Pre commit fixes (#167)

* chore(dependencies): updated kube-vip to 0.5.6

* fix(pre-commit): pin to hash

* fix(pre-commit): added more hooks and fixed lint

* fix(pre-commit): added pre-commit hook so we don't have to run it manually

* fix(pre-commit): Added docs to readme

* fix(pre-commit): added texthooks

* fix(pre-commit): pin to hash

* fix(pre-commit): added mor hooks and fixed lint

* fix(lint): Fixing quotes

* fix(ci): only run test if linting passes

* fix(ci): convert to reusable workflows

* fix(pr template): Reorder steps

.ansible-lint

@@ -1,3 +1,17 @@
 ---
+exclude_paths:
+  # default paths
+  - '.cache/'
+  - '.github/'
+  - 'test/fixtures/formatting-before/'
+  - 'test/fixtures/formatting-prettier/'
+
+  # The "converge" and "reset" playbooks use import_playbook in
+  # conjunction with the "env" lookup plugin, which lets the
+  # syntax check of ansible-lint fail.
+  - 'molecule/**/converge.yml'
+  - 'molecule/**/prepare.yml'
+  - 'molecule/**/reset.yml'
+
 skip_list:
   - 'fqcn-builtins'

.editorconfig

@@ -0,0 +1,13 @@
+root = true
+[*]
+indent_style = space
+indent_size = 2
+charset = utf-8
+trim_trailing_whitespace = true
+insert_final_newline = true
+end_of_line = lf
+max_line_length = off
+[Makefile]
+indent_style = tab
+[*.go]
+indent_style = tab

.github/PULL_REQUEST_TEMPLATE.md

@@ -11,4 +11,5 @@
 - [ ] Ran `site.yml` playbook
 - [ ] Ran `reset.yml` playbook
 - [ ] Did not add any unnecessary changes
+- [ ] Ran pre-commit install at least once before committing
 - [ ] 🚀

.github/dependabot.yml

@@ -0,0 +1,11 @@
+---
+version: 2
+updates:
+  - package-ecosystem: "pip"
+    directory: "/"
+    schedule:
+      interval: "daily"
+    rebase-strategy: "auto"
+    ignore:
+      - dependency-name: "*"
+        update-types: ["version-update:semver-major"]

.github/download-boxes.sh

@@ -0,0 +1,37 @@
+#!/bin/bash
+
+# download-boxes.sh
+# Check all molecule.yml files for required Vagrant boxes and download the ones that are not
+# already present on the system.
+
+set -euo pipefail
+
+GIT_ROOT=$(git rev-parse --show-toplevel)
+PROVIDER=virtualbox
+
+# Read all boxes for all platforms from the "molecule.yml" files
+all_boxes=$(cat "${GIT_ROOT}"/molecule/*/molecule.yml |
+    yq -r '.platforms[].box' |         # Read the "box" property of each node under "platforms"
+    grep --invert-match --regexp=--- | # Filter out file separators
+    sort |
+    uniq)
+
+# Read the boxes that are currently present on the system (for the current provider)
+present_boxes=$(
+    (vagrant box list |
+        grep "${PROVIDER}" | # Filter by boxes available for the current provider
+        awk '{print $1;}' |  # The box name is the first word in each line
+        sort |
+        uniq) ||
+        echo "" # In case any of these commands fails, just use an empty list
+)
+
+# The boxes that we need to download are the ones present in $all_boxes, but not $present_boxes.
+download_boxes=$(comm -2 -3 <(echo "${all_boxes}") <(echo "${present_boxes}"))
+
+# Actually download the necessary boxes
+if [ -n "${download_boxes}" ]; then
+    echo "${download_boxes}" | while IFS= read -r box; do
+        vagrant box add --provider "${PROVIDER}" "${box}"
+    done
+fi

.github/workflows/ci.yml

@@ -0,0 +1,15 @@
+---
+name: "CI"
+on:
+  pull_request:
+  push:
+    branches:
+      - master
+    paths-ignore:
+      - '**/README.md'
+jobs:
+  lint:
+    uses: ./.github/workflows/lint.yml
+  test:
+    uses: ./.github/workflows/test.yml
+    needs: [lint]

.github/workflows/lint.yml

@@ -1,31 +1,68 @@
 ---
-name: Lint
-'on':
-  pull_request:
-  push:
-    branches:
-      - master
-
+name: Linting
+on:
+  workflow_call:
 jobs:
-
-  test:
-    name: Lint
+  pre-commit-ci:
+    name: Pre-Commit
     runs-on: ubuntu-latest
+    env:
+      PYTHON_VERSION: "3.10"
 
     steps:
-      - name: Check out the codebase.
-        uses: actions/checkout@v2
-
-      - name: Set up Python 3.7.
-        uses: actions/setup-python@v2
+      - name: Check out the codebase
+        uses: actions/checkout@2541b1294d2704b0964813337f33b291d3f8596b # 3.0.2
         with:
-          python-version: '3.x'
+          ref: ${{ github.event.pull_request.head.sha }}
 
-      - name: Install test dependencies.
-        run: pip3 install yamllint ansible-lint ansible
+      - name: Set up Python ${{ env.PYTHON_VERSION }}
+        uses: actions/setup-python@13ae5bb136fac2878aff31522b9efb785519f984 # 4.3.0
+        with:
+          python-version: ${{ env.PYTHON_VERSION }}
+          cache: 'pip' # caching pip dependencies
 
-      - name: Run yamllint.
-        run: yamllint .
+      - name: Cache pip
+        uses: actions/cache@9b0c1fce7a93df8e3bb8926b0d6e9d89e92f20a7 # 3.0.11
+        with:
+          path: ~/.cache/pip
+          key: ${{ runner.os }}-pip-${{ hashFiles('./requirements.txt') }}
+          restore-keys: |
+            ${{ runner.os }}-pip-
 
-      - name: Run ansible-lint.
-        run: ansible-lint
+      - name: Cache Ansible
+        uses: actions/cache@9b0c1fce7a93df8e3bb8926b0d6e9d89e92f20a7 # 3.0.11
+        with:
+          path: ~/.ansible/collections
+          key: ${{ runner.os }}-ansible-${{ hashFiles('collections/requirements.txt') }}
+          restore-keys: |
+            ${{ runner.os }}-ansible-
+
+      - name: Install dependencies
+        run: |
+          echo "::group::Upgrade pip"
+          python3 -m pip install --upgrade pip
+          echo "::endgroup::"
+
+          echo "::group::Install Python requirements from requirements.txt"
+          python3 -m pip install -r requirements.txt
+          echo "::endgroup::"
+
+          echo "::group::Install Ansible role requirements from collections/requirements.yml"
+          ansible-galaxy install -r collections/requirements.yml
+          echo "::endgroup::"
+
+      - name: Run pre-commit
+        uses: pre-commit/action@646c83fcd040023954eafda54b4db0192ce70507 # 3.0.0
+
+  ensure-pinned-actions:
+    name: Ensure SHA Pinned Actions
+    runs-on: self-hosted
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@2541b1294d2704b0964813337f33b291d3f8596b # 3.0.2
+      - name: Ensure SHA pinned actions
+        uses: zgosalvez/github-actions-ensure-sha-pinned-actions@6ca5574367befbc9efdb2fa25978084159c5902d # 1.3.0
+        with:
+          allowlist: |
+            aws-actions/
+            docker/login-action

.github/workflows/test.yml

@@ -0,0 +1,91 @@
+---
+name: Test
+on:
+  workflow_call:
+jobs:
+  molecule:
+    name: Molecule
+    runs-on: macos-12
+    strategy:
+      matrix:
+        scenario:
+          - default
+          - ipv6
+          - single_node
+      fail-fast: false
+    env:
+      PYTHON_VERSION: "3.10"
+
+    steps:
+      - name: Check out the codebase
+        uses: actions/checkout@2541b1294d2704b0964813337f33b291d3f8596b # 3.0.2
+        with:
+          ref: ${{ github.event.pull_request.head.sha }}
+
+      - name: Configure VirtualBox
+        run: |-
+          sudo mkdir -p /etc/vbox
+          cat <<EOF | sudo tee -a /etc/vbox/networks.conf > /dev/null
+          * 192.168.30.0/24
+          * fdad:bad:ba55::/64
+          EOF
+
+      - name: Cache pip
+        uses: actions/cache@9b0c1fce7a93df8e3bb8926b0d6e9d89e92f20a7 # 3.0.11
+        with:
+          path: ~/.cache/pip
+          key: ${{ runner.os }}-pip-${{ hashFiles('./requirements.txt') }}
+          restore-keys: |
+            ${{ runner.os }}-pip-
+
+      - name: Cache Vagrant boxes
+        uses: actions/cache@9b0c1fce7a93df8e3bb8926b0d6e9d89e92f20a7 # 3.0.11
+        with:
+          path: |
+            ~/.vagrant.d/boxes
+          key: vagrant-boxes-${{ hashFiles('**/molecule.yml') }}
+          restore-keys: |
+            vagrant-boxes
+
+      - name: Download Vagrant boxes for all scenarios
+        # To save some cache space, all scenarios share the same cache key.
+        # On the other hand, this means that the cache contents should be
+        # the same across all scenarios. This step ensures that.
+        run: ./.github/download-boxes.sh
+
+      - name: Set up Python ${{ env.PYTHON_VERSION }}
+        uses: actions/setup-python@13ae5bb136fac2878aff31522b9efb785519f984 # 4.3.0
+        with:
+          python-version: ${{ env.PYTHON_VERSION }}
+          cache: 'pip' # caching pip dependencies
+
+      - name: Install dependencies
+        run: |
+          echo "::group::Upgrade pip"
+          python3 -m pip install --upgrade pip
+          echo "::endgroup::"
+
+          echo "::group::Install Python requirements from requirements.txt"
+          python3 -m pip install -r requirements.txt
+          echo "::endgroup::"
+
+      - name: Test with molecule
+        run: molecule test --scenario-name ${{ matrix.scenario }}
+        env:
+          ANSIBLE_K3S_LOG_DIR: ${{ runner.temp }}/logs/k3s-ansible/${{ matrix.scenario }}
+          ANSIBLE_SSH_RETRIES: 4
+          ANSIBLE_TIMEOUT: 60
+          PY_COLORS: 1
+          ANSIBLE_FORCE_COLOR: 1
+
+      - name: Upload log files
+        if: always() # do this even if a step before has failed
+        uses: actions/upload-artifact@83fd05a356d7e2593de66fc9913b3002723633cb # 3.1.1
+        with:
+          name: logs
+          path: |
+            ${{ runner.temp }}/logs
+
+      - name: Delete old box versions
+        if: always() # do this even if a step before has failed
+        run: vagrant box prune --force

