k3s_server: add kube_vip_arp parameter (#550)

With the kube_vip_arp parameter it is possible to set or unset the
vip_arp environment variable of the kube-vip-ds daemonset. The value of
the kube_vip_arp is true by default to not change the existing default.

Signed-off-by: Christian Berendt <berendt@osism.tech>
Co-authored-by: Techno Tim <timothystewart6@gmail.com>

.ansible-lint

@@ -13,5 +13,9 @@ exclude_paths:
   - 'molecule/**/prepare.yml'
   - 'molecule/**/reset.yml'
 
+  # The file was generated by galaxy ansible - don't mess with it.
+  - 'galaxy.yml'
+
 skip_list:
   - 'fqcn-builtins'
+  - var-naming[no-role-prefix]

.github/ISSUE_TEMPLATE.md

@@ -37,6 +37,11 @@ systemd_dir: ""
 
 flannel_iface: ""
 
+#calico_iface: ""
+calico_ebpf: ""
+calico_cidr: ""
+calico_tag: ""
+
 apiserver_endpoint: ""
 
 k3s_token: "NA"
@@ -46,6 +51,9 @@ extra_agent_args: ""
 
 kube_vip_tag_version: ""
 
+kube_vip_cloud_provider_tag_version: ""
+kube_vip_lb_ip_range: ""
+
 metal_lb_speaker_tag_version: ""
 metal_lb_controller_tag_version: ""
 

.github/dependabot.yml

@@ -9,3 +9,18 @@ updates:
     ignore:
       - dependency-name: "*"
         update-types: ["version-update:semver-major"]
+
+  - package-ecosystem: "github-actions"
+    directory: "/"
+    schedule:
+      interval: "daily"
+    rebase-strategy: "auto"
+
+  - package-ecosystem: "docker"
+    directory: "/"
+    schedule:
+      interval: "daily"
+    rebase-strategy: "auto"
+    ignore:
+      - dependency-name: "*"
+        update-types: ["version-update:semver-major"]

.github/download-boxes.sh

@@ -9,12 +9,17 @@ set -euo pipefail
 GIT_ROOT=$(git rev-parse --show-toplevel)
 PROVIDER=virtualbox
 
-# Read all boxes for all platforms from the "molecule.yml" files
+yq --version
-all_boxes=$(cat "${GIT_ROOT}"/molecule/*/molecule.yml |
+
-    yq -r '.platforms[].box' |         # Read the "box" property of each node under "platforms"
+# Define the path to the molecule.yml files
-    grep --invert-match --regexp=--- | # Filter out file separators
+MOLECULE_YML_PATH="${GIT_ROOT}/molecule/*/molecule.yml"
-    sort |
+
-    uniq)
+# Extract and sort unique boxes from all molecule.yml files
+all_boxes=$(for file in $MOLECULE_YML_PATH; do
+    yq eval '.platforms[].box' "$file"
+done | sort -u)
+
+echo all_boxes: "$all_boxes"
 
 # Read the boxes that are currently present on the system (for the current provider)
 present_boxes=$(

.github/workflows/cache.yml

@@ -0,0 +1,42 @@
+---
+name: "Cache"
+on:
+  workflow_call:
+jobs:
+  molecule:
+    name: cache
+    runs-on: self-hosted
+    env:
+      PYTHON_VERSION: "3.11"
+
+    steps:
+      - name: Check out the codebase
+        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332 # 4.1.7
+        with:
+          ref: ${{ github.event.pull_request.head.sha }}
+
+      - name: Set up Python ${{ env.PYTHON_VERSION }}
+        uses: actions/setup-python@39cd14951b08e74b54015e9e001cdefcf80e669f # 5.1.1
+        with:
+          python-version: ${{ env.PYTHON_VERSION }}
+          cache: 'pip' # caching pip dependencies
+
+      - name: Cache Vagrant boxes
+        id: cache-vagrant
+        uses: actions/cache@0c45773b623bea8c8e75f6c82b208c3cf94ea4f9 # 4.0.2
+        with:
+          lookup-only: true #if it exists, we don't need to restore and can skip the next step
+          path: |
+            ~/.vagrant.d/boxes
+          key: vagrant-boxes-${{ 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.
+        if: steps.cache-vagrant.outputs.cache-hit != 'true' # only run if false since this is just a cache step
+        run: |
+          ./.github/download-boxes.sh
+          vagrant box list

.github/workflows/ci.yml

@@ -2,14 +2,26 @@
 name: "CI"
 on:
   pull_request:
-  push:
+    types:
-    branches:
+      - opened
-      - master
+      - synchronize
     paths-ignore:
-      - '**/README.md'
+      - '**/.gitignore'
+      - '**/FUNDING.yml'
+      - '**/host.ini'
+      - '**/*.md'
+      - '**/.editorconfig'
+      - '**/ansible.example.cfg'
+      - '**/deploy.sh'
+      - '**/LICENSE'
+      - '**/reboot.sh'
+      - '**/reset.sh'
 jobs:
+  pre:
+    uses: ./.github/workflows/cache.yml
   lint:
     uses: ./.github/workflows/lint.yml
+    needs: [pre]
   test:
     uses: ./.github/workflows/test.yml
-    needs: [lint]
+    needs: [pre, lint]

.github/workflows/lint.yml

@@ -5,37 +5,27 @@ on:
 jobs:
   pre-commit-ci:
     name: Pre-Commit
-    runs-on: ubuntu-latest
+    runs-on: self-hosted
     env:
       PYTHON_VERSION: "3.11"
 
     steps:
       - name: Check out the codebase
-        uses: actions/checkout@e2f20e631ae6d7dd3b768f56a5d2af784dd54791 # v3 2.5.0
+        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332 # 4.1.7
         with:
           ref: ${{ github.event.pull_request.head.sha }}
 
       - name: Set up Python ${{ env.PYTHON_VERSION }}
-        uses: actions/setup-python@75f3110429a8c05be0e1bf360334e4cced2b63fa # 2.3.3
+        uses: actions/setup-python@39cd14951b08e74b54015e9e001cdefcf80e669f # 5.1.1
         with:
           python-version: ${{ env.PYTHON_VERSION }}
           cache: 'pip' # caching pip dependencies
 
-      - name: Cache pip
+      - name: Restore Ansible cache
-        uses: actions/cache@9b0c1fce7a93df8e3bb8926b0d6e9d89e92f20a7 # 3.0.11
+        uses: actions/cache/restore@0c45773b623bea8c8e75f6c82b208c3cf94ea4f9 # 4.0.2
-        with:
-          path: ~/.cache/pip
-          key: ${{ runner.os }}-pip-${{ hashFiles('./requirements.txt') }}
-          restore-keys: |
-            ${{ runner.os }}-pip-
-
-      - name: Cache Ansible
-        uses: actions/cache@9b0c1fce7a93df8e3bb8926b0d6e9d89e92f20a7 # 3.0.11
         with:
           path: ~/.ansible/collections
-          key: ${{ runner.os }}-ansible-${{ hashFiles('collections/requirements.txt') }}
+          key: ansible-${{ hashFiles('collections/requirements.yml') }}
-          restore-keys: |
-            ${{ runner.os }}-ansible-
 
       - name: Install dependencies
         run: |
@@ -47,21 +37,17 @@ jobs:
           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
+        uses: pre-commit/action@2c7b3805fd2a0fd8c1884dcaebf91fc102a13ecd # 3.0.1
 
   ensure-pinned-actions:
     name: Ensure SHA Pinned Actions
-    runs-on: ubuntu-latest
+    runs-on: self-hosted
     steps:
       - name: Checkout code
-        uses: actions/checkout@e2f20e631ae6d7dd3b768f56a5d2af784dd54791 # v3 2.5.0
+        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332 # 4.1.7
       - name: Ensure SHA pinned actions
-        uses: zgosalvez/github-actions-ensure-sha-pinned-actions@af2eb3226618e2494e3d9084f515ad6dcf16e229 # 2.0.1
+        uses: zgosalvez/github-actions-ensure-sha-pinned-actions@b88cd0aad2c36a63e42c71f81cb1958fed95ac87 # 3.0.10
         with:
           allowlist: |
             aws-actions/

.github/workflows/test.yml

@@ -5,23 +5,51 @@ on:
 jobs:
   molecule:
     name: Molecule
-    runs-on: macos-12
+    runs-on: self-hosted
     strategy:
       matrix:
         scenario:
           - default
-          - ipv6
+          # - ipv6
           - single_node
+          - calico
+          - cilium
+          - kube-vip
       fail-fast: false
     env:
       PYTHON_VERSION: "3.11"
 
     steps:
       - name: Check out the codebase
-        uses: actions/checkout@e2f20e631ae6d7dd3b768f56a5d2af784dd54791 # v3 2.5.0
+        uses: actions/checkout@692973e3d937129bcbf40652eb9f2f61becf3332 # 4.1.7
         with:
           ref: ${{ github.event.pull_request.head.sha }}
 
+      # these steps are necessary if not using ephemeral nodes
+      - name: Delete old Vagrant box versions
+        if: always() # do this even if a step before has failed
+        run: vagrant box prune --force
+
+      - name: Remove all local Vagrant boxes
+        if: always() # do this even if a step before has failed
+        run: if vagrant box list 2>/dev/null; then vagrant box list | cut -f 1 -d ' ' | xargs -L 1 vagrant box remove -f 2>/dev/null && echo "All Vagrant boxes removed." || echo "No Vagrant boxes found."; else echo "No Vagrant boxes found."; fi
+
+      - name: Remove all Virtualbox VMs
+        if: always() # do this even if a step before has failed
+        run: VBoxManage list vms | awk -F'"' '{print $2}' | xargs -I {} VBoxManage unregistervm --delete "{}"
+
+      - name: Remove all Virtualbox HDs
+        if: always() # do this even if a step before has failed
+        run: VBoxManage list hdds | awk -F':' '/^UUID:/ {print $2}' | xargs -I {} VBoxManage closemedium disk "{}" --delete
+
+      - name: Remove all Virtualbox Networks
+        if: always() # do this even if a step before has failed
+        run: VBoxManage list hostonlyifs | grep '^Name:' | awk '{print $2}' | grep '^vboxnet' | xargs -I {} VBoxManage hostonlyif remove {}
+
+      - name: Remove Virtualbox network config
+        if: always() # do this even if a step before has failed
+        run: sudo rm /etc/vbox/networks.conf || true
+
       - name: Configure VirtualBox
         run: |-
           sudo mkdir -p /etc/vbox
@@ -30,35 +58,19 @@ jobs:
           * 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@75f3110429a8c05be0e1bf360334e4cced2b63fa # 2.3.3
+        uses: actions/setup-python@39cd14951b08e74b54015e9e001cdefcf80e669f # 5.1.1
         with:
           python-version: ${{ env.PYTHON_VERSION }}
           cache: 'pip' # caching pip dependencies
 
