fix(ci): align Vagrant prewarm profile

- Match the minimum CPU and memory used by Ubuntu Molecule platforms
- Restore Vagrant's normal key insertion after password authentication
- Cover the canonical prewarm configuration in the fixture

.ansible-lint

@@ -1,20 +1,27 @@
 ---
+profile: production
 exclude_paths:
   # default paths
-  - '.cache/'
-  - '.github/'
-  - 'test/fixtures/formatting-before/'
-  - 'test/fixtures/formatting-prettier/'
+  - .cache/
+  - .ansible/
+  - .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'
+  - molecule/**/converge.yml
+  - molecule/**/prepare.yml
+  - molecule/**/reset.yml
 
   # The file was generated by galaxy ansible - don't mess with it.
-  - 'galaxy.yml'
+  - galaxy.yml
 
 skip_list:
-  - 'fqcn-builtins'
+  - var-naming[no-role-prefix]
+
+# The Molecule Vagrant driver injects this module at runtime. The custom create
+# playbook is syntax-checked separately against the exact pinned plugin module.
+mock_modules:
+  - vagrant

.github/ISSUE_TEMPLATE.md

@@ -1,5 +1,5 @@
 
-<!-- It's a good idea to check this post first for general troubleshooting https://github.com/techno-tim/k3s-ansible/discussions/19   -->
+<!-- It's a good idea to check this post first for general troubleshooting https://github.com/timothystewart6/k3s-ansible/discussions/19   -->
 
 <!--- Provide a general summary of the issue in the Title above -->
 
@@ -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: ""
 
@@ -74,4 +82,4 @@ node
 ## Possible Solution
 <!--- Not obligatory, but suggest a fix/reason for the bug, -->
 
-- [ ] I've checked the [General Troubleshooting Guide](https://github.com/techno-tim/k3s-ansible/discussions/20)
+- [ ] I've checked the [General Troubleshooting Guide](https://github.com/timothystewart6/k3s-ansible/discussions/20)

.github/actionlint.yaml

@@ -0,0 +1,6 @@
+---
+self-hosted-runner:
+  labels:
+    - k3s-ci
+    - virtualbox
+    - nested-virt

.github/download-boxes.sh

@@ -1,37 +1,91 @@
 #!/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.
+# Validate the pinned Vagrant box set and download exact versions that are not
+# already present in VAGRANT_HOME.
 
 set -euo pipefail
 
 GIT_ROOT=$(git rev-parse --show-toplevel)
 PROVIDER=virtualbox
+LOCK_FILE="${VAGRANT_BOX_LOCK_FILE:-${GIT_ROOT}/.github/vagrant-boxes.lock}"
 
-# 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)
+MOLECULE_YML_PATH=("${GIT_ROOT}"/molecule/*/molecule.yml)
 
-# Read the boxes that are currently present on the system (for the current provider)
+# Extract the unique boxes referenced by the scenarios.
+declared_boxes=$(for file in "${MOLECULE_YML_PATH[@]}"; do
+    yq -r '.platforms[].box' "$file"
+done | sort -u)
+
+if [[ ! -r "$LOCK_FILE" ]]; then
+    printf 'Vagrant box lock file is missing or unreadable: %s\n' "$LOCK_FILE" >&2
+    exit 1
+fi
+
+lock_entries=$(awk '
+    /^[[:space:]]*#/ || NF == 0 { next }
+    NF != 3 {
+        printf "Invalid lock entry on line %d: expected box, version, architecture\n", NR > "/dev/stderr"
+        invalid = 1
+        next
+    }
+    { print $1 " " $2 " " $3 }
+    END { exit invalid }
+' "$LOCK_FILE")
+
+duplicate_boxes=$(printf '%s\n' "$lock_entries" | awk '{ print $1 }' | sort | uniq -d)
+if [[ -n "$duplicate_boxes" ]]; then
+    printf 'Duplicate Vagrant box lock entries:\n%s\n' "$duplicate_boxes" >&2
+    exit 1
+fi
+
+locked_boxes=$(printf '%s\n' "$lock_entries" | sort)
+locked_names=$(printf '%s\n' "$locked_boxes" | awk '{ print $1 }')
+missing_locks=$(comm -23 <(printf '%s\n' "$declared_boxes") <(printf '%s\n' "$locked_names"))
+unused_locks=$(comm -13 <(printf '%s\n' "$declared_boxes") <(printf '%s\n' "$locked_names"))
+
+if [[ -n "$missing_locks" || -n "$unused_locks" ]]; then
+    if [[ -n "$missing_locks" ]]; then
+        printf 'Scenario boxes missing from the lock file:\n%s\n' "$missing_locks" >&2
+    fi
+    if [[ -n "$unused_locks" ]]; then
+        printf 'Lock entries not referenced by a scenario:\n%s\n' "$unused_locks" >&2
+    fi
+    exit 1
+fi
+
+printf 'Pinned Vagrant boxes:\n%s\n' "$locked_boxes"
+
+# Read exact box, provider, version, and architecture tuples already present.
 present_boxes=$(
-    (vagrant box list |
-        grep "${PROVIDER}" | # Filter by boxes available for the current provider
-        awk '{print $1;}' |  # The box name is the first word in each line
-        sort |
-        uniq) ||
-        echo "" # In case any of these commands fails, just use an empty list
+    vagrant box list --machine-readable |
+        awk -F, -v expected_provider="$PROVIDER" '
+            $3 == "box-name" { name = $4; next }
+            $3 == "box-provider" { provider = $4; next }
+            $3 == "box-version" { version = $4; next }
+            $3 == "box-architecture" {
+                architecture = $4
+                if (provider == expected_provider) {
+                    print name " " version " " architecture
+                }
+                name = provider = version = architecture = ""
+            }
+        ' |
+        sort -u
 )
 
-# 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}"))
+download_boxes=$(comm -23 \
+    <(printf '%s\n' "$locked_boxes") \
+    <(printf '%s\n' "$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}"
+if [[ -n "$download_boxes" ]]; then
+    printf '%s\n' "$download_boxes" | while read -r box version architecture; do
+        vagrant box add \
+            --provider "$PROVIDER" \
+            --box-version "$version" \
+            --architecture "$architecture" \
+            "$box"
     done
+else
+    printf 'All pinned Vagrant boxes are already present.\n'
 fi

.github/scripts/cleanup-runner-resources.sh

@@ -0,0 +1,249 @@
+#!/usr/bin/env bash
+
+set -Eeuo pipefail
+
+usage() {
+  printf '%s\n' \
+    'Usage: cleanup-runner-resources.sh [--snapshot|--dry-run|--apply]' \
+    '' \
+    'Discover and, with --apply, remove only VirtualBox resources referenced by' \
+    'repository-owned Molecule Vagrant state. The default is --dry-run.'
+}
+
+mode="dry-run"
+case "${1:-}" in
+  "") ;;
+  --snapshot) mode="snapshot" ;;
+  --dry-run) mode="dry-run" ;;
+  --apply) mode="apply" ;;
+  --help|-h) usage; exit 0 ;;
+  *) usage >&2; exit 2 ;;
+esac
+
+home_dir="${HOME:?HOME must be set}"
+molecule_root="${K3S_CI_MOLECULE_ROOT:-${home_dir}/.cache/molecule}"
+repository_name="${K3S_CI_MOLECULE_PROJECT:-k3s-ansible}"
+virtualbox_root="${K3S_CI_VIRTUALBOX_ROOT:-${home_dir}/VirtualBox VMs}"
+hostonly_marker="${K3S_CI_HOSTONLY_MARKER:-${home_dir}/.cache/k3s-ci/hostonly-interfaces}"
+
+record_hostonly() {
+  local marker_dir="${hostonly_marker%/*}"
+  local marker_tmp="${hostonly_marker}.tmp"
+  local hostonly_inventory
+  if ! hostonly_inventory="$(VBoxManage list hostonlyifs)"; then
+    fail_closed 'unable to inventory VirtualBox host-only interfaces'
+  fi
+  mkdir -p -- "$marker_dir"
+  awk -F': ' '
+    /^Name:/ { name=$2 }
+    /^IPAddress:/ { print name "|" $2 }
+  ' <<< "$hostonly_inventory" > "$marker_tmp"
+  mv -- "$marker_tmp" "$hostonly_marker"
+  chmod 600 "$hostonly_marker"
+  printf 'Recorded host-only interface baseline: %s\n' "$hostonly_marker"
+}
+
+cleanup_hostonly() {
+  local hostonly_inventory
+  if [[ ! -f "$hostonly_marker" ]]; then
+    printf 'No host-only interface baseline found; leaving interfaces unchanged.\n'
+    return 0
+  fi
+
+  if ! hostonly_inventory="$(VBoxManage list hostonlyifs)"; then
+    fail_closed 'unable to inventory VirtualBox host-only interfaces'
+  fi
+
+  while IFS='|' read -r interface_name interface_ip; do
+    [[ "$interface_name" == vboxnet* ]] || continue
+    [[ "$interface_ip" == 192.168.30.* || "$interface_ip" == fdad:bad:ba55:* ]] || continue
+    if grep -Fqx "${interface_name}|${interface_ip}" "$hostonly_marker"; then
+      continue
+    fi
+    if [[ "$mode" == apply ]]; then
+      VBoxManage hostonlyif remove "$interface_name"
+      printf 'Removed host-only interface %s (%s)\n' "$interface_name" "$interface_ip"
+    else
+      printf 'Would remove host-only interface %s (%s)\n' "$interface_name" "$interface_ip"
+    fi
+  done < <(awk -F': ' '
+    /^Name:/ { name=$2 }
+    /^IPAddress:/ { print name "|" $2 }
+  ' <<< "$hostonly_inventory")
+}
+
+if [[ "$mode" == snapshot ]]; then
+  record_hostonly
+  exit 0
+fi
+
+resolve_existing_dir() {
+  local candidate="$1"
+  if [[ ! -d "$candidate" ]]; then
+    return 1
+  fi
+  readlink -f -- "$candidate"
+}
+
+root_contains() {
+  local root="$1"
+  local path="$2"
+  [[ "$path" == "$root"/* ]]
+}
+
+is_supported_scenario() {
+  case "$1" in
+    default|single_node|calico|cilium|kube-vip|ipv6) return 0 ;;
+    *) return 1 ;;
+  esac
+}
+
+is_unregistered_vm_error() {
+  grep -Eq 'Could not find a registered machine|VBOX_E_OBJECT_NOT_FOUND'
+}
+
+fail_closed() {
+  printf 'cleanup refused: %s\n' "$1" >&2
+  exit 3
+}
+
+if [[ ! "$repository_name" =~ ^[A-Za-z0-9._-]+$ ]]; then
+  fail_closed 'invalid Molecule repository name'
+fi
+
+print_inventory() {
+  local phase="$1"
+  printf '%s VirtualBox inventory:\n' "$phase"
+  VBoxManage list vms || true
+  VBoxManage list hdds || true
+  VBoxManage list hostonlyifs || true
+}
+
+molecule_root_real="$(resolve_existing_dir "$molecule_root" || true)"
+if [[ -z "$molecule_root_real" ]]; then
+  printf 'No Molecule root exists: %s\n' "$molecule_root"
+  cleanup_hostonly
+  exit 0
+fi
+
+print_inventory before
+
+repository_root_real="$(resolve_existing_dir "$molecule_root_real/$repository_name" || true)"
+if [[ -z "$repository_root_real" ]]; then
+  printf 'No repository Molecule state root exists: %s\n' "$molecule_root_real/$repository_name"
+  cleanup_hostonly
+  print_inventory after
+  exit 0
+fi
+if ! root_contains "$molecule_root_real" "$repository_root_real"; then
+  fail_closed "repository Molecule state root is outside Molecule root: $repository_root_real"
+fi
+
+declare -a state_files=()
+while IFS= read -r -d '' state_file; do
+  state_files+=("$state_file")
+done < <(find "$repository_root_real" -mindepth 6 -maxdepth 6 -type f \
+  -path '*/.vagrant/machines/*/virtualbox/id' -print0 2>/dev/null)
+
+if ((${#state_files[@]} == 0)); then
+  printf 'No repository-owned Molecule Vagrant state found under %s\n' "$repository_root_real"
+  cleanup_hostonly
+  print_inventory after
+  exit 0
+fi
+
+virtualbox_root_real="$(resolve_existing_dir "$virtualbox_root" || true)"
+
+declare -a vm_records=()
+for state_file in "${state_files[@]}"; do
+  if [[ ! -f "$state_file" ]]; then
+    printf 'Skipping Vagrant state removed with its stale scenario directory: %s\n' "$state_file"
+    continue
+  fi
+  state_file_real="$(readlink -f -- "$state_file")"
+  state_dir="${state_file_real%/.vagrant/machines/*/virtualbox/id}"
+  machine_dir="${state_file_real%/virtualbox/id}"
+  machine_name="${machine_dir##*/}"
+  scenario_name="${state_dir##*/}"
+
+  if ! root_contains "$repository_root_real" "$state_dir"; then
+    fail_closed "state path is outside the repository Molecule root: $state_file_real"
+  fi
+  if ! is_supported_scenario "$scenario_name"; then
+    fail_closed "unexpected Molecule scenario: $scenario_name"
+  fi
+  if [[ "$machine_name" != control* && "$machine_name" != node* ]]; then
+    fail_closed "unexpected Molecule machine name: $machine_name"
+  fi
+
+  vm_uuid="$(tr -d '[:space:]' < "$state_file_real")"
+  if [[ ! "$vm_uuid" =~ ^[0-9a-fA-F-]{36}$ ]]; then
+    fail_closed "invalid VirtualBox UUID in $state_file_real"
+  fi
+
+  if ! vm_info="$(VBoxManage showvminfo "$vm_uuid" --machinereadable 2>&1)"; then
+    if is_unregistered_vm_error <<< "$vm_info"; then
+      printf 'Stale Vagrant state without a registered VM: %s (%s)\n' "$machine_name" "$vm_uuid"
+      if [[ "$mode" == apply ]]; then
+        rm -rf -- "${state_dir}/.vagrant"
+        printf 'Removed stale Vagrant state: %s\n' "${state_dir}/.vagrant"
+      fi
+      continue
+    fi
+    fail_closed "unable to inspect VirtualBox VM $vm_uuid: $vm_info"
+  fi
+
+  if [[ -z "$virtualbox_root_real" ]]; then
+    fail_closed "VirtualBox VM root does not exist: $virtualbox_root"
+  fi
+
+  cfg_file="$(awk -F= '$1 == "CfgFile" {gsub(/"/, "", $2); print $2; exit}' <<< "$vm_info")"
+  if [[ -z "$cfg_file" ]]; then
+    fail_closed "VirtualBox configuration path missing for $vm_uuid"
+  fi
+  cfg_file_real="$(readlink -f -- "$cfg_file")"
+  if ! root_contains "$virtualbox_root_real" "$cfg_file_real"; then
+    fail_closed "VM configuration is outside VirtualBox root: $cfg_file_real"
+  fi
+
+  while IFS= read -r disk_path; do
+    [[ -z "$disk_path" ]] && continue
+    disk_path_real="$(readlink -f -- "$disk_path" 2>/dev/null || true)"
+    if [[ -z "$disk_path_real" ]] || ! root_contains "$virtualbox_root_real" "$disk_path_real"; then
+      fail_closed "attached disk is outside VirtualBox root: $disk_path"
+    fi
+  done < <(awk -F= '$1 ~ /^(SATA|IDE|SCSI|SAS|VirtioSCSI|NVMe)-[0-9]+-[0-9]+$/ {gsub(/"/, "", $2); print $2}' <<< "$vm_info")
+
+  vm_records+=("$vm_uuid|$machine_name|$cfg_file_real")
+done
+
+if ((${#vm_records[@]} == 0)); then
+  printf 'No live repository-owned VirtualBox resources found\n'
+  cleanup_hostonly
+  print_inventory after
+  exit 0
+fi
+
+for record in "${vm_records[@]}"; do
+  IFS='|' read -r vm_uuid machine_name cfg_file_real <<< "$record"
+  if [[ "$mode" == dry-run ]]; then
+    printf 'Would remove VM %s (%s) config=%s\n' "$machine_name" "$vm_uuid" "$cfg_file_real"
+    continue
+  fi
+
+  vm_state="$(VBoxManage showvminfo "$vm_uuid" --machinereadable | awk -F= '$1 == "VMState" {gsub(/"/, "", $2); print $2; exit}')"
+  if [[ "$vm_state" != poweroff && "$vm_state" != saved ]]; then
+    VBoxManage controlvm "$vm_uuid" poweroff
+  fi
+  VBoxManage unregistervm "$vm_uuid" --delete
+  printf 'Removed VM %s (%s)\n' "$machine_name" "$vm_uuid"
+done
+
+cleanup_hostonly
+print_inventory after
+
+if [[ "$mode" == apply ]]; then
+  printf 'Repository-owned VM and host-only interface cleanup complete.\n'
+else
+  printf 'Dry run complete. No resources were modified.\n'
+fi

