Author: lewismc Date: Sun Sep 20 12:54:49 2015 New Revision: 1704129 URL: http://svn.apache.org/viewvc?rev=1704129&view=rev Log: NUTCH-2050 Upgrade HBase and Hadoop versioning on 2.X HBase Docker
Modified: nutch/branches/2.x/docker/hbase/Dockerfile nutch/branches/2.x/docker/hbase/README.md Modified: nutch/branches/2.x/docker/hbase/Dockerfile URL: http://svn.apache.org/viewvc/nutch/branches/2.x/docker/hbase/Dockerfile?rev=1704129&r1=1704128&r2=1704129&view=diff ============================================================================== --- nutch/branches/2.x/docker/hbase/Dockerfile (original) +++ nutch/branches/2.x/docker/hbase/Dockerfile Sun Sep 20 12:54:49 2015 @@ -35,8 +35,8 @@ RUN echo oracle-java7-installer shared/a RUN apt-get install -y ant openssh-server zookeeperd vim telnet subversion rsync curl build-essential maven # Download Hadoop -RUN wget -q 'https://archive.apache.org/dist/hadoop/core/hadoop-2.4.0/hadoop-2.4.0.tar.gz' -RUN wget -q 'https://github.com/apache/hbase/archive/0.94.14.tar.gz' && mv 0.94.14.tar.gz hbase-0.94.14.tar.gz +RUN wget -q 'https://archive.apache.org/dist/hadoop/core/hadoop-2.5.1/hadoop-2.5.1.tar.gz' +RUN wget -q 'http://archive.apache.org/dist/hbase/hbase-0.98.8/hbase-0.98.8-hadoop2-bin.tar.gz' RUN wget -q 'https://protobuf.googlecode.com/files/protobuf-2.5.0.tar.gz' RUN svn checkout http://svn.apache.org/repos/asf/nutch/branches/2.x/ nutch-sources @@ -55,11 +55,11 @@ RUN chown hduser /home/hduser/.ssh/confi RUN sed -ri 's/session[[:blank:]]+required[[:blank:]]+pam_loginuid.so/session optional pam_loginuid.so/g' /etc/pam.d/sshd # Deploy and setup file permissions -RUN tar xvfz /root/hadoop-2.4.0.tar.gz -C /opt && \ - ln -s /opt/hadoop-2.4.0 /opt/hadoop && \ - chown -R root:root /opt/hadoop-2.4.0 && \ - mkdir /opt/hadoop-2.4.0/logs && \ - chown -R hduser:hadoop /opt/hadoop-2.4.0/logs +RUN tar xvfz /root/hadoop-2.5.1.tar.gz -C /opt && \ + ln -s /opt/hadoop-2.5.1 /opt/hadoop && \ + chown -R root:root /opt/hadoop-2.5.1 && \ + mkdir /opt/hadoop-2.5.1/logs && \ + chown -R hduser:hadoop /opt/hadoop-2.5.1/logs # Unpack and compile Google protobuf RUN tar xvfz /root/protobuf-2.5.0.tar.gz -C /opt && \ @@ -67,14 +67,11 @@ RUN tar xvfz /root/protobuf-2.5.0.tar.gz RUN cd /opt/protobuf-2.5.0 && ./configure && make && make check && make install # Deploy and setup file permissions -RUN tar xvfz /root/hbase-0.94.14.tar.gz -C /opt && \ - chown -R root:root /opt/hbase-0.94.14 -# http://hbase.apache.org/book.html#basic.prerequisites - 4.1.1 - HBase has to be compiled from sources :( -RUN vim -c '%s/2.4.0a/2.5.0/g' -c '%s/2.0.0-alpha/2.4.0' -c 'x' /opt/hbase-0.94.14/pom.xml -RUN cd /opt/hbase-0.94.14/ && mvn clean install assembly:single -Dhadoop.profile=2.0 -DskipTests +RUN tar xvfz /root/hbase-0.98.8-hadoop2-bin.tar.gz -C /opt && \ + chown -R root:root /opt/hbase-0.98.8-hadoop2 # link binaries, create logs directory -RUN ln -s /opt/hbase-0.94.14/target/hbase-0.94.14/hbase-0.94.14 /opt/hbase && mkdir /opt/hbase/logs && \ +RUN ln -s /opt/hbase-0.98.8-hadoop2 /opt/hbase && mkdir /opt/hbase/logs && \ chown -R hduser:hadoop /opt/hbase/logs # Deploy and setup file permissions Modified: nutch/branches/2.x/docker/hbase/README.md URL: http://svn.apache.org/viewvc/nutch/branches/2.x/docker/hbase/README.md?rev=1704129&r1=1704128&r2=1704129&view=diff ============================================================================== --- nutch/branches/2.x/docker/hbase/README.md (original) +++ nutch/branches/2.x/docker/hbase/README.md Sun Sep 20 12:54:49 2015 @@ -1,6 +1,6 @@ # Nutch Dockerfile # -This directory contains Dockerfile of [Nutch](http://nutch.apache.org) for [Docker](https://www.docker.com/)'s [automated build](https://registry.hub.docker.com/u/dockerfile/elasticsearch/) published to the [Hub Registry](https://registry.hub.docker.com/). +This directory contains a Dockerfile of [Nutch 2.X](http://nutch.apache.org) for [Docker](https://www.docker.com/). ## What is Nutch? @@ -14,9 +14,9 @@ Nutch can run on a single machine, but g Current configuration of this image consists of components: -* Hadoop 2.4.0 -* HBase 0.94.14 -* Nutch 2.x +* Apache Hadoop 2.5.1 +* Apache HBase 0.98.8-hadoop2 +* Apache Nutch 2.X HEAD (this will ensure that you are always running off of bleeding edge) ## Base Image @@ -57,3 +57,7 @@ Review configuration in /opt/nutch/conf/ /opt/nutch/bin/nutch parse <batchId> /opt/nutch/bin/nutch updatedb <batchId> [...] + +## Resources + +For more information on Nutch 2.X please see the [tutorials](http://wiki.apache.org/nutch/#Nutch_2.X_tutorial.28s.29) and [Nutch 2.X wiki space](http://wiki.apache.org/nutch/#Nutch_2.x).