball}" && \
       curl ${curl_opts} "${remote_tarball}" > "${local_tarball}"
     # if the file still doesn't exist, lets try `wget` and cross our fingers
-    [ ! -f "${local_tarball}" ] && [ -n "`which wget 2>/dev/null`" ] && \
+    [ ! -f "${local_tarball}" ] && [ $(command -v wget) ] && \
       echo "exec: wget ${wget_opts} ${remote_tarball}" && \
       wget ${wget_opts} -O "${local_tarball}" "${remote_tarball}"
     # if both were unsuccessful, exit
@@ -68,10 +68,10 @@ install_app() {
 # Install maven under the build/ folder
 install_mvn() {
   install_app \
-    "http://apache.claz.org/maven/maven-3/3.2.3/binaries" \
-    "apache-maven-3.2.3-bin.tar.gz" \
-    "apache-maven-3.2.3/bin/mvn"
-  MVN_BIN="${_DIR}/apache-maven-3.2.3/bin/mvn"
+    "http://archive.apache.org/dist/maven/maven-3/3.2.5/binaries" \
+    "apache-maven-3.2.5-bin.tar.gz" \
+    "apache-maven-3.2.5/bin/mvn"
+  MVN_BIN="${_DIR}/apache-maven-3.2.5/bin/mvn"
 }
 
 # Install zinc under the build/ folder

build/mvn

@@ -50,9 +50,9 @@ acquire_sbt_jar () {
     # Download
     printf "Attempting to fetch sbt\n"
     JAR_DL="${JAR}.part"
-    if hash curl 2>/dev/null; then
+    if [ $(command -v curl) ]; then
       (curl --silent ${URL1} > "${JAR_DL}" || curl --silent ${URL2} > "${JAR_DL}") && mv "${JAR_DL}" "${JAR}"
-    elif hash wget 2>/dev/null; then
+    elif [ $(command -v wget) ]; then
       (wget --quiet ${URL1} -O "${JAR_DL}" || wget --quiet ${URL2} -O "${JAR_DL}") && mv "${JAR_DL}" "${JAR}"
     else
       printf "You do not have curl or wget installed, please install sbt manually from http://www.scala-sbt.org/\n"