Merge pull request #115 from parente/spark-1.6.0-toree

Bump to Spark 1.6.0 with Apache Toree

all-spark-notebook/Dockerfile

@@ -10,11 +10,15 @@ USER root
 RUN apt-get -y update && apt-get -y install jq
 
 # Spark dependencies
-ENV APACHE_SPARK_VERSION 1.5.1
+ENV APACHE_SPARK_VERSION 1.6.0
 RUN apt-get -y update && \
     apt-get install -y --no-install-recommends openjdk-7-jre-headless && \
     apt-get clean
-RUN wget -qO - http://d3kbcqa49mib13.cloudfront.net/spark-${APACHE_SPARK_VERSION}-bin-hadoop2.6.tgz | tar -xz -C /usr/local/
+RUN cd /tmp && \
+        wget -q http://d3kbcqa49mib13.cloudfront.net/spark-${APACHE_SPARK_VERSION}-bin-hadoop2.6.tgz && \
+        echo "439fe7793e0725492d3d36448adcd1db38f438dd1392bffd556b58bb9a3a2601 *spark-${APACHE_SPARK_VERSION}-bin-hadoop2.6.tgz" | sha256sum -c - && \
+        tar xzf spark-${APACHE_SPARK_VERSION}-bin-hadoop2.6.tgz -C /usr/local && \
+        rm spark-${APACHE_SPARK_VERSION}-bin-hadoop2.6.tgz
 RUN cd /usr/local && ln -s spark-${APACHE_SPARK_VERSION}-bin-hadoop2.6 spark
 
 # Mesos dependencies
@@ -29,17 +33,18 @@ RUN apt-key adv --keyserver keyserver.ubuntu.com --recv E56151BF && \
 # Scala Spark kernel (build and cleanup)
 RUN cd /tmp && \
     echo deb http://dl.bintray.com/sbt/debian / > /etc/apt/sources.list.d/sbt.list && \
+    apt-key adv --keyserver keyserver.ubuntu.com --recv 99E82A75642AC823 && \
     apt-get update && \
-    git clone https://github.com/ibm-et/spark-kernel.git && \
+    git clone https://github.com/apache/incubator-toree.git && \
     apt-get install -yq --force-yes --no-install-recommends sbt && \
-    cd spark-kernel && \
-    git checkout 3905e47815 && \
+    cd incubator-toree && \
+    git checkout 846292233c && \
     make dist SHELL=/bin/bash && \
-    mv dist/spark-kernel /opt/spark-kernel && \
-    chmod +x /opt/spark-kernel && \
+    mv dist/toree-kernel /opt/toree-kernel && \
+    chmod +x /opt/toree-kernel && \
     rm -rf ~/.ivy2 && \
     rm -rf ~/.sbt && \
-    rm -rf /tmp/spark-kernel && \
+    rm -rf /tmp/incubator-toree && \
     apt-get remove -y sbt && \
     apt-get clean
 

