minor changes to use the latest spark binary - thanks

Dockerfile

@@ -1,5 +1,6 @@
 FROM ubuntu:14.04
 
+
 MAINTAINER Pakhomov Egor <[email protected]>
 
 RUN apt-get -y update
@@ -10,21 +11,40 @@ RUN /bin/echo debconf shared/accepted-oracle-license-v1-1 select true | /usr/bin
 RUN DEBIAN_FRONTEND=noninteractive apt-get -y install oracle-java7-installer oracle-java7-set-default
 
 RUN apt-get -y install curl
-RUN curl -s http://d3kbcqa49mib13.cloudfront.net/spark-1.3.0-bin-hadoop2.4.tgz | tar -xz -C /usr/local/
-RUN cd /usr/local && ln -s spark-1.3.0-bin-hadoop2.4 spark
+RUN apt-get -y update 
+RUN apt-get install -y python-numpy python-pandas
+RUN apt-get install -y python-pip
+RUN apt-get install -y libopenblas-dev liblapack-dev liblapacke-dev libatlas-base-dev libatlas-dev
+
+
+RUN pip install requests
+RUN pip install boto
+
+
+RUN curl -s http://d3kbcqa49mib13.cloudfront.net/spark-1.5.1-bin-hadoop2.6.tgz | tar -xz -C /usr/local/
+RUN cd /usr/local && ln -s spark-1.5.1-bin-hadoop2.6 spark
 ADD scripts/start-master.sh /start-master.sh
 ADD scripts/start-worker /start-worker.sh
+
 ADD scripts/spark-shell.sh  /spark-shell.sh
 ADD scripts/spark-defaults.conf /spark-defaults.conf
 ADD scripts/remove_alias.sh /remove_alias.sh
 ENV SPARK_HOME /usr/local/spark
 
+
+RUN cp $SPARK_HOME/conf/spark-env.sh.template $SPARK_HOME/conf/spark-env.sh 
+RUN /bin/echo "export SPARK_WORKER_INSTANCES=2" >> $SPARK_HOME/conf/spark-env.sh
+RUN ln -s $SPARK_HOME/sbin/start-slaves.sh /start-slaves.sh
+RUN ln -s $SPARK_HOME/sbin/start-slave.sh /start-slave.sh
+
+
 ENV SPARK_MASTER_OPTS="-Dspark.driver.port=7001 -Dspark.fileserver.port=7002 -Dspark.broadcast.port=7003 -Dspark.replClassServer.port=7004 -Dspark.blockManager.port=7005 -Dspark.executor.port=7006 -Dspark.ui.port=4040 -Dspark.broadcast.factory=org.apache.spark.broadcast.HttpBroadcastFactory"
 ENV SPARK_WORKER_OPTS="-Dspark.driver.port=7001 -Dspark.fileserver.port=7002 -Dspark.broadcast.port=7003 -Dspark.replClassServer.port=7004 -Dspark.blockManager.port=7005 -Dspark.executor.port=7006 -Dspark.ui.port=4040 -Dspark.broadcast.factory=org.apache.spark.broadcast.HttpBroadcastFactory"
 
 ENV SPARK_MASTER_PORT 7077
 ENV SPARK_MASTER_WEBUI_PORT 8080
 ENV SPARK_WORKER_PORT 8888
-ENV SPARK_WORKER_WEBUI_PORT 8081
+ENV SPARK_WORKER_WEBUI_PORT 9091
+
+EXPOSE 8080 7077 8888 9091 4040 7001 7002 7003 7004 7005 7006 
 
-EXPOSE 8080 7077 8888 8081 4040 7001 7002 7003 7004 7005 7006 

README.md

@@ -14,6 +14,10 @@ To run worker execute:
 ```
 ./start-worker.sh
 ```
+or start 2 slaves
+
+    $SPARK_HOME/sbin/start-slave.sh $SPARK_MASTER_IP:7077
+
 You can run multiple workers. Every worker would be able to find master by it's container name "spark_master".
 
 To run spark shell against this cluster execute:

scripts/spark-shell.sh

@@ -3,7 +3,7 @@ export SPARK_LOCAL_IP=`awk 'NR==1 {print $1}' /etc/hosts`
 /remove_alias.sh # problems with hostname alias, see https://issues.apache.org/jira/browse/SPARK-6680
 cd /usr/local/spark
 ./bin/spark-shell \
-	--master spark://${SPARK_MASTER_PORT_7077_TCP_ADDR}:${SPARK_MASTER_ENV_SPARK_MASTER_PORT}  \
+	--master spark://${SPARK_MASTER_IP}:${SPARK_MASTER_PORT}  \
 	-i ${SPARK_LOCAL_IP} \
 	--properties-file /spark-defaults.conf \
 	"$@" 

start-master.sh

@@ -1,3 +1,3 @@
 #!/usr/bin/env bash
-docker pull epahomov/docker-spark
-docker run -d -t -P --name spark_master epahomov/docker-spark /start-master.sh "$@"
+docker pull meyerson/docker-spark
+docker run -d -t -P --name spark_master meyerson/docker-spark /start-master.sh "$@"

start-worker.sh

@@ -1,3 +1,3 @@
 #!/usr/bin/env bash
-docker pull epahomov/docker-spark
-docker run -d -t -P --link spark_master:spark_master epahomov/docker-spark /start-worker.sh "$@"
+docker pull meyerson/docker-spark
+docker run -d -t -P --link spark_master:spark_master meyerson/docker-spark /start-worker.sh "$@"