.gitignore

@@ -1 +1,2 @@
-.vagrant
+.env/
+*.log

.pre-commit-config.yaml

@@ -0,0 +1,35 @@
+---
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: 3298ddab3c13dd77d6ce1fc0baf97691430d84b0  # v4.3.0
+    hooks:
+      - id: requirements-txt-fixer
+      - id: sort-simple-yaml
+      - id: detect-private-key
+      - id: check-merge-conflict
+      - id: end-of-file-fixer
+      - id: mixed-line-ending
+      - id: trailing-whitespace
+        args: [--markdown-linebreak-ext=md]
+  - repo: https://github.com/adrienverge/yamllint.git
+    rev: 9cce2940414e9560ae4c8518ddaee2ac1863a4d2  # v1.28.0
+    hooks:
+      - id: yamllint
+        args: [-c=.yamllint]
+  - repo: https://github.com/ansible-community/ansible-lint.git
+    rev: a058554b9bcf88f12ad09ab9fb93b267a214368f  # v6.8.6
+    hooks:
+      - id: ansible-lint
+  - repo: https://github.com/shellcheck-py/shellcheck-py
+    rev: 4c7c3dd7161ef39e984cb295e93a968236dc8e8a  # v0.8.0.4
+    hooks:
+      - id: shellcheck
+  - repo: https://github.com/Lucas-C/pre-commit-hooks
+    rev: 04618e68aa2380828a36a23ff5f65a06ae8f59b9  # v1.3.1
+    hooks:
+      - id: remove-crlf
+      - id: remove-tabs
+  - repo: https://github.com/sirosen/texthooks
+    rev: 30d9af95631de0d7cff4e282bde9160d38bb0359  # 0.4.0
+    hooks:
+      - id: fix-smartquotes

README.md

@@ -10,15 +10,15 @@ If you want more context on how this works, see:
 
 📄 [Documentation](https://docs.technotim.live/posts/k3s-etcd-ansible/) (including example commands)
 
-📺 [Video](https://www.youtube.com/watch?v=CbkEWcUZ7zM)
+📺 [Watch the Video](https://www.youtube.com/watch?v=CbkEWcUZ7zM)
 
 ## 📖 k3s Ansible Playbook
 
 Build a Kubernetes cluster using Ansible with k3s. The goal is easily install a HA Kubernetes cluster on machines running:
 
-- [X] Debian
-- [X] Ubuntu
-- [X] CentOS
+- [x] Debian (tested on version 11)
+- [x] Ubuntu (tested on version 22.04)
+- [x] Rocky (tested on version 9)
 
 on processor architecture:
 
@@ -29,6 +29,11 @@ on processor architecture:
 ## ✅ System requirements
 
 - Deployment environment must have Ansible 2.4.0+.  If you need a quick primer on Ansible [you can check out my docs and setting up Ansible](https://docs.technotim.live/posts/ansible-automation/).
+
+- You will also need to install collections that this playbook uses by running `ansible-galaxy collection install -r ./collections/requirements.yml` (important❗)
+
+- [`netaddr` package](https://pypi.org/project/netaddr/) must be available to Ansible. If you have installed Ansible via apt, this is already taken care of. If you have installed Ansible via `pip`, make sure to install `netaddr` into the respective virtual environment.
+
 - `server` and `agent` nodes should have passwordless SSH access, if not you can supply arguments to provide credentials `--ask-pass --ask-become-pass` to each command.
 
 ## 🚀 Getting Started
@@ -100,18 +105,20 @@ See the commands [here](https://docs.technotim.live/posts/k3s-etcd-ansible/#test
 
 Be sure to see [this post](https://github.com/techno-tim/k3s-ansible/discussions/20) on how to troubleshoot common problems
 
-### 🔷 Vagrant
+### Testing the playbook using molecule
 
-You may want to kickstart your k3s cluster by using Vagrant to quickly build you all needed VMs with one command.
-Head to the `vagrant` subfolder and type `vagrant up` to get your environment setup.
-After the VMs have got build, deploy k3s using the Ansible playbook `site.yml` by the
-`vagrant provision --provision-with ansible` command.
+This playbook includes a [molecule](https://molecule.rtfd.io/)-based test setup.
+It is run automatically in CI, but you can also run the tests locally.
+This might be helpful for quick feedback in a few cases.
+You can find more information about it [here](molecule/README.md).
+
+### Pre-commit Hooks
+
+This repo uses `pre-commit` and `pre-commit-hooks` to lint and fix common style and syntax errors.  Be sure to install python packages and then run `pre-commit install`.  For more information, see [pre-commit](https://pre-commit.com/)
 
 ## Thanks 🤝
 
-This repo is really standing on the shoulders of giants.  To all those who have contributed.
-
-Thanks to these repos for code and ideas:
+This repo is really standing on the shoulders of giants. Thank you to all those who have contributed and thanks to these repos for code and ideas:
 
 - [k3s-io/k3s-ansible](https://github.com/k3s-io/k3s-ansible)
 - [geerlingguy/turing-pi-cluster](https://github.com/geerlingguy/turing-pi-cluster)

ansible.cfg

@@ -2,11 +2,22 @@
 nocows                  = True
 roles_path              = ./roles
 inventory               = ./hosts.ini
+stdout_callback         = yaml
 
 remote_tmp              = $HOME/.ansible/tmp
 local_tmp               = $HOME/.ansible/tmp
-pipelining = True
-become = True
+timeout                 = 60
 host_key_checking       = False
 deprecation_warnings    = False
 callback_whitelist      = profile_tasks
+log_path                = ./ansible.log
+
+[privilege_escalation]
+become                  = True
+
+[ssh_connection]
+scp_if_ssh              = smart
+retries                 = 3
+ssh_args                = -o ControlMaster=auto -o ControlPersist=30m -o Compression=yes -o ServerAliveInterval=15s
+pipelining              = True
+control_path            = %(directory)s/%%h-%%r

collections/requirements.yml

@@ -1,3 +1,6 @@
 ---
 collections:
+  - name: ansible.utils
   - name: community.general
+  - name: ansible.posix
+  - name: kubernetes.core

example/service.yml

@@ -4,6 +4,7 @@ kind: Service
 metadata:
   name: nginx
 spec:
+  ipFamilyPolicy: PreferDualStack
   selector:
     app: nginx
   ports:

inventory/sample/group_vars/all.yml

@@ -1,5 +1,5 @@
 ---
-k3s_version: v1.24.3+k3s1
+k3s_version: v1.24.7+k3s1
 # this is the user that has ssh access to these machines
 ansible_user: ansibleuser
 systemd_dir: /etc/systemd/system
@@ -17,16 +17,35 @@ apiserver_endpoint: "192.168.30.222"
 # this token should be alpha numeric only
 k3s_token: "some-SUPER-DEDEUPER-secret-password"
 
-# change these to your liking, the only required one is--disable servicelb
-extra_server_args: "--disable servicelb --disable traefik"
-extra_agent_args: ""
+# The IP on which the node is reachable in the cluster.
+# Here, a sensible default is provided, you can still override
+# it for each of your hosts, though.
+k3s_node_ip: '{{ ansible_facts[flannel_iface]["ipv4"]["address"] }}'
+
+# Disable the taint manually by setting: k3s_master_taint = false
+k3s_master_taint: "{{ true if groups['node'] | default([]) | length >= 1 else false }}"
+
+# these arguments are recommended for servers as well as agents:
+extra_args: >-
+  --flannel-iface={{ flannel_iface }}
+  --node-ip={{ k3s_node_ip }}
+
+# change these to your liking, the only required are: --disable servicelb, --tls-san {{ apiserver_endpoint }}
+extra_server_args: >-
+  {{ extra_args }}
+  {{ '--node-taint node-role.kubernetes.io/master=true:NoSchedule' if k3s_master_taint else '' }}
+  --tls-san {{ apiserver_endpoint }}
+  --disable servicelb
+  --disable traefik
+extra_agent_args: >-
+  {{ extra_args }}
 