+      - name: Restore vagrant Boxes cache
+        uses: actions/cache/restore@0c45773b623bea8c8e75f6c82b208c3cf94ea4f9 # 4.0.2
+        with:
+          path: ~/.vagrant.d/boxes
+          key: vagrant-boxes-${{ hashFiles('**/molecule.yml') }}
+          fail-on-cache-miss: true
+
       - name: Install dependencies
         run: |
           echo "::group::Upgrade pip"
@@ -75,18 +87,40 @@ jobs:
         env:
           ANSIBLE_K3S_LOG_DIR: ${{ runner.temp }}/logs/k3s-ansible/${{ matrix.scenario }}
           ANSIBLE_SSH_RETRIES: 4
-          ANSIBLE_TIMEOUT: 60
+          ANSIBLE_TIMEOUT: 120
           PY_COLORS: 1
           ANSIBLE_FORCE_COLOR: 1
 
+      # these steps are necessary if not using ephemeral nodes
+      - name: Delete old Vagrant box versions
+        if: always() # do this even if a step before has failed
+        run: vagrant box prune --force
+
+      - name: Remove all local Vagrant boxes
+        if: always() # do this even if a step before has failed
+        run: if vagrant box list 2>/dev/null; then vagrant box list | cut -f 1 -d ' ' | xargs -L 1 vagrant box remove -f 2>/dev/null && echo "All Vagrant boxes removed." || echo "No Vagrant boxes found."; else echo "No Vagrant boxes found."; fi
+
+      - name: Remove all Virtualbox VMs
+        if: always() # do this even if a step before has failed
+        run: VBoxManage list vms | awk -F'"' '{print $2}' | xargs -I {} VBoxManage unregistervm --delete "{}"
+
+      - name: Remove all Virtualbox HDs
+        if: always() # do this even if a step before has failed
+        run: VBoxManage list hdds | awk -F':' '/^UUID:/ {print $2}' | xargs -I {} VBoxManage closemedium disk "{}" --delete
+
+      - name: Remove all Virtualbox Networks
+        if: always() # do this even if a step before has failed
+        run: VBoxManage list hostonlyifs | grep '^Name:' | awk '{print $2}' | grep '^vboxnet' | xargs -I {} VBoxManage hostonlyif remove {}
+
+      - name: Remove Virtualbox network config
+        if: always() # do this even if a step before has failed
+        run: sudo rm /etc/vbox/networks.conf || true
+
       - name: Upload log files
         if: always() # do this even if a step before has failed
-        uses: actions/upload-artifact@83fd05a356d7e2593de66fc9913b3002723633cb # 3.1.1
+        uses: actions/upload-artifact@0b2256b8c012f0828dc542b3febcab082c67f72b # 4.3.4
         with:
           name: logs
           path: |
             ${{ runner.temp }}/logs
-
+          overwrite: true
-      - name: Delete old box versions
-        if: always() # do this even if a step before has failed
-        run: vagrant box prune --force

.gitignore

@@ -1,3 +1,4 @@
 .env/
 *.log
 ansible.cfg
+kubeconfig

.pre-commit-config.yaml

@@ -1,7 +1,7 @@
 ---
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: f71fa2c1f9cf5cb705f73dffe4b21f7c61470ba9  # frozen: v4.4.0
+    rev: v4.5.0
     hooks:
       - id: requirements-txt-fixer
       - id: sort-simple-yaml
@@ -12,24 +12,24 @@ repos:
       - id: trailing-whitespace
         args: [--markdown-linebreak-ext=md]
   - repo: https://github.com/adrienverge/yamllint.git
-    rev: b05e028c5881819161d11cb543fd96a30c06cceb  # frozen: v1.32.0
+    rev: v1.33.0
     hooks:
       - id: yamllint
         args: [-c=.yamllint]
   - repo: https://github.com/ansible-community/ansible-lint.git
-    rev: 3293b64b939c0de16ef8cb81dd49255e475bf89a  # frozen: v6.17.2
+    rev: v6.22.2
     hooks:
       - id: ansible-lint
   - repo: https://github.com/shellcheck-py/shellcheck-py
-    rev: 375289a39f5708101b1f916eb729e8d6da96993f  # frozen: v0.9.0.5
+    rev: v0.9.0.6
     hooks:
       - id: shellcheck
   - repo: https://github.com/Lucas-C/pre-commit-hooks
-    rev: 12885e376b93dc4536ad68d156065601e4433665  # frozen: v1.5.1
+    rev: v1.5.4
     hooks:
       - id: remove-crlf
       - id: remove-tabs
   - repo: https://github.com/sirosen/texthooks
-    rev: c4ffd3e31669dd4fa4d31a23436cc13839730084  # frozen: 0.5.0
+    rev: 0.6.4
     hooks:
       - id: fix-smartquotes

.yamllint

@@ -6,4 +6,6 @@ rules:
     max: 120
     level: warning
   truthy:
-    allowed-values: ['true', 'false', 'yes', 'no']
+    allowed-values: ['true', 'false']
+ignore:
+  - galaxy.yml

README.md

@@ -4,7 +4,7 @@
 
 This playbook will build an HA Kubernetes cluster with `k3s`, `kube-vip` and MetalLB via `ansible`.
 
-This is based on the work from [this fork](https://github.com/212850a/k3s-ansible) which is based on the work from [k3s-io/k3s-ansible](https://github.com/k3s-io/k3s-ansible). It uses [kube-vip](https://kube-vip.chipzoller.dev/) to create a load balancer for control plane, and [metal-lb](https://metallb.universe.tf/installation/) for its service `LoadBalancer`.
+This is based on the work from [this fork](https://github.com/212850a/k3s-ansible) which is based on the work from [k3s-io/k3s-ansible](https://github.com/k3s-io/k3s-ansible). It uses [kube-vip](https://kube-vip.io/) to create a load balancer for control plane, and [metal-lb](https://metallb.universe.tf/installation/) for its service `LoadBalancer`.
 
 If you want more context on how this works, see:
 
@@ -96,8 +96,22 @@ ansible-playbook reset.yml -i inventory/my-cluster/hosts.ini
 To copy your `kube config` locally so that you can access your **Kubernetes** cluster run:
 
 ```bash
-scp debian@master_ip:~/.kube/config ~/.kube/config
+scp debian@master_ip:/etc/rancher/k3s/k3s.yaml ~/.kube/config
 ```
+If you get file Permission denied, go into the node and temporarly run:
+```bash
+sudo chmod 777 /etc/rancher/k3s/k3s.yaml
+```
+Then copy with the scp command and reset the permissions back to:
+```bash
+sudo chmod 600 /etc/rancher/k3s/k3s.yaml
+```
+
+You'll then want to modify the config to point to master IP by running:
+```bash
+sudo nano ~/.kube/config
+```
+Then change `server: https://127.0.0.1:6443` to match your master IP: `server: https://192.168.1.222:6443`
 
 ### 🔨 Testing your cluster
 
@@ -118,6 +132,28 @@ You can find more information about it [here](molecule/README.md).
 
 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/)
 
+## 🌌 Ansible Galaxy
+
+This collection can now be used in larger ansible projects.
+
+Instructions:
+
+- create or modify a file `collections/requirements.yml` in your project
+
+```yml
+collections:
+  - name: ansible.utils
+  - name: community.general
+  - name: ansible.posix
+  - name: kubernetes.core
+  - name: https://github.com/techno-tim/k3s-ansible.git
+    type: git
+    version: master
+```
+
+- install via `ansible-galaxy collection install -r ./collections/requirements.yml`
+- every role is now available via the prefix `techno_tim.k3s_ansible.` e.g. `techno_tim.k3s_ansible.lxc`
+
 ## Thanks 🤝
 
 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:

galaxy.yml

@@ -0,0 +1,81 @@
+### REQUIRED
+# The namespace of the collection. This can be a company/brand/organization or product namespace under which all
+# content lives. May only contain alphanumeric lowercase characters and underscores. Namespaces cannot start with
+# underscores or numbers and cannot contain consecutive underscores
+namespace: techno_tim
+
+# The name of the collection. Has the same character restrictions as 'namespace'
+name: k3s_ansible
+
+# The version of the collection. Must be compatible with semantic versioning
+version: 1.0.0
+
+# The path to the Markdown (.md) readme file. This path is relative to the root of the collection
+readme: README.md
+
+# A list of the collection's content authors. Can be just the name or in the format 'Full Name <email> (url)
+# @nicks:irc/im.site#channel'
+authors:
+- your name <example@domain.com>
+
+
+### OPTIONAL but strongly recommended
+# A short summary description of the collection
+description: >
+  The easiest way to bootstrap a self-hosted High Availability Kubernetes
+  cluster. A fully automated HA k3s etcd install with kube-vip, MetalLB,
+  and more.
+
+# Either a single license or a list of licenses for content inside of a collection. Ansible Galaxy currently only
+# accepts L(SPDX,https://spdx.org/licenses/) licenses. This key is mutually exclusive with 'license_file'
+license:
+- Apache-2.0
+
+
+# A list of tags you want to associate with the collection for indexing/searching. A tag name has the same character
+# requirements as 'namespace' and 'name'
+tags:
+  - etcd
+  - high-availability
+  - k8s
+  - k3s
+  - k3s-cluster
+  - kube-vip
+  - kubernetes
+  - metallb
+  - rancher
+
+# Collections that this collection requires to be installed for it to be usable. The key of the dict is the
+# collection label 'namespace.name'. The value is a version range
+# L(specifiers,https://python-semanticversion.readthedocs.io/en/latest/#requirement-specification). Multiple version
+# range specifiers can be set and are separated by ','
+dependencies:
+  ansible.utils: '*'
+  ansible.posix: '*'
+  community.general: '*'
+  kubernetes.core: '*'
+
+# The URL of the originating SCM repository
+repository: https://github.com/techno-tim/k3s-ansible
+
+# The URL to any online docs
+documentation: https://github.com/techno-tim/k3s-ansible
+
+# The URL to the homepage of the collection/project
+homepage: https://www.youtube.com/watch?v=CbkEWcUZ7zM
+
+# The URL to the collection issue tracker
+issues: https://github.com/techno-tim/k3s-ansible/issues
+
+# A list of file glob-like patterns used to filter any files or directories that should not be included in the build
+# artifact. A pattern is matched from the relative path of the file or directory of the collection directory. This
+# uses 'fnmatch' to match the files or directories. Some directories and files like 'galaxy.yml', '*.pyc', '*.retry',
+# and '.git' are always filtered. Mutually exclusive with 'manifest'
+build_ignore: []
+
+# A dict controlling use of manifest directives used in building the collection artifact. The key 'directives' is a
+# list of MANIFEST.in style
+# L(directives,https://packaging.python.org/en/latest/guides/using-manifest-in/#manifest-in-commands). The key
+# 'omit_default_directives' is a boolean that controls whether the default directives are used. Mutually exclusive
+# with 'build_ignore'
+# manifest: null

inventory/sample/group_vars/all.yml

@@ -1,5 +1,5 @@
 ---
-k3s_version: v1.27.4+k3s1
+k3s_version: v1.30.2+k3s2
 # this is the user that has ssh access to these machines
 ansible_user: ansibleuser
 systemd_dir: /etc/systemd/system
@@ -10,6 +10,30 @@ system_timezone: "Your/Timezone"
 # interface which will be used for flannel
 flannel_iface: "eth0"
 
