Merge pull request #2 from apache/master

Updating to latest Spark master

.rat-excludes

@@ -1,4 +1,5 @@
 target
+cache
 .gitignore
 .gitattributes
 .project
@@ -18,6 +19,7 @@ fairscheduler.xml.template
 spark-defaults.conf.template
 log4j.properties
 log4j.properties.template
+metrics.properties
 metrics.properties.template
 slaves
 slaves.template

assembly/pom.xml

@@ -36,10 +36,6 @@
     <spark.jar.dir>scala-${scala.binary.version}</spark.jar.dir>
     <spark.jar.basename>spark-assembly-${project.version}-hadoop${hadoop.version}.jar</spark.jar.basename>
     <spark.jar>${project.build.directory}/${spark.jar.dir}/${spark.jar.basename}</spark.jar>
-    <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>
   </properties>
 
   <dependencies>
@@ -118,6 +114,16 @@
                 <exclude>META-INF/*.RSA</exclude>
               </excludes>
             </filter>
+            <filter>
+              <!-- Exclude libgfortran, libgcc for license issues -->
+              <artifact>org.jblas:jblas</artifact>
+              <excludes>
+                <!-- Linux amd64 is OK; not statically linked -->
+                <exclude>lib/static/Linux/i386/**</exclude>
+                <exclude>lib/static/Mac OS X/**</exclude>
+                <exclude>lib/static/Windows/**</exclude>
+              </excludes>
+            </filter>
           </filters>
         </configuration>
         <executions>
@@ -217,113 +223,6 @@
         </plugins>
       </build>
     </profile>
-    <profile>
-      <id>deb</id>
-      <build>
-        <plugins>
-          <plugin>
-            <groupId>org.codehaus.mojo</groupId>
-            <artifactId>buildnumber-maven-plugin</artifactId>
-            <version>1.2</version>
-            <executions>
-              <execution>
-                <phase>validate</phase>
-                <goals>
-                  <goal>create</goal>
-                </goals>
-                <configuration>
-                  <shortRevisionLength>8</shortRevisionLength>
-                </configuration>
-              </execution>
-            </executions>
-          </plugin>
-          <plugin>
-            <groupId>org.vafer</groupId>
-            <artifactId>jdeb</artifactId>
-            <version>0.11</version>
-            <executions>
-              <execution>
-                <phase>package</phase>
-                <goals>
-                  <goal>jdeb</goal>
-                </goals>
-                <configuration>
-                  <deb>${project.build.directory}/${deb.pkg.name}_${project.version}-${buildNumber}_all.deb</deb>
-                  <attach>false</attach>
-                  <compression>gzip</compression>
-                  <dataSet>
-                    <data>
-                      <src>${spark.jar}</src>
-                      <type>file</type>
-                      <mapper>
-                        <type>perm</type>
-                        <user>${deb.user}</user>
-                        <group>${deb.user}</group>
-                        <prefix>${deb.install.path}/jars</prefix>
-                      </mapper>
-                    </data>
-                    <data>
-                      <src>${basedir}/src/deb/RELEASE</src>
-                      <type>file</type>
-                      <mapper>
-                        <type>perm</type>
-                        <user>${deb.user}</user>
-                        <group>${deb.user}</group>
-                        <prefix>${deb.install.path}</prefix>
-                      </mapper>
-                    </data>
-                    <data>
-                      <src>${basedir}/../conf</src>
-                      <type>directory</type>
-                      <mapper>
-                        <type>perm</type>
-                        <user>${deb.user}</user>
-                        <group>${deb.user}</group>
-                        <prefix>${deb.install.path}/conf</prefix>
-                        <filemode>744</filemode>
-                      </mapper>
-                    </data>
-                    <data>
-                      <src>${basedir}/../bin</src>
-                      <type>directory</type>
-                      <mapper>
-                        <type>perm</type>
-                        <user>${deb.user}</user>
-                        <group>${deb.user}</group>
-                        <prefix>${deb.install.path}/bin</prefix>
-                        <filemode>${deb.bin.filemode}</filemode>
-                      </mapper>
-                    </data>
-                    <data>
-                      <src>${basedir}/../sbin</src>
-                      <type>directory</type>
-                      <mapper>
-                        <type>perm</type>
-                        <user>${deb.user}</user>
-                        <group>${deb.user}</group>
-                        <prefix>${deb.install.path}/sbin</prefix>
-                        <filemode>744</filemode>
-                      </mapper>
-                    </data>
-                    <data>
-                      <src>${basedir}/../python</src>
-                      <type>directory</type>
-                      <mapper>
-                        <type>perm</type>
-                        <user>${deb.user}</user>
-                        <group>${deb.user}</group>
-                        <prefix>${deb.install.path}/python</prefix>
-                        <filemode>744</filemode>
-                      </mapper>
-                    </data>
-                  </dataSet>
-                </configuration>
-              </execution>
-            </executions>
-          </plugin>
-        </plugins>
-      </build>
-    </profile>
     <profile>
       <id>kinesis-asl</id>
       <dependencies>

