Quick Vagrant machine with Hadoop & Spark using Ansible

playbook.yml

---
  - name: Spark Development in a Box
    hosts: all
    become: yes
    become_method: sudo
    become_user: root
    gather_facts: no

    pre_tasks:
      - name: 'install python2'
        raw: sudo apt-get -y install python-simplejson

    tasks:
      - name: Update and upgrade apt packages
        apt:
          update_cache: yes

      - name: Install latest version of "openjdk-8-jdk" no "install-recommends"
        apt:
          name: openjdk-8-jdk
          state: latest
          install_recommends: no

      - name: Download Hadoop with Spark
        get_url:
          url: http://d3kbcqa49mib13.cloudfront.net/spark-2.2.0-bin-hadoop2.7.tgz
          dest: /home/vagrant

      - name: Untar Hadoop with Spark
        shell: cd /home/vagrant; tar -zxf spark-2.2.0-bin-hadoop2.7.tgz

Vagrantfile

Vagrant.configure("2") do |config|
  config.vm.box = "ubuntu/xenial64"
  config.vm.hostname = "spark.xenial.box"
  config.vm.network :private_network, ip: "192.168.0.42"

  config.vm.synced_folder "./data", "/vagrant_data"

  config.vm.provider "virtualbox" do |vb|
    vb.gui = false
    vb.memory = 4096
    vb.cpus = 2
  end

  config.vm.provision "ansible" do |ansible|
    ansible.playbook = "playbook.yml"
  end
end