 # image tag for kube-vip
-kube_vip_tag_version: "v0.5.0"
+kube_vip_tag_version: "v0.5.6"
 
 # image tag for metal lb
-metal_lb_speaker_tag_version: "v0.13.4"
-metal_lb_controller_tag_version: "v0.13.4"
+metal_lb_speaker_tag_version: "v0.13.7"
+metal_lb_controller_tag_version: "v0.13.7"
 
 # metallb ip range for load balancer
 metal_lb_ip_range: "192.168.30.80-192.168.30.90"

molecule/README.md

@@ -0,0 +1,73 @@
+# Test suites for `k3s-ansible`
+
+This folder contains the [molecule](https://molecule.rtfd.io/)-based test setup for this playbook.
+
+## Scenarios
+
+We have these scenarios:
+
+- **default**:
+  A 3 control + 2 worker node cluster based very closely on the [sample inventory](../inventory/sample/).
+- **ipv6**:
+  A cluster that is externally accessible via IPv6 ([more information](ipv6/README.md))
+  To save a bit of test time, this cluster is _not_ highly available, it consists of only one control and one worker node.
+- **single_node**:
+  Very similar to the default scenario, but uses only a single node for all cluster functionality.
+
+## How to execute
+
+To test on your local machine, follow these steps:
+
+### System requirements
+
+Make sure that the following software packages are available on your system:
+
+- [Python 3](https://www.python.org/downloads)
+- [Vagrant](https://www.vagrantup.com/downloads)
+- [VirtualBox](https://www.virtualbox.org/wiki/Downloads)
+
+### Set up VirtualBox networking on Linux and macOS
+
+_You can safely skip this if you are working on Windows._
+
+Furthermore, the test cluster uses the `192.168.30.0/24` subnet which is [not set up by VirtualBox automatically](https://www.virtualbox.org/manual/ch06.html#network_hostonly).
+To set the subnet up for use with VirtualBox, please make sure that `/etc/vbox/networks.conf` exists and that it contains this line:
+
+```
+* 192.168.30.0/24
+* fdad:bad:ba55::/64
+```
+
+### Install Python dependencies
+
+You will get [Molecule, Ansible and a few extra dependencies](../requirements.txt) via [pip](https://pip.pypa.io/).
+Usually, it is advisable to work in a [virtual environment](https://docs.python.org/3/tutorial/venv.html) for this:
+
+```bash
+cd /path/to/k3s-ansible
+
+# Create a virtualenv at ".env". You only need to do this once.
+python3 -m venv .env
+
+# Activate the virtualenv for your current shell session.
+# If you start a new session, you will have to repeat this.
+source .env/bin/activate
+
+# Install the required packages into the virtualenv.
+# These remain installed across shell sessions.
+python3 -m pip install -r requirements.txt
+```
+
+### Run molecule
+
+With the virtual environment from the previous step active in your shell session, you can now use molecule to test the playbook.
+Interesting commands are:
+
+- `molecule create`: Create virtual machines for the test cluster nodes.
+- `molecule destroy`: Delete the virtual machines for the test cluster nodes.
+- `molecule converge`: Run the `site` playbook on the nodes of the test cluster.
+- `molecule side_effect`: Run the `reset` playbook on the nodes of the test cluster.
+- `molecule verify`: Verify that the cluster works correctly.
+- `molecule test`: The "all-in-one" sequence of steps that is executed in CI.
+  This includes the `create`, `converge`, `verify`, `side_effect` and `destroy` steps.
+  See [`molecule.yml`](default/molecule.yml) for more details.

molecule/default/molecule.yml

@@ -0,0 +1,99 @@
+---
+dependency:
+  name: galaxy
+driver:
+  name: vagrant
+platforms:
+
+  - name: control1
+    box: generic/ubuntu2204
+    memory: 2048
+    cpus: 2
+    groups:
+      - k3s_cluster
+      - master
+    interfaces:
+      - network_name: private_network
+        ip: 192.168.30.38
+    config_options:
+      # We currently can not use public-key based authentication on Ubuntu 22.04,
+      # see: https://github.com/chef/bento/issues/1405
+      ssh.username: "vagrant"
+      ssh.password: "vagrant"
+
+  - name: control2
+    box: generic/debian11
+    memory: 2048
+    cpus: 2
+    groups:
+      - k3s_cluster
+      - master
+    interfaces:
+      - network_name: private_network
+        ip: 192.168.30.39
+
+  - name: control3
+    box: generic/rocky9
+    memory: 2048
+    cpus: 2
+    groups:
+      - k3s_cluster
+      - master
+    interfaces:
+      - network_name: private_network
+        ip: 192.168.30.40
+
+  - name: node1
+    box: generic/ubuntu2204
+    memory: 2048
+    cpus: 2
+    groups:
+      - k3s_cluster
+      - node
+    interfaces:
+      - network_name: private_network
+        ip: 192.168.30.41
+    config_options:
+      # We currently can not use public-key based authentication on Ubuntu 22.04,
+      # see: https://github.com/chef/bento/issues/1405
+      ssh.username: "vagrant"
+      ssh.password: "vagrant"
+
+  - name: node2
+    box: generic/rocky9
+    memory: 2048
+    cpus: 2
+    groups:
+      - k3s_cluster
+      - node
+    interfaces:
+      - network_name: private_network
+        ip: 192.168.30.42
+
+provisioner:
+  name: ansible
+  playbooks:
+    converge: ../resources/converge.yml
+    side_effect: ../resources/reset.yml
+    verify: ../resources/verify.yml
+  inventory:
+    links:
+      group_vars: ../../inventory/sample/group_vars
+scenario:
+  test_sequence:
+    - dependency
+    - lint
+    - cleanup
+    - destroy
+    - syntax
+    - create
+    - prepare
+    - converge
+    # idempotence is not possible with the playbook in its current form.
+    - verify
+    # We are repurposing side_effect here to test the reset playbook.
+    # This is why we do not run it before verify (which tests the cluster),
+    # but after the verify step.
+    - side_effect
+    - cleanup
+    - destroy

molecule/default/overrides.yml

@@ -0,0 +1,11 @@
+---
+- name: Apply overrides
+  hosts: all
+  tasks:
+    - name: Override host variables
+      ansible.builtin.set_fact:
+        # See: https://github.com/flannel-io/flannel/blob/67d603aaf45ef80f5dd39f43714fc5e6f8a637eb/Documentation/troubleshooting.md#Vagrant  # noqa yaml[line-length]
+        flannel_iface: eth1
+
+        # The test VMs might be a bit slow, so we give them more time to join the cluster:
+        retry_count: 45

molecule/default/prepare.yml

@@ -0,0 +1,22 @@
+---
+- name: Apply overrides
+  ansible.builtin.import_playbook: >-
+    {{ lookup("ansible.builtin.env", "MOLECULE_SCENARIO_DIRECTORY") }}/overrides.yml
+
+- name: Network setup
+  hosts: all
+  tasks:
+    - name: Disable firewalld
+      when: ansible_distribution == "Rocky"
+      # Rocky Linux comes with firewalld enabled. It blocks some of the network
+      # connections needed for our k3s cluster. For our test setup, we just disable
+      # it since the VM host's firewall is still active for connections to and from
+      # the Internet.
+      # When building your own cluster, please DO NOT blindly copy this. Instead,
+      # please create a custom firewall configuration that fits your network design
+      # and security needs.
+      ansible.builtin.systemd:
+        name: firewalld
+        enabled: no
+        state: stopped
+      become: true

molecule/ipv6/README.md

@@ -0,0 +1,35 @@
+# Sample IPv6 configuration for `k3s-ansible`
+
+This scenario contains a cluster configuration which is _IPv6 first_, but still supports dual-stack networking with IPv4 for most things.
+This means:
+
+- The API server VIP is an IPv6 address.
+- The MetalLB pool consists of both IPv4 and IPv4 addresses.
+- Nodes as well as cluster-internal resources (pods and services) are accessible via IPv4 as well as IPv6.
+
+## Network design
+
+All IPv6 addresses used in this scenario share a single `/48` prefix: `fdad:bad:ba55`.
+The following subnets are used:
+
+- `fdad:bad:ba55:`**`0`**`::/64` is the subnet which contains the cluster components meant for external access.
+  That includes:
+
+  - The VIP for the Kubernetes API server: `fdad:bad:ba55::333`
+  - Services load-balanced by MetalLB: `fdad:bad:ba55::1b:0/112`
+  - Cluster nodes: `fdad:bad:ba55::de:0/112`
+  - The host executing Vagrant: `fdad:bad:ba55::1`
+
+  In a home lab setup, this might be your LAN.
+
+- `fdad:bad:ba55:`**`4200`**`::/56` is used internally by the cluster for pods.
+
+- `fdad:bad:ba55:`**`4300`**`::/108` is used internally by the cluster for services.
+
+IPv4 networking is also available:
+
+- The nodes have addresses inside `192.168.123.0/24`.
+  MetalLB also has a bit of address space in this range: `192.168.123.80-192.168.123.90`
+- For pods and services, the k3s defaults (`10.42.0.0/16` and `10.43.0.0/16)` are used.
+
+Note that the host running Vagrant is not part any of these IPv4 networks.