+# uncomment calico_iface to use tigera operator/calico cni instead of flannel https://docs.tigera.io/calico/latest/about
+# calico_iface: "eth0"
+calico_ebpf: false           # use eBPF dataplane instead of iptables
+calico_tag: "v3.28.0"        # calico version tag
+
+# uncomment cilium_iface to use cilium cni instead of flannel or calico
+# ensure v4.19.57, v5.1.16, v5.2.0 or more recent kernel
+# cilium_iface: "eth0"
+cilium_mode: "native"        # native when nodes on same subnet or using bgp, else set routed
+cilium_tag: "v1.16.0"        # cilium version tag
+cilium_hubble: true          # enable hubble observability relay and ui
+
+# if using calico or cilium, you may specify the cluster pod cidr pool
+cluster_cidr: "10.52.0.0/16"
+
+# enable cilium bgp control plane for lb services and pod cidrs. disables metallb.
+cilium_bgp: false
+
+# bgp parameters for cilium cni. only active when cilium_iface is defined and cilium_bgp is true.
+cilium_bgp_my_asn: "64513"
+cilium_bgp_peer_asn: "64512"
+cilium_bgp_peer_address: "192.168.30.1"
+cilium_bgp_lb_cidr: "192.168.31.0/24"   # cidr for cilium loadbalancer ipam
+
 # apiserver_endpoint is virtual ip-address which will be configured on each master
 apiserver_endpoint: "192.168.30.222"
 
@@ -20,28 +44,42 @@ k3s_token: "some-SUPER-DEDEUPER-secret-password"
 # 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"] }}'
+k3s_node_ip: "{{ ansible_facts[(cilium_iface | default(calico_iface | default(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 }}
+  {{ '--flannel-iface=' + flannel_iface if calico_iface is not defined and cilium_iface is not defined else '' }}
   --node-ip={{ k3s_node_ip }}
 
 # change these to your liking, the only required are: --disable servicelb, --tls-san {{ apiserver_endpoint }}
+# the contents of the if block is also required if using calico or cilium
 extra_server_args: >-
   {{ extra_args }}
   {{ '--node-taint node-role.kubernetes.io/master=true:NoSchedule' if k3s_master_taint else '' }}
+  {% if calico_iface is defined or cilium_iface is defined %}
+  --flannel-backend=none
+  --disable-network-policy
+  --cluster-cidr={{ cluster_cidr | default('10.52.0.0/16') }}
+  {% endif %}
   --tls-san {{ apiserver_endpoint }}
   --disable servicelb
   --disable traefik
+
 extra_agent_args: >-
   {{ extra_args }}
 
 # image tag for kube-vip
-kube_vip_tag_version: "v0.5.12"
+kube_vip_tag_version: "v0.8.2"
+
+# tag for kube-vip-cloud-provider manifest
+# kube_vip_cloud_provider_tag_version: "main"
+
+# kube-vip ip range for load balancer
+# (uncomment to use kube-vip for services instead of MetalLB)
+# kube_vip_lb_ip_range: "192.168.30.80-192.168.30.90"
 
 # metallb type frr or native
 metal_lb_type: "native"
@@ -55,8 +93,8 @@ metal_lb_mode: "layer2"
 # metal_lb_bgp_peer_address: "192.168.30.1"
 
 # image tag for metal lb
-metal_lb_speaker_tag_version: "v0.13.9"
+metal_lb_speaker_tag_version: "v0.14.8"
-metal_lb_controller_tag_version: "v0.13.9"
+metal_lb_controller_tag_version: "v0.14.8"
 
 # metallb ip range for load balancer
 metal_lb_ip_range: "192.168.30.80-192.168.30.90"
@@ -66,9 +104,9 @@ metal_lb_ip_range: "192.168.30.80-192.168.30.90"
 # Please read https://gist.github.com/triangletodd/02f595cd4c0dc9aac5f7763ca2264185 before using this.
 # Most notably, your containers must be privileged, and must not have nesting set to true.
 # Please note this script disables most of the security of lxc containers, with the trade off being that lxc
-# containers are significantly more resource efficent compared to full VMs.
+# containers are significantly more resource efficient compared to full VMs.
 # Mixing and matching VMs and lxc containers is not supported, ymmv if you want to do this.
-# I would only really recommend using this if you have partiularly low powered proxmox nodes where the overhead of
+# I would only really recommend using this if you have particularly low powered proxmox nodes where the overhead of
 # VMs would use a significant portion of your available resources.
 proxmox_lxc_configure: false
 # the user that you would use to ssh into the host, for example if you run ssh some-user@my-proxmox-host,
@@ -81,3 +119,53 @@ proxmox_lxc_ct_ids:
   - 202
   - 203
   - 204
+
+# Only enable this if you have set up your own container registry to act as a mirror / pull-through cache
+# (harbor / nexus / docker's official registry / etc).
+# Can be beneficial for larger dev/test environments (for example if you're getting rate limited by docker hub),
+# or air-gapped environments where your nodes don't have internet access after the initial setup
+# (which is still needed for downloading the k3s binary and such).
+# k3s's documentation about private registries here: https://docs.k3s.io/installation/private-registry
+custom_registries: false
+# The registries can be authenticated or anonymous, depending on your registry server configuration.
+# If they allow anonymous access, simply remove the following bit from custom_registries_yaml
+#   configs:
+#     "registry.domain.com":
+#       auth:
+#         username: yourusername
+#         password: yourpassword
+# The following is an example that pulls all images used in this playbook through your private registries.
+# It also allows you to pull your own images from your private registry, without having to use imagePullSecrets
+# in your deployments.
+# If all you need is your own images and you don't care about caching the docker/quay/ghcr.io images,
+# you can just remove those from the mirrors: section.
+custom_registries_yaml: |
+  mirrors:
+    docker.io:
+      endpoint:
+        - "https://registry.domain.com/v2/dockerhub"
+    quay.io:
+      endpoint:
+        - "https://registry.domain.com/v2/quayio"
+    ghcr.io:
+      endpoint:
+        - "https://registry.domain.com/v2/ghcrio"
+    registry.domain.com:
+      endpoint:
+        - "https://registry.domain.com"
+
+  configs:
+    "registry.domain.com":
+      auth:
+        username: yourusername
+        password: yourpassword
+
+# On some distros like Diet Pi, there is no dbus installed. dbus required by the default reboot command.
+# Uncomment if you need a custom reboot command
+# custom_reboot_command: /usr/sbin/shutdown -r now
+
+# Only enable and configure these if you access the internet through a proxy
+# proxy_env:
+#   HTTP_PROXY: "http://proxy.domain.local:3128"
+#   HTTPS_PROXY: "http://proxy.domain.local:3128"
+#   NO_PROXY: "*.domain.local,127.0.0.0/8,10.0.0.0/8,172.16.0.0/12,192.168.0.0/16"

molecule/README.md

@@ -13,6 +13,12 @@ We have these scenarios:
   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.
+- **calico**:
+  The same as single node, but uses calico cni instead of flannel.
+- **cilium**:
+  The same as single node, but uses cilium cni instead of flannel.
+- **kube-vip**
+  The same as single node, but uses kube-vip as service loadbalancer instead of MetalLB
 
 ## How to execute
 

molecule/calico/molecule.yml

@@ -0,0 +1,49 @@
+---
+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: 192.168.30.62
+provisioner:
+  name: ansible
+  env:
+    ANSIBLE_VERBOSITY: 1
+  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
+    - 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/calico/overrides.yml

@@ -0,0 +1,16 @@
+---
+- 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
+        calico_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 other scenarios
+        apiserver_endpoint: "192.168.30.224"
+        metal_lb_ip_range: "192.168.30.100-192.168.30.109"

molecule/cilium/molecule.yml

@@ -0,0 +1,49 @@
+---
+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: 192.168.30.63
+provisioner:
+  name: ansible
+  env:
+    ANSIBLE_VERBOSITY: 1
+  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
+    - 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/cilium/overrides.yml

@@ -0,0 +1,16 @@
+---
+- 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
+        cilium_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 other scenarios
+        apiserver_endpoint: "192.168.30.225"
+        metal_lb_ip_range: "192.168.30.110-192.168.30.119"

molecule/default/molecule.yml

@@ -7,7 +7,7 @@ platforms:
 
   - name: control1
     box: generic/ubuntu2204
-    memory: 2048
+    memory: 1024
     cpus: 2
     groups:
       - k3s_cluster
@@ -22,8 +22,8 @@ platforms:
       ssh.password: "vagrant"
 
   - name: control2
-    box: generic/debian11
+    box: generic/debian12
-    memory: 2048
+    memory: 1024
     cpus: 2
     groups:
       - k3s_cluster
@@ -34,7 +34,7 @@ platforms:
 
   - name: control3
     box: generic/rocky9
-    memory: 2048
+    memory: 1024
     cpus: 2
     groups:
       - k3s_cluster
@@ -45,7 +45,7 @@ platforms:
 
   - name: node1
     box: generic/ubuntu2204
-    memory: 2048
+    memory: 1024
     cpus: 2
     groups:
       - k3s_cluster
@@ -61,7 +61,7 @@ platforms:
 