bin/compute-classpath.sh

@@ -76,7 +76,7 @@ fi
 
 num_jars=0
 
-for f in ${assembly_folder}/spark-assembly*hadoop*.jar; do
+for f in "${assembly_folder}"/spark-assembly*hadoop*.jar; do
   if [[ ! -e "$f" ]]; then
     echo "Failed to find Spark assembly in $assembly_folder" 1>&2
     echo "You need to build Spark before running this program." 1>&2
@@ -88,7 +88,7 @@ done
 
 if [ "$num_jars" -gt "1" ]; then
   echo "Found multiple Spark assembly jars in $assembly_folder:" 1>&2
-  ls ${assembly_folder}/spark-assembly*hadoop*.jar 1>&2
+  ls "${assembly_folder}"/spark-assembly*hadoop*.jar 1>&2
   echo "Please remove all but one jar." 1>&2
   exit 1
 fi

bin/run-example

@@ -42,7 +42,7 @@ fi
 
 JAR_COUNT=0
 
-for f in ${JAR_PATH}/spark-examples-*hadoop*.jar; do
+for f in "${JAR_PATH}"/spark-examples-*hadoop*.jar; do
   if [[ ! -e "$f" ]]; then
     echo "Failed to find Spark examples assembly in $FWDIR/lib or $FWDIR/examples/target" 1>&2
     echo "You need to build Spark before running this program" 1>&2
@@ -54,7 +54,7 @@ done
 
 if [ "$JAR_COUNT" -gt "1" ]; then
   echo "Found multiple Spark examples assembly jars in ${JAR_PATH}" 1>&2
-  ls ${JAR_PATH}/spark-examples-*hadoop*.jar 1>&2
+  ls "${JAR_PATH}"/spark-examples-*hadoop*.jar 1>&2
   echo "Please remove all but one jar." 1>&2
   exit 1
 fi

bin/spark-submit2.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/utils.sh

@@ -35,7 +35,8 @@ function gatherSparkSubmitOpts() {
       --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)
+      --total-executor-cores | --executor-cores | --queue | --num-executors | --archives | \
+      --proxy-user)
         if [[ $# -lt 2 ]]; then
           "$SUBMIT_USAGE_FUNCTION"
           exit 1;

bin/windows-utils.cmd

@@ -33,6 +33,7 @@ SET opts="%opts:~1,-1% \<--conf\> \<--properties-file\> \<--driver-memory\> \<--
 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\> \<--packages\> \<--repositories\>"
+SET opts="%opts:~1,-1% \<--proxy-user\>"
 
 echo %1 | findstr %opts% >nul
 if %ERRORLEVEL% equ 0 (

build/mvn

@@ -21,6 +21,8 @@
 _DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )"
 # Preserve the calling directory
 _CALLING_DIR="$(pwd)"
+# Options used during compilation
+_COMPILE_JVM_OPTS="-Xmx2g -XX:MaxPermSize=512M -XX:ReservedCodeCacheSize=512m"
 
 # Installs any application tarball given a URL, the expected tarball name,
 # and, optionally, a checkable binary path to determine if the binary has
@@ -34,14 +36,14 @@ 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
@@ -136,14 +138,15 @@ cd "${_CALLING_DIR}"
 # Now that zinc is ensured to be installed, check its status and, if its
 # not running or just installed, start it
 if [ -n "${ZINC_INSTALL_FLAG}" -o -z "`${ZINC_BIN} -status`" ]; then
+  export ZINC_OPTS=${ZINC_OPTS:-"$_COMPILE_JVM_OPTS"}
   ${ZINC_BIN} -shutdown
   ${ZINC_BIN} -start -port ${ZINC_PORT} \
     -scala-compiler "${SCALA_COMPILER}" \
     -scala-library "${SCALA_LIBRARY}" &>/dev/null
 fi
 
