Deploy Ansible with GitHub Actions

"Automate, customize, and execute your software development workflows right in your repository with GitHub Actions." Says the introduction on the GitHub Actions documentation page. How does this relate to Ansible? Ansible is code and because of that, you can build a workflow that deploys it based on Git events. Such as a push or pull request to the repository.

Create an Ansible Action

GitHub Actions are individual tasks that you combine to create jobs and customize workflows. Using a Docker container Action, you will create your own to run Ansible whenever you push or merge a pull request.

Create the Ansible Action directory.

mkdir .github/actions/ansible

Create a new Dockerfile.

FROM  <DockerHub-UserName>/ansible-in-containers

COPY ./entrypoint.sh /entrypoint.sh

ENTRYPOINT ["bash","/entrypoint.sh"]

Copy the entrypoint.sh script to the Ansible Action directory.

#BASH
Copy entrypoint.sh .github/actions/ansible

#POWERSHELL
Copy-Item entrypoint.sh .github/actions/ansible

Create the action.yml in the new directory.

name: 'Ansible'
description: 'Runs an Ansible playbook'
inputs:
  playbook:
    description: 'Ansible playbook to run'
    required: true
    default: playbook.yml
  inventory:
    description: 'Ansible inventory to use'
    required: true
    default: localhost
runs:
  using: 'docker'
  image: 'Dockerfile'
  args:
    - ${{ inputs.playbook }}
    - ${{ inputs.inventory }}

Name and description give context to what the action is and what it does. Inputs define the parameters used by the Docker container Action. The playbook and inventory are required inputs for this action because without them the entry point arguments would be empty and the ansible-command would fail to run. Each of the inputs also has a default value.

Within the runs section where the magic happens. Setting using to docker is what specifies the Action type as a Docker container Action. Setting the image to Dockerfile instructs the Action to use the Dockerfile local to the Action's directory to build the container used by the Action. Args then are passed in after the image is built and the Action runs the container.

Create the Workflow

Workflows are custom automated processes that allow you to orchestrate your build, test, and release. Using a workflow you will lint all your Ansible files, then run the Ansible Docker container Action.

Create the workflow directory

mkdir .github/workflows

Create the deploy_ansible.yml workflow file.

name: deploy ansible

on:
  push:
    branches:
    - master
  pull_request:
    branches:
    - master

jobs:
  build:
    runs-on: ubuntu-latest
    steps:
    - name: checkout repo
      uses: actions/checkout@v2
    - name: Lint Ansible Playbook
      uses: ansible/ansible-lint-action@master
      with:
        targets: ""
  deployAnsible:
    needs: build
    runs-on: ubuntu-latest
    steps:
    - uses: actions/checkout@v1
    - uses: ./.github/actions/ansible
      with: 
        playbook: playbook.yml
        inventory: localhost

The above will create a GitHub workflow named deploy Ansible. It will only be triggered when there is a push or pull request made to the master branch of the repository. Once triggered the workflow will kick-off two jobs. First, the build job runs. Build runs a public GitHub Action called ansible-lint which runs the ansible-lint command-line utility against all .yml or.yaml files in your repository. If ansible-lint is successful the second job is triggered. Running the Ansible Docker container action deployAnsible runs using the with values provided as arguments to the container. The container then runs the ansible-playbook command with the arguments specified in the with list.

Only one thing remains, push your changes. GitHub will detect the files within the .github directory and create the Actions and Workflow based on the .yml documents in the corresponding directories. Give it a minute or two, then your repository on GitHub.com, and review the action's results under the Actions tab.

Conclusion

You've now learned how to build, run, and deploy Ansible inside a Docker container. Containers are no longer something only developers use to run applications. It's also how sysadmins, DevOps engineers, and SREs deploy infrastructure as code. Using containers yourself you'll see the benefits first hand. Containers provide a consistent development experience for you, your team, and release pipelines, versioned images of your Ansible environment, increased portability, and flexibility. Containers are the future of infrastructure, not just web apps. Don't wait until you need to learn about them, start today, start now.

Read the full blog post, "Using Ansible in Containers" on duffney.io