   - name: node2
     box: generic/rocky9
-    memory: 2048
+    memory: 1024
     cpus: 2
     groups:
       - k3s_cluster
@@ -72,6 +72,8 @@ platforms:
 
 provisioner:
   name: ansible
+  env:
+    ANSIBLE_VERBOSITY: 1
   playbooks:
     converge: ../resources/converge.yml
     side_effect: ../resources/reset.yml
@@ -82,7 +84,6 @@ provisioner:
 scenario:
   test_sequence:
     - dependency
-    - lint
     - cleanup
     - destroy
     - syntax

molecule/default/prepare.yml

@@ -17,6 +17,6 @@
       # and security needs.
       ansible.builtin.systemd:
         name: firewalld
-        enabled: no
+        enabled: false
         state: stopped
       become: true

molecule/ipv6/molecule.yml

@@ -6,7 +6,7 @@ driver:
 platforms:
   - name: control1
     box: generic/ubuntu2204
-    memory: 2048
+    memory: 1024
     cpus: 2
     groups:
       - k3s_cluster
@@ -22,7 +22,7 @@ platforms:
 
   - name: control2
     box: generic/ubuntu2204
-    memory: 2048
+    memory: 1024
     cpus: 2
     groups:
       - k3s_cluster
@@ -38,7 +38,7 @@ platforms:
 
   - name: node1
     box: generic/ubuntu2204
-    memory: 2048
+    memory: 1024
     cpus: 2
     groups:
       - k3s_cluster
@@ -53,6 +53,8 @@ platforms:
       ssh.password: "vagrant"
 provisioner:
   name: ansible
+  env:
+    ANSIBLE_VERBOSITY: 1
   playbooks:
     converge: ../resources/converge.yml
     side_effect: ../resources/reset.yml
@@ -63,7 +65,6 @@ provisioner:
 scenario:
   test_sequence:
     - dependency
-    - lint
     - cleanup
     - destroy
     - syntax

molecule/kube-vip/molecule.yml

@@ -0,0 +1,49 @@
+---
+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: 192.168.30.62
+provisioner:
+  name: ansible
+  env:
+    ANSIBLE_VERBOSITY: 1
+  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
+    - 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/kube-vip/overrides.yml

@@ -0,0 +1,17 @@
+---
+- 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
+        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 other scenarios
+        apiserver_endpoint: "192.168.30.225"
+        # Use kube-vip instead of MetalLB
+        kube_vip_lb_ip_range: "192.168.30.110-192.168.30.119"

molecule/resources/verify_from_outside/tasks/test/deploy-example.yml

@@ -35,7 +35,7 @@
     - name: Assert that the nginx welcome page is available
       ansible.builtin.uri:
         url: http://{{ ip | ansible.utils.ipwrap }}:{{ port_ }}/
-        return_content: yes
+        return_content: true
       register: result
       failed_when: "'Welcome to nginx!' not in result.content"
       vars:

molecule/single_node/molecule.yml

@@ -21,6 +21,8 @@ platforms:
         ip: 192.168.30.50
 provisioner:
   name: ansible
+  env:
+    ANSIBLE_VERBOSITY: 1
   playbooks:
     converge: ../resources/converge.yml
     side_effect: ../resources/reset.yml
@@ -31,7 +33,6 @@ provisioner:
 scenario:
   test_sequence:
     - dependency
-    - lint
     - cleanup
     - destroy
     - syntax

reboot.yml

@@ -1,9 +1,10 @@
 ---
 - name: Reboot k3s_cluster
   hosts: k3s_cluster
-  gather_facts: yes
+  gather_facts: true
   tasks:
     - name: Reboot the nodes (and Wait upto 5 mins max)
       become: true
       reboot:
+        reboot_command: "{{ custom_reboot_command | default(omit) }}"
         reboot_timeout: 300

requirements.in

@@ -1,10 +1,10 @@
-ansible-core>=2.13.5
+ansible-core>=2.16.2
 jmespath>=1.0.1
-jsonpatch>=1.32
+jsonpatch>=1.33
-kubernetes>=25.3.0
+kubernetes>=29.0.0
-molecule-vagrant>=1.0.0
+molecule-plugins[vagrant]
-molecule>=4.0.3
+molecule>=6.0.3
-netaddr>=0.8.0
+netaddr>=0.10.1
-pre-commit>=2.20.0
+pre-commit>=3.6.0
-pre-commit-hooks>=1.3.1
+pre-commit-hooks>=4.5.0
-pyyaml>=6.0
+pyyaml>=6.0.1

requirements.txt

@@ -4,174 +4,165 @@
 #
 #    pip-compile requirements.in
 #
-ansible-compat==3.0.1
+ansible-compat==4.1.11
     # via molecule
-ansible-core==2.15.2
+ansible-core==2.17.2
     # via
     #   -r requirements.in
     #   ansible-compat
-arrow==1.2.3
+    #   molecule
-    # via jinja2-time
+attrs==23.2.0
-attrs==22.1.0
+    # via
-    # via jsonschema
+    #   jsonschema
-binaryornot==0.4.4
+    #   referencing
-    # via cookiecutter
+bracex==2.4
-cachetools==5.2.0
+    # via wcmatch
+cachetools==5.3.2
     # via google-auth
-certifi==2022.9.24
+certifi==2023.11.17
     # via
     #   kubernetes
     #   requests
-cffi==1.15.1
+cffi==1.16.0
     # via cryptography
-cfgv==3.3.1
+cfgv==3.4.0
     # via pre-commit
-chardet==5.0.0
+charset-normalizer==3.3.2
-    # via binaryornot
-charset-normalizer==2.1.1
     # via requests
-click==8.1.3
+click==8.1.7
     # via
     #   click-help-colors
-    #   cookiecutter
     #   molecule
-click-help-colors==0.9.1
+click-help-colors==0.9.4
     # via molecule
-commonmark==0.9.1
+cryptography==41.0.7
-    # via rich
-cookiecutter==2.1.1
-    # via molecule
-cryptography==38.0.3
     # via ansible-core
-distlib==0.3.6
+distlib==0.3.8
     # via virtualenv
-distro==1.8.0
-    # via selinux
 enrich==1.2.7
     # via molecule
-filelock==3.8.0
+filelock==3.13.1
     # via virtualenv
-google-auth==2.14.0
+google-auth==2.26.2
     # via kubernetes
-identify==2.5.8
+identify==2.5.33
     # via pre-commit
-idna==3.4
+idna==3.6
     # via requests
-jinja2==3.1.2
+jinja2==3.1.3
     # 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==1.33
     # via -r requirements.in
-jsonpointer==2.3
+jsonpointer==2.4
     # via jsonpatch
-jsonschema==4.17.0
+jsonschema==4.21.1
     # via
     #   ansible-compat
     #   molecule
-kubernetes==25.3.0
+jsonschema-specifications==2023.12.1
+    # via jsonschema
+kubernetes==29.0.0
     # via -r requirements.in
-markupsafe==2.1.1
+markdown-it-py==3.0.0
+    # via rich
+markupsafe==2.1.4
     # via jinja2
-molecule==4.0.4
+mdurl==0.1.2
+    # via markdown-it-py
+molecule==6.0.3
     # via
     #   -r requirements.in
-    #   molecule-vagrant
+    #   molecule-plugins
-molecule-vagrant==1.0.0
+molecule-plugins[vagrant]==23.5.3
     # via -r requirements.in
-netaddr==0.8.0
+netaddr==0.10.1
     # via -r requirements.in
-nodeenv==1.7.0
+nodeenv==1.8.0
     # via pre-commit
 oauthlib==3.2.2
-    # via requests-oauthlib
+    # via
-packaging==21.3
+    #   kubernetes
+    #   requests-oauthlib
+packaging==23.2
     # via
     #   ansible-compat
     #   ansible-core
     #   molecule
-platformdirs==2.5.2
+platformdirs==4.1.0
     # via virtualenv
-pluggy==1.0.0
+pluggy==1.3.0
     # via molecule
-pre-commit==2.21.0
+pre-commit==3.8.0
     # via -r requirements.in
-pre-commit-hooks==4.4.0
+pre-commit-hooks==4.6.0
     # via -r requirements.in
-pyasn1==0.4.8
+pyasn1==0.5.1
     # via
     #   pyasn1-modules
     #   rsa
-pyasn1-modules==0.2.8
+pyasn1-modules==0.3.0
     # via google-auth
 pycparser==2.21
     # via cffi
-pygments==2.13.0
+pygments==2.17.2
     # via rich
-pyparsing==3.0.9
-    # via packaging
-pyrsistent==0.19.2
-    # via jsonschema
 python-dateutil==2.8.2
-    # via
+    # via kubernetes
-    #   arrow
-    #   kubernetes
-python-slugify==6.1.2
-    # via cookiecutter
 python-vagrant==1.0.0
-    # via molecule-vagrant
+    # via molecule-plugins
 pyyaml==6.0.1
     # via
     #   -r requirements.in
     #   ansible-compat
     #   ansible-core
-    #   cookiecutter
     #   kubernetes
     #   molecule
-    #   molecule-vagrant
     #   pre-commit
-requests==2.28.1
+referencing==0.32.1
+    # via
+    #   jsonschema
+    #   jsonschema-specifications
+requests==2.31.0
     # via
-    #   cookiecutter
     #   kubernetes
     #   requests-oauthlib
 requests-oauthlib==1.3.1
     # via kubernetes
-resolvelib==0.8.1
+resolvelib==1.0.1
     # via ansible-core
-rich==12.6.0
+rich==13.7.0
     # via
     #   enrich
     #   molecule
+rpds-py==0.17.1
+    # via
+    #   jsonschema
+    #   referencing
 rsa==4.9
     # via google-auth
-ruamel-yaml==0.17.21
+ruamel-yaml==0.18.5
     # via pre-commit-hooks
-selinux==0.2.1
+ruamel-yaml-clib==0.2.8
-    # via molecule-vagrant
+    # via ruamel-yaml
 six==1.16.0
     # via
-    #   google-auth
     #   kubernetes
     #   python-dateutil
 subprocess-tee==0.4.1
     # via ansible-compat
-text-unidecode==1.3
+urllib3==2.1.0
-    # via python-slugify
-urllib3==1.26.12
     # via
     #   kubernetes
     #   requests
-virtualenv==20.16.6
+virtualenv==20.25.0
     # via pre-commit
-websocket-client==1.4.2
+wcmatch==8.5
+    # via molecule
+websocket-client==1.7.0
     # via kubernetes
 
 # The following packages are considered to be unsafe in a requirements file:

reset.yml

@@ -1,7 +1,7 @@
 ---
 - name: Reset k3s cluster
   hosts: k3s_cluster
-  gather_facts: yes
+  gather_facts: true
   roles:
     - role: reset
       become: true
@@ -12,12 +12,13 @@
     - name: Reboot and wait for node to come back up
       become: true
       reboot:
+        reboot_command: "{{ custom_reboot_command | default(omit) }}"
         reboot_timeout: 3600
 
