# Use parameters passed in during launch to configure Hadoop
USER_DATA=`wget -q -O - http://169.254.169.254/1.0/user-data`
NO_INSTANCES=`python -c "print '$USER_DATA'.split(',')[0]"`
MASTER_HOST=`python -c "print '$USER_DATA'.split(',')[1]"`
HADOOP_HOME=`ls -d /usr/local/hadoop-*`
echo $NO_INSTANCES, $MASTER_HOST, $HADOOP_HOME
 
sed -i -e "s|# export HADOOP_MASTER=.*|export HADOOP_MASTER=$MASTER_HOST:$HADOOP_HOME|" \
    $HADOOP_HOME/conf/hadoop-env.sh
      
cat > $HADOOP_HOME/conf/hadoop-site.xml <<EOF
<?xml version="1.0"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>

<configuration>

<property>
  <name>hadoop.tmp.dir</name>
  <value>/mnt/hadoop</value>
</property>

<property>
  <name>fs.default.name</name>
  <value>$MASTER_HOST:50001</value>
</property>

<property>
  <name>mapred.job.tracker</name>
  <value>$MASTER_HOST:50002</value>
</property>

</configuration>
EOF

cat > $HADOOP_HOME/conf/mapred-default.xml <<EOF
<?xml version="1.0"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>

<configuration>

<property>
  <name>mapred.map.tasks</name>
  <value>$(( NO_INSTANCES * 10 ))</value>
</property>

<property>
  <name>mapred.reduce.tasks</name>
  <value>$(( NO_INSTANCES * 3 ))</value>
</property>

</configuration>
EOF