.github/scripts/collect-runner-diagnostics.sh

@@ -0,0 +1,47 @@
+#!/usr/bin/env bash
+
+set -Eeuo pipefail
+
+output_dir="${1:-${RUNNER_TEMP:-/tmp}/k3s-ci-diagnostics}"
+mkdir -p -- "$output_dir"
+umask 077
+
+run_capture() {
+  local output_file="$1"
+  shift
+  {
+    printf '$'
+    printf ' %q' "$@"
+    printf '\n'
+    "$@"
+  } > "$output_dir/$output_file" 2>&1 || true
+}
+
+run_capture system.txt uname -a
+run_capture runner-user.txt id
+run_capture memory.txt free -h
+run_capture disk.txt df -h
+run_capture virtualbox-version VBoxManage --version
+run_capture virtualbox-vms VBoxManage list vms
+run_capture virtualbox-running-vms VBoxManage list runningvms
+run_capture virtualbox-disks VBoxManage list hdds
+run_capture virtualbox-hostonlyifs VBoxManage list hostonlyifs
+run_capture virtualbox-groups VBoxManage list groups
+run_capture vagrant-status vagrant global-status
+run_capture molecule-state find "${HOME}/.cache/molecule" -maxdepth 6 -type f -path '*/.vagrant/machines/*/virtualbox/id' -print
+
+scenario_name="${K3S_CI_SCENARIO_NAME:-}"
+if [[ "$scenario_name" =~ ^[A-Za-z0-9_-]+$ ]]; then
+  molecule_state_dir="${HOME}/.cache/molecule/k3s-ansible/${scenario_name}"
+  for log_name in vagrant.out vagrant.err; do
+    if [[ -r "${molecule_state_dir}/${log_name}" ]]; then
+      cp -- "${molecule_state_dir}/${log_name}" "$output_dir/${scenario_name}-${log_name}"
+    fi
+  done
+fi
+
+if [[ -r /etc/vbox/networks.conf ]]; then
+  cp -- /etc/vbox/networks.conf "$output_dir/virtualbox-networks.conf"
+fi
+
+printf 'Diagnostics written to %s\n' "$output_dir"

.github/scripts/monitor-runner-resources.sh

@@ -0,0 +1,44 @@
+#!/usr/bin/env bash
+
+set -Eeuo pipefail
+
+output_dir="${1:?output directory is required}"
+interval="${2:-10}"
+[[ "$interval" =~ ^[1-9][0-9]*$ ]] || {
+  printf 'monitor interval must be a positive integer\n' >&2
+  exit 2
+}
+
+mkdir -p -- "$output_dir"
+umask 077
+
+free -h > "$output_dir/memory-before.txt"
+df -h > "$output_dir/disk-before.txt"
+vmstat -w "$interval" > "$output_dir/vmstat.txt" &
+vmstat_pid=$!
+
+iostat_pid=""
+if command -v iostat >/dev/null 2>&1; then
+  iostat -dx "$interval" > "$output_dir/iostat.txt" &
+  iostat_pid=$!
+else
+  printf 'iostat is not installed on this runner\n' > "$output_dir/iostat-unavailable.txt"
+fi
+
+cleanup() {
+  local rc=$?
+  trap - EXIT INT TERM
+  kill "$vmstat_pid" 2>/dev/null || true
+  [[ -z "$iostat_pid" ]] || kill "$iostat_pid" 2>/dev/null || true
+  wait "$vmstat_pid" 2>/dev/null || true
+  [[ -z "$iostat_pid" ]] || wait "$iostat_pid" 2>/dev/null || true
+  free -h > "$output_dir/memory-after.txt"
+  df -h > "$output_dir/disk-after.txt"
+  exit "$rc"
+}
+trap cleanup EXIT INT TERM
+
+while :; do
+  sleep 3600 &
+  wait $!
+done

