1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
|
#!/bin/bash
# Here do anything needed to install the service
# i.e. apt-get install -y foo or bzr branch http://myserver/mycode /srv/webroot
set -x
ensemble-log "install script"
export TERM=linux
# Add the Hadoop PPA
ensemble-log "Adding ppa"
apt-add-repository ppa:canonical-sig/thirdparty
ensemble-log "updating cache"
apt-get update
# Calculate our IP Address
ensemble-log "calculating ip"
IP_ADDRESS=`curl http://169.254.169.254/latest/meta-data/local-ipv4`
PUBLIC_DNS=`curl http://169.254.169.254/latest/meta-data/public-hostname`
ensemble-log "Private IP: ${IP_ADDRESS}"
ensemble-log "Public DNS: ${PUBLIC_DNS}"
# Preseed our Namenode, Jobtracker and HDFS Data directory
NAMENODE=${IP_ADDRESS}
JOBTRACKER=${IP_ADDRESS}
HDFSDATADIR="/var/lib/hadoop-0.20/dfs/data"
ensemble-log "Namenode: ${NAMENODE}"
ensemble-log "Jobtracker: ${JOBTRACKER}"
ensemble-log "HDFS Dir: ${HDFSDATADIR}"
echo debconf hadoop/namenode string ${NAMENODE}| /usr/bin/debconf-set-selections
echo debconf hadoop/jobtracker string ${JOBTRACKER}| /usr/bin/debconf-set-selections
echo debconf hadoop/hdfsdatadir string ${HDFSDATADIR}| /usr/bin/debconf-set-selections
# Install the packages
ensemble-log "installing packages"
apt-get install -y hadoop-0.20-namenode hadoop-0.20-jobtracker
# This is where we start praying that everything is working :)
ensemble-log "Point your browser to http://${public-hostname}:50070"
|