molecule/ipv6/host_vars/control1.yml

@@ -0,0 +1,3 @@
+---
+node_ipv4: 192.168.123.11
+node_ipv6: fdad:bad:ba55::de:11

molecule/ipv6/host_vars/node1.yml

@@ -0,0 +1,3 @@
+---
+node_ipv4: 192.168.123.21
+node_ipv6: fdad:bad:ba55::de:21

molecule/ipv6/molecule.yml

@@ -0,0 +1,65 @@
+---
+dependency:
+  name: galaxy
+driver:
+  name: vagrant
+platforms:
+
+  - name: control1
+    box: generic/ubuntu2204
+    memory: 2048
+    cpus: 2
+    groups:
+      - k3s_cluster
+      - master
+    interfaces:
+      - network_name: private_network
+        ip: fdad:bad:ba55::de:11
+    config_options:
+      # We currently can not use public-key based authentication on Ubuntu 22.04,
+      # see: https://github.com/chef/bento/issues/1405
+      ssh.username: "vagrant"
+      ssh.password: "vagrant"
+
+  - name: node1
+    box: generic/ubuntu2204
+    memory: 2048
+    cpus: 2
+    groups:
+      - k3s_cluster
+      - node
+    interfaces:
+      - network_name: private_network
+        ip: fdad:bad:ba55::de:21
+    config_options:
+      # We currently can not use public-key based authentication on Ubuntu 22.04,
+      # see: https://github.com/chef/bento/issues/1405
+      ssh.username: "vagrant"
+      ssh.password: "vagrant"
+provisioner:
+  name: ansible
+  playbooks:
+    converge: ../resources/converge.yml
+    side_effect: ../resources/reset.yml
+    verify: ../resources/verify.yml
+  inventory:
+    links:
+      group_vars: ../../inventory/sample/group_vars
+scenario:
+  test_sequence:
+    - dependency
+    - lint
+    - cleanup
+    - destroy
+    - syntax
+    - create
+    - prepare
+    - converge
+    # idempotence is not possible with the playbook in its current form.
+    - verify
+    # We are repurposing side_effect here to test the reset playbook.
+    # This is why we do not run it before verify (which tests the cluster),
+    # but after the verify step.
+    - side_effect
+    - cleanup
+    - destroy

molecule/ipv6/overrides.yml

@@ -0,0 +1,45 @@
+---
+- name: Apply overrides
+  hosts: all
+  tasks:
+    - name: Override host variables (1/2)
+      ansible.builtin.set_fact:
+        # See: https://github.com/flannel-io/flannel/blob/67d603aaf45ef80f5dd39f43714fc5e6f8a637eb/Documentation/troubleshooting.md#Vagrant  # noqa yaml[line-length]
+        flannel_iface: eth1
+
+        # The test VMs might be a bit slow, so we give them more time to join the cluster:
+        retry_count: 45
+
+        # IPv6 configuration
+        # ######################################################################
+
+        # The API server will be reachable on IPv6 only
+        apiserver_endpoint: fdad:bad:ba55::333
+
+        # We give MetalLB address space for both IPv4 and IPv6
+        metal_lb_ip_range:
+          - fdad:bad:ba55::1b:0/112
+          - 192.168.123.80-192.168.123.90
+
+        # k3s_node_ip is by default set to the IPv4 address of flannel_iface.
+        # We want IPv6 addresses here of course, so we just specify them
+        # manually below.
+        k3s_node_ip: "{{ node_ipv4 }},{{ node_ipv6 }}"
+
+    - name: Override host variables (2/2)
+      # Since "extra_args" depends on "k3s_node_ip" and "flannel_iface" we have
+      # to set this AFTER overriding the both of them.
+      ansible.builtin.set_fact:
+        # A few extra server args are necessary:
+        #  - the network policy needs to be disabled.
+        #  - we need to manually specify the subnets for services and pods, as
+        #    the default has IPv4 ranges only.
+        extra_server_args: >-
+          {{ extra_args }}
+          --tls-san {{ apiserver_endpoint }}
+          {{ '--node-taint node-role.kubernetes.io/master=true:NoSchedule' if k3s_master_taint else '' }}
+          --disable servicelb
+          --disable traefik
+          --disable-network-policy
+          --cluster-cidr=10.42.0.0/16,fdad:bad:ba55:4200::/56
+          --service-cidr=10.43.0.0/16,fdad:bad:ba55:4300::/108

molecule/ipv6/prepare.yml

@@ -0,0 +1,51 @@
+---
+- name: Apply overrides
+  ansible.builtin.import_playbook: >-
+    {{ lookup("ansible.builtin.env", "MOLECULE_SCENARIO_DIRECTORY") }}/overrides.yml
+
+- name: Configure dual-stack networking
+  hosts: all
+  become: true
+
+  # Unfortunately, as of 2022-09, Vagrant does not support the configuration
+  # of both IPv4 and IPv6 addresses for a single network adapter. So we have
+  # to configure that ourselves.
+  # Moreover, we have to explicitly enable IPv6 for the loopback interface.
+
+  tasks:
+    - name: Enable IPv6 for network interfaces
+      ansible.posix.sysctl:
+        name: net.ipv6.conf.{{ item }}.disable_ipv6
+        value: "0"
+      with_items:
+        - all
+        - default
+        - lo
+
+    - name: Disable duplicate address detection
+      # Duplicate address detection did repeatedly fail within the virtual
+      # network. But since this setup does not use SLAAC anyway, we can safely
+      # disable it.
+      ansible.posix.sysctl:
+        name: net.ipv6.conf.{{ item }}.accept_dad
+        value: "0"
+      with_items:
+        - "{{ flannel_iface }}"
+
+    - name: Write IPv4 configuration
+      ansible.builtin.template:
+        src: 55-flannel-ipv4.yaml.j2
+        dest: /etc/netplan/55-flannel-ipv4.yaml
+        owner: root
+        group: root
+        mode: 0644
+      register: netplan_template
+
+    - name: Apply netplan configuration
+      # Conceptually, this should be a handler rather than a task.
+      # However, we are currently not in a role context - creating
+      # one just for this seemed overkill.
+      when: netplan_template.changed
+      ansible.builtin.command:
+        cmd: netplan apply
+      changed_when: true

molecule/ipv6/templates/55-flannel-ipv4.yaml.j2

@@ -0,0 +1,8 @@
+---
+network:
+  version: 2
+  renderer: networkd
+  ethernets:
+    {{ flannel_iface }}:
+      addresses:
+      - {{ node_ipv4 }}/24

molecule/resources/converge.yml

@@ -0,0 +1,7 @@
+---
+- name: Apply overrides
+  ansible.builtin.import_playbook: >-
+    {{ lookup("ansible.builtin.env", "MOLECULE_SCENARIO_DIRECTORY") }}/overrides.yml
+
+- name: Converge
+  ansible.builtin.import_playbook: ../../site.yml

molecule/resources/reset.yml

@@ -0,0 +1,7 @@
+---
+- name: Apply overrides
+  ansible.builtin.import_playbook: >-
+    {{ lookup("ansible.builtin.env", "MOLECULE_SCENARIO_DIRECTORY") }}/overrides.yml
+
+- name: Reset
+  ansible.builtin.import_playbook: ../../reset.yml

molecule/resources/verify.yml

@@ -0,0 +1,5 @@
+---
+- name: Verify
+  hosts: all
+  roles:
+    - verify/from_outside

molecule/resources/verify/from_outside/defaults/main.yml

@@ -0,0 +1,9 @@
+---
+# A host outside of the cluster from which the checks shall be performed
+outside_host: localhost
+
+# This kubernetes namespace will be used for testing
+testing_namespace: molecule-verify-from-outside
+
+# The directory in which the example manifests reside
+example_manifests_path: ../../../../example

molecule/resources/verify/from_outside/tasks/kubecfg-cleanup.yml

@@ -0,0 +1,5 @@
+---
+- name: Clean up kubecfg
+  ansible.builtin.file:
+    path: "{{ kubecfg.path }}"
+    state: absent

molecule/resources/verify/from_outside/tasks/kubecfg-fetch.yml

@@ -0,0 +1,19 @@
+---
+- name: Create temporary directory for kubecfg
+  ansible.builtin.tempfile:
+    state: directory
+    suffix: kubecfg
+  register: kubecfg
+- name: Gathering facts
+  delegate_to: "{{ groups['master'][0] }}"
+  ansible.builtin.gather_facts:
+- name: Download kubecfg
+  ansible.builtin.fetch:
+    src: "{{ ansible_env.HOME }}/.kube/config"
+    dest: "{{ kubecfg.path }}/"
+    flat: true
+  delegate_to: "{{ groups['master'][0] }}"
+  delegate_facts: true
+- name: Store path to kubecfg
+  ansible.builtin.set_fact:
+    kubecfg_path: "{{ kubecfg.path }}/config"

molecule/resources/verify/from_outside/tasks/main.yml

@@ -0,0 +1,14 @@
+---
+- name: Verify
+  run_once: true
+  delegate_to: "{{ outside_host }}"
+  block:
+    - name: "Test CASE: Get kube config"
+      ansible.builtin.import_tasks: kubecfg-fetch.yml
+    - name: "TEST CASE: Get nodes"
+      ansible.builtin.include_tasks: test/get-nodes.yml
+    - name: "TEST CASE: Deploy example"
+      ansible.builtin.include_tasks: test/deploy-example.yml
+  always:
+    - name: "TEST CASE: Cleanup"
+      ansible.builtin.import_tasks: kubecfg-cleanup.yml