.github/scripts/prepare-vagrant-box-masters.sh

@@ -0,0 +1,219 @@
+#!/usr/bin/env bash
+
+set -Eeuo pipefail
+
+fail() {
+  printf 'Vagrant box master preparation refused: %s\n' "$1" >&2
+  exit 3
+}
+
+root_contains() {
+  local root="$1"
+  local path="$2"
+  [[ "$path" == "$root"/* ]]
+}
+
+read_machine_value() {
+  local machine_info="$1"
+  local key="$2"
+  awk -F= -v key="$key" '$1 == key {gsub(/"/, "", $2); print $2; exit}' <<< "$machine_info"
+}
+
+read_extra_data() {
+  local uuid="$1"
+  local key="$2"
+  local value
+  value="$(VBoxManage getextradata "$uuid" "$key" 2>/dev/null || true)"
+  [[ "$value" == 'Value: '* ]] || return 1
+  printf '%s\n' "${value#Value: }"
+}
+
+validate_owned_master() {
+  local uuid="$1"
+  local box="$2"
+  local version="$3"
+  local architecture="$4"
+  local machine_info cfg_file cfg_file_real vm_state groups disk_path disk_path_real
+
+  [[ "$uuid" =~ ^[0-9a-fA-F-]{36}$ ]] || return 1
+  machine_info="$(VBoxManage showvminfo "$uuid" --machinereadable 2>/dev/null)" || return 1
+  vm_state="$(read_machine_value "$machine_info" VMState)"
+  groups="$(read_machine_value "$machine_info" groups)"
+  cfg_file="$(read_machine_value "$machine_info" CfgFile)"
+  [[ "$vm_state" == poweroff ]] || return 1
+  [[ ",$groups," == *,/k3s-ansible/box-masters,* ]] || return 1
+  [[ -n "$cfg_file" ]] || return 1
+  cfg_file_real="$(readlink -f -- "$cfg_file" 2>/dev/null || true)"
+  [[ -n "$cfg_file_real" ]] || return 1
+  root_contains "$virtualbox_root_real" "$cfg_file_real" || return 1
+
+  [[ "$(read_extra_data "$uuid" k3s-ansible/owner || true)" == box-master ]] || return 1
+  [[ "$(read_extra_data "$uuid" k3s-ansible/box || true)" == "$box" ]] || return 1
+  [[ "$(read_extra_data "$uuid" k3s-ansible/version || true)" == "$version" ]] || return 1
+  [[ "$(read_extra_data "$uuid" k3s-ansible/architecture || true)" == "$architecture" ]] || return 1
+
+  while IFS= read -r disk_path; do
+    [[ -z "$disk_path" || "$disk_path" == none ]] && continue
+    disk_path_real="$(readlink -f -- "$disk_path" 2>/dev/null || true)"
+    [[ -n "$disk_path_real" ]] || return 1
+    root_contains "$virtualbox_root_real" "$disk_path_real" || return 1
+  done < <(awk -F= '$1 ~ /^(SATA|IDE|SCSI|SAS|VirtioSCSI|NVMe)-[0-9]+-[0-9]+$/ {
+    gsub(/"/, "", $2); print $2
+  }' <<< "$machine_info")
+}
+
+write_prewarm_vagrantfile() {
+  local destination="$1"
+  local box="$2"
+  local version="$3"
+  {
+    printf '%s\n' "Vagrant.configure('2') do |config|"
+    printf '  config.vm.box = "%s"\n' "$box"
+    printf '  config.vm.box_version = "%s"\n' "$version"
+    # generic/ubuntu2204 does not accept Vagrant's bundled insecure key.
+    # Match the repository's Molecule connection settings for the short-lived
+    # prewarm clone so Vagrant can record its linked-clone master.
+    if [[ "$box" == 'generic/ubuntu2204' ]]; then
+      printf '%s\n' \
+        '  config.ssh.username = "vagrant"' \
+        '  config.ssh.password = "vagrant"'
+    fi
+    printf '%s\n' \
+      '  config.vm.synced_folder ".", "/vagrant", disabled: true' \
+      '  config.vm.hostname = "k3s-ansible-box-prewarm"' \
+      '  config.vm.boot_timeout = 600' \
+      '  config.vm.provider "virtualbox" do |virtualbox|' \
+      '    virtualbox.linked_clone = true' \
+      '    virtualbox.memory = 1024' \
+      '    virtualbox.cpus = 2' \
+      '  end' \
+      'end'
+  } > "$destination"
+}
+
+cleanup_prewarm() {
+  local rc=$?
+  trap - EXIT
+  if [[ -n "${prewarm_dir:-}" && -d "$prewarm_dir" ]]; then
+    VAGRANT_CWD="$prewarm_dir" vagrant destroy --force >/dev/null 2>&1 || true
+    rm -rf -- "$prewarm_dir"
+  fi
+  exit "$rc"
+}
+
+create_owned_master() {
+  local box="$1"
+  local version="$2"
+  local architecture="$3"
+  local master_id_file="$4"
+  local mapping_file="$5"
+  local uuid machine_info cfg_file cfg_file_real vm_state mapping_tmp
+
+  # A master_id restored from an immutable cache is only a hint. Without the
+  # runner-local ownership record and matching VirtualBox metadata it is not
+  # trusted, adopted, modified, or deleted.
+  rm -f -- "$master_id_file"
+
+  prewarm_dir="$(mktemp -d "${master_root}/prewarm.XXXXXX")"
+  trap cleanup_prewarm EXIT
+  write_prewarm_vagrantfile "$prewarm_dir/Vagrantfile" "$box" "$version"
+
+  printf 'Creating runner-owned linked-clone master for %s %s %s\n' \
+    "$box" "$version" "$architecture"
+  VAGRANT_CWD="$prewarm_dir" vagrant up --provider virtualbox --no-provision
+
+  [[ -r "$master_id_file" ]] || fail "Vagrant did not record a master UUID for $box"
+  uuid="$(tr -d '[:space:]' < "$master_id_file")"
+  [[ "$uuid" =~ ^[0-9a-fA-F-]{36}$ ]] || fail "Vagrant recorded an invalid master UUID for $box"
+
+  machine_info="$(VBoxManage showvminfo "$uuid" --machinereadable 2>/dev/null)" || \
+    fail "Vagrant master $uuid for $box is not registered"
+  vm_state="$(read_machine_value "$machine_info" VMState)"
+  cfg_file="$(read_machine_value "$machine_info" CfgFile)"
+  cfg_file_real="$(readlink -f -- "$cfg_file" 2>/dev/null || true)"
+  [[ "$vm_state" == poweroff ]] || fail "new Vagrant master $uuid is not powered off"
+  if [[ -z "$cfg_file_real" ]] || ! root_contains "$virtualbox_root_real" "$cfg_file_real"; then
+    fail "new Vagrant master $uuid is outside the runner VirtualBox root"
+  fi
+
+  VAGRANT_CWD="$prewarm_dir" vagrant destroy --force
+  VBoxManage modifyvm "$uuid" --groups /k3s-ansible/box-masters
+  VBoxManage setextradata "$uuid" k3s-ansible/owner box-master
+  VBoxManage setextradata "$uuid" k3s-ansible/box "$box"
+  VBoxManage setextradata "$uuid" k3s-ansible/version "$version"
+  VBoxManage setextradata "$uuid" k3s-ansible/architecture "$architecture"
+  validate_owned_master "$uuid" "$box" "$version" "$architecture" || \
+    fail "new Vagrant master $uuid failed ownership validation"
+
+  rm -rf -- "$prewarm_dir"
+  prewarm_dir=""
+  trap - EXIT
+
+  mapping_tmp="${mapping_file}.tmp"
+  printf '%s\n' "$uuid" > "$mapping_tmp"
+  chmod 600 "$mapping_tmp"
+  mv -- "$mapping_tmp" "$mapping_file"
+  printf '%s\n' "$uuid" > "$master_id_file"
+  chmod 600 "$master_id_file"
+  printf 'Created and recorded owned master %s for %s\n' "$uuid" "$box"
+}
+
+repository_root="${K3S_CI_REPOSITORY_ROOT:-$(git rev-parse --show-toplevel)}"
+lock_file="${VAGRANT_BOX_LOCK_FILE:-${repository_root}/.github/vagrant-boxes.lock}"
+vagrant_home="${VAGRANT_HOME:?VAGRANT_HOME must be set}"
+master_root="${K3S_CI_VAGRANT_MASTER_ROOT:-${HOME:?HOME must be set}/.cache/k3s-ci/vagrant-masters}"
+virtualbox_root="${K3S_CI_VIRTUALBOX_ROOT:-${HOME}/VirtualBox VMs}"
+
+[[ -r "$lock_file" ]] || fail "box lock file is missing or unreadable: $lock_file"
+[[ -d "$vagrant_home/boxes" ]] || fail "Vagrant box directory is missing: $vagrant_home/boxes"
+[[ -d "$virtualbox_root" ]] || fail "VirtualBox root is missing: $virtualbox_root"
+
+box_root_real="$(readlink -f -- "$vagrant_home/boxes")"
+virtualbox_root_real="$(readlink -f -- "$virtualbox_root")"
+mkdir -p -- "$master_root"
+chmod 700 "$master_root"
+
+exec 9> "${master_root}/prepare.lock"
+flock 9
+
+lock_entries="$(awk '
+  /^[[:space:]]*#/ || NF == 0 { next }
+  NF != 3 { invalid = 1; next }
+  { print $1 " " $2 " " $3 }
+  END { exit invalid }
+' "$lock_file")" || fail 'invalid Vagrant box lock entry'
+[[ -n "$lock_entries" ]] || fail 'Vagrant box lock is empty'
+
+while read -r box version architecture; do
+  [[ "$box" =~ ^[A-Za-z0-9._-]+/[A-Za-z0-9._-]+$ ]] || fail "invalid box name: $box"
+  [[ "$version" =~ ^[A-Za-z0-9._-]+$ ]] || fail "invalid box version: $version"
+  [[ "$architecture" =~ ^[A-Za-z0-9._-]+$ ]] || fail "invalid box architecture: $architecture"
+
+  box_slug="${box//\//-VAGRANTSLASH-}"
+  record_slug="${box//\//_}-${version}-${architecture}"
+  box_dir="${vagrant_home}/boxes/${box_slug}/${version}/${architecture}/virtualbox"
+  [[ -d "$box_dir" ]] || fail "pinned box is not installed: $box $version $architecture"
+  box_dir_real="$(readlink -f -- "$box_dir")"
+  root_contains "$box_root_real" "$box_dir_real" || fail "box directory is outside VAGRANT_HOME: $box_dir_real"
+
+  master_id_file="${box_dir_real}/master_id"
+  mapping_file="${master_root}/${record_slug}.uuid"
+  uuid=""
+  if [[ -r "$mapping_file" ]]; then
+    uuid="$(tr -d '[:space:]' < "$mapping_file")"
+  fi
+
+  if [[ -n "$uuid" ]] && validate_owned_master "$uuid" "$box" "$version" "$architecture"; then
+    printf '%s\n' "$uuid" > "$master_id_file"
+    chmod 600 "$master_id_file"
+    printf 'Reusing owned master %s for %s %s %s\n' "$uuid" "$box" "$version" "$architecture"
+    continue
+  fi
+
+  if [[ -e "$mapping_file" ]]; then
+    printf 'Owned master record is stale for %s; rebuilding without deleting any VM or disk.\n' "$box"
+  fi
+  create_owned_master "$box" "$version" "$architecture" "$master_id_file" "$mapping_file"
+done <<< "$lock_entries"
+
+printf 'All pinned Vagrant box masters are ready.\n'

.github/scripts/test-cleanup-runner-resources.sh

@@ -0,0 +1,129 @@
+#!/usr/bin/env bash
+
+# shellcheck disable=SC2016
+
+set -Eeuo pipefail
+
+repo_root="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")/../.." && pwd)"
+test_root="$(mktemp -d "${TMPDIR:-/tmp}/k3s-ci-cleanup-test.XXXXXX")"
+trap 'rm -rf -- "$test_root"' EXIT
+
+molecule_root="$test_root/molecule"
+virtualbox_root="$test_root/VirtualBox VMs"
+fake_bin="$test_root/bin"
+mkdir -p -- "$molecule_root/k3s-ansible/single_node/.vagrant/machines/control1/virtualbox" \
+  "$molecule_root/k3s-ansible/single_node/.vagrant/machines/control2/virtualbox" \
+  "$virtualbox_root/control1" "$virtualbox_root/unmarked" "$fake_bin"
+printf '%s\n' '11111111-1111-1111-1111-111111111111' \
+  > "$molecule_root/k3s-ansible/single_node/.vagrant/machines/control1/virtualbox/id"
+printf '%s\n' '22222222-2222-2222-2222-222222222222' \
+  > "$molecule_root/k3s-ansible/single_node/.vagrant/machines/control2/virtualbox/id"
+touch "$virtualbox_root/control1/control1.vbox" "$virtualbox_root/control1/disk.vdi" \
+  "$virtualbox_root/unmarked/unmarked.vbox"
+
+printf '%s\n' \
+  '#!/usr/bin/env bash' \
+  'set -Eeuo pipefail' \
+  'case "${1:-}" in' \
+  '  list)' \
+  '    if [[ "${2:-}" == hostonlyifs && "${FAKE_HOSTONLY_FAIL:-false}" == true ]]; then exit 1; fi' \
+  '    exit 0' \
+  '    ;;' \
+  '  showvminfo)' \
+  '    if [[ "${FAKE_VM_MODE:-normal}" == missing ]]; then' \
+  '      printf '\''VBoxManage: error: Could not find a registered machine named "missing"\n'\'' >&2' \
+  '      exit 1' \
+  '    fi' \
+  '    if [[ "${FAKE_VM_MODE:-normal}" == fault ]]; then' \
+  '      printf '\''VBoxManage: error: VirtualBox service is unavailable\n'\'' >&2' \
+  '      exit 1' \
+  '    fi' \
+  '    printf '\''CfgFile="%s"\n'\'' "${FAKE_VBOX_ROOT}/control1/control1.vbox"' \
+  '    printf '\''SATA-0-0="%s"\n'\'' "${FAKE_VBOX_ROOT}/control1/disk.vdi"' \
+  '    printf '\''VMState="running"\n'\''' \
+  '    ;;' \
+  '  controlvm) printf '\''controlvm %s\n'\'' "$*" >> "${FAKE_LOG}" ;;' \
+  '  unregistervm)' \
+  '    printf '\''unregistervm %s\n'\'' "$*" >> "${FAKE_LOG}"' \
+  '    rm -f -- "${FAKE_VBOX_ROOT}/control1/control1.vbox" "${FAKE_VBOX_ROOT}/control1/disk.vdi"' \
+  '    ;;' \
+  '  *) : ;;' \
+  'esac' > "$fake_bin/VBoxManage"
+chmod 700 "$fake_bin/VBoxManage"
+
+output="$test_root/output.txt"
+if PATH="$fake_bin:$PATH" \
+  HOME="$test_root/home" \
+  K3S_CI_MOLECULE_ROOT="$molecule_root" \
+  K3S_CI_MOLECULE_PROJECT=k3s-ansible \
+  K3S_CI_VIRTUALBOX_ROOT="$virtualbox_root" \
+  K3S_CI_HOSTONLY_MARKER="$test_root/hostonly-baseline" \
+  FAKE_VM_MODE=fault \
+  FAKE_VBOX_ROOT="$virtualbox_root" \
+  FAKE_LOG="$test_root/vbox.log" \
+  bash "$repo_root/.github/scripts/cleanup-runner-resources.sh" --apply > "$output" 2>&1; then
+  printf '%s\n' 'cleanup unexpectedly accepted a VirtualBox inspection failure' >&2
+  exit 1
+fi
+grep -Fq 'cleanup refused: unable to inspect VirtualBox VM' "$output"
+[[ -f "$molecule_root/k3s-ansible/single_node/.vagrant/machines/control1/virtualbox/id" ]]
+
+printf '%s\n' 'vboxnet0|192.168.30.1' > "$test_root/hostonly-baseline"
+if PATH="$fake_bin:$PATH" \
+  HOME="$test_root/home" \
+  K3S_CI_MOLECULE_ROOT="$molecule_root" \
+  K3S_CI_MOLECULE_PROJECT=k3s-ansible \
+  K3S_CI_VIRTUALBOX_ROOT="$virtualbox_root" \
+  K3S_CI_HOSTONLY_MARKER="$test_root/hostonly-baseline" \
+  FAKE_HOSTONLY_FAIL=true \
+  FAKE_VBOX_ROOT="$virtualbox_root" \
+  FAKE_LOG="$test_root/vbox.log" \
+  bash "$repo_root/.github/scripts/cleanup-runner-resources.sh" --dry-run > "$output" 2>&1; then
+  printf '%s\n' 'cleanup unexpectedly accepted a host-only inventory failure' >&2
+  exit 1
+fi
+grep -Fq 'cleanup refused: unable to inventory VirtualBox host-only interfaces' "$output"
+
+PATH="$fake_bin:$PATH" \
+  HOME="$test_root/home" \
+  K3S_CI_MOLECULE_ROOT="$molecule_root" \
+  K3S_CI_MOLECULE_PROJECT=k3s-ansible \
+  K3S_CI_VIRTUALBOX_ROOT="$virtualbox_root" \
+  K3S_CI_HOSTONLY_MARKER="$test_root/hostonly-baseline" \
+  FAKE_VBOX_ROOT="$virtualbox_root" \
+  FAKE_LOG="$test_root/vbox.log" \
+  bash "$repo_root/.github/scripts/cleanup-runner-resources.sh" --dry-run > "$output"
+
+grep -Fq 'Would remove VM control1 (11111111-1111-1111-1111-111111111111)' "$output"
+[[ ! -e "$test_root/vbox.log" ]]
+
+PATH="$fake_bin:$PATH" \
+  HOME="$test_root/home" \
+  K3S_CI_MOLECULE_ROOT="$molecule_root" \
+  K3S_CI_MOLECULE_PROJECT=k3s-ansible \
+  K3S_CI_VIRTUALBOX_ROOT="$virtualbox_root" \
+  K3S_CI_HOSTONLY_MARKER="$test_root/hostonly-baseline" \
+  FAKE_VBOX_ROOT="$virtualbox_root" \
+  FAKE_LOG="$test_root/vbox.log" \
+  bash "$repo_root/.github/scripts/cleanup-runner-resources.sh" --apply > "$output"
+
+grep -Fq 'controlvm 11111111-1111-1111-1111-111111111111 poweroff' "$test_root/vbox.log"
+grep -Fq 'unregistervm unregistervm 11111111-1111-1111-1111-111111111111 --delete' "$test_root/vbox.log"
+[[ ! -e "$virtualbox_root/control1/control1.vbox" ]]
+[[ -e "$virtualbox_root/unmarked/unmarked.vbox" ]]
+
+PATH="$fake_bin:$PATH" \
+  HOME="$test_root/home" \
+  K3S_CI_MOLECULE_ROOT="$molecule_root" \
+  K3S_CI_MOLECULE_PROJECT=k3s-ansible \
+  K3S_CI_VIRTUALBOX_ROOT="$virtualbox_root" \
+  K3S_CI_HOSTONLY_MARKER="$test_root/hostonly-baseline" \
+  FAKE_VM_MODE=missing \
+  FAKE_VBOX_ROOT="$virtualbox_root" \
+  FAKE_LOG="$test_root/vbox.log" \
+  bash "$repo_root/.github/scripts/cleanup-runner-resources.sh" --apply > "$output"
+
+grep -Fq 'Stale Vagrant state without a registered VM' "$output"
+[[ ! -d "$molecule_root/k3s-ansible/single_node/.vagrant" ]]
+
+printf 'cleanup-runner-resources fixture test passed\n'

