hadoop.sh

# Add Cloudera repositories
sudo sh -c 'echo "deb http://archive.cloudera.com/debian `lsb_release -c -s`-cdh3 contrib" > /etc/apt/sources.list.d/cloudera.list'
sudo sh -c 'echo "deb-src http://archive.cloudera.com/debian `lsb_release -c -s`-cdh3 contrib" >> /etc/apt/sources.list.d/cloudera.list'
wget -q -O - http://archive.cloudera.com/debian/archive.key | sudo apt-key add -
sudo apt-get update
sudo apt-get -y install hadoop

# Install Hue
sudo apt-get -y install hadoop-0.20-conf-pseudo-hue

# Install Sqoop
sudo apt-get -y install sqoop

# Install Hive (already installed by Hue but sqoop needs the "hive" command which is missing)
sudo apt-get -y install hadoop-hive
sudo -u postgres createuser -S -D -R -P hive
sudo -u postgres createdb -O hive hive
# Next step is to configure /etc/hive/conf/hive-site.xml to use a database (PostgreSQL) as a metastore
# See here for instructions: http://wiki.apache.org/hadoop/Hive/AdminManual/MetastoreAdmin#Local_Metastore
# and change hive_conf_dir /etc/hue/hue-beeswax.ini to hive_conf_dir=/etc/hive/conf
# This assumes you used 'hive' as the password for the hive PostgreSQL account
wget http://gist.github.com/raw/485836/512357fef1be0ac9cf8596770939355fc61a4d1c/hive-site.xml
sudo mv hive-site.xml /etc/hive/conf
sudo chown root:root /etc/hive/conf/hive-site.xml
wget http://gist.github.com/raw/485836/e32b00bc69744509123ef584be226328c37ccf77/hue-beeswax.ini
sudo mv hue-beeswax.ini /etc/hue

# Now we have to download and install the PostgreSQL JDBC driver for Sqoop
wget http://jdbc.postgresql.org/download/postgresql-8.4-701.jdbc4.jar
sudo mv postgresql-8.4-701.jdbc4.jar /usr/lib/hadoop-0.20/lib/
sudo chown -R hadoop:hadoop /usr/lib/hadoop-0.20/lib/postgresql-8.4-701.jdbc4.jar

# Start Hadoop
# Web interfaces on ports 50070 (HDFS), 50030 (Map/Reduce) and 8088 (Hue)
for x in /etc/init.d/hadoop-0.20-*; do sudo $x start; done
sudo /etc/init.d/hue start