molecule/resources/verify/from_outside/tasks/test/deploy-example.yml

@@ -0,0 +1,58 @@
+---
+- name: Deploy example
+  block:
+    - name: "Create namespace: {{ testing_namespace }}"
+      kubernetes.core.k8s:
+        api_version: v1
+        kind: Namespace
+        name: "{{ testing_namespace }}"
+        state: present
+        wait: true
+        kubeconfig: "{{ kubecfg_path }}"
+
+    - name: Apply example manifests
+      kubernetes.core.k8s:
+        src: "{{ example_manifests_path }}/{{ item }}"
+        namespace: "{{ testing_namespace }}"
+        state: present
+        wait: true
+        kubeconfig: "{{ kubecfg_path }}"
+      with_items:
+        - deployment.yml
+        - service.yml
+
+    - name: Get info about nginx service
+      kubernetes.core.k8s_info:
+        kind: service
+        name: nginx
+        namespace: "{{ testing_namespace }}"
+        kubeconfig: "{{ kubecfg_path }}"
+      vars: &load_balancer_metadata
+        metallb_ip: status.loadBalancer.ingress[0].ip
+        metallb_port: spec.ports[0].port
+      register: nginx_services
+
+    - name: Assert that the nginx welcome page is available
+      ansible.builtin.uri:
+        url: http://{{ ip | ansible.utils.ipwrap }}:{{ port }}/
+        return_content: yes
+      register: result
+      failed_when: "'Welcome to nginx!' not in result.content"
+      vars:
+        ip: >-
+          {{ nginx_services.resources[0].status.loadBalancer.ingress[0].ip }}
+        port: >-
+          {{ nginx_services.resources[0].spec.ports[0].port }}
+      # Deactivated linter rules:
+      #   - jinja[invalid]: As of version 6.6.0, ansible-lint complains that the input to ipwrap
+      #                     would be undefined. This will not be the case during playbook execution.
+      # noqa jinja[invalid]
+
+  always:
+    - name: "Remove namespace: {{ testing_namespace }}"
+      kubernetes.core.k8s:
+        api_version: v1
+        kind: Namespace
+        name: "{{ testing_namespace }}"
+        state: absent
+        kubeconfig: "{{ kubecfg_path }}"

molecule/resources/verify/from_outside/tasks/test/get-nodes.yml

@@ -0,0 +1,28 @@
+---
+- name: Get all nodes in cluster
+  kubernetes.core.k8s_info:
+    kind: node
+    kubeconfig: "{{ kubecfg_path }}"
+  register: cluster_nodes
+
+- name: Assert that the cluster contains exactly the expected nodes
+  ansible.builtin.assert:
+    that: found_nodes == expected_nodes
+    success_msg: "Found nodes as expected: {{ found_nodes }}"
+    fail_msg: "Expected nodes {{ expected_nodes }}, but found nodes {{ found_nodes }}"
+  vars:
+    found_nodes: >-
+      {{ cluster_nodes | json_query('resources[*].metadata.name') | unique | sort }}
+    expected_nodes: |-
+      {{
+        (
+          ( groups['master'] | default([]) ) +
+          ( groups['node'] | default([]) )
+        )
+        | unique
+        | sort
+      }}
+  # Deactivated linter rules:
+  #   - jinja[invalid]: As of version 6.6.0, ansible-lint complains that the input to ipwrap
+  #                     would be undefined. This will not be the case during playbook execution.
+  # noqa jinja[invalid]

molecule/single_node/molecule.yml

@@ -0,0 +1,48 @@
+---
+dependency:
+  name: galaxy
+driver:
+  name: vagrant
+platforms:
+  - name: control1
+    box: generic/ubuntu2204
+    memory: 4096
+    cpus: 4
+    config_options:
+      # We currently can not use public-key based authentication on Ubuntu 22.04,
+      # see: https://github.com/chef/bento/issues/1405
+      ssh.username: "vagrant"
+      ssh.password: "vagrant"
+    groups:
+      - k3s_cluster
+      - master
+    interfaces:
+      - network_name: private_network
+        ip: 192.168.30.50
+provisioner:
+  name: ansible
+  playbooks:
+    converge: ../resources/converge.yml
+    side_effect: ../resources/reset.yml
+    verify: ../resources/verify.yml
+  inventory:
+    links:
+      group_vars: ../../inventory/sample/group_vars
+scenario:
+  test_sequence:
+    - dependency
+    - lint
+    - cleanup
+    - destroy
+    - syntax
+    - create
+    - prepare
+    - converge
+    # idempotence is not possible with the playbook in its current form.
+    - verify
+    # We are repurposing side_effect here to test the reset playbook.
+    # This is why we do not run it before verify (which tests the cluster),
+    # but after the verify step.
+    - side_effect
+    - cleanup
+    - destroy

molecule/single_node/overrides.yml

@@ -0,0 +1,15 @@
+---
+- name: Apply overrides
+  hosts: all
+  tasks:
+    - name: Override host variables
+      ansible.builtin.set_fact:
+        # See: https://github.com/flannel-io/flannel/blob/67d603aaf45ef80f5dd39f43714fc5e6f8a637eb/Documentation/troubleshooting.md#Vagrant  # noqa yaml[line-length]
+        flannel_iface: eth1
+
+        # The test VMs might be a bit slow, so we give them more time to join the cluster:
+        retry_count: 45
+
+        # Make sure that our IP ranges do not collide with those of the default scenario
+        apiserver_endpoint: "192.168.30.223"
+        metal_lb_ip_range: "192.168.30.91-192.168.30.99"

reboot.sh

@@ -0,0 +1,3 @@
+#!/bin/bash
+
+ansible-playbook reboot.yml -i inventory/my-cluster/hosts.ini

reboot.yml

@@ -0,0 +1,9 @@
+---
+- name: Reboot k3s_cluster
+  hosts: k3s_cluster
+  gather_facts: yes
+  become: yes
+  tasks:
+    - name: Reboot the nodes (and Wait upto 5 mins max)
+      reboot:
+        reboot_timeout: 300

requirements.in

@@ -0,0 +1,12 @@
+ansible-core>=2.13.5
+ansible-lint>=6.8.6
+jmespath>=1.0.1
+jsonpatch>=1.32
+kubernetes>=25.3.0
+molecule-vagrant>=1.0.0
+molecule>=4.0.3
+netaddr>=0.8.0
+pre-commit>=2.20.0
+pre-commit-hooks>=1.3.1
+pyyaml>=6.0
+yamllint>=1.28.0

requirements.txt

@@ -0,0 +1,228 @@
+#
+# This file is autogenerated by pip-compile with python 3.8
+# To update, run:
+#
+#    pip-compile requirements.in
+#
+ansible-compat==2.2.4
+    # via
+    #   ansible-lint
+    #   molecule
+ansible-core==2.13.5
+    # via
+    #   -r requirements.in
+    #   ansible-lint
+ansible-lint==6.8.6
+    # via -r requirements.in
+arrow==1.2.3
+    # via jinja2-time
+attrs==22.1.0
+    # via jsonschema
+binaryornot==0.4.4
+    # via cookiecutter
+black==22.10.0
+    # via ansible-lint
+bracex==2.3.post1
+    # via wcmatch
+cachetools==5.2.0
+    # via google-auth
+certifi==2022.9.24
+    # via
+    #   kubernetes
+    #   requests
+cffi==1.15.1
+    # via cryptography
+cfgv==3.3.1
+    # via pre-commit
+chardet==5.0.0
+    # via binaryornot
+charset-normalizer==2.1.1
+    # via requests
+click==8.1.3
+    # via
+    #   black
+    #   click-help-colors
+    #   cookiecutter
+    #   molecule
+click-help-colors==0.9.1
+    # via molecule
+commonmark==0.9.1
+    # via rich
+cookiecutter==2.1.1
+    # via molecule
+cryptography==38.0.3
+    # via ansible-core
+distlib==0.3.6
+    # via virtualenv
+distro==1.8.0
+    # via selinux
+enrich==1.2.7
+    # via molecule
+filelock==3.8.0
+    # via
+    #   ansible-lint
+    #   virtualenv
+google-auth==2.14.0
+    # via kubernetes
+identify==2.5.8
+    # via pre-commit
+idna==3.4
+    # via requests
+importlib-resources==5.10.0
+    # via jsonschema
+jinja2==3.1.2
+    # via
+    #   ansible-core
+    #   cookiecutter
+    #   jinja2-time
+    #   molecule
+    #   molecule-vagrant
+jinja2-time==0.2.0
+    # via cookiecutter
+jmespath==1.0.1
+    # via -r requirements.in
+jsonpatch==1.32
+    # via -r requirements.in
+jsonpointer==2.3
+    # via jsonpatch
+jsonschema==4.17.0
+    # via
+    #   ansible-compat
+    #   ansible-lint
+    #   molecule
+kubernetes==25.3.0
+    # via -r requirements.in
+markupsafe==2.1.1
+    # via jinja2
+molecule==4.0.3
+    # via
+    #   -r requirements.in
+    #   molecule-vagrant
+molecule-vagrant==1.0.0
+    # via -r requirements.in
+mypy-extensions==0.4.3
+    # via black
+netaddr==0.8.0
+    # via -r requirements.in
+nodeenv==1.7.0
+    # via pre-commit
+oauthlib==3.2.2
+    # via requests-oauthlib
+packaging==21.3
+    # via
+    #   ansible-compat
+    #   ansible-core
+    #   ansible-lint
+    #   molecule
+pathspec==0.10.1
+    # via
+    #   black
+    #   yamllint
+pkgutil-resolve-name==1.3.10
+    # via jsonschema
+platformdirs==2.5.2
+    # via
+    #   black
+    #   virtualenv
+pluggy==1.0.0
+    # via molecule
+pre-commit==2.20.0
+    # via -r requirements.in
+pre-commit-hooks==4.3.0
+    # via -r requirements.in
+pyasn1==0.4.8
+    # via
+    #   pyasn1-modules
+    #   rsa
+pyasn1-modules==0.2.8
+    # via google-auth
+pycparser==2.21
+    # via cffi
+pygments==2.13.0
+    # via rich
+pyparsing==3.0.9
+    # via packaging
+pyrsistent==0.19.2
+    # via jsonschema
+python-dateutil==2.8.2
+    # via
+    #   arrow
+    #   kubernetes
+python-slugify==6.1.2
+    # via cookiecutter
+python-vagrant==1.0.0
+    # via molecule-vagrant
+pyyaml==6.0
+    # via
+    #   -r requirements.in
+    #   ansible-compat
+    #   ansible-core
+    #   ansible-lint
+    #   cookiecutter
+    #   kubernetes
+    #   molecule
+    #   molecule-vagrant
+    #   pre-commit
+    #   yamllint
+requests==2.28.1
+    # via
+    #   cookiecutter
+    #   kubernetes
+    #   requests-oauthlib
+requests-oauthlib==1.3.1
+    # via kubernetes
+resolvelib==0.8.1
+    # via ansible-core
+rich==12.6.0
+    # via
+    #   ansible-lint
+    #   enrich
+    #   molecule
+rsa==4.9
+    # via google-auth
+ruamel-yaml==0.17.21
+    # via
+    #   ansible-lint
+    #   pre-commit-hooks
+ruamel-yaml-clib==0.2.7
+    # via ruamel-yaml
+selinux==0.2.1
+    # via molecule-vagrant
+six==1.16.0
+    # via
+    #   google-auth
+    #   kubernetes
+    #   python-dateutil
+subprocess-tee==0.3.5
+    # via ansible-compat
+text-unidecode==1.3
+    # via python-slugify
+toml==0.10.2
+    # via pre-commit
+tomli==2.0.1
+    # via
+    #   black
+    #   pre-commit-hooks
+typing-extensions==4.4.0
+    # via
+    #   black
+    #   rich
+urllib3==1.26.12
+    # via
+    #   kubernetes
+    #   requests
+virtualenv==20.16.6
+    # via pre-commit
+wcmatch==8.4.1
+    # via ansible-lint
+websocket-client==1.4.2
+    # via kubernetes
+yamllint==1.28.0
+    # via
+    #   -r requirements.in
+    #   ansible-lint
+zipp==3.10.0
+    # via importlib-resources
+
+# The following packages are considered to be unsafe in a requirements file:
+# setuptools