.github/scripts/test-fixtures/mock-flock

@@ -0,0 +1,4 @@
+#!/usr/bin/env bash
+
+set -Eeuo pipefail
+[[ "${1:-}" =~ ^[0-9]+$ ]]

.github/scripts/test-fixtures/mock-vagrant

@@ -0,0 +1,30 @@
+#!/usr/bin/env bash
+
+set -Eeuo pipefail
+
+printf '%s\n' "$*" >> "$MOCK_VAGRANT_LOG"
+case "${1:-}" in
+  up)
+    if [[ -n "${MOCK_VAGRANTFILE_CAPTURE:-}" ]]; then
+      cp -- "$VAGRANT_CWD/Vagrantfile" "$MOCK_VAGRANTFILE_CAPTURE"
+    fi
+    counter_file="$MOCK_VBOX_STATE/counter"
+    counter=0
+    [[ ! -r "$counter_file" ]] || counter="$(cat "$counter_file")"
+    counter=$((counter + 1))
+    printf '%s\n' "$counter" > "$counter_file"
+    uuid="00000000-0000-4000-8000-$(printf '%012d' "$counter")"
+    vm_dir="$MOCK_VBOX_ROOT/master-$counter"
+    mkdir -p -- "$vm_dir"
+    : > "$vm_dir/master.vbox"
+    : > "$vm_dir/master.vdi"
+    printf '%s\n' \
+      'VMState="poweroff"' \
+      'groups="/"' \
+      "CfgFile=\"$vm_dir/master.vbox\"" \
+      "SATA-0-0=\"$vm_dir/master.vdi\"" > "$MOCK_VBOX_STATE/vm-$uuid"
+    printf '%s\n' "$uuid" > "$MOCK_BOX_DIR/master_id"
+    ;;
+  destroy) ;;
+  *) exit 2 ;;
+esac

.github/scripts/test-fixtures/mock-vboxmanage

@@ -0,0 +1,40 @@
+#!/usr/bin/env bash
+
+set -Eeuo pipefail
+
+printf '%s\n' "$*" >> "$MOCK_VBOX_LOG"
+command_name="${1:-}"
+uuid="${2:-}"
+
+case "$command_name" in
+  showvminfo)
+    [[ -r "$MOCK_VBOX_STATE/vm-$uuid" ]] || exit 1
+    cat "$MOCK_VBOX_STATE/vm-$uuid"
+    ;;
+  getextradata)
+    key_slug="${3//\//_}"
+    if [[ ! -r "$MOCK_VBOX_STATE/extra-$uuid-$key_slug" ]]; then
+      printf '%s\n' 'No value set!'
+      exit 0
+    fi
+    printf 'Value: '
+    cat "$MOCK_VBOX_STATE/extra-$uuid-$key_slug"
+    ;;
+  modifyvm)
+    [[ "${3:-}" == --groups ]]
+    awk -v groups="${4:-}" '
+      $1 !~ /^groups=/ { print }
+      END { printf "groups=\"%s\"\n", groups }
+    ' "$MOCK_VBOX_STATE/vm-$uuid" > "$MOCK_VBOX_STATE/vm-$uuid.tmp"
+    mv "$MOCK_VBOX_STATE/vm-$uuid.tmp" "$MOCK_VBOX_STATE/vm-$uuid"
+    ;;
+  setextradata)
+    key_slug="${3//\//_}"
+    printf '%s\n' "${4:-}" > "$MOCK_VBOX_STATE/extra-$uuid-$key_slug"
+    ;;
+  unregistervm|closemedium)
+    printf '%s\n' 'destructive VirtualBox command invoked' >&2
+    exit 99
+    ;;
+  *) exit 2 ;;
+esac

.github/scripts/test-k3s-server-bootstrap.sh

@@ -0,0 +1,35 @@
+#!/usr/bin/env bash
+
+set -Eeuo pipefail
+
+repo_root="$(git rev-parse --show-toplevel)"
+main_tasks="$repo_root/roles/k3s_server/tasks/main.yml"
+join_tasks="$repo_root/roles/k3s_server/tasks/join_master.yml"
+
+for task_file in "$main_tasks" "$join_tasks"; do
+  for property in \
+    'Delegate=yes' \
+    'TasksMax=infinity' \
+    'KillMode=process' \
+    'LimitNOFILE=1048576' \
+    'LimitNPROC=infinity' \
+    'LimitCORE=infinity'; do
+    grep -Fq -- "$property" "$task_file" || {
+      printf '%s is missing transient K3s property %s\n' "$task_file" "$property" >&2
+      exit 1
+    }
+  done
+done
+
+if grep -Fq -- "node-role.kubernetes.io/master=true' -o=jsonpath" "$main_tasks"; then
+  printf 'control-plane registration still depends on the optional legacy master role key\n' >&2
+  exit 1
+fi
+
+grep -Fq -- "map('extract', hostvars, 'ansible_hostname')" "$main_tasks"
+grep -Fq -- 'difference(nodes.stdout.split())' "$main_tasks"
+grep -Fq -- 'crd/addons.k3s.cattle.io' "$main_tasks"
+grep -Fq -- 'crd/helmcharts.helm.cattle.io' "$main_tasks"
+grep -Fq -- 'crd/helmchartconfigs.helm.cattle.io' "$main_tasks"
+
+printf 'K3s transient bootstrap regression test passed\n'

.github/scripts/test-prepare-vagrant-box-masters.sh

@@ -0,0 +1,91 @@
+#!/usr/bin/env bash
+
+set -Eeuo pipefail
+
+repo_root="$(git rev-parse --show-toplevel)"
+fixture="$(mktemp -d)"
+trap 'rm -rf -- "$fixture"' EXIT
+
+mock_bin="$fixture/bin"
+mock_state="$fixture/state"
+mock_home="$fixture/home"
+mock_vagrant_home="$fixture/vagrant-home"
+mock_box_dir="$mock_vagrant_home/boxes/generic-VAGRANTSLASH-ubuntu2204/4.3.12/amd64/virtualbox"
+mock_vbox_root="$mock_home/VirtualBox VMs"
+mock_master_root="$mock_home/.cache/k3s-ci/vagrant-masters"
+lock_file="$fixture/vagrant-boxes.lock"
+mkdir -p -- "$mock_bin" "$mock_state" "$mock_box_dir" "$mock_vbox_root"
+printf '%s\n' 'generic/ubuntu2204 4.3.12 amd64' > "$lock_file"
+ln -s "$repo_root/.github/scripts/test-fixtures/mock-vboxmanage" "$mock_bin/VBoxManage"
+ln -s "$repo_root/.github/scripts/test-fixtures/mock-vagrant" "$mock_bin/vagrant"
+ln -s "$repo_root/.github/scripts/test-fixtures/mock-flock" "$mock_bin/flock"
+
+export PATH="$mock_bin:$PATH"
+export HOME="$mock_home"
+export VAGRANT_HOME="$mock_vagrant_home"
+export VAGRANT_BOX_LOCK_FILE="$lock_file"
+export K3S_CI_REPOSITORY_ROOT="$repo_root"
+export K3S_CI_VAGRANT_MASTER_ROOT="$mock_master_root"
+export K3S_CI_VIRTUALBOX_ROOT="$mock_vbox_root"
+export MOCK_VBOX_STATE="$mock_state"
+export MOCK_VBOX_ROOT="$mock_vbox_root"
+export MOCK_BOX_DIR="$mock_box_dir"
+export MOCK_VBOX_LOG="$fixture/vbox.log"
+export MOCK_VAGRANT_LOG="$fixture/vagrant.log"
+export MOCK_VAGRANTFILE_CAPTURE="$fixture/prewarm-Vagrantfile"
+: > "$MOCK_VBOX_LOG"
+: > "$MOCK_VAGRANT_LOG"
+
+unowned_uuid='99999999-9999-4999-8999-999999999999'
+printf '%s\n' "$unowned_uuid" > "$mock_box_dir/master_id"
+
+script="$repo_root/.github/scripts/prepare-vagrant-box-masters.sh"
+first_output="$fixture/first-output"
+second_output="$fixture/second-output"
+third_output="$fixture/third-output"
+
+"$script" > "$first_output"
+grep -Fq 'config.ssh.username = "vagrant"' "$MOCK_VAGRANTFILE_CAPTURE"
+grep -Fq 'config.ssh.password = "vagrant"' "$MOCK_VAGRANTFILE_CAPTURE"
+if grep -Fq 'config.ssh.insert_key' "$MOCK_VAGRANTFILE_CAPTURE"; then
+  printf 'prewarm Vagrantfile unexpectedly overrides Vagrant SSH key insertion\n' >&2
+  exit 1
+fi
+grep -Fq 'virtualbox.memory = 1024' "$MOCK_VAGRANTFILE_CAPTURE"
+grep -Fq 'virtualbox.cpus = 2' "$MOCK_VAGRANTFILE_CAPTURE"
+grep -Fq 'config.vm.boot_timeout = 600' "$MOCK_VAGRANTFILE_CAPTURE"
+mapping_file="$mock_master_root/generic_ubuntu2204-4.3.12-amd64.uuid"
+test -s "$mapping_file"
+cmp -s "$mapping_file" "$mock_box_dir/master_id"
+grep -Fq 'Created and recorded owned master' "$first_output"
+grep -Fq 'modifyvm' "$MOCK_VBOX_LOG"
+grep -Fq 'setextradata' "$MOCK_VBOX_LOG"
+if grep -Fq "$unowned_uuid" "$MOCK_VBOX_LOG"; then
+  printf 'unowned cached master UUID was unexpectedly inspected or modified\n' >&2
+  exit 1
+fi
+if grep -Eq 'unregistervm|closemedium' "$MOCK_VBOX_LOG"; then
+  printf 'master preparation invoked a destructive VirtualBox command\n' >&2
+  exit 1
+fi
+
+: > "$MOCK_VAGRANT_LOG"
+"$script" > "$second_output"
+grep -Fq 'Reusing owned master' "$second_output"
+if grep -Fq 'up ' "$MOCK_VAGRANT_LOG"; then
+  printf 'valid owned master was unexpectedly rebuilt\n' >&2
+  exit 1
+fi
+
+stale_uuid="$(tr -d '[:space:]' < "$mapping_file")"
+rm -f -- "$mock_state/vm-$stale_uuid"
+: > "$MOCK_VAGRANT_LOG"
+"$script" > "$third_output"
+grep -Fq 'rebuilding without deleting any VM or disk' "$third_output"
+grep -Fq 'up ' "$MOCK_VAGRANT_LOG"
+if grep -Eq 'unregistervm|closemedium' "$MOCK_VBOX_LOG"; then
+  printf 'stale master recovery invoked a destructive VirtualBox command\n' >&2
+  exit 1
+fi
+
+printf 'Vagrant box master preparation fixture test passed\n'