 - name: Revert changes to Proxmox cluster
   hosts: proxmox
   gather_facts: true
-  become: yes
+  become: true
   remote_user: "{{ proxmox_lxc_ssh_user }}"
   roles:
     - role: reset_proxmox_lxc

roles/k3s_agent/tasks/http_proxy.yml

@@ -0,0 +1,18 @@
+---
+- name: Create k3s-node.service.d directory
+  file:
+    path: '{{ systemd_dir }}/k3s-node.service.d'
+    state: directory
+    owner: root
+    group: root
+    mode: '0755'
+  when: proxy_env is defined
+
+- name: Copy K3s http_proxy conf file
+  template:
+    src: "http_proxy.conf.j2"
+    dest: "{{ systemd_dir }}/k3s-node.service.d/http_proxy.conf"
+    owner: root
+    group: root
+    mode: '0755'
+  when: proxy_env is defined

roles/k3s_agent/tasks/main.yml

@@ -1,16 +1,36 @@
 ---
+- name: Check for PXE-booted system
+  block:
+    - name: Check if system is PXE-booted
+      ansible.builtin.command:
+        cmd: cat /proc/cmdline
+      register: boot_cmdline
+      changed_when: false
+      check_mode: false
 
-- name: Copy K3s service file
+    - name: Set fact for PXE-booted system
-  template:
+      ansible.builtin.set_fact:
+        is_pxe_booted: "{{ 'root=/dev/nfs' in boot_cmdline.stdout }}"
+      when: boot_cmdline.stdout is defined
+
+    - name: Include http_proxy configuration tasks
+      ansible.builtin.include_tasks: http_proxy.yml
+
+- name: Deploy K3s http_proxy conf
+  include_tasks: http_proxy.yml
+  when: proxy_env is defined
+
+- name: Configure the k3s service
+  ansible.builtin.template:
     src: "k3s.service.j2"
     dest: "{{ systemd_dir }}/k3s-node.service"
     owner: root
     group: root
-    mode: 0755
+    mode: '0755'
 
-- name: Enable and check K3s service
+- name: Manage k3s service
-  systemd:
+  ansible.builtin.systemd:
     name: k3s-node
-    daemon_reload: yes
+    daemon_reload: true
     state: restarted
-    enabled: yes
+    enabled: true

roles/k3s_agent/templates/http_proxy.conf.j2

@@ -0,0 +1,4 @@
+[Service]
+Environment=HTTP_PROXY={{ proxy_env.HTTP_PROXY }}
+Environment=HTTPS_PROXY={{ proxy_env.HTTPS_PROXY }}
+Environment=NO_PROXY={{ proxy_env.NO_PROXY }}

roles/k3s_agent/templates/k3s.service.j2

@@ -7,11 +7,14 @@ 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 | ansible.utils.ipwrap }}:6443 --token {{ hostvars[groups[group_name_master | default('master')][0]]['token'] | default(k3s_token) }} {{ extra_agent_args | default("") }}
+# Conditional snapshotter based on PXE boot status
+ExecStart=/usr/local/bin/k3s agent \
+  --server https://{{ apiserver_endpoint | ansible.utils.ipwrap }}:6443 \
+  {% if is_pxe_booted | default(false) %}--snapshotter native \
+  {% endif %}--token {{ hostvars[groups[group_name_master | default('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
-# in the kernel. We recommend using cgroups to do container-local accounting.
 LimitNOFILE=1048576
 LimitNPROC=infinity
 LimitCORE=infinity

roles/k3s_custom_registries/defaults/main.yml

@@ -0,0 +1,6 @@
+---
+# Indicates whether custom registries for k3s should be configured
+# Possible values:
+#   - present
+#   - absent
+state: present

roles/k3s_custom_registries/tasks/main.yml

@@ -0,0 +1,17 @@
+---
+
+- name: Create directory /etc/rancher/k3s
+  file:
+    path: "/etc/{{ item }}"
+    state: directory
+    mode: '0755'
+  loop:
+    - rancher
+    - rancher/k3s
+
+- name: Insert registries into /etc/rancher/k3s/registries.yaml
+  blockinfile:
+    path: /etc/rancher/k3s/registries.yaml
+    block: "{{ custom_registries_yaml }}"
+    mode: '0600'
+    create: true

roles/k3s_server/defaults/main.yml

@@ -4,6 +4,9 @@
 # will determine the right interface automatically at runtime.
 kube_vip_iface: null
 
+# Enables ARP broadcasts from Leader
+kube_vip_arp: true
+
 # Name of the master group
 group_name_master: master
 

roles/k3s_server/tasks/http_proxy.yml

@@ -0,0 +1,18 @@
+---
+
+- name: Create k3s.service.d directory
+  file:
+    path: '{{ systemd_dir }}/k3s.service.d'
+    state: directory
+    owner: root
+    group: root
+    mode: '0755'
+
+
+- name: Copy K3s http_proxy conf file
+  template:
+    src: "http_proxy.conf.j2"
+    dest: "{{ systemd_dir }}/k3s.service.d/http_proxy.conf"
+    owner: root
+    group: root
+    mode: '0755'

roles/k3s_server/tasks/kube-vip.yml

@@ -0,0 +1,27 @@
+---
+- name: Create manifests directory on first master
+  file:
+    path: /var/lib/rancher/k3s/server/manifests
+    state: directory
+    owner: root
+    group: root
+    mode: 0644
+  when: ansible_hostname == hostvars[groups[group_name_master | default('master')][0]]['ansible_hostname']
+
+- name: Download vip cloud provider manifest to first master
+  ansible.builtin.get_url:
+    url: "https://raw.githubusercontent.com/kube-vip/kube-vip-cloud-provider/{{ kube_vip_cloud_provider_tag_version | default('main') }}/manifest/kube-vip-cloud-controller.yaml"  # noqa yaml[line-length]
+    dest: "/var/lib/rancher/k3s/server/manifests/kube-vip-cloud-controller.yaml"
+    owner: root
+    group: root
+    mode: 0644
+  when: ansible_hostname == hostvars[groups[group_name_master | default('master')][0]]['ansible_hostname']
+
+- name: Copy kubevip configMap manifest to first master
+  template:
+    src: "kubevip.yaml.j2"
+    dest: "/var/lib/rancher/k3s/server/manifests/kubevip.yaml"
+    owner: root
+    group: root
+    mode: 0644
+  when: ansible_hostname == hostvars[groups[group_name_master | default('master')][0]]['ansible_hostname']

roles/k3s_server/tasks/main.yml

@@ -6,17 +6,35 @@
     state: stopped
   failed_when: false
 
+# k3s-init won't work if the port is already in use
+- name: Stop k3s
+  systemd:
+    name: k3s
+    state: stopped
+  failed_when: false
+
 - name: Clean previous runs of k3s-init  # noqa command-instead-of-module
   # The systemd module does not support "reset-failed", so we need to resort to command.
   command: systemctl reset-failed k3s-init
   failed_when: false
   changed_when: false
 
+- name: Deploy K3s http_proxy conf
+  include_tasks: http_proxy.yml
+  when: proxy_env is defined
+
 - name: Deploy vip manifest
   include_tasks: vip.yml
 
 - name: Deploy metallb manifest
   include_tasks: metallb.yml
+  tags: metallb
+  when: kube_vip_lb_ip_range is not defined and (not cilium_bgp or cilium_iface is not defined)
+
+- name: Deploy kube-vip manifest
+  include_tasks: kube-vip.yml
+  tags: kubevip
+  when: kube_vip_lb_ip_range is defined
 
 - name: Init cluster inside the transient k3s-init service
   command:
@@ -24,7 +42,7 @@
                       -p Restart=on-failure \
                       --unit=k3s-init \
                       k3s server {{ server_init_args }}"
-    creates: "{{ systemd_dir }}/k3s.service"
+    creates: "{{ systemd_dir }}/k3s-init.service"
 
 - name: Verification
   when: not ansible_check_mode
@@ -62,9 +80,9 @@
 - name: Enable and check K3s service
   systemd:
     name: k3s
-    daemon_reload: yes
+    daemon_reload: true
     state: restarted
-    enabled: yes
+    enabled: true
 
 - name: Wait for node-token
   wait_for:
@@ -105,7 +123,7 @@
   copy:
     src: /etc/rancher/k3s/k3s.yaml
     dest: "{{ ansible_user_dir }}/.kube/config"
-    remote_src: yes
+    remote_src: true
     owner: "{{ ansible_user_id }}"
     mode: "u=rw,g=,o="
 

roles/k3s_server/tasks/vip.yml

@@ -10,7 +10,7 @@
 
 - name: Download vip rbac manifest to first master
   ansible.builtin.get_url:
-    url: "https://raw.githubusercontent.com/kube-vip/kube-vip/{{ kube_vip_tag_version }}/docs/manifests/rbac.yaml"
+    url: "https://kube-vip.io/manifests/rbac.yaml"
     dest: "/var/lib/rancher/k3s/server/manifests/vip-rbac.yaml"
     owner: root
     group: root

roles/k3s_server/templates/http_proxy.conf.j2

@@ -0,0 +1,4 @@
+[Service]
+Environment=HTTP_PROXY={{ proxy_env.HTTP_PROXY }}
+Environment=HTTPS_PROXY={{ proxy_env.HTTPS_PROXY }}
+Environment=NO_PROXY={{ proxy_env.NO_PROXY }}

roles/k3s_server/templates/kubevip.yaml.j2

@@ -0,0 +1,13 @@
+---
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: kubevip
+  namespace: kube-system
+data:
+{% if kube_vip_lb_ip_range is string %}
+{# kube_vip_lb_ip_range was used in the legacy way: single string instead of a list #}
+{#   => transform to list with single element #}
+{% set kube_vip_lb_ip_range = [kube_vip_lb_ip_range] %}
+{% endif %}
+  range-global: {{ kube_vip_lb_ip_range | join(',') }}

roles/k3s_server/templates/vip.yaml.j2

@@ -27,7 +27,7 @@ spec:
         - manager
         env:
         - name: vip_arp
-          value: "true"
+          value: "{{ 'true' if kube_vip_arp | bool else 'false' }}"
         - name: port
           value: "6443"
 {% if kube_vip_iface %}
@@ -43,7 +43,7 @@ spec:
         - name: vip_ddns
           value: "false"
         - name: svc_enable
-          value: "false"
+          value: "{{ 'true' if kube_vip_lb_ip_range is defined else 'false' }}"
         - name: vip_leaderelection
           value: "true"
         - name: vip_leaseduration

roles/k3s_server_post/defaults/main.yml

@@ -1,6 +1,6 @@
 ---
 # Timeout to wait for MetalLB services to come up
-metal_lb_available_timeout: 120s
+metal_lb_available_timeout: 240s
 