reset.yml

@@ -5,3 +5,9 @@
   become: yes
   roles:
     - role: reset
+    - role: raspberrypi
+      vars: {state: absent}
+  post_tasks:
+    - name: Reboot and wait for node to come back up
+      reboot:
+        reboot_timeout: 3600

roles/k3s/master/defaults/main.yml

@@ -2,10 +2,10 @@
 ansible_user: root
 server_init_args: >-
   {% if groups['master'] | length > 1 %}
-    {% if ansible_host == hostvars[groups['master'][0]]['ansible_host'] | default(groups['master'][0]) %}
+    {% if ansible_hostname == hostvars[groups['master'][0]]['ansible_hostname'] %}
       --cluster-init
     {% else %}
-      --server https://{{ hostvars[groups['master'][0]]['ansible_host'] | default(groups['master'][0]) }}:6443
+      --server https://{{ hostvars[groups['master'][0]].k3s_node_ip }}:6443
     {% endif %}
     --token {{ k3s_token }}
   {% endif %}

roles/k3s/master/tasks/fetch_k3s_init_logs.yml

@@ -0,0 +1,28 @@
+---
+# Download logs of k3s-init.service from the nodes to localhost.
+# Note that log_destination must be set.
+
+- name: Fetch k3s-init.service logs
+  ansible.builtin.command:
+    cmd: journalctl --all --unit=k3s-init.service
+  changed_when: false
+  register: k3s_init_log
+
+- name: Create {{ log_destination }}
+  delegate_to: localhost
+  run_once: true
+  become: false
+  ansible.builtin.file:
+    path: "{{ log_destination }}"
+    state: directory
+    mode: "0755"
+
+- name: Store logs to {{ log_destination }}
+  delegate_to: localhost
+  become: false
+  ansible.builtin.template:
+    src: content.j2
+    dest: "{{ log_destination }}/k3s-init@{{ ansible_hostname }}.log"
+    mode: 0644
+  vars:
+    content: "{{ k3s_init_log.stdout }}"

roles/k3s/master/tasks/main.yml

@@ -20,7 +20,7 @@
     owner: root
     group: root
     mode: 0644
-  when: ansible_host == hostvars[groups['master'][0]]['ansible_host'] | default(groups['master'][0])
+  when: ansible_hostname == hostvars[groups['master'][0]]['ansible_hostname']
 
 - name: Copy vip rbac manifest to first master
   template:
@@ -29,7 +29,7 @@
     owner: root
     group: root
     mode: 0644
-  when: ansible_host == hostvars[groups['master'][0]]['ansible_host'] | default(groups['master'][0])
+  when: ansible_hostname == hostvars[groups['master'][0]]['ansible_hostname']
 
 - name: Copy vip manifest to first master
   template:
@@ -38,34 +38,26 @@
     owner: root
     group: root
     mode: 0644
-  when: ansible_host == hostvars[groups['master'][0]]['ansible_host'] | default(groups['master'][0])
+  when: ansible_hostname == hostvars[groups['master'][0]]['ansible_hostname']
 
-- name: Copy metallb namespace manifest to first master
+# these will be copied and installed now, then tested later and apply config
+- name: Copy metallb namespace to first master
   template:
     src: "metallb.namespace.j2"
     dest: "/var/lib/rancher/k3s/server/manifests/metallb-namespace.yaml"
     owner: root
     group: root
     mode: 0644
-  when: ansible_host == hostvars[groups['master'][0]]['ansible_host'] | default(groups['master'][0])
+  when: ansible_hostname == hostvars[groups['master'][0]]['ansible_hostname']
 
-- name: Copy metallb ConfigMap manifest to first master
+- name: Copy metallb namespace to first master
   template:
-    src: "metallb.ipaddresspool.j2"
-    dest: "/var/lib/rancher/k3s/server/manifests/metallb-configmap.yaml"
+    src: "metallb.crds.j2"
+    dest: "/var/lib/rancher/k3s/server/manifests/metallb-crds.yaml"
     owner: root
     group: root
     mode: 0644
-  when: ansible_host == hostvars[groups['master'][0]]['ansible_host'] | default(groups['master'][0])
-
-- name: Copy metallb main manifest to first master
-  template:
-    src: "metallb.yaml.j2"
-    dest: "/var/lib/rancher/k3s/server/manifests/metallb.yaml"
-    owner: root
-    group: root
-    mode: 0644
-  when: ansible_host == hostvars[groups['master'][0]]['ansible_host'] | default(groups['master'][0])
+  when: ansible_hostname == hostvars[groups['master'][0]]['ansible_hostname']
 
 - name: Init cluster inside the transient k3s-init service
   command:
@@ -88,11 +80,18 @@
       delay: 10
       changed_when: false
   always:
+    - name: Save logs of k3s-init.service
+      include_tasks: fetch_k3s_init_logs.yml
+      when: log_destination
+      vars:
+        log_destination: >-
+          {{ lookup('ansible.builtin.env', 'ANSIBLE_K3S_LOG_DIR', default=False) }}
     - name: Kill the temporary service used for initialization
       systemd:
         name: k3s-init
         state: stopped
       failed_when: false
+  when: not ansible_check_mode
 
 - name: Copy K3s service file
   register: k3s_service
@@ -153,12 +152,19 @@
     owner: "{{ ansible_user }}"
     mode: "u=rw,g=,o="
 
-- name: Configure kubectl cluster to https://{{ apiserver_endpoint }}:6443
+- name: Configure kubectl cluster to {{ endpoint_url }}
   command: >-
     k3s kubectl config set-cluster default
-      --server=https://{{ apiserver_endpoint }}:6443
+      --server={{ endpoint_url }}
       --kubeconfig ~{{ ansible_user }}/.kube/config
   changed_when: true
+  vars:
+    endpoint_url: >-
+      https://{{ apiserver_endpoint | ansible.utils.ipwrap }}:6443
+  # Deactivated linter rules:
+  #   - jinja[invalid]: As of version 6.6.0, ansible-lint complains that the input to ipwrap
+  #                     would be undefined. This will not be the case during playbook execution.
+  # noqa jinja[invalid]
 
 - name: Create kubectl symlink
   file:
@@ -184,7 +190,6 @@
     file_type: directory
   register: k3s_server_manifests_directories
 
