Centos 6.4 x64 Vagrant box with Hadoop and dependencies (Java, yum)

Author: CodeMangler

.gitignore

@@ -0,0 +1,5 @@
+.DS_Store
+.vagrant
+cookbooks/*
+tmp
+

Cheffile

@@ -0,0 +1,8 @@
+#!/usr/bin/env ruby
+#^syntax detection
+
+site 'http://community.opscode.com/api/v1'
+
+cookbook 'yum'
+cookbook 'java'
+cookbook 'cdh', :path => 'site-cookbooks/cdh'

Cheffile.lock

@@ -0,0 +1,16 @@
+SITE
+  remote: http://community.opscode.com/api/v1
+  specs:
+    java (1.22.0)
+    yum (3.2.0)
+
+PATH
+  remote: site-cookbooks/cdh
+  specs:
+    cdh (0.1.0)
+
+DEPENDENCIES
+  cdh (>= 0)
+  java (>= 0)
+  yum (>= 0)
+

Vagrantfile

@@ -0,0 +1,36 @@
+Vagrant.configure('2') do |config|
+  config.vm.box = 'centos6.4'
+  config.vm.box_url = 'http://developer.nrel.gov/downloads/vagrant-boxes/CentOS-6.4-x86_64-v20130309.box'
+  config.vm.synced_folder '.', '/home/vagrant/cdh'
+
+  config.vm.define :cdh do |cdh|
+    public_ip = "10.201.112.42"
+
+    cdh.vm.network :private_network, ip: public_ip
+    cdh.vm.hostname = "cdh.local"
+
+    cdh.vm.provider :virtualbox do |vb|
+      vb.name = "cdh"
+      vb.customize ["modifyvm", :id, "--memory", 1024]
+    end
+
+    cdh.vm.provision :chef_solo do |chef|
+      chef.cookbooks_path = "cookbooks"
+      chef.add_recipe "yum"
+      chef.add_recipe "java"
+      chef.add_recipe "cdh"
+
+      chef.log_level = :debug
+
+      chef.json = {
+        java:{
+          install_flavor: "oracle",
+          jdk_version: "7",
+          oracle: {
+            accept_oracle_download_terms: true
+          }
+        }
+      }
+    end
+  end
+end

site-cookbooks/cdh/attributes/defaults.rb

@@ -0,0 +1,3 @@
+default[:cdh] = {
+  public_ip: '127.0.0.1',
+}

site-cookbooks/cdh/metadata.rb

@@ -0,0 +1,4 @@
+maintainer       "CodeMangler"
+maintainer_email "hsdpal@gmail.com"
+description      "Installs/Configures CDH5 (Hadoop and misc)"
+version          "0.1"

site-cookbooks/cdh/recipes/default.rb

@@ -0,0 +1,23 @@
+## Cookbook Name:: freeswitch
+## Recipe:: default
+##
+
+## Build requirements
+package 'git-core'
+package 'rpm-build'
+
+template '/etc/yum.repos.d/cdh5.repo' do
+  source 'cdh5.repo.erb'
+end
+
+%w(hadoop-yarn-resourcemanager hadoop-hdfs-namenode hadoop-yarn-nodemanager hadoop-hdfs-datanode hadoop-mapreduce hadoop-mapreduce-historyserver hadoop-yarn-proxyserver hadoop-client).each do |pkg|
+  package pkg do
+    action :upgrade
+  end  
+end
+
+%w(hadoop-0.20-mapreduce-jobtracker hadoop-0.20-mapreduce-tasktracker hadoop-hdfs-datanode).each do |pkg|
+  package pkg do
+    action :upgrade
+  end  
+end

site-cookbooks/cdh/templates/default/cdh5.repo.erb

@@ -0,0 +1,6 @@
+[cloudera-cdh5]
+# Packages for Cloudera's Distribution for Hadoop, Version 5, on RedHat	or CentOS 6 x86_64
+name=Cloudera's Distribution for Hadoop, Version 5
+baseurl=http://archive.cloudera.com/cdh5/redhat/6/x86_64/cdh/5/
+gpgkey = http://archive.cloudera.com/cdh5/redhat/6/x86_64/cdh/RPM-GPG-KEY-cloudera    
+gpgcheck = 1