From 4ede488cda468c809ac44ecf3dfa8ddfb288962b Mon Sep 17 00:00:00 2001 From: Michael Mior Date: Sun, 12 Mar 2017 16:03:36 -0400 Subject: [PATCH 1/3] Update to Spark 2.0.0 --- Dockerfile | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/Dockerfile b/Dockerfile index 7fbcaf0..586e729 100644 --- a/Dockerfile +++ b/Dockerfile @@ -1,14 +1,14 @@ -FROM sequenceiq/hadoop-docker:2.6.0 +FROM sequenceiq/hadoop-docker:2.7.0 MAINTAINER SequenceIQ -#support for Hadoop 2.6.0 -RUN curl -s http://d3kbcqa49mib13.cloudfront.net/spark-1.6.1-bin-hadoop2.6.tgz | tar -xz -C /usr/local/ -RUN cd /usr/local && ln -s spark-1.6.1-bin-hadoop2.6 spark +#support for Hadoop 2.7.0 +RUN curl -s http://d3kbcqa49mib13.cloudfront.net/spark-2.0.0-bin-hadoop2.7.tgz | tar -xz -C /usr/local/ +RUN cd /usr/local && ln -s spark-2.0.0-bin-hadoop2.7 spark ENV SPARK_HOME /usr/local/spark RUN mkdir $SPARK_HOME/yarn-remote-client ADD yarn-remote-client $SPARK_HOME/yarn-remote-client -RUN $BOOTSTRAP && $HADOOP_PREFIX/bin/hadoop dfsadmin -safemode leave && $HADOOP_PREFIX/bin/hdfs dfs -put $SPARK_HOME-1.6.1-bin-hadoop2.6/lib /spark +RUN $BOOTSTRAP && $HADOOP_PREFIX/bin/hadoop dfsadmin -safemode leave && $HADOOP_PREFIX/bin/hdfs dfs -put $SPARK_HOME-2.0.0-bin-hadoop2.7/jars /spark ENV YARN_CONF_DIR $HADOOP_PREFIX/etc/hadoop ENV PATH $PATH:$SPARK_HOME/bin:$HADOOP_PREFIX/bin From 6d6f6272d209ca97c818e6c3837e71e59a1de3a3 Mon Sep 17 00:00:00 2001 From: Michael Mior Date: Sun, 12 Mar 2017 16:23:22 -0400 Subject: [PATCH 2/3] Update README with new versions --- README.md | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/README.md b/README.md index 7158578..f9f1b5b 100644 --- a/README.md +++ b/README.md @@ -10,12 +10,12 @@ The base Hadoop Docker image is also available as an official [Docker image](htt ##Pull the image from Docker Repository ``` -docker pull sequenceiq/spark:1.6.0 +docker pull sequenceiq/spark:2.0.0 ``` ## Building the image ``` -docker build --rm -t sequenceiq/spark:1.6.0 . +docker build --rm -t sequenceiq/spark:2.0.0 ``` ## Running the image @@ -24,16 +24,16 @@ docker build --rm -t sequenceiq/spark:1.6.0 . * in your /etc/hosts file add $(boot2docker ip) as host 'sandbox' to make it easier to access your sandbox UI * open yarn UI ports when running container ``` -docker run -it -p 8088:8088 -p 8042:8042 -p 4040:4040 -h sandbox sequenceiq/spark:1.6.0 bash +docker run -it -p 8088:8088 -p 8042:8042 -p 4040:4040 -h sandbox sequenceiq/spark:2.0.0 bash ``` or ``` -docker run -d -h sandbox sequenceiq/spark:1.6.0 -d +docker run -d -h sandbox sequenceiq/spark:2.0.0 -d ``` ## Versions ``` -Hadoop 2.6.0 and Apache Spark v1.6.0 on Centos +Hadoop 2.7.0 and Apache Spark v2.0.0 on Centos ``` ## Testing @@ -71,7 +71,7 @@ spark-submit \ --driver-memory 1g \ --executor-memory 1g \ --executor-cores 1 \ -$SPARK_HOME/lib/spark-examples-1.6.0-hadoop2.6.0.jar +$SPARK_HOME/lib/spark-examples-2.0.0-hadoop2.7.0.jar ``` Estimating Pi (yarn-client mode): @@ -84,7 +84,7 @@ spark-submit \ --driver-memory 1g \ --executor-memory 1g \ --executor-cores 1 \ -$SPARK_HOME/lib/spark-examples-1.6.0-hadoop2.6.0.jar +$SPARK_HOME/lib/spark-examples-2.0.0-hadoop2.7.0.jar ``` ### Submitting from the outside of the container From b359f70d3ee44493adfb0078cc0b787ce08d9d28 Mon Sep 17 00:00:00 2001 From: Michael Mior Date: Sun, 12 Mar 2017 16:41:38 -0400 Subject: [PATCH 3/3] Possible fix for YARN JAR path --- bootstrap.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/bootstrap.sh b/bootstrap.sh index c01eeda..da74a88 100755 --- a/bootstrap.sh +++ b/bootstrap.sh @@ -13,7 +13,7 @@ cd $HADOOP_PREFIX/share/hadoop/common ; for cp in ${ACP//,/ }; do echo == $cp; sed s/HOSTNAME/$HOSTNAME/ /usr/local/hadoop/etc/hadoop/core-site.xml.template > /usr/local/hadoop/etc/hadoop/core-site.xml # setting spark defaults -echo spark.yarn.jar hdfs:///spark/spark-assembly-1.6.0-hadoop2.6.0.jar > $SPARK_HOME/conf/spark-defaults.conf +echo spark.yarn.jar hdfs:///spark/spark-yarn_2.11-2.0.0.jar > $SPARK_HOME/conf/spark-defaults.conf cp $SPARK_HOME/conf/metrics.properties.template $SPARK_HOME/conf/metrics.properties service sshd start