-
 - name: Remove manifests and folders that are only needed for bootstrapping cluster so k3s doesn't auto apply on start
   file:
     path: "{{ item.path }}"
@@ -192,3 +197,5 @@
   with_items:
     - "{{ k3s_server_manifests.files }}"
     - "{{ k3s_server_manifests_directories.files }}"
+  loop_control:
+    label: "{{ item.path }}"

roles/k3s/master/templates/content.j2

@@ -0,0 +1,5 @@
+{#
+    This is a really simple template that just outputs the
+    value of the "content" variable.
+#}
+{{ content }}

roles/k3s/master/templates/metallb.crds.j2

@@ -77,7 +77,7 @@ spec:
                     aggregationLength:
                       default: 32
                       description: The aggregation-length advertisement option lets
-                        you “roll up” the /32s into a larger prefix.
+                        you "roll up" the /32s into a larger prefix.
                       format: int32
                       minimum: 1
                       type: integer
@@ -167,7 +167,7 @@ spec:
                     aggregationLength:
                       default: 32
                       description: The aggregation-length advertisement option lets
-                        you “roll up” the /32s into a larger prefix.
+                        you "roll up" the /32s into a larger prefix.
                       format: int32
                       minimum: 1
                       type: integer
@@ -359,7 +359,7 @@ spec:
               aggregationLength:
                 default: 32
                 description: The aggregation-length advertisement option lets you
-                  “roll up” the /32s into a larger prefix. Defaults to 32. Works for
+                  "roll up" the /32s into a larger prefix. Defaults to 32. Works for
                   IPv4 addresses.
                 format: int32
                 minimum: 1
@@ -367,7 +367,7 @@ spec:
               aggregationLengthV6:
                 default: 128
                 description: The aggregation-length advertisement option lets you
-                  “roll up” the /128s into a larger prefix. Defaults to 128. Works
+                  "roll up" the /128s into a larger prefix. Defaults to 128. Works
                   for IPv6 addresses.
                 format: int32
                 type: integer
@@ -1118,85 +1118,6 @@ metadata:
   name: speaker
   namespace: metallb-system
 ---
-apiVersion: policy/v1beta1
-kind: PodSecurityPolicy
-metadata:
-  labels:
-    app: metallb
-  name: controller
-spec:
-  allowPrivilegeEscalation: false
-  allowedCapabilities: []
-  allowedHostPaths: []
-  defaultAddCapabilities: []
-  defaultAllowPrivilegeEscalation: false
-  fsGroup:
-    ranges:
-    - max: 65535
-      min: 1
-    rule: MustRunAs
-  hostIPC: false
-  hostNetwork: false
-  hostPID: false
-  privileged: false
-  readOnlyRootFilesystem: true
-  requiredDropCapabilities:
-  - ALL
-  runAsUser:
-    ranges:
-    - max: 65535
-      min: 1
-    rule: MustRunAs
-  seLinux:
-    rule: RunAsAny
-  supplementalGroups:
-    ranges:
-    - max: 65535
-      min: 1
-    rule: MustRunAs
-  volumes:
-  - configMap
-  - secret
-  - emptyDir
----
-apiVersion: policy/v1beta1
-kind: PodSecurityPolicy
-metadata:
-  labels:
-    app: metallb
-  name: speaker
-spec:
-  allowPrivilegeEscalation: false
-  allowedCapabilities:
-  - NET_RAW
-  allowedHostPaths: []
-  defaultAddCapabilities: []
-  defaultAllowPrivilegeEscalation: false
-  fsGroup:
-    rule: RunAsAny
-  hostIPC: false
-  hostNetwork: true
-  hostPID: false
-  hostPorts:
-  - max: 7472
-    min: 7472
-  - max: 7946
-    min: 7946
-  privileged: true
-  readOnlyRootFilesystem: true
-  requiredDropCapabilities:
-  - ALL
-  runAsUser:
-    rule: RunAsAny
-  seLinux:
-    rule: RunAsAny
-  supplementalGroups:
-    rule: RunAsAny
-  volumes:
-  - configMap
-  - secret
-  - emptyDir
----
 apiVersion: rbac.authorization.k8s.io/v1
 kind: Role
 metadata:
@@ -1789,6 +1710,7 @@ webhooks:
     apiVersions:
     - v1beta1
     operations:
+    - CREATE
     - DELETE
     resources:
     - bfdprofiles

roles/k3s/master/templates/metallb.ipaddresspool.j2

@@ -1,14 +0,0 @@
-apiVersion: metallb.io/v1beta1
-kind: IPAddressPool
-metadata:
-  name: first-pool
-  namespace: metallb-system
-spec:
-  addresses:
-  - {{ metal_lb_ip_range }}
----
-apiVersion: metallb.io/v1beta1
-kind: L2Advertisement
-metadata:
-  name: default
-  namespace: metallb-system

roles/k3s/master/templates/metallb.namespace.j2

@@ -4,4 +4,3 @@ metadata:
   name: metallb-system
   labels:
     app: metallb
-    

roles/k3s/master/templates/vip.yaml.j2

@@ -33,7 +33,7 @@ spec:
         - name: vip_interface
           value: {{ flannel_iface }}
         - name: vip_cidr
-          value: "32"
+          value: "{{ apiserver_endpoint | ansible.utils.ipsubnet | ansible.utils.ipaddr('prefix') }}"
         - name: cp_enable
           value: "true"
         - name: cp_namespace

roles/k3s/node/templates/k3s.service.j2

@@ -7,7 +7,7 @@ After=network-online.target
 Type=notify
 ExecStartPre=-/sbin/modprobe br_netfilter
 ExecStartPre=-/sbin/modprobe overlay
-ExecStart=/usr/local/bin/k3s agent --server https://{{ apiserver_endpoint }}:6443 --token {{ hostvars[groups['master'][0]]['token'] | default(k3s_token) }} {{ extra_agent_args | default("") }}
+ExecStart=/usr/local/bin/k3s agent --server https://{{ apiserver_endpoint | ansible.utils.ipwrap }}:6443 --token {{ hostvars[groups['master'][0]]['token'] | default(k3s_token) }} {{ extra_agent_args | default("") }}
 KillMode=process
 Delegate=yes
 # Having non-zero Limit*s causes performance problems due to accounting overhead

roles/k3s/post/defaults/main.yml

@@ -0,0 +1,3 @@
+---
+# Timeout to wait for MetalLB services to come up
+metal_lb_available_timeout: 120s

roles/k3s/post/tasks/main.yml

@@ -0,0 +1,94 @@
+---
+- name: Create manifests directory for temp configuration
+  file:
+    path: /tmp/k3s
+    state: directory
+    owner: "{{ ansible_user }}"
+    mode: 0755
+  with_items: "{{ groups['master'] }}"
+  run_once: true
+
+- name: Copy metallb CRs manifest to first master
+  template:
+    src: "metallb.crs.j2"
+    dest: "/tmp/k3s/metallb-crs.yaml"
+    owner: "{{ ansible_user }}"
+    mode: 0755
+  with_items: "{{ groups['master'] }}"
+  run_once: true
+
+- name: Test metallb-system namespace
+  command: >-
+    k3s kubectl -n metallb-system
+  changed_when: false
+  with_items: "{{ groups['master'] }}"
+  run_once: true
+
+- name: Wait for MetalLB resources
+  command: >-
+    k3s kubectl wait {{ item.resource }}
+    --namespace='metallb-system'
+    {% if item.name | default(False) -%}{{ item.name }}{%- endif %}
+    {% if item.selector | default(False) -%}--selector='{{ item.selector }}'{%- endif %}
+    {% if item.condition | default(False) -%}{{ item.condition }}{%- endif %}
+    --timeout='{{ metal_lb_available_timeout }}'
+  changed_when: false
+  run_once: true
+  with_items:
+    - description: controller
+      resource: deployment
+      name: controller
+      condition: --for condition=Available=True
+    - description: webhook service
+      resource: pod
+      selector: component=controller
+      condition: --for=jsonpath='{.status.phase}'=Running
+    - description: pods in replica sets
+      resource: pod
+      selector: component=controller,app=metallb
+      condition: --for condition=Ready
+    - description: ready replicas of controller
+      resource: replicaset
+      selector: component=controller,app=metallb
+      condition: --for=jsonpath='{.status.readyReplicas}'=1
+    - description: fully labeled replicas of controller
+      resource: replicaset
+      selector: component=controller,app=metallb
+      condition: --for=jsonpath='{.status.fullyLabeledReplicas}'=1
+    - description: available replicas of controller
+      resource: replicaset
+      selector: component=controller,app=metallb
+      condition: --for=jsonpath='{.status.availableReplicas}'=1
+  loop_control:
+    label: "{{ item.description }}"
+
+- name: Test metallb-system webhook-service endpoint
+  command: >-
+    k3s kubectl -n metallb-system get endpoints webhook-service
+  changed_when: false
+  with_items: "{{ groups['master'] }}"
+  run_once: true
+
+- name: Apply metallb CRs
+  command: >-
+    k3s kubectl apply -f /tmp/k3s/metallb-crs.yaml
+    --timeout='{{ metal_lb_available_timeout }}'
+  register: this
+  changed_when: false
+  run_once: true
+  until: this.rc == 0
+  retries: 5
+
+- name: Test metallb-system resources
+  command: >-
+    k3s kubectl -n metallb-system get {{ item }}
+  changed_when: false
+  run_once: true
+  with_items:
+    - IPAddressPool
+    - L2Advertisement
+
+- name: Remove tmp directory used for manifests
+  file:
+    path: /tmp/k3s
+    state: absent