 # Name of the master group
 group_name_master: master

roles/k3s_server_post/tasks/calico.yml

@@ -0,0 +1,114 @@
+---
+- name: Deploy Calico to cluster
+  when: ansible_hostname == hostvars[groups[group_name_master | default('master')][0]]['ansible_hostname']
+  run_once: true
+  block:
+    - name: Create manifests directory on first master
+      file:
+        path: /tmp/k3s
+        state: directory
+        owner: root
+        group: root
+        mode: 0755
+
+    - name: "Download to first master: manifest for Tigera Operator and Calico CRDs"
+      ansible.builtin.get_url:
+        url: "https://raw.githubusercontent.com/projectcalico/calico/{{ calico_tag }}/manifests/tigera-operator.yaml"
+        dest: "/tmp/k3s/tigera-operator.yaml"
+        owner: root
+        group: root
+        mode: 0755
+
+    - name: Copy Calico custom resources manifest to first master
+      ansible.builtin.template:
+        src: "calico.crs.j2"
+        dest: /tmp/k3s/custom-resources.yaml
+        owner: root
+        group: root
+        mode: 0755
+
+    - name: Deploy or replace Tigera Operator
+      block:
+        - name: Deploy Tigera Operator
+          ansible.builtin.command:
+            cmd: kubectl create -f /tmp/k3s/tigera-operator.yaml
+          register: create_operator
+          changed_when: "'created' in create_operator.stdout"
+          failed_when: "'Error' in create_operator.stderr and 'already exists' not in create_operator.stderr"
+      rescue:
+        - name: Replace existing Tigera Operator
+          ansible.builtin.command:
+            cmd: kubectl replace -f /tmp/k3s/tigera-operator.yaml
+          register: replace_operator
+          changed_when: "'replaced' in replace_operator.stdout"
+          failed_when: "'Error' in replace_operator.stderr"
+
+    - name: Wait for Tigera Operator resources
+      command: >-
+        k3s kubectl wait {{ item.type }}/{{ item.name }}
+        --namespace='tigera-operator'
+        --for=condition=Available=True
+        --timeout=30s
+      register: tigera_result
+      changed_when: false
+      until: tigera_result is succeeded
+      retries: 7
+      delay: 7
+      with_items:
+        - {name: tigera-operator, type: deployment}
+      loop_control:
+        label: "{{ item.type }}/{{ item.name }}"
+
+    - name: Deploy Calico custom resources
+      block:
+        - name: Deploy custom resources for Calico
+          ansible.builtin.command:
+            cmd: kubectl create -f /tmp/k3s/custom-resources.yaml
+          register: create_cr
+          changed_when: "'created' in create_cr.stdout"
+          failed_when: "'Error' in create_cr.stderr and 'already exists' not in create_cr.stderr"
+      rescue:
+        - name: Apply new Calico custom resource manifest
+          ansible.builtin.command:
+            cmd: kubectl apply -f /tmp/k3s/custom-resources.yaml
+          register: apply_cr
+          changed_when: "'configured' in apply_cr.stdout or 'created' in apply_cr.stdout"
+          failed_when: "'Error' in apply_cr.stderr"
+
+    - name: Wait for Calico system resources to be available
+      command: >-
+        {% if item.type == 'daemonset' %}
+        k3s kubectl wait pods
+        --namespace='{{ item.namespace }}'
+        --selector={{ item.selector }}
+        --for=condition=Ready
+        {% else %}
+        k3s kubectl wait {{ item.type }}/{{ item.name }}
+        --namespace='{{ item.namespace }}'
+        --for=condition=Available
+        {% endif %}
+        --timeout=30s
+      register: cr_result
+      changed_when: false
+      until: cr_result is succeeded
+      retries: 30
+      delay: 7
+      with_items:
+        - {name: calico-typha, type: deployment, namespace: calico-system}
+        - {name: calico-kube-controllers, type: deployment, namespace: calico-system}
+        - {name: csi-node-driver, type: daemonset, selector: 'k8s-app=csi-node-driver', namespace: calico-system}
+        - {name: calico-node, type: daemonset, selector: 'k8s-app=calico-node', namespace: calico-system}
+        - {name: calico-apiserver, type: deployment, namespace: calico-apiserver}
+      loop_control:
+        label: "{{ item.type }}/{{ item.name }}"
+
+    - name: Patch Felix configuration for eBPF mode
+      ansible.builtin.command:
+        cmd: >
+          kubectl patch felixconfiguration default
+          --type='merge'
+          --patch='{"spec": {"bpfKubeProxyIptablesCleanupEnabled": false}}'
+      register: patch_result
+      changed_when: "'felixconfiguration.projectcalico.org/default patched' in patch_result.stdout"
+      failed_when: "'Error' in patch_result.stderr"
+      when: calico_ebpf

roles/k3s_server_post/tasks/cilium.yml

@@ -0,0 +1,253 @@
+---
+- name: Prepare Cilium CLI on first master and deploy CNI
+  when: ansible_hostname == hostvars[groups[group_name_master | default('master')][0]]['ansible_hostname']
+  run_once: true
+  block:
+    - name: Create tmp directory on first master
+      file:
+        path: /tmp/k3s
+        state: directory
+        owner: root
+        group: root
+        mode: 0755
+
+    - name: Check if Cilium CLI is installed
+      ansible.builtin.command: cilium version
+      register: cilium_cli_installed
+      failed_when: false
+      changed_when: false
+      ignore_errors: true
+
+    - name: Check for Cilium CLI version in command output
+      set_fact:
+        installed_cli_version: >-
+          {{
+            cilium_cli_installed.stdout_lines
+            | join(' ')
+            | regex_findall('cilium-cli: (v\d+\.\d+\.\d+)')
+            | first
+            | default('unknown')
+          }}
+      when: cilium_cli_installed.rc == 0
+
+    - name: Get latest stable Cilium CLI version file
+      ansible.builtin.get_url:
+        url: "https://raw.githubusercontent.com/cilium/cilium-cli/main/stable.txt"
+        dest: "/tmp/k3s/cilium-cli-stable.txt"
+        owner: root
+        group: root
+        mode: 0755
+
+    - name: Read Cilium CLI stable version from file
+      ansible.builtin.command: cat /tmp/k3s/cilium-cli-stable.txt
+      register: cli_ver
+      changed_when: false
+
+    - name: Log installed Cilium CLI version
+      ansible.builtin.debug:
+        msg: "Installed Cilium CLI version: {{ installed_cli_version | default('Not installed') }}"
+
+    - name: Log latest stable Cilium CLI version
+      ansible.builtin.debug:
+        msg: "Latest Cilium CLI version: {{ cli_ver.stdout }}"
+
+    - name: Determine if Cilium CLI needs installation or update
+      set_fact:
+        cilium_cli_needs_update: >-
+          {{
+            cilium_cli_installed.rc != 0 or
+            (cilium_cli_installed.rc == 0 and
+            installed_cli_version != cli_ver.stdout)
+          }}
+
+    - name: Install or update Cilium CLI
+      when: cilium_cli_needs_update
+      block:
+        - name: Set architecture variable
+          ansible.builtin.set_fact:
+            cli_arch: "{{ 'arm64' if ansible_architecture == 'aarch64' else 'amd64' }}"
+
+        - name: Download Cilium CLI and checksum
+          ansible.builtin.get_url:
+            url: "{{ cilium_base_url }}/cilium-linux-{{ cli_arch }}{{ item }}"
+            dest: "/tmp/k3s/cilium-linux-{{ cli_arch }}{{ item }}"
+            owner: root
+            group: root
+            mode: 0755
+          loop:
+            - ".tar.gz"
+            - ".tar.gz.sha256sum"
+          vars:
+            cilium_base_url: "https://github.com/cilium/cilium-cli/releases/download/{{ cli_ver.stdout }}"
+
+        - name: Verify the downloaded tarball
+          ansible.builtin.shell: |
+            cd /tmp/k3s && sha256sum --check cilium-linux-{{ cli_arch }}.tar.gz.sha256sum
+          args:
+            executable: /bin/bash
+          changed_when: false
+
+        - name: Extract Cilium CLI to /usr/local/bin
+          ansible.builtin.unarchive:
+            src: "/tmp/k3s/cilium-linux-{{ cli_arch }}.tar.gz"
+            dest: /usr/local/bin
+            remote_src: true
+
+        - name: Remove downloaded tarball and checksum file
+          ansible.builtin.file:
+            path: "{{ item }}"
+            state: absent
+          loop:
+            - "/tmp/k3s/cilium-linux-{{ cli_arch }}.tar.gz"
+            - "/tmp/k3s/cilium-linux-{{ cli_arch }}.tar.gz.sha256sum"
+
+    - name: Wait for connectivity to kube VIP
+      ansible.builtin.command: ping -c 1 {{ apiserver_endpoint }}
+      register: ping_result
+      until: ping_result.rc == 0
+      retries: 21
+      delay: 1
+      ignore_errors: true
+      changed_when: false
+
+    - name: Fail if kube VIP not reachable
+      ansible.builtin.fail:
+        msg: "API endpoint {{ apiserver_endpoint }} is not reachable"
+      when: ping_result.rc != 0
+
+    - name: Test for existing Cilium install
+      ansible.builtin.command: k3s kubectl -n kube-system get daemonsets cilium
+      register: cilium_installed
+      failed_when: false
+      changed_when: false
+      ignore_errors: true
+
+    - name: Check existing Cilium install
+      when: cilium_installed.rc == 0
+      block:
+
+        - name: Check Cilium version
+          ansible.builtin.command: cilium version
+          register: cilium_version
+          failed_when: false
+          changed_when: false
+          ignore_errors: true
+
+        - name: Parse installed Cilium version
+          set_fact:
+            installed_cilium_version: >-
+              {{
+                cilium_version.stdout_lines
+                | join(' ')
+                | regex_findall('cilium image.+(\d+\.\d+\.\d+)')
+                | first
+                | default('unknown')
+              }}
+
+        - name: Determine if Cilium needs update
+          set_fact:
+            cilium_needs_update: >-
+              {{ 'v' + installed_cilium_version != cilium_tag }}
+
+        - name: Log result
+          ansible.builtin.debug:
+            msg: >
+              Installed Cilium version: {{ installed_cilium_version }},
+              Target Cilium version: {{ cilium_tag }},
+              Update needed: {{ cilium_needs_update }}
+
+    - name: Install Cilium
+      ansible.builtin.command: >-
+        {% if cilium_installed.rc != 0 %}
+        cilium install
+        {% else %}
+        cilium upgrade
+        {% endif %}
+        --version "{{ cilium_tag }}"
+        --helm-set operator.replicas="1"
+        {{ '--helm-set devices=' + cilium_iface if cilium_iface != 'auto' else '' }}
+        --helm-set ipam.operator.clusterPoolIPv4PodCIDRList={{ cluster_cidr }}
+        {% if cilium_mode == "native" or (cilium_bgp and cilium_exportPodCIDR != 'false') %}
+        --helm-set ipv4NativeRoutingCIDR={{ cluster_cidr }}
+        {% endif %}
+        --helm-set k8sServiceHost="127.0.0.1"
+        --helm-set k8sServicePort="6444"
+        --helm-set routingMode={{ cilium_mode | default("native") }}
+        --helm-set autoDirectNodeRoutes={{ "true" if cilium_mode == "native" else "false" }}
+        --helm-set kubeProxyReplacement={{ kube_proxy_replacement | default("true") }}
+        --helm-set bpf.masquerade={{ enable_bpf_masquerade | default("true") }}
+        --helm-set bgpControlPlane.enabled={{ cilium_bgp | default("false") }}
+        --helm-set hubble.enabled={{ "true" if cilium_hubble else "false" }}
+        --helm-set hubble.relay.enabled={{ "true" if cilium_hubble else "false" }}
+        --helm-set hubble.ui.enabled={{ "true" if cilium_hubble else "false" }}
+        {% if kube_proxy_replacement is not false %}
+        --helm-set bpf.loadBalancer.algorithm={{ bpf_lb_algorithm | default("maglev") }}
+        --helm-set bpf.loadBalancer.mode={{ bpf_lb_mode | default("hybrid") }}
+        {% endif %}
+      environment:
+        KUBECONFIG: "{{ ansible_user_dir }}/.kube/config"
+      register: cilium_install_result
+      changed_when: cilium_install_result.rc == 0
+      when: cilium_installed.rc != 0 or cilium_needs_update
+
+    - name: Wait for Cilium resources
+      command: >-
+        {% if item.type == 'daemonset' %}
+        k3s kubectl wait pods
+        --namespace=kube-system
+        --selector='k8s-app=cilium'
+        --for=condition=Ready
+        {% else %}
+        k3s kubectl wait {{ item.type }}/{{ item.name }}
+        --namespace=kube-system
+        --for=condition=Available
+        {% endif %}
+        --timeout=30s
+      register: cr_result
+      changed_when: false
+      until: cr_result is succeeded
+      retries: 30
+      delay: 7
+      with_items:
+        - {name: cilium-operator, type: deployment}
+        - {name: cilium, type: daemonset, selector: 'k8s-app=cilium'}
+        - {name: hubble-relay, type: deployment, check_hubble: true}
+        - {name: hubble-ui, type: deployment, check_hubble: true}
+      loop_control:
+        label: "{{ item.type }}/{{ item.name }}"
+      when: >-
+        not item.check_hubble | default(false) or (item.check_hubble | default(false) and cilium_hubble)
+
+    - name: Configure Cilium BGP
+      when: cilium_bgp
+      block:
+
+        - name: Copy BGP manifests to first master
+          ansible.builtin.template:
+            src: "cilium.crs.j2"
+            dest: /tmp/k3s/cilium-bgp.yaml
+            owner: root
+            group: root
+            mode: 0755
+
+        - name: Apply BGP manifests
+          ansible.builtin.command:
+            cmd: kubectl apply -f /tmp/k3s/cilium-bgp.yaml
+          register: apply_cr
+          changed_when: "'configured' in apply_cr.stdout or 'created' in apply_cr.stdout"
+          failed_when: "'is invalid' in apply_cr.stderr"
+          ignore_errors: true
+
+        - name: Print error message if BGP manifests application fails
+          ansible.builtin.debug:
+            msg: "{{ apply_cr.stderr }}"
+          when: "'is invalid' in apply_cr.stderr"
+
+        - name: Test for BGP config resources
+          ansible.builtin.command: "{{ item }}"
+          loop:
+            - k3s kubectl get CiliumBGPPeeringPolicy.cilium.io
+            - k3s kubectl get CiliumLoadBalancerIPPool.cilium.io
+          changed_when: false
+          loop_control:
+            label: "{{ item }}"