 # Set any `mvn` options if not already present
-export MAVEN_OPTS=${MAVEN_OPTS:-"-Xmx2g -XX:MaxPermSize=512M -XX:ReservedCodeCacheSize=512m"}
+export MAVEN_OPTS=${MAVEN_OPTS:-"$_COMPILE_JVM_OPTS"}
 
 # Last, call the `mvn` command as usual
 ${MVN_BIN} "$@"

build/sbt

@@ -125,4 +125,32 @@ loadConfigFile() {
 [[ -f "$etc_sbt_opts_file" ]] && set -- $(loadConfigFile "$etc_sbt_opts_file") "$@"
 [[ -f "$sbt_opts_file" ]] && set -- $(loadConfigFile "$sbt_opts_file") "$@"
 
+exit_status=127
+saved_stty=""
+
+restoreSttySettings() {
+  stty $saved_stty
+  saved_stty=""
+}
+
+onExit() {
+  if [[ "$saved_stty" != "" ]]; then
+    restoreSttySettings
+  fi
+  exit $exit_status
+}
+
+saveSttySettings() {
+  saved_stty=$(stty -g 2>/dev/null)
+  if [[ ! $? ]]; then
+    saved_stty=""
+  fi
+}
+
+saveSttySettings
+trap onExit INT
+
 run "$@"
+
+exit_status=$?
+onExit

build/sbt-launch-lib.bash

@@ -81,7 +81,7 @@ execRunner () {
     echo ""
   }
 
-  exec "$@"
+  "$@"
 }
 
 addJava () {

conf/metrics.properties.template

@@ -122,6 +122,15 @@
 
 #worker.sink.csv.unit=minutes
 
+# Enable Slf4jSink for all instances by class name
+#*.sink.slf4j.class=org.apache.spark.metrics.sink.Slf4jSink
+
+# Polling period for Slf4JSink
+#*.sink.sl4j.period=1
+
+#*.sink.sl4j.unit=minutes
+
+
 # Enable jvm source for instance master, worker, driver and executor
 #master.source.jvm.class=org.apache.spark.metrics.source.JvmSource
 

core/pom.xml

@@ -132,6 +132,13 @@
       <artifactId>jetty-servlet</artifactId>
       <scope>compile</scope>
     </dependency>
+    <!-- Because we mark jetty as provided and shade it, its dependency
+         orbit is ignored, so we explicitly list it here (see SPARK-5557).-->
+    <dependency>
+      <groupId>org.eclipse.jetty.orbit</groupId>
+      <artifactId>javax.servlet</artifactId>
+      <version>${orbit.version}</version>
+    </dependency>
 
     <dependency>
       <groupId>org.apache.commons</groupId>
@@ -236,6 +243,14 @@
       <groupId>io.dropwizard.metrics</groupId>
       <artifactId>metrics-graphite</artifactId>
     </dependency>
+    <dependency>
+      <groupId>com.fasterxml.jackson.core</groupId>
+      <artifactId>jackson-databind</artifactId>
+    </dependency>
+    <dependency>
+      <groupId>com.fasterxml.jackson.module</groupId>
+      <artifactId>jackson-module-scala_2.10</artifactId>
+    </dependency>
     <dependency>
       <groupId>org.apache.derby</groupId>
       <artifactId>derby</artifactId>
@@ -314,16 +329,6 @@
       <artifactId>scalacheck_${scala.binary.version}</artifactId>
       <scope>test</scope>
     </dependency>
-    <dependency>
-      <groupId>org.easymock</groupId>
-      <artifactId>easymockclassextension</artifactId>
-      <scope>test</scope>
-    </dependency>
-    <dependency>
-      <groupId>asm</groupId>
-      <artifactId>asm</artifactId>
-      <scope>test</scope>
-    </dependency>
     <dependency>
       <groupId>junit</groupId>
       <artifactId>junit</artifactId>