.github/scripts/vagrant-up-timed.sh

@@ -0,0 +1,24 @@
+#!/usr/bin/env bash
+
+set -Eeuo pipefail
+
+if (($# < 2)); then
+  printf 'Usage: vagrant-up-timed.sh WORKDIR MACHINE [MACHINE ...]\n' >&2
+  exit 2
+fi
+
+workdir="$1"
+shift
+timing_log="${K3S_CI_CREATE_TIMING_LOG:-${RUNNER_TEMP:-/tmp}/k3s-ci-create-timing.log}"
+mkdir -p -- "${timing_log%/*}"
+
+printf '%s batch-start machines=%s\n' "$(date --iso-8601=ns)" "$*" | tee -a "$timing_log"
+set +e
+VAGRANT_CWD="$workdir" vagrant up "$@" --provider virtualbox --no-provision 2>&1 |
+  while IFS= read -r line; do
+    printf '%s %s\n' "$(date --iso-8601=ns)" "$line"
+  done | tee -a "$timing_log"
+rc=${PIPESTATUS[0]}
+set -e
+printf '%s batch-end rc=%d machines=%s\n' "$(date --iso-8601=ns)" "$rc" "$*" | tee -a "$timing_log"
+exit "$rc"

.github/test-download-boxes.sh

@@ -0,0 +1,92 @@
+#!/usr/bin/env bash
+
+# The single-quoted expressions below are written into fake executables and
+# intentionally expand only when those executables run.
+# shellcheck disable=SC2016
+
+set -Eeuo pipefail
+
+repo_root=$(git rev-parse --show-toplevel)
+test_root=$(mktemp -d)
+fake_bin="$test_root/bin"
+fake_log="$test_root/vagrant.log"
+output="$test_root/output.txt"
+mkdir -p "$fake_bin"
+trap 'rm -rf "$test_root"' EXIT
+
+printf '%s\n' \
+    '#!/usr/bin/env bash' \
+    'set -Eeuo pipefail' \
+    'printf "%s\n" generic/debian12 generic/rocky9 generic/ubuntu2204' \
+    >"$fake_bin/yq"
+
+printf '%s\n' \
+    '#!/usr/bin/env bash' \
+    'set -Eeuo pipefail' \
+    'emit_box() {' \
+    '    printf "0,,box-name,%s\n" "$1"' \
+    '    printf "0,,box-provider,virtualbox\n"' \
+    '    printf "0,,box-version,4.3.12\n"' \
+    '    printf "0,,box-architecture,amd64\n"' \
+    '}' \
+    'if [[ "${1:-}" == box && "${2:-}" == list ]]; then' \
+    '    emit_box generic/debian12' \
+    '    emit_box generic/rocky9' \
+    '    if [[ "${FAKE_PRESENT_MODE:-all}" == all ]]; then' \
+    '        emit_box generic/ubuntu2204' \
+    '    fi' \
+    'elif [[ "${1:-}" == box && "${2:-}" == add ]]; then' \
+    '    printf "%s\n" "$*" >>"${FAKE_VAGRANT_LOG:?}"' \
+    'else' \
+    '    printf "Unexpected vagrant arguments: %s\n" "$*" >&2' \
+    '    exit 1' \
+    'fi' \
+    >"$fake_bin/vagrant"
+chmod +x "$fake_bin/yq" "$fake_bin/vagrant"
+
+PATH="$fake_bin:$PATH" \
+    FAKE_VAGRANT_LOG="$fake_log" \
+    "$repo_root/.github/download-boxes.sh" >"$output"
+grep -Fq 'All pinned Vagrant boxes are already present.' "$output"
+[[ ! -e "$fake_log" ]]
+
+PATH="$fake_bin:$PATH" \
+    FAKE_PRESENT_MODE=partial \
+    FAKE_VAGRANT_LOG="$fake_log" \
+    "$repo_root/.github/download-boxes.sh" >"$output"
+grep -Fxq \
+    'box add --provider virtualbox --box-version 4.3.12 --architecture amd64 generic/ubuntu2204' \
+    "$fake_log"
+
+incomplete_lock="$test_root/incomplete.lock"
+printf '%s\n' \
+    'generic/debian12 4.3.12 amd64' \
+    'generic/rocky9 4.3.12 amd64' \
+    >"$incomplete_lock"
+if PATH="$fake_bin:$PATH" \
+    VAGRANT_BOX_LOCK_FILE="$incomplete_lock" \
+    FAKE_VAGRANT_LOG="$fake_log" \
+    "$repo_root/.github/download-boxes.sh" >"$output" 2>&1; then
+    printf 'Download script accepted a lock missing a scenario box.\n' >&2
+    exit 1
+fi
+grep -Fq 'Scenario boxes missing from the lock file:' "$output"
+grep -Fq 'generic/ubuntu2204' "$output"
+
+duplicate_lock="$test_root/duplicate.lock"
+printf '%s\n' \
+    'generic/debian12 4.3.12 amd64' \
+    'generic/debian12 4.3.11 amd64' \
+    'generic/rocky9 4.3.12 amd64' \
+    'generic/ubuntu2204 4.3.12 amd64' \
+    >"$duplicate_lock"
+if PATH="$fake_bin:$PATH" \
+    VAGRANT_BOX_LOCK_FILE="$duplicate_lock" \
+    FAKE_VAGRANT_LOG="$fake_log" \
+    "$repo_root/.github/download-boxes.sh" >"$output" 2>&1; then
+    printf 'Download script accepted duplicate box lock entries.\n' >&2
+    exit 1
+fi
+grep -Fq 'Duplicate Vagrant box lock entries:' "$output"
+
+printf 'Vagrant box download tests passed.\n'

.github/vagrant-boxes.lock

@@ -0,0 +1,4 @@
+# box version architecture
+generic/debian12 4.3.12 amd64
+generic/rocky9 4.3.12 amd64
+generic/ubuntu2204 4.3.12 amd64

.github/workflows/cache.yml

@@ -5,38 +5,53 @@ on:
 jobs:
   molecule:
     name: cache
-    runs-on: self-hosted
+    runs-on: [self-hosted, linux, x64, k3s-ci, virtualbox, nested-virt]
     env:
       PYTHON_VERSION: "3.11"
+      VAGRANT_DEFAULT_PROVIDER: virtualbox
+      VAGRANT_HOME: ${{ github.workspace }}/.vagrant-home
 
     steps:
       - name: Check out the codebase
-        uses: actions/checkout@e2f20e631ae6d7dd3b768f56a5d2af784dd54791 # v3 2.5.0
+        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # 7.0.1
         with:
-          ref: ${{ github.event.pull_request.head.sha }}
+          ref: ${{ github.event.pull_request.head.sha || github.sha }}
+
+      - name: Check nested VirtualBox platform
+        run: |
+          set -Eeuo pipefail
+          grep -Eq 'vmx|svm' /proc/cpuinfo
+          test -c /dev/kvm
+          test -c /dev/vboxdrv
+          VBoxManage --version
+          vagrant --version
+          test -r /etc/vbox/networks.conf
+          test "$(stat -c '%u' /etc/vbox/networks.conf)" -eq 0
+          free -h
+          df -Pk "${RUNNER_TEMP}"
 
       - name: Set up Python ${{ env.PYTHON_VERSION }}
-        uses: actions/setup-python@75f3110429a8c05be0e1bf360334e4cced2b63fa # 2.3.3
+        uses: actions/setup-python@5fda3b95a4ea91299a34e894583c3862153e4b97 # 7.0.0
         with:
           python-version: ${{ env.PYTHON_VERSION }}
           cache: 'pip' # caching pip dependencies
 
       - name: Cache Vagrant boxes
         id: cache-vagrant
-        uses: actions/cache@13aacd865c20de90d75de3b17ebe84f7a17d57d2 # 4.0
+        uses: actions/cache@55cc8345863c7cc4c66a329aec7e433d2d1c52a9 # 6.1.0
         with:
-          lookup-only: true #if it exists, we don't need to restore and can skip the next step
+          # This producer only needs to know whether the immutable cache exists.
+          # Molecule jobs restore it after this job completes.
+          lookup-only: true
           path: |
-            ~/.vagrant.d/boxes
-          key: vagrant-boxes-${{ hashFiles('**/molecule.yml') }}
-          restore-keys: |
-            vagrant-boxes
+            .vagrant-home/boxes
+          key: vagrant-boxes-${{ runner.name }}-${{ runner.os }}-${{ runner.arch }}-virtualbox-7.2-vagrant-2.4-${{ hashFiles('.github/vagrant-boxes.lock') }} # yamllint disable-line rule:line-length
 
       - 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
+        # An exact hit skips both cache restoration and upstream downloads.
+        # A lock change builds and saves one clean, version-pinned cache.
+        if: steps.cache-vagrant.outputs.cache-hit != 'true'
         run: |
           ./.github/download-boxes.sh
+          ./.github/scripts/prepare-vagrant-box-masters.sh
           vagrant box list

.github/workflows/ci.yml

@@ -2,17 +2,37 @@
 name: "CI"
 on:
   pull_request:
-  push:
-    branches:
-      - master
+    types:
+      - opened
+      - synchronize
+      - reopened
+      - ready_for_review
     paths-ignore:
-      - '**/README.md'
+      - '**/.gitignore'
+      - '**/FUNDING.yml'
+      - '**/host.ini'
+      - '**/*.md'
+      - '**/.editorconfig'
+      - '**/ansible.example.cfg'
+      - '**/deploy.sh'
+      - '**/LICENSE'
+      - '**/reboot.sh'
+      - '**/reset.sh'
+  workflow_dispatch:
+
+permissions:
+  contents: read
+
+concurrency:
+  group: ci-${{ github.event.pull_request.number || github.run_id }}
+  cancel-in-progress: true
+
 jobs:
   pre:
     uses: ./.github/workflows/cache.yml
+    needs: [lint]
   lint:
     uses: ./.github/workflows/lint.yml
-    needs: [pre]
   test:
     uses: ./.github/workflows/test.yml
     needs: [pre, lint]

.github/workflows/lint.yml

@@ -5,24 +5,25 @@ on:
 jobs:
   pre-commit-ci:
     name: Pre-Commit
-    runs-on: self-hosted
+    runs-on: ubuntu-latest
     env:
-      PYTHON_VERSION: "3.11"
+      PYTHON_VERSION: "3.12"
 
     steps:
       - name: Check out the codebase
-        uses: actions/checkout@e2f20e631ae6d7dd3b768f56a5d2af784dd54791 # v3 2.5.0
+        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # 7.0.1
         with:
-          ref: ${{ github.event.pull_request.head.sha }}
+          ref: ${{ github.event.pull_request.head.sha || github.sha }}
 
       - name: Set up Python ${{ env.PYTHON_VERSION }}
-        uses: actions/setup-python@75f3110429a8c05be0e1bf360334e4cced2b63fa # 2.3.3
+        uses: actions/setup-python@5fda3b95a4ea91299a34e894583c3862153e4b97 # 7.0.0
         with:
           python-version: ${{ env.PYTHON_VERSION }}
           cache: 'pip' # caching pip dependencies
 
       - name: Restore Ansible cache
-        uses: actions/cache/restore@13aacd865c20de90d75de3b17ebe84f7a17d57d2 # 4.0
+        id: cache-ansible
+        uses: actions/cache/restore@55cc8345863c7cc4c66a329aec7e433d2d1c52a9 # 6.1.0
         with:
           path: ~/.ansible/collections
           key: ansible-${{ hashFiles('collections/requirements.yml') }}
@@ -37,17 +38,37 @@ jobs:
           python3 -m pip install -r requirements.txt
           echo "::endgroup::"
 