roles/k3s_server_post/tasks/main.yml

@@ -1,6 +1,18 @@
 ---
+- name: Deploy calico
+  include_tasks: calico.yml
+  tags: calico
+  when: calico_iface is defined and cilium_iface is not defined
+
+- name: Deploy cilium
+  include_tasks: cilium.yml
+  tags: cilium
+  when: cilium_iface is defined
+
 - name: Deploy metallb pool
   include_tasks: metallb.yml
+  tags: metallb
+  when: kube_vip_lb_ip_range is not defined and (not cilium_bgp or cilium_iface is not defined)
 
 - name: Remove tmp directory used for manifests
   file:

roles/k3s_server_post/tasks/metallb.yml

@@ -8,6 +8,27 @@
   with_items: "{{ groups[group_name_master | default('master')] }}"
   run_once: true
 
+- name: Delete outdated metallb replicas
+  shell: |-
+    set -o pipefail
+
+    REPLICAS=$(k3s kubectl --namespace='metallb-system' get replicasets \
+      -l 'component=controller,app=metallb' \
+      -o jsonpath='{.items[0].spec.template.spec.containers[0].image}, {.items[0].metadata.name}' 2>/dev/null || true)
+    REPLICAS_SETS=$(echo ${REPLICAS} | grep -v '{{ metal_lb_controller_tag_version }}' | sed -e "s/^.*\s//g")
+    if [ -n "${REPLICAS_SETS}" ] ; then
+      for REPLICAS in "${REPLICAS_SETS}"
+      do
+        k3s kubectl --namespace='metallb-system' \
+          delete rs "${REPLICAS}"
+      done
+    fi
+  args:
+    executable: /bin/bash
+  changed_when: false
+  run_once: true
+  with_items: "{{ groups[group_name_master | default('master')] }}"
+
 - name: Copy metallb CRs manifest to first master
   template:
     src: "metallb.crs.j2"
@@ -62,9 +83,23 @@
   loop_control:
     label: "{{ item.description }}"
 
+- name: Set metallb webhook service name
+  set_fact:
+    metallb_webhook_service_name: >-
+      {{
+        (
+          (metal_lb_controller_tag_version | regex_replace('^v', ''))
+          is
+          version('0.14.4', '<', version_type='semver')
+        ) | ternary(
+          'webhook-service',
+          'metallb-webhook-service'
+        )
+      }}
+
 - name: Test metallb-system webhook-service endpoint
   command: >-
-    k3s kubectl -n metallb-system get endpoints webhook-service
+    k3s kubectl -n metallb-system get endpoints {{ metallb_webhook_service_name }}
   changed_when: false
   with_items: "{{ groups[group_name_master | default('master')] }}"
   run_once: true

roles/k3s_server_post/templates/calico.crs.j2

@@ -0,0 +1,41 @@
+# This section includes base Calico installation configuration.
+# For more information, see: https://docs.tigera.io/calico/latest/reference/installation/api#operator.tigera.io/v1.Installation
+apiVersion: operator.tigera.io/v1
+kind: Installation
+metadata:
+  name: default
+spec:
+  # Configures Calico networking.
+  calicoNetwork:
+    # Note: The ipPools section cannot be modified post-install.
+    ipPools:
+    - blockSize: {{ calico_blockSize | default('26') }}
+      cidr: {{ cluster_cidr | default('10.52.0.0/16') }}
+      encapsulation: {{ calico_encapsulation | default('VXLANCrossSubnet') }}
+      natOutgoing: {{ calico_natOutgoing | default('Enabled') }}
+      nodeSelector: {{ calico_nodeSelector | default('all()') }}
+    nodeAddressAutodetectionV4:
+      interface: {{ calico_iface  }}
+    linuxDataplane: {{ 'BPF' if calico_ebpf else 'Iptables' }}
+
+---
+
+# This section configures the Calico API server.
+# For more information, see: https://docs.tigera.io/calico/latest/reference/installation/api#operator.tigera.io/v1.APIServer
+apiVersion: operator.tigera.io/v1
+kind: APIServer
+metadata:
+  name: default
+spec: {}
+
+{% if calico_ebpf %}
+---
+kind: ConfigMap
+apiVersion: v1
+metadata:
+  name: kubernetes-services-endpoint
+  namespace: tigera-operator
+data:
+  KUBERNETES_SERVICE_HOST: '{{ apiserver_endpoint }}'
+  KUBERNETES_SERVICE_PORT: '6443'
+{% endif %}

roles/k3s_server_post/templates/cilium.crs.j2

@@ -0,0 +1,34 @@
+apiVersion: "cilium.io/v2alpha1"
+kind: CiliumBGPPeeringPolicy
+metadata:
+ name: 01-bgp-peering-policy
+spec: # CiliumBGPPeeringPolicySpec
+ virtualRouters: # []CiliumBGPVirtualRouter
+ - localASN: {{ cilium_bgp_my_asn }}
+   exportPodCIDR: {{ cilium_exportPodCIDR | default('true') }}
+   neighbors: # []CiliumBGPNeighbor
+    - peerAddress: '{{ cilium_bgp_peer_address + "/32"}}'
+      peerASN: {{ cilium_bgp_peer_asn }}
+      eBGPMultihopTTL: 10
+      connectRetryTimeSeconds: 120
+      holdTimeSeconds: 90
+      keepAliveTimeSeconds: 30
+      gracefulRestart:
+        enabled: true
+        restartTimeSeconds: 120
+   serviceSelector:
+      matchExpressions:
+         - {key: somekey, operator: NotIn, values: ['never-used-value']}
+---
+apiVersion: "cilium.io/v2alpha1"
+kind: CiliumLoadBalancerIPPool
+metadata:
+  name: "01-lb-pool"
+spec:
+  blocks:
+{% if "/" in cilium_bgp_lb_cidr %}
+  - cidr: {{ cilium_bgp_lb_cidr }}
+{% else %}
+  - start: {{ cilium_bgp_lb_cidr.split('-')[0] }}
+    stop: {{ cilium_bgp_lb_cidr.split('-')[1] }}
+{% endif %}

roles/lxc/handlers/main.yml

@@ -2,3 +2,5 @@
 - name: Reboot server
   become: true
   reboot:
+    reboot_command: "{{ custom_reboot_command | default(omit) }}"
+  listen: reboot server

roles/prereq/defaults/main.yml

@@ -0,0 +1,4 @@
+---
+secure_path:
+  RedHat: '/sbin:/bin:/usr/sbin:/usr/bin:/usr/local/bin'
+  Suse: '/usr/sbin:/usr/bin:/sbin:/bin:/usr/local/bin'

roles/prereq/tasks/main.yml

@@ -14,21 +14,24 @@
     name: net.ipv4.ip_forward
     value: "1"
     state: present
-    reload: yes
+    reload: true
+  tags: sysctl
 