all-spark-notebook/README.md

@@ -8,7 +8,7 @@
 * Scala 2.10.x
 * pyspark, pandas, matplotlib, scipy, seaborn, scikit-learn pre-installed for Python
 * ggplot2, rcurl preinstalled for R
-* Spark 1.5.1 for use in local mode or to connect to a cluster of Spark workers
+* Spark 1.6.0 for use in local mode or to connect to a cluster of Spark workers
 * Mesos client 0.22 binary that can communicate with a Mesos master
 * Unprivileged user `jovyan` (uid=1000, configurable, see options) in group `users` (gid=100) with ownership over `/home/jovyan` and `/opt/conda`
 * [tini](https://github.com/krallin/tini) as the container entrypoint and [start-notebook.sh](../minimal-notebook/start-notebook.sh) as the default command
@@ -106,8 +106,8 @@ conf = pyspark.SparkConf()
 # point to mesos master or zookeeper entry (e.g., zk://10.10.10.10:2181/mesos)
 conf.setMaster("mesos://10.10.10.10:5050")
 # point to spark binary package in HDFS or on local filesystem on all slave
-# nodes (e.g., file:///opt/spark/spark-1.5.1-bin-hadoop2.6.tgz)
-conf.set("spark.executor.uri", "hdfs://10.10.10.10/spark/spark-1.5.1-bin-hadoop2.6.tgz")
+# nodes (e.g., file:///opt/spark/spark-1.6.0-bin-hadoop2.6.tgz)
+conf.set("spark.executor.uri", "hdfs://10.10.10.10/spark/spark-1.6.0-bin-hadoop2.6.tgz")
 # set other options as desired
 conf.set("spark.executor.memory", "8g")
 conf.set("spark.core.connection.ack.wait.timeout", "1200")
@@ -139,10 +139,10 @@ library(SparkR)
 # point to mesos master or zookeeper entry (e.g., zk://10.10.10.10:2181/mesos)\
 # as the first argument
 # point to spark binary package in HDFS or on local filesystem on all slave
-# nodes (e.g., file:///opt/spark/spark-1.5.1-bin-hadoop2.6.tgz) in sparkEnvir
+# nodes (e.g., file:///opt/spark/spark-1.6.0-bin-hadoop2.6.tgz) in sparkEnvir
 # set other options in sparkEnvir
 sc <- sparkR.init("mesos://10.10.10.10:5050", sparkEnvir=list(
-    spark.executor.uri="hdfs://10.10.10.10/spark/spark-1.5.1-bin-hadoop2.6.tgz",
+    spark.executor.uri="hdfs://10.10.10.10/spark/spark-1.6.0-bin-hadoop2.6.tgz",
     spark.executor.memory="8g"
     )
 )
@@ -176,7 +176,7 @@ For instance, a kernel spec file with information about a Mesos master, Spark bi
         "--master=mesos://10.10.10.10:5050"
     ],
     "env": {
-        "SPARK_CONFIGURATION": "spark.executor.memory=8g,spark.executor.uri=hdfs://10.10.10.10/spark/spark-1.5.1-bin-hadoop2.6.tgz"
+        "SPARK_CONFIGURATION": "spark.executor.memory=8g,spark.executor.uri=hdfs://10.10.10.10/spark/spark-1.6.0-bin-hadoop2.6.tgz"
     }
 }
 ```

all-spark-notebook/kernel.json

 {
-    "display_name": "Scala 2.10.4",
+    "display_name": "Apache Toree (Scala 2.10.4)",
     "language": "scala",
     "argv": [
-        "/opt/spark-kernel/bin/spark-kernel",
+        "/opt/toree-kernel/bin/toree-kernel",
         "--profile",
         "{connection_file}"
     ]
-}
+}
\ No newline at end of file

pyspark-notebook/Dockerfile

@@ -10,11 +10,15 @@ USER root
 RUN apt-get -y update && apt-get -y install jq
 
 # Spark dependencies
-ENV APACHE_SPARK_VERSION 1.5.1
+ENV APACHE_SPARK_VERSION 1.6.0
 RUN apt-get -y update && \
     apt-get install -y --no-install-recommends openjdk-7-jre-headless && \
     apt-get clean
-RUN wget -qO - http://d3kbcqa49mib13.cloudfront.net/spark-${APACHE_SPARK_VERSION}-bin-hadoop2.6.tgz | tar -xz -C /usr/local/
+RUN cd /tmp && \
+        wget -q http://d3kbcqa49mib13.cloudfront.net/spark-${APACHE_SPARK_VERSION}-bin-hadoop2.6.tgz && \
+        echo "439fe7793e0725492d3d36448adcd1db38f438dd1392bffd556b58bb9a3a2601 *spark-${APACHE_SPARK_VERSION}-bin-hadoop2.6.tgz" | sha256sum -c - && \
+        tar xzf spark-${APACHE_SPARK_VERSION}-bin-hadoop2.6.tgz -C /usr/local && \
+        rm spark-${APACHE_SPARK_VERSION}-bin-hadoop2.6.tgz
 RUN cd /usr/local && ln -s spark-${APACHE_SPARK_VERSION}-bin-hadoop2.6 spark
 
 # Mesos dependencies

pyspark-notebook/README.md

@@ -5,7 +5,7 @@
 * Jupyter Notebook 4.1.x
 * Conda Python 3.x and Python 2.7.x environments
 * pyspark, pandas, matplotlib, scipy, seaborn, scikit-learn pre-installed
-* Spark 1.5.1 for use in local mode or to connect to a cluster of Spark workers
+* Spark 1.6.0 for use in local mode or to connect to a cluster of Spark workers
 * Mesos client 0.22 binary that can communicate with a Mesos master
 * Unprivileged user `jovyan` (uid=1000, configurable, see options) in group `users` (gid=100) with ownership over `/home/jovyan` and `/opt/conda`
 * [tini](https://github.com/krallin/tini) as the container entrypoint and [start-notebook.sh](../minimal-notebook/start-notebook.sh) as the default command
@@ -64,8 +64,8 @@ conf = pyspark.SparkConf()
 # point to mesos master or zookeeper entry (e.g., zk://10.10.10.10:2181/mesos)
 conf.setMaster("mesos://10.10.10.10:5050")
 # point to spark binary package in HDFS or on local filesystem on all slave
-# nodes (e.g., file:///opt/spark/spark-1.5.1-bin-hadoop2.6.tgz)
-conf.set("spark.executor.uri", "hdfs://10.122.193.209/spark/spark-1.5.1-bin-hadoop2.6.tgz")
+# nodes (e.g., file:///opt/spark/spark-1.6.0-bin-hadoop2.6.tgz)
+conf.set("spark.executor.uri", "hdfs://10.122.193.209/spark/spark-1.6.0-bin-hadoop2.6.tgz")
 # set other options as desired
 conf.set("spark.executor.memory", "8g")
 conf.set("spark.core.connection.ack.wait.timeout", "1200")