+      - name: Install Ansible collections with retries
+        if: steps.cache-ansible.outputs.cache-hit != 'true'
+        run: |
+          set -Eeuo pipefail
+          for attempt in 1 2 3 4 5; do
+            if ansible-galaxy collection install -r collections/requirements.yml; then
+              exit 0
+            fi
+            echo "Ansible Galaxy attempt ${attempt} failed; retrying."
+            sleep $((attempt * 10))
+          done
+          exit 1
+
+      - name: Save Ansible collection cache
+        if: steps.cache-ansible.outputs.cache-hit != 'true'
+        uses: actions/cache/save@55cc8345863c7cc4c66a329aec7e433d2d1c52a9 # 6.1.0
+        with:
+          path: ~/.ansible/collections
+          key: ansible-${{ hashFiles('collections/requirements.yml') }}
+
       - 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: self-hosted
+    runs-on: ubuntu-latest
     steps:
       - name: Checkout code
-        uses: actions/checkout@e2f20e631ae6d7dd3b768f56a5d2af784dd54791 # v3 2.5.0
+        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # 7.0.1
       - 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@3db98c0363e2fa5df3e1c4c471777a7c10b24cc9 # 5.0.5
         with:
           allowlist: |
             aws-actions/

.github/workflows/test.yml

@@ -5,44 +5,64 @@ on:
 jobs:
   molecule:
     name: Molecule
-    runs-on: self-hosted
+    runs-on: [self-hosted, linux, x64, k3s-ci, virtualbox, nested-virt]
     strategy:
       matrix:
         scenario:
           - default
-          - ipv6
           - single_node
-      fail-fast: false
+          - calico
+          - cilium
+          - kube-vip
+          # - ipv6
+      fail-fast: true
+      max-parallel: 1
     env:
       PYTHON_VERSION: "3.11"
+      VAGRANT_DEFAULT_PROVIDER: virtualbox
+      VAGRANT_HOME: ${{ github.workspace }}/.vagrant-home
 
     steps:
       - name: Check out the codebase
-        uses: actions/checkout@e2f20e631ae6d7dd3b768f56a5d2af784dd54791 # v3 2.5.0
+        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # 7.0.1
         with:
-          ref: ${{ github.event.pull_request.head.sha }}
+          ref: ${{ github.event.pull_request.head.sha || github.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: Clean repository-owned resources before testing
+        run: ./.github/scripts/cleanup-runner-resources.sh --apply
+
+      - name: Record host-only network baseline
+        run: ./.github/scripts/cleanup-runner-resources.sh --snapshot
+
+      - name: Check nested VirtualBox platform
+        run: |
+          set -Eeuo pipefail
+          grep -Eq 'vmx|svm' /proc/cpuinfo
+          test -c /dev/kvm
+          test -c /dev/vboxdrv
+          VBoxManage --version
+          vagrant --version
+          test -r /etc/vbox/networks.conf
+          test "$(stat -c '%u' /etc/vbox/networks.conf)" -eq 0
+          free -h
+          df -Pk "${RUNNER_TEMP}"
 
       - name: Set up Python ${{ env.PYTHON_VERSION }}
-        uses: actions/setup-python@75f3110429a8c05be0e1bf360334e4cced2b63fa # 2.3.3
+        uses: actions/setup-python@5fda3b95a4ea91299a34e894583c3862153e4b97 # 7.0.0
         with:
           python-version: ${{ env.PYTHON_VERSION }}
           cache: 'pip' # caching pip dependencies
 
       - name: Restore vagrant Boxes cache
-        uses: actions/cache/restore@13aacd865c20de90d75de3b17ebe84f7a17d57d2 # 4.0
+        uses: actions/cache/restore@55cc8345863c7cc4c66a329aec7e433d2d1c52a9 # 6.1.0
         with:
-          path: ~/.vagrant.d/boxes
-          key: vagrant-boxes-${{ hashFiles('**/molecule.yml') }}
+          path: .vagrant-home/boxes
+          key: vagrant-boxes-${{ runner.name }}-${{ runner.os }}-${{ runner.arch }}-virtualbox-7.2-vagrant-2.4-${{ hashFiles('.github/vagrant-boxes.lock') }} # yamllint disable-line rule:line-length
           fail-on-cache-miss: true
 
+      - name: Prepare runner-owned Vagrant box masters
+        run: ./.github/scripts/prepare-vagrant-box-masters.sh
+
       - name: Install dependencies
         run: |
           echo "::group::Upgrade pip"
@@ -54,7 +74,20 @@ jobs:
           echo "::endgroup::"
 
       - name: Test with molecule
-        run: molecule test --scenario-name ${{ matrix.scenario }}
+        run: |
+          set -Eeuo pipefail
+          resource_dir="${RUNNER_TEMP}/logs/resources/${{ matrix.scenario }}"
+          timing_file="${RUNNER_TEMP}/logs/timing/${{ matrix.scenario }}.txt"
+          mkdir -p -- "${timing_file%/*}"
+          ./.github/scripts/monitor-runner-resources.sh "$resource_dir" 10 &
+          monitor_pid=$!
+          stop_monitor() {
+            kill -TERM "$monitor_pid" 2>/dev/null || true
+            wait "$monitor_pid" 2>/dev/null || true
+          }
+          trap stop_monitor EXIT
+          /usr/bin/time -v -o "$timing_file" \
+            molecule test --scenario-name ${{ matrix.scenario }}
         timeout-minutes: 90
         env:
           ANSIBLE_K3S_LOG_DIR: ${{ runner.temp }}/logs/k3s-ansible/${{ matrix.scenario }}
@@ -62,36 +95,24 @@ jobs:
           ANSIBLE_TIMEOUT: 120
           PY_COLORS: 1
           ANSIBLE_FORCE_COLOR: 1
+          K3S_CI_CREATE_TIMING_LOG: ${{ runner.temp }}/logs/timing/${{ matrix.scenario }}-create.log
 
-      # 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: Collect runner diagnostics
+        if: always()
+        run: ./.github/scripts/collect-runner-diagnostics.sh "${RUNNER_TEMP}/logs/runner"
+        env:
+          K3S_CI_SCENARIO_NAME: ${{ matrix.scenario }}
 
-      - name: Remove all local Vagrant boxes
-        if: always() # do this even if a step before has failed
-        run: vagrant box list | cut -f 1 -d ' ' | xargs -L 1 vagrant box remove -f
-
-      - 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
+      - name: Clean repository-owned resources after testing
+        if: always()
+        run: ./.github/scripts/cleanup-runner-resources.sh --apply
 
       - 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@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # 7.0.1
         with:
-          name: logs
+          name: logs-${{ matrix.scenario }}-${{ github.run_id }}-${{ github.run_attempt }}
           path: |
             ${{ runner.temp }}/logs
+          if-no-files-found: warn
+          retention-days: 14

.gitignore

@@ -1,3 +1,6 @@
 .env/
 *.log
 ansible.cfg
+.ansible/
+kubeconfig
+zIgnore/

.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 +12,53 @@ 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
+        additional_dependencies: [ansible-core==2.18.0]
+        language_version: python3.12
+        args: [--offline]
   - 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
+  - repo: local
+    hooks:
+      - id: cleanup-runner-resources-test
+        name: cleanup runner resources test
+        entry: .github/scripts/test-cleanup-runner-resources.sh
+        language: system
+        pass_filenames: false
+        files: ^\.github/scripts/(cleanup-runner-resources|test-cleanup-runner-resources)\.sh$
+      - id: download-vagrant-boxes-test
+        name: Vagrant box download test
+        entry: .github/test-download-boxes.sh
+        language: system
+        pass_filenames: false
+        files: ^\.github/(download-boxes|test-download-boxes)\.sh$|^\.github/vagrant-boxes\.lock$
+      - id: prepare-vagrant-box-masters-test
+        name: Vagrant box master preparation test
+        entry: .github/scripts/test-prepare-vagrant-box-masters.sh
+        language: system
+        pass_filenames: false
+        files: ^\.github/scripts/(prepare-vagrant-box-masters|test-prepare-vagrant-box-masters)\.sh$
+      - id: k3s-server-bootstrap-test
+        name: K3s transient bootstrap test
+        entry: .github/scripts/test-k3s-server-bootstrap.sh
+        language: system
+        pass_filenames: false
+        files: ^roles/k3s_server/tasks/(main|join_master)\.yml$|^\.github/scripts/test-k3s-server-bootstrap\.sh$

.yamllint

@@ -2,10 +2,19 @@
 extends: default
 
 rules:
+  comments:
+    min-spaces-from-content: 1
+  comments-indentation: false
+  braces:
+    max-spaces-inside: 1
+  octal-values:
+    forbid-implicit-octal: true
+    forbid-explicit-octal: true
   line-length:
     max: 120
     level: warning
   truthy:
-    allowed-values: ['true', 'false']
+    allowed-values: ["true", "false"]
+
 ignore:
   - galaxy.yml

README.md

@@ -8,7 +8,7 @@ This is based on the work from [this fork](https://github.com/212850a/k3s-ansibl
 
 If you want more context on how this works, see:
 
-📄 [Documentation](https://technotim.live/posts/k3s-etcd-ansible/) (including example commands)
+📄 [Documentation](https://technotim.com/posts/k3s-etcd-ansible/) (including example commands)
 
 📺 [Watch the Video](https://www.youtube.com/watch?v=CbkEWcUZ7zM)
 
@@ -28,7 +28,7 @@ on processor architecture:
 
 ## ✅ System requirements
 
-- Control Node (the machine you are running `ansible` commands) must have Ansible 2.11+ If you need a quick primer on Ansible [you can check out my docs and setting up Ansible](https://technotim.live/posts/ansible-automation/).
+- Control Node (the machine you are running `ansible` commands) must have Ansible 2.11+ If you need a quick primer on Ansible [you can check out my docs and setting up Ansible](https://technotim.com/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❗)
 
