Ansible playbook for GPU nodes

master-playbook.yml

---
- hosts: all
  vars:
    ansible_connect_timeout: 300
  become: true
  tasks:
    - name: Update and upgrade apt packages
      apt:
        update_cache: yes
        upgrade: yes

    - name: Install packages that allow apt to be used over HTTPS
      apt:
        name: "{{ packages }}"
        state: present
        update_cache: yes
      vars:
        packages:
        - apt-transport-https
        - ca-certificates
        - curl
        - gnupg-agent
        - software-properties-common
    
    - name: Install build-essential package
      apt:
        name: "{{ packages }}"
        state: present
        update_cache: yes
      vars:
        packages:
        - build-essential
    
    - name: Add a pin for cuda driver
      get_url:
        url: https://developer.download.nvidia.com/compute/cuda/repos/ubuntu1804/x86_64/cuda-ubuntu1804.pin
        dest: /etc/apt/preferences.d/cuda-ubuntu1804.pin
        mode: '0644'
    
    - name: Install a cuda driver repository
      apt:
        deb: http://developer.download.nvidia.com/compute/cuda/10.2/Prod/local_installers/cuda-repo-ubuntu1804-10-2-local-10.2.89-440.33.01_1.0-1_amd64.deb

    - name: Add an apt signing key for cuda driver
      apt_key:
        file: /var/cuda-repo-10-2-local-10.2.89-440.33.01/7fa2af80.pub
        state: present

    - name: Install the cuda drivers
      apt:
        name: cuda-drivers
        state: present
        update_cache: yes

    - name: Add an apt signing key for Docker
      apt_key:
        url: https://download.docker.com/linux/ubuntu/gpg
        state: present

    - name: Add apt repository for stable version
      apt_repository:
        repo: deb [arch=amd64] https://download.docker.com/linux/ubuntu focal stable
        state: present

    - name: Install docker and its dependecies
      apt: 
        name: "{{ packages }}"
        state: present
        update_cache: yes
      vars:
        packages:
        - docker-ce 
        - docker-ce-cli 
        - containerd.io
      notify:
        - docker status

    - name: Add vagrant user to docker group
      user:
        name: vagrant
        group: docker

    - name: Reboot
      reboot:
        
    - name: Add an apt signing key for NVIDIA Docker
      apt_key:
        url: https://nvidia.github.io/nvidia-docker/gpgkey
        state: present

    - name: Add NVidia-Docker repository source
      get_url:
        url: https://nvidia.github.io/nvidia-docker/{{ hostvars[inventory_hostname].ansible_distribution | lower }}{{ hostvars[inventory_hostname].ansible_distribution_version }}/nvidia-docker.list
        dest: /etc/apt/sources.list.d/nvidia-docker.list
        mode: '0644'

    - name: Install nvidia-docker2
      apt:
        name: nvidia-container-toolkit
        state: present
        update_cache: yes

    - name: Reload Docker daemon
      systemd:
        name: docker
        state: reloaded

  #   - name: Remove swapfile from /etc/fstab
  #     mount:
  #       name: "{{ item }}"
  #       fstype: swap
  #       state: absent
  #     with_items:
  #       - swap
  #       - none

  #   - name: Disable swap
  #     command: swapoff -a
  #     when: ansible_swaptotal_mb > 0

  #   - name: Add an apt signing key for Kubernetes
  #     apt_key:
  #       url: https://packages.cloud.google.com/apt/doc/apt-key.gpg
  #       state: present

  #   - name: Adding apt repository for Kubernetes
  #     apt_repository:
  #       repo: deb https://apt.kubernetes.io/ kubernetes-xenial main
  #       state: present
  #       filename: kubernetes.list

  #   - name: Install Kubernetes binaries
  #     apt: 
  #       name: "{{ packages }}"
  #       state: present
  #       update_cache: yes
  #     vars:
  #       packages:
  #         - kubelet 
  #         - kubeadm 
  #         - kubectl

  #   - name: Configure node ip
  #     lineinfile:
  #       create: yes
  #       path: /etc/default/kubelet
  #       line: KUBELET_EXTRA_ARGS=--node-ip={{ node_ip }}

  #   - name: Restart kubelet
  #     service:
  #       name: kubelet
  #       daemon_reload: yes
  #       state: restarted

  #   - name: Initialize the Kubernetes cluster using kubeadm
  #     command: kubeadm init --apiserver-advertise-address="192.168.50.10" --apiserver-cert-extra-sans="192.168.50.10" --node-name k8s-master --pod-network-cidr=192.168.0.0/16

  #   - name: Setup kubeconfig for vagrant user
  #     command: "{{ item }}"
  #     with_items:
  #     - mkdir -p /home/vagrant/.kube
  #     - cp -i /etc/kubernetes/admin.conf /home/vagrant/.kube/config
  #     - chown vagrant:vagrant /home/vagrant/.kube/config

  #   - name: Install calico pod network
  #     become: false
  #     command: kubectl apply -f https://docs.projectcalico.org/manifests/calico.yaml

  #   - name: Generate join command
  #     command: kubeadm token create --print-join-command
  #     register: join_command

  #   - name: Copy join command to local file
  #     become: false
  #     local_action: copy content="{{ join_command.stdout_lines[0] }}" dest="./join-command"
    
  #   - name: Add an apt signing key for helm
  #     apt_key:
  #       url: https://helm.baltorepo.com/organization/signing.asc
  #       state: present

  #   - name: Install apt-transport-https
  #     apt: 
  #       name: apt-transport-https
  #       state: present
  #       update_cache: yes
    
  #   - name: Adding apt repository for helm
  #     apt_repository:
  #       repo: deb https://baltocdn.com/helm/stable/debian/ all main
  #       state: present
  #       filename: helm-stable-debian.list

  #   - name: Install helm
  #     apt: 
  #       name: helm
  #       state: present
  #       update_cache: yes
    
  #   - name: Copy admin.conf to /vagrant/k8s-setup
  #     copy:
  #       src: /etc/kubernetes/admin.conf
  #       dest: /vagrant/k8s-setup/admin.conf
  #       mode: 0644

  handlers:
    - name: docker status
      service: name=docker state=started