roles/k3s/post/templates/metallb.crs.j2

@@ -0,0 +1,21 @@
+apiVersion: metallb.io/v1beta1
+kind: IPAddressPool
+metadata:
+  name: first-pool
+  namespace: metallb-system
+spec:
+  addresses:
+{% if metal_lb_ip_range is string %}
+{# metal_lb_ip_range was used in the legacy way: single string instead of a list #}
+{#   => transform to list with single element #}
+{% set metal_lb_ip_range = [metal_lb_ip_range] %}
+{% endif %}
+{% for range in metal_lb_ip_range %}
+  - {{ range }}
+{% endfor %}
+---
+apiVersion: metallb.io/v1beta1
+kind: L2Advertisement
+metadata:
+  name: default
+  namespace: metallb-system

roles/prereq/tasks/main.yml

@@ -23,6 +23,13 @@
     state: present
     reload: yes
 
+- name: Enable IPv6 router advertisements
+  sysctl:
+    name: net.ipv6.conf.all.accept_ra
+    value: "2"
+    state: present
+    reload: yes
+
 - name: Add br_netfilter to /etc/modules-load.d/
   copy:
     content: "br_netfilter"

roles/raspberrypi/defaults/main.yml

@@ -0,0 +1,6 @@
+---
+# Indicates whether the k3s prerequisites for Raspberry Pi should be set up
+# Possible values:
+#   - present
+#   - absent
+state: present

roles/raspberrypi/handlers/main.yml

@@ -1,3 +1,3 @@
 ---
-- name: reboot
+- name: Reboot
   reboot:

roles/raspberrypi/tasks/main.yml

@@ -47,13 +47,20 @@
     - raspberry_pi|default(false)
     - ansible_facts.lsb.description|default("") is match("Debian.*bullseye")
 
-- name: execute OS related tasks on the Raspberry Pi
+- name: execute OS related tasks on the Raspberry Pi - {{ action }}
   include_tasks: "{{ item }}"
   with_first_found:
-    - "prereq/{{ detected_distribution }}-{{ detected_distribution_major_version }}.yml"
-    - "prereq/{{ detected_distribution }}.yml"
-    - "prereq/{{ ansible_distribution }}-{{ ansible_distribution_major_version }}.yml"
-    - "prereq/{{ ansible_distribution }}.yml"
-    - "prereq/default.yml"
+    - "{{ action }}/{{ detected_distribution }}-{{ detected_distribution_major_version }}.yml"
+    - "{{ action }}/{{ detected_distribution }}.yml"
+    - "{{ action }}/{{ ansible_distribution }}-{{ ansible_distribution_major_version }}.yml"
+    - "{{ action }}/{{ ansible_distribution }}.yml"
+    - "{{ action }}/default.yml"
+  vars:
+    action: >-
+      {% if state == "present" -%}
+      setup
+      {%- else -%}
+      teardown
+      {%- endif %}
   when:
     - raspberry_pi|default(false)

roles/raspberrypi/tasks/setup/Raspbian.yml

@@ -13,7 +13,6 @@
 - name: Flush iptables before changing to iptables-legacy
   iptables:
     flush: true
-  changed_when: false   # iptables flush always returns changed
 
 - name: Changing to iptables-legacy
   alternatives:

roles/raspberrypi/tasks/setup/Rocky.yml

@@ -1,8 +1,9 @@
 ---
-- name: Enable cgroup via boot commandline if not already enabled for Centos
+- name: Enable cgroup via boot commandline if not already enabled for Rocky
   lineinfile:
     path: /boot/cmdline.txt
     backrefs: yes
     regexp: '^((?!.*\bcgroup_enable=cpuset cgroup_memory=1 cgroup_enable=memory\b).*)$'
     line: '\1 cgroup_enable=cpuset cgroup_memory=1 cgroup_enable=memory'
   notify: reboot
+  when: not ansible_check_mode

roles/raspberrypi/tasks/setup/Ubuntu.yml

@@ -8,5 +8,6 @@
   notify: reboot
 
 - name: Install linux-modules-extra-raspi
-  apt: name=linux-modules-extra-raspi state=present
-  when: raspberry_pi
+  apt:
+    name: linux-modules-extra-raspi
+    state: present

roles/raspberrypi/tasks/teardown/Raspbian.yml

@@ -0,0 +1 @@
+---

roles/raspberrypi/tasks/teardown/Rocky.yml

@@ -0,0 +1 @@
+---

roles/raspberrypi/tasks/teardown/Ubuntu.yml

@@ -0,0 +1,5 @@
+---
+- name: Remove linux-modules-extra-raspi
+  apt:
+    name: linux-modules-extra-raspi
+    state: absent

roles/raspberrypi/tasks/teardown/default.yml

@@ -0,0 +1 @@
+---

roles/reset/tasks/main.yml

@@ -10,7 +10,7 @@
     - k3s-node
     - k3s-init
 
-- name: pkill -9 -f "k3s/data/[^/]+/bin/containerd-shim-runc"
+- name: RUN pkill -9 -f "k3s/data/[^/]+/bin/containerd-shim-runc"
   register: pkill_containerd_shim_runc
   command: pkill -9 -f "k3s/data/[^/]+/bin/containerd-shim-runc"
   changed_when: "pkill_containerd_shim_runc.rc == 0"
@@ -44,16 +44,13 @@
     - /var/lib/kubelet
     - /var/lib/rancher/k3s
     - /var/lib/rancher/
-    - /usr/local/bin/k3s
     - /var/lib/cni/
 
-- name: daemon_reload
+- name: Reload daemon_reload
   systemd:
     daemon_reload: yes
 
-- name: Remove linux-modules-extra-raspi
-  apt: name=linux-modules-extra-raspi state=absent
-
-- name: Reboot and wait for node to come back up
-  reboot:
-    reboot_timeout: 3600
+- name: Remove tmp directory used for manifests
+  file:
+    path: /tmp/k3s
+    state: absent

site.yml

@@ -17,3 +17,8 @@
   become: yes
   roles:
     - role: k3s/node
+
+- hosts: master
+  become: yes
+  roles:
+    - role: k3s/post

vagrant/Vagrantfile

@@ -1,79 +0,0 @@
-# -*- mode: ruby -*-
-# vi: set ft=ruby :
-
-Vagrant.configure("2") do |config|
-    # General configuration
-    config.vm.box = "generic/ubuntu2110"
-    config.vm.synced_folder ".", "/vagrant", disabled: true
-    config.ssh.insert_key = false
-
-    config.vm.provider :virtualbox do |v|
-        v.memory = 4096
-        v.cpus = 2
-        v.linked_clone = true
-    end
-
-    # Control Node 1
-    config.vm.define "control1" do |control1|
-        control1.vm.hostname = "control1"
-        control1.vm.network "private_network", ip: "192.168.30.38"
-    end
-
-    # Control Node 2
-    config.vm.define "control2" do |control2|
-        control2.vm.hostname = "control2"
-        control2.vm.network "private_network", ip: "192.168.30.39"
-    end
-
-    # Control Node 3
-    config.vm.define "control3" do |control3|
-        control3.vm.hostname = "control3"
-        control3.vm.network "private_network", ip: "192.168.30.40"
-    end
-
-    # Worker Node 1
-    config.vm.define "node1" do |node1|
-        node1.vm.hostname = "node1"
-        node1.vm.network "private_network", ip: "192.168.30.41"
-    end
-
-    # Worker Node 2
-    config.vm.define "node2" do |node2|
-        node2.vm.hostname = "node2"
-        node2.vm.network "private_network", ip: "192.168.30.42"
-    end
-
-    config.vm.provision "ansible",type: "ansible", run: "never" do |ansible|
-        ansible.playbook = "../site.yml"
-        ansible.limit = "all"
-        ansible.groups = {
-          "master" => ["control1", "control2", "control3"],
-          "node" => ["node1", "node2"],
-          "k3s_cluster:children" => ["master", "node"],
-          "k3s_cluster:vars" => {"k3s_version" => "v1.23.4+k3s1",
-                                 "ansible_user" => "vagrant",
-                                 "systemd_dir" => "/etc/systemd/system",
-                                 "flannel_iface" => "eth1",
-                                 "apiserver_endpoint" => "192.168.30.222",
-                                 "k3s_token" => "supersecret",
-                                 "extra_server_args" => "--node-ip={{ ansible_eth1.ipv4.address }} --flannel-iface={{ flannel_iface }} --no-deploy servicelb --no-deploy traefik",
-                                 "extra_agent_args" => "--flannel-iface={{ flannel_iface }}",
-                                 "kube_vip_tag_version" => "v0.4.2",
-                                 "metal_lb_speaker_tag_version" => "v0.12.1",
-                                 "metal_lb_controller_tag_version" => "v0.12.1",
-                                 "metal_lb_ip_range" => "192.168.30.80-192.168.30.90",
-                                 "retry_count" => "30"}
-        }
-        ansible.host_vars = {
-          "control1" => {
-            "server_init_args" => "--cluster-init --token {{ k3s_token }} {{ extra_server_args | default('') }}"
-          },
-          "control2" => {
-            "server_init_args" => "--server https://192.168.30.38:6443 --token {{ k3s_token }} {{ extra_server_args | default('') }}"
-          },
-          "control3" => {
-            "server_init_args" => "--server https://192.168.30.38:6443 --token {{ k3s_token }} {{ extra_server_args | default('') }}"
-          }
-        }
-    end
-end