 - name: Enable IPv6 forwarding
   ansible.posix.sysctl:
     name: net.ipv6.conf.all.forwarding
     value: "1"
     state: present
-    reload: yes
+    reload: true
+  tags: sysctl
 
 - name: Enable IPv6 router advertisements
   ansible.posix.sysctl:
     name: net.ipv6.conf.all.accept_ra
     value: "2"
     state: present
-    reload: yes
+    reload: true
+  tags: sysctl
 
 - name: Add br_netfilter to /etc/modules-load.d/
   copy:
@@ -48,18 +51,19 @@
     name: "{{ item }}"
     value: "1"
     state: present
-    reload: yes
+    reload: true
   when: ansible_os_family == "RedHat"
   loop:
     - net.bridge.bridge-nf-call-iptables
     - net.bridge.bridge-nf-call-ip6tables
+  tags: sysctl
 
 - name: Add /usr/local/bin to sudo secure_path
   lineinfile:
-    line: 'Defaults    secure_path = /sbin:/bin:/usr/sbin:/usr/bin:/usr/local/bin'
+    line: 'Defaults    secure_path = {{ secure_path[ansible_os_family] }}'
     regexp: "Defaults(\\s)*secure_path(\\s)*="
     state: present
     insertafter: EOF
     path: /etc/sudoers
     validate: 'visudo -cf %s'
-  when: ansible_os_family == "RedHat"
+  when: ansible_os_family in [ "RedHat", "Suse" ]

roles/proxmox_lxc/handlers/main.yml

@@ -5,7 +5,9 @@
       set_fact:
         proxmox_lxc_filtered_ids: >-
           {{ proxmox_lxc_filtered_files | map("split", "/") | map("last") | map("split", ".") | map("first") }}
+      listen: reboot containers
     - name: Reboot container
       command: "pct reboot {{ item }}"
       loop: "{{ proxmox_lxc_filtered_ids }}"
       changed_when: true
+      listen: reboot containers

roles/raspberrypi/handlers/main.yml

@@ -1,3 +1,5 @@
 ---
 - name: Reboot
   reboot:
+    reboot_command: "{{ custom_reboot_command | default(omit) }}"
+  listen: reboot

roles/raspberrypi/tasks/main.yml

@@ -17,21 +17,27 @@
   when:
     grep_cpuinfo_raspberrypi.rc == 0 or grep_device_tree_model_raspberrypi.rc == 0
 
-- name: Set detected_distribution to Raspbian
+- name: Set detected_distribution to Raspbian (ARM64 on Raspbian, Debian Buster/Bullseye/Bookworm)
   set_fact:
     detected_distribution: Raspbian
-  when: >
+  vars:
-    raspberry_pi|default(false) and
+    allowed_descriptions:
-    ( ansible_facts.lsb.id|default("") == "Raspbian" or
+      - "[Rr]aspbian.*"
-      ansible_facts.lsb.description|default("") is match("[Rr]aspbian.*") )
+      - "Debian.*buster"
+      - "Debian.*bullseye"
+      - "Debian.*bookworm"
+  when:
+    - ansible_facts.architecture is search("aarch64")
+    - raspberry_pi|default(false)
+    - ansible_facts.lsb.description|default("") is match(allowed_descriptions | join('|'))
 
-- name: Set detected_distribution to Raspbian (ARM64 on Debian Buster)
+- name: Set detected_distribution to Raspbian (ARM64 on Debian Bookworm)
   set_fact:
     detected_distribution: Raspbian
   when:
     - ansible_facts.architecture is search("aarch64")
     - raspberry_pi|default(false)
-    - ansible_facts.lsb.description|default("") is match("Debian.*buster")
+    - ansible_facts.lsb.description|default("") is match("Debian.*bookworm")
 
 - name: Set detected_distribution_major_version
   set_fact:
@@ -39,14 +45,6 @@
   when:
     - detected_distribution | default("") == "Raspbian"
 
-- name: Set detected_distribution to Raspbian (ARM64 on Debian Bullseye)
-  set_fact:
-    detected_distribution: Raspbian
-  when:
-    - ansible_facts.architecture is search("aarch64")
-    - raspberry_pi|default(false)
-    - ansible_facts.lsb.description|default("") is match("Debian.*bullseye")
-
 - name: Execute OS related tasks on the Raspberry Pi - {{ action_ }}
   include_tasks: "{{ item }}"
   with_first_found:

roles/raspberrypi/tasks/setup/Raspbian.yml

@@ -1,7 +1,27 @@
 ---
+- name: Test for cmdline path
+  stat:
+    path: /boot/firmware/cmdline.txt
+  register: boot_cmdline_path
+  failed_when: false
+  changed_when: false
+
+- name: Set cmdline path based on Debian version and command result
+  set_fact:
+    cmdline_path: >-
+      {{
+        (
+          boot_cmdline_path.stat.exists and
+          ansible_facts.lsb.description | default('') is match('Debian.*(?!(bookworm|sid))')
+        ) | ternary(
+          '/boot/firmware/cmdline.txt',
+          '/boot/cmdline.txt'
+        )
+      }}
+
 - name: Activating cgroup support
   lineinfile:
-    path: /boot/cmdline.txt
+    path: "{{ cmdline_path }}"
     regexp: '^((?!.*\bcgroup_enable=cpuset cgroup_memory=1 cgroup_enable=memory\b).*)$'
     line: '\1 cgroup_enable=cpuset cgroup_memory=1 cgroup_enable=memory'
     backrefs: true

roles/raspberrypi/tasks/setup/Rocky.yml

@@ -2,7 +2,7 @@
 - name: Enable cgroup via boot commandline if not already enabled for Rocky
   lineinfile:
     path: /boot/cmdline.txt
-    backrefs: yes
+    backrefs: true
     regexp: '^((?!.*\bcgroup_enable=cpuset cgroup_memory=1 cgroup_enable=memory\b).*)$'
     line: '\1 cgroup_enable=cpuset cgroup_memory=1 cgroup_enable=memory'
   notify: reboot

roles/raspberrypi/tasks/setup/Ubuntu.yml

@@ -2,7 +2,7 @@
 - name: Enable cgroup via boot commandline if not already enabled for Ubuntu on a Raspberry Pi
   lineinfile:
     path: /boot/firmware/cmdline.txt
-    backrefs: yes
+    backrefs: true
     regexp: '^((?!.*\bcgroup_enable=cpuset cgroup_memory=1 cgroup_enable=memory\b).*)$'
     line: '\1 cgroup_enable=cpuset cgroup_memory=1 cgroup_enable=memory'
   notify: reboot

roles/reset/tasks/main.yml

@@ -3,7 +3,7 @@
   systemd:
     name: "{{ item }}"
     state: stopped
-    enabled: no
+    enabled: false
   failed_when: false
   with_items:
     - k3s
@@ -45,10 +45,22 @@
     - /var/lib/rancher/k3s
     - /var/lib/rancher/
     - /var/lib/cni/
+    - /etc/cni/net.d
+
+- name: Remove K3s http_proxy files
+  file:
+    name: "{{ item }}"
+    state: absent
+  with_items:
+    - "{{ systemd_dir }}/k3s.service.d/http_proxy.conf"
+    - "{{ systemd_dir }}/k3s.service.d"
+    - "{{ systemd_dir }}/k3s-node.service.d/http_proxy.conf"
+    - "{{ systemd_dir }}/k3s-node.service.d"
+  when: proxy_env is defined
 
 - name: Reload daemon_reload
   systemd:
-    daemon_reload: yes
+    daemon_reload: true
 
 - name: Remove tmp directory used for manifests
   file:

site.yml

@@ -1,15 +1,26 @@
 ---
+- name: Pre tasks
+  hosts: all
+  pre_tasks:
+    - name: Verify Ansible is version 2.11 or above. (If this fails you may need to update Ansible)
+      assert:
+        that: "ansible_version.full is version_compare('2.11', '>=')"
+        msg: >
+          "Ansible is out of date. See here for more info: https://docs.technotim.live/posts/ansible-automation/"
+
 - name: Prepare Proxmox cluster
   hosts: proxmox
   gather_facts: true
-  become: yes
+  become: true
+  environment: "{{ proxy_env | default({}) }}"
   roles:
     - role: proxmox_lxc
       when: proxmox_lxc_configure
 
 - name: Prepare k3s nodes
   hosts: k3s_cluster
-  gather_facts: yes
+  gather_facts: true
+  environment: "{{ proxy_env | default({}) }}"
   roles:
     - role: lxc
       become: true
@@ -20,21 +31,38 @@
       become: true
     - role: raspberrypi
       become: true
+    - role: k3s_custom_registries
+      become: true
+      when: custom_registries
 
 - name: Setup k3s servers
   hosts: master
+  environment: "{{ proxy_env | default({}) }}"
   roles:
     - role: k3s_server
       become: true
 
 - name: Setup k3s agents
   hosts: node
+  environment: "{{ proxy_env | default({}) }}"
   roles:
     - role: k3s_agent
       become: true
 
 - name: Configure k3s cluster
   hosts: master
+  environment: "{{ proxy_env | default({}) }}"
   roles:
     - role: k3s_server_post
       become: true
+
+- name: Storing kubeconfig in the playbook directory
+  hosts: master
+  environment: "{{ proxy_env | default({}) }}"
+  tasks:
+    - name: Copying kubeconfig from {{ hostvars[groups[group_name_master | default('master')][0]]['ansible_hostname'] }}
+      ansible.builtin.fetch:
+        src: "{{ ansible_user_dir }}/.kube/config"
+        dest: ./kubeconfig
+        flat: true
+      when: ansible_hostname == hostvars[groups[group_name_master | default('master')][0]]['ansible_hostname']