@@ -96,16 +96,102 @@ 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
 
-See the commands [here](https://technotim.live/posts/k3s-etcd-ansible/#testing-your-cluster).
+See the commands [here](https://technotim.com/posts/k3s-etcd-ansible/#testing-your-cluster).
+
+### Variables
+
+| Role(s) | Variable | Type | Default | Required | Description |
+|---|---|---|---|---|---|
+| `download` | `k3s_version` | string | ❌ | Required | K3s binaries version |
+| `k3s_agent`, `k3s_server`, `k3s_server_post` | `apiserver_endpoint` | string | ❌ | Required | Virtual ip-address configured on each master |
+| `k3s_agent` | `extra_agent_args` | string | `null` | Not required | Extra arguments for agents nodes |
+| `k3s_agent`, `k3s_server` | `group_name_master` | string | `null` | Not required | Name othe master group |
+| `k3s_agent` | `k3s_token` | string | `null` | Not required | Token used to communicate between masters |
+| `k3s_agent`, `k3s_server` | `proxy_env` | dict | `null` | Not required | Internet proxy configurations |
+| `k3s_agent`, `k3s_server` | `proxy_env.HTTP_PROXY` | string | ❌ | Required | HTTP internet proxy |
+| `k3s_agent`, `k3s_server` | `proxy_env.HTTPS_PROXY` | string | ❌ | Required | HTTP internet proxy |
+| `k3s_agent`, `k3s_server` | `proxy_env.NO_PROXY` | string | ❌ | Required | Addresses that will not use the proxies |
+| `k3s_agent`, `k3s_server`, `reset` | `systemd_dir` | string | `/etc/systemd/system` | Not required | Path to systemd services |
+| `k3s_custom_registries` | `custom_registries_yaml` | string | ❌ | Required | YAML block defining custom registries. 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. |
+| `k3s_server`, `k3s_server_post` | `cilium_bgp` | bool | `~` | Not required | Enable cilium BGP control plane for LB services and pod cidrs. Disables the use of MetalLB. |
+| `k3s_server`, `k3s_server_post` | `cilium_iface` | string | ❌ | Not required | The network interface used for when Cilium is enabled |
+| `k3s_server` | `extra_server_args` | string | `""` | Not required | Extra arguments for server nodes |
+| `k3s_server` | `k3s_create_kubectl_symlink` | bool | `false` | Not required | Create the kubectl -> k3s symlink |
+| `k3s_server` | `k3s_create_crictl_symlink` | bool | `true` | Not required | Create the crictl -> k3s symlink |
+| `k3s_server` | `kube_vip_arp` | bool | `true` | Not required | Enables kube-vip ARP broadcasts |
+| `k3s_server` | `kube_vip_bgp` | bool | `false` | Not required | Enables kube-vip BGP peering |
+| `k3s_server` | `kube_vip_bgp_routerid` | string | `"127.0.0.1"` | Not required | Defines the router ID for the kube-vip BGP server |
+| `k3s_server` | `kube_vip_bgp_as` | string | `"64513"` | Not required | Defines the AS for the kube-vip BGP server |
+| `k3s_server` | `kube_vip_bgp_peeraddress` | string | `"192.168.30.1"` | Not required | Defines the address for the kube-vip BGP peer |
+| `k3s_server` | `kube_vip_bgp_peeras` | string | `"64512"` | Not required | Defines the AS for the kube-vip BGP peer |
+| `k3s_server` | `kube_vip_bgp_peers` | list | `[]` | Not required | List of BGP peer ASN & address pairs |
+| `k3s_server` | `kube_vip_bgp_peers_groups` | list | `['k3s_master']` | Not required | Inventory group in which to search for additional `kube_vip_bgp_peers` parameters to merge. |
+| `k3s_server` | `kube_vip_iface` | string | `~` | Not required | Explicitly define an interface that ALL control nodes should use to propagate the VIP, define it here. Otherwise, kube-vip will determine the right interface automatically at runtime. |
+| `k3s_server` | `kube_vip_tag_version` | string | `v0.7.2` | Not required | Image tag for kube-vip |
+| `k3s_server` | `kube_vip_cloud_provider_tag_version` | string | `main` | Not required | Tag for kube-vip-cloud-provider manifest when enable |
+| `k3s_server`, `k3_server_post` | `kube_vip_lb_ip_range` | string | `~` | Not required | IP range for kube-vip load balancer |
+| `k3s_server`, `k3s_server_post` | `metal_lb_controller_tag_version` | string | `v0.14.3` | Not required | Image tag for MetalLB |
+| `k3s_server` | `metal_lb_speaker_tag_version` | string | `v0.14.3` | Not required | Image tag for MetalLB |
+| `k3s_server` | `metal_lb_type` | string | `native` | Not required | Use FRR mode or native. Valid values are `frr` and `native` |
+| `k3s_server` | `retry_count` | int | `20` | Not required | Amount of retries when verifying that nodes joined |
+| `k3s_server` | `server_init_args` | string | ❌ | Not required | Arguments for server nodes |
+| `k3s_server_post` | `bpf_lb_algorithm` | string | `maglev` | Not required | BPF lb algorithm |
+| `k3s_server_post` | `bpf_lb_mode` | string | `hybrid` | Not required | BPF lb mode |
+| `k3s_server_post` | `calico_blocksize` | int | `26` | Not required | IP pool block size |
+| `k3s_server_post` | `calico_ebpf` | bool | `false` | Not required | Use eBPF dataplane instead of iptables |
+| `k3s_server_post` | `calico_encapsulation` | string | `VXLANCrossSubnet` | Not required | IP pool encapsulation |
+| `k3s_server_post` | `calico_natOutgoing` | string | `Enabled` | Not required | IP pool NAT outgoing |
+| `k3s_server_post` | `calico_nodeSelector` | string | `all()` | Not required | IP pool node selector |
+| `k3s_server_post` | `calico_iface` | string | `~` | Not required | The network interface used for when Calico is enabled |
+| `k3s_server_post` | `calico_tag` | string | `v3.27.2` | Not required | Calico version tag |
+| `k3s_server_post` | `cilium_bgp_my_asn` | int | `64513` | Not required | Local ASN for BGP peer |
+| `k3s_server_post` | `cilium_bgp_peer_asn` | int | `64512` | Not required | BGP peer ASN |
+| `k3s_server_post` | `cilium_bgp_peer_address` | string | `~` | Not required | BGP peer address |
+| `k3s_server_post` | `cilium_bgp_neighbors` | list | `[]` | Not required | List of BGP peer ASN & address pairs |
+| `k3s_server_post` | `cilium_bgp_neighbors_groups` | list | `['k3s_all']` | Not required | Inventory group in which to search for additional `cilium_bgp_neighbors` parameters to merge. |
+| `k3s_server_post` | `cilium_bgp_lb_cidr` | string | `192.168.31.0/24` | Not required | BGP load balancer IP range |
+| `k3s_server_post` | `cilium_exportPodCIDR` | bool | `true` | Not required | Export pod CIDR |
+| `k3s_server_post` | `cilium_hubble` | bool | `true` | Not required | Enable Cilium Hubble |
+| `k3s_server_post` | `cilium_hubble` | bool | `true` | Not required | Enable Cilium Hubble |
+| `k3s_server_post` | `cilium_mode` | string | `native` | Not required | Inner-node communication mode (choices are `native` and `routed`) |
+| `k3s_server_post` | `cluster_cidr` | string | `10.52.0.0/16` | Not required | Inner-cluster IP range |
+| `k3s_server_post` | `enable_bpf_masquerade` | bool | `true` | Not required | Use IP masquerading |
+| `k3s_server_post` | `kube_proxy_replacement` | bool | `true` | Not required | Replace the native kube-proxy with Cilium |
+| `k3s_server_post` | `metal_lb_available_timeout` | string | `240s` | Not required | Wait for MetalLB resources |
+| `k3s_server_post` | `metal_lb_ip_range` | string | `192.168.30.80-192.168.30.90` | Not required | MetalLB ip range for load balancer |
+| `k3s_server_post` | `metal_lb_controller_tag_version` | string | `v0.14.3` | Not required | Image tag for MetalLB |
+| `k3s_server_post` | `metal_lb_mode` | string | `layer2` | Not required | Metallb mode (choices are `bgp` and `layer2`) |
+| `k3s_server_post` | `metal_lb_bgp_my_asn` | string | `~` | Not required | BGP ASN configurations |
+| `k3s_server_post` | `metal_lb_bgp_peer_asn` | string | `~` | Not required | BGP peer ASN configurations |
+| `k3s_server_post` | `metal_lb_bgp_peer_address` | string | `~` | Not required | BGP peer address |
+| `lxc` | `custom_reboot_command` | string | `~` | Not required | Command to run on reboot |
+| `prereq` | `system_timezone` | string | `null` | Not required | Timezone to be set on all nodes |
+| `proxmox_lxc`, `reset_proxmox_lxc` | `proxmox_lxc_ct_ids` | list | ❌ | Required | Proxmox container ID list |
+| `raspberrypi` | `state` | string | `present` | Not required | Indicates whether the k3s prerequisites for Raspberry Pi should be set up (possible values are `present` and `absent`) |
+
 
 ### Troubleshooting
 
-Be sure to see [this post](https://github.com/techno-tim/k3s-ansible/discussions/20) on how to troubleshoot common problems
+Be sure to see [this post](https://github.com/timothystewart6/k3s-ansible/discussions/20) on how to troubleshoot common problems
 
 ### Testing the playbook using molecule
 
@@ -132,7 +218,7 @@ collections:
   - name: community.general
   - name: ansible.posix
   - name: kubernetes.core
-  - name: https://github.com/techno-tim/k3s-ansible.git
+  - name: https://github.com/timothystewart6/k3s-ansible.git
     type: git
     version: master
 ```

galaxy.yml

@@ -56,16 +56,16 @@ dependencies:
   kubernetes.core: '*'
 
 # The URL of the originating SCM repository
-repository: https://github.com/techno-tim/k3s-ansible
+repository: https://github.com/timothystewart6/k3s-ansible
 
 # The URL to any online docs
-documentation: https://github.com/techno-tim/k3s-ansible
+documentation: https://github.com/timothystewart6/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
+issues: https://github.com/timothystewart6/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

inventory/sample/group_vars/all.yml

@@ -1,53 +1,103 @@
 ---
-k3s_version: v1.28.5+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
 
 # Set your timezone
-system_timezone: "Your/Timezone"
+system_timezone: Your/Timezone
 
 # interface which will be used for flannel
-flannel_iface: "eth0"
+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
+
+# enable kube-vip ARP broadcasts
+kube_vip_arp: true
+
+# enable kube-vip BGP peering
+kube_vip_bgp: false
+
+# bgp parameters for kube-vip
+kube_vip_bgp_routerid: "127.0.0.1"  # Defines the router ID for the BGP server
+kube_vip_bgp_as: "64513"  # Defines the AS for the BGP server
+kube_vip_bgp_peeraddress: "192.168.30.1"  # Defines the address for the BGP peer
+kube_vip_bgp_peeras: "64512"  # Defines the AS for the BGP peer
 
 # apiserver_endpoint is virtual ip-address which will be configured on each master
-apiserver_endpoint: "192.168.30.222"
+apiserver_endpoint: 192.168.30.222
 
 # k3s_token is required  masters can talk together securely
 # this token should be alpha numeric only
-k3s_token: "some-SUPER-DEDEUPER-secret-password"
+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"
+metal_lb_type: native
 
 # metallb mode layer2 or bgp
-metal_lb_mode: "layer2"
+metal_lb_mode: layer2
 
 # bgp options
 # metal_lb_bgp_my_asn: "64513"
@@ -55,11 +105,11 @@ 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_controller_tag_version: "v0.13.9"
+metal_lb_speaker_tag_version: v0.14.8
+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"
+metal_lb_ip_range: 192.168.30.80-192.168.30.90
 
 # Only enable if your nodes are proxmox LXC nodes, make sure to configure your proxmox nodes
 # in your hosts.ini file.
@@ -122,6 +172,10 @@ custom_registries_yaml: |
         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"

inventory/sample/group_vars/proxmox.yml

@@ -1,2 +1,2 @@
 ---
-ansible_user: '{{ proxmox_lxc_ssh_user }}'
+ansible_user: "{{ proxmox_lxc_ssh_user }}"

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 +1,17 @@
+---
+- 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
+        calico_iface: eth1
+        kube_vip_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 +1,17 @@
+---
+- 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
+        cilium_iface: eth1
+        kube_vip_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/create.yml

@@ -0,0 +1,87 @@
+---
+- name: Create
+  hosts: localhost
+  connection: local
+  gather_facts: false
+  no_log: "{{ molecule_no_log }}"
+  vars:
+    create_batches:
+      - [control1, control2]
+      - [control3, node1]
+      - [node2]
+  tasks:
+    - name: Verify that bounded batches cover the configured platforms exactly once
+      ansible.builtin.assert:
+        that:
+          - create_batches | flatten | sort == molecule_yml.platforms | map(attribute='name') | sort
+          - create_batches | flatten | length == create_batches | flatten | unique | length
+          - create_batches | map('length') | max <= 2
+        fail_msg: Bounded create batches do not match the configured default platforms.
+
+    - name: Check for existing Vagrant machine state
+      ansible.builtin.stat:
+        path: "{{ molecule_ephemeral_directory }}/.vagrant/machines"
+      register: vagrant_machine_state
+
+    - name: Generate the complete Vagrant configuration for a clean create # noqa fqcn[action]
+      vagrant:
+        instances: "{{ molecule_yml.platforms }}"
+        default_box: "{{ molecule_yml.driver.default_box | default('generic/alpine316') }}"
+        provider_name: "{{ molecule_yml.driver.provider.name | default(omit, true) }}"
+        provision: "{{ molecule_yml.driver.provision | default(omit) }}"
+        cachier: "{{ molecule_yml.driver.cachier | default(omit) }}"
+        parallel: false
+        state: halt
+      when: not vagrant_machine_state.stat.exists
+      changed_when: false
+
+    - name: Start clean Vagrant guests in bounded batches
+      ansible.builtin.command:
+        argv: >-
+          {{
+            [molecule_project_directory + '/.github/scripts/vagrant-up-timed.sh',
+             molecule_ephemeral_directory] + item
+          }}
+      loop: "{{ create_batches }}"
+      loop_control:
+        label: "{{ item | join(', ') }}"
+      when: not vagrant_machine_state.stat.exists
+      changed_when: true
+
+    - name: Reconcile all instances and collect their connection configuration # noqa fqcn[action]
+      vagrant:
+        instances: "{{ molecule_yml.platforms }}"
+        default_box: "{{ molecule_yml.driver.default_box | default('generic/alpine316') }}"
+        provider_name: "{{ molecule_yml.driver.provider.name | default(omit, true) }}"
+        provision: "{{ molecule_yml.driver.provision | default(omit) }}"
+        cachier: "{{ molecule_yml.driver.cachier | default(omit) }}"
+        parallel: false
+        state: up
+      register: server
+      no_log: false
+
+    - name: Populate instance configuration dictionaries
+      ansible.builtin.set_fact:
+        instance_conf_dict:
+          instance: "{{ item.Host }}"
+          address: "{{ item.HostName }}"
+          user: "{{ item.User }}"
+          port: "{{ item.Port }}"
+          identity_file: "{{ item.IdentityFile }}"
+      loop: "{{ server.results }}"
+      register: instance_config_dict
+
+    - name: Convert instance configuration dictionaries to a list
+      ansible.builtin.set_fact:
+        instance_conf: >-
+          {{
+            instance_config_dict.results
+            | map(attribute='ansible_facts.instance_conf_dict')
+            | list
+          }}
+
+    - name: Write Molecule instance configuration
+      ansible.builtin.copy:
+        content: "{{ instance_conf | to_json | from_json | to_yaml }}"
+        dest: "{{ molecule_instance_config }}"
+        mode: "0600"

molecule/default/molecule.yml

@@ -3,8 +3,10 @@ dependency:
   name: galaxy
 driver:
   name: vagrant
+  # The Vagrant driver warns that parallel VirtualBox creation can cause
+  # platform issues. Keep this five-node, mixed-distribution scenario serial.
+  parallel: false
 platforms:
-
   - name: control1
     box: generic/ubuntu2204
     memory: 1024
@@ -12,14 +14,18 @@ platforms:
     groups:
       - k3s_cluster
       - master
+    # Keep adapter 2 stable across linked-clone rebuilds so stale host-only
+    # neighbor state still identifies the current scenario guest.
+    provider_raw_config_args:
+      - "customize ['modifyvm', :id, '--mac-address2', '080027A13038']"
     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"
+      ssh.username: vagrant
+      ssh.password: vagrant
 
   - name: control2
     box: generic/debian12
@@ -28,6 +34,8 @@ platforms:
     groups:
       - k3s_cluster
       - master
+    provider_raw_config_args:
+      - "customize ['modifyvm', :id, '--mac-address2', '080027A13039']"
     interfaces:
       - network_name: private_network
         ip: 192.168.30.39
@@ -39,6 +47,8 @@ platforms:
     groups:
       - k3s_cluster
       - master
+    provider_raw_config_args:
+      - "customize ['modifyvm', :id, '--mac-address2', '080027A13040']"
     interfaces:
       - network_name: private_network
         ip: 192.168.30.40
@@ -50,14 +60,16 @@ platforms:
     groups:
       - k3s_cluster
       - node
+    provider_raw_config_args:
+      - "customize ['modifyvm', :id, '--mac-address2', '080027A13041']"
     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"
+      ssh.username: vagrant
+      ssh.password: vagrant
 
   - name: node2
     box: generic/rocky9
@@ -66,6 +78,8 @@ platforms:
     groups:
       - k3s_cluster
       - node
+    provider_raw_config_args:
+      - "customize ['modifyvm', :id, '--mac-address2', '080027A13042']"
     interfaces:
       - network_name: private_network
         ip: 192.168.30.42
@@ -75,6 +89,7 @@ provisioner:
   env:
     ANSIBLE_VERBOSITY: 1
   playbooks:
+    create: create.yml
     converge: ../resources/converge.yml
     side_effect: ../resources/reset.yml
     verify: ../resources/verify.yml

molecule/default/overrides.yml

@@ -7,6 +7,9 @@
         # See:
         # https://github.com/flannel-io/flannel/blob/67d603aaf45ef80f5dd39f43714fc5e6f8a637eb/Documentation/troubleshooting.md#Vagrant
         flannel_iface: eth1
+        # kube-vip cannot infer the cluster interface in these multi-NIC
+        # Vagrant guests because the default route is on eth0.
+        kube_vip_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

@@ -5,18 +5,137 @@
 
 - name: Network setup
   hosts: all
+  vars:
+    primary_master: "{{ groups[group_name_master | default('master')][0] }}"
+    primary_cluster_ip: >-
+      {{ hostvars[primary_master].k3s_node_ip | split(',') | first }}
+    cluster_interface: >-
+      {{ cilium_iface | default(calico_iface | default(flannel_iface)) }}
+    primary_cluster_interface: >-
+      {{ hostvars[primary_master].cilium_iface
+      | default(hostvars[primary_master].calico_iface
+      | default(hostvars[primary_master].flannel_iface)) }}
+    primary_cluster_mac: >-
+      {{ hostvars[primary_master].ansible_facts[primary_cluster_interface].macaddress }}
   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.
+    - name: Gather service facts
+      ansible.builtin.service_facts:
+
+    - name: Disable guest firewall services
+      # The disposable test guests use an isolated VirtualBox network. A distro
+      # firewall can allow ICMP while silently blocking the inter-node Kubernetes
+      # API connection, so disable the known guest firewalls consistently.
       # 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
+        name: "{{ item }}"
         enabled: false
         state: stopped
       become: true
+      loop:
+        - firewalld.service
+        - nftables.service
+        - ufw.service
+      when: item in ansible_facts.services
+
+    - name: Verify the private cluster interface
+      ansible.builtin.assert:
+        that:
+          - flannel_iface in ansible_facts
+          - ansible_facts[flannel_iface].ipv4 is defined
+          - ansible_facts[flannel_iface].ipv4.address is defined
+        fail_msg: >-
+          The Vagrant private interface {{ flannel_iface }} does not have an
+          IPv4 address on {{ inventory_hostname }}.
+
+    - name: Pin disposable cluster peer neighbor entries
+      ansible.builtin.command:
+        argv:
+          - ip
+          - neigh
+          - replace
+          - "{{ peer_cluster_ip }}"
+          - lladdr
+          - "{{ peer_cluster_mac }}"
+          - nud
+          - permanent
+          - dev
+          - "{{ cluster_interface }}"
+      become: true
+      changed_when: false
+      loop: "{{ groups['k3s_cluster'] }}"
+      loop_control:
+        label: "{{ inventory_hostname }} -> {{ item }}"
+      vars:
+        peer_cluster_interface: >-
+          {{ hostvars[item].cilium_iface
+          | default(hostvars[item].calico_iface
+          | default(hostvars[item].flannel_iface)) }}
+        peer_cluster_ip: >-
+          {{ hostvars[item].k3s_node_ip | split(',') | first }}
+        peer_cluster_mac: >-
+          {{ hostvars[item].ansible_facts[peer_cluster_interface].macaddress }}
+      when: item != inventory_hostname
+
+    - name: Verify guest-to-guest cluster network reachability
+      ansible.builtin.command:
+        argv:
+          - ping
+          - -c
+          - "1"
+          - -W
+          - "1"
+          - "{{ primary_cluster_ip }}"
+      register: primary_cluster_ping
+      until: primary_cluster_ping.rc == 0
+      retries: 6
+      delay: 2
+      changed_when: false
+
+    - name: Read the primary neighbor entry
+      ansible.builtin.command:
+        argv:
+          - ip
+          - neigh
+          - show
+          - to
+          - "{{ primary_cluster_ip }}"
+          - dev
+          - "{{ cluster_interface }}"
+      register: primary_cluster_neighbor
+      changed_when: false
+      when: inventory_hostname != primary_master
+
+    - name: Verify the primary neighbor identity
+      ansible.builtin.assert:
+        that:
+          - (primary_cluster_mac | lower) in (primary_cluster_neighbor.stdout | lower)
+        fail_msg: >-
+          {{ inventory_hostname }} resolved primary {{ primary_cluster_ip }} to
+          an unexpected MAC on {{ cluster_interface }}. Expected
+          {{ primary_cluster_mac }}, got: {{ primary_cluster_neighbor.stdout }}
+      when: inventory_hostname != primary_master
+
+    - name: Verify GitHub release host DNS
+      ansible.builtin.getent:
+        database: hosts
+        key: github.com
+      register: github_dns
+      retries: 6
+      delay: 5
+      until: github_dns is succeeded
+
+    - name: Verify k3s checksum URL is reachable
+      ansible.builtin.uri:
+        url: >-
+          https://github.com/k3s-io/k3s/releases/download/{{ k3s_version
+          }}/sha256sum-amd64.txt
+        method: HEAD
+        follow_redirects: safe
+        status_code: [200, 302]
+        timeout: 15
+      register: k3s_checksum_request
+      retries: 3
+      delay: 5
+      until: k3s_checksum_request.status in [200, 302]

molecule/ipv6/molecule.yml

@@ -17,8 +17,8 @@ platforms:
     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"
+      ssh.username: vagrant
+      ssh.password: vagrant
 
   - name: control2
     box: generic/ubuntu2204
@@ -33,8 +33,8 @@ platforms:
     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"
+      ssh.username: vagrant
+      ssh.password: vagrant
 
   - name: node1
     box: generic/ubuntu2204
@@ -49,8 +49,8 @@ platforms:
     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"
+      ssh.username: vagrant
+      ssh.password: vagrant
 provisioner:
   name: ansible
   env:

molecule/ipv6/prepare.yml

@@ -38,7 +38,7 @@
         dest: /etc/netplan/55-flannel-ipv4.yaml
         owner: root
         group: root
-        mode: 0644
+        mode: "0644"
       register: netplan_template
 
     - name: Apply netplan configuration

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 +1,18 @@
+---
+- 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
+        kube_vip_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

@@ -27,7 +27,7 @@
         name: nginx
         namespace: "{{ testing_namespace }}"
         kubeconfig: "{{ kubecfg_path }}"
-      vars: &load_balancer_metadata
+      vars:
         metallb_ip: status.loadBalancer.ingress[0].ip
         metallb_port: spec.ports[0].port
       register: nginx_services

molecule/resources/verify_from_outside/tasks/test/get-nodes.yml

@@ -9,7 +9,7 @@
   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 }}"
+    fail_msg: Expected nodes {{ expected_nodes }}, but found nodes {{ found_nodes }}
   vars:
     found_nodes: >-
       {{ cluster_nodes | json_query('resources[*].metadata.name') | unique | sort }}

molecule/single_node/molecule.yml

@@ -11,8 +11,8 @@ platforms:
     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"
+      ssh.username: vagrant
+      ssh.password: vagrant
     groups:
       - k3s_cluster
       - master

molecule/single_node/overrides.yml

@@ -7,10 +7,11 @@
         # See:
         # https://github.com/flannel-io/flannel/blob/67d603aaf45ef80f5dd39f43714fc5e6f8a637eb/Documentation/troubleshooting.md#Vagrant
         flannel_iface: eth1
+        kube_vip_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"
+        apiserver_endpoint: 192.168.30.223
+        metal_lb_ip_range: 192.168.30.91-192.168.30.99

reboot.yml

@@ -5,5 +5,6 @@
   tasks:
     - name: Reboot the nodes (and Wait upto 5 mins max)
       become: true
-      reboot:
+      ansible.builtin.reboot:
+        reboot_command: "{{ custom_reboot_command | default(omit) }}"
         reboot_timeout: 300

requirements.txt

@@ -6,7 +6,7 @@
 #
 ansible-compat==4.1.11
     # via molecule
-ansible-core==2.16.2
+ansible-core==2.18.0
     # via
     #   -r requirements.in
     #   ansible-compat
@@ -77,7 +77,7 @@ molecule==6.0.3
     # via
     #   -r requirements.in
     #   molecule-plugins
-molecule-plugins[vagrant]==23.5.0
+molecule-plugins[vagrant]==23.5.3
     # via -r requirements.in
 netaddr==0.10.1
     # via -r requirements.in
@@ -96,9 +96,9 @@ platformdirs==4.1.0
     # via virtualenv
 pluggy==1.3.0
     # via molecule
-pre-commit==3.6.0
+pre-commit==3.8.0
     # via -r requirements.in
-pre-commit-hooks==4.5.0
+pre-commit-hooks==4.6.0
     # via -r requirements.in
 pyasn1==0.5.1
     # via
@@ -114,7 +114,7 @@ python-dateutil==2.8.2
     # via kubernetes
 python-vagrant==1.0.0
     # via molecule-plugins
-pyyaml==6.0.1
+pyyaml==6.0.2
     # via
     #   -r requirements.in
     #   ansible-compat

reset.yml

@@ -7,11 +7,12 @@
       become: true
     - role: raspberrypi
       become: true
-      vars: {state: absent}
+      vars: { state: absent }
   post_tasks:
     - name: Reboot and wait for node to come back up
       become: true
-      reboot:
+      ansible.builtin.reboot:
+        reboot_command: "{{ custom_reboot_command | default(omit) }}"
         reboot_timeout: 3600
 
 - name: Revert changes to Proxmox cluster

roles/download/meta/main.yml

@@ -0,0 +1,8 @@
+---
+argument_specs:
+  main:
+    short_description: Manage the downloading of K3S binaries
+    options:
+      k3s_version:
+        description: The desired version of K3S
+        required: true

roles/download/tasks/main.yml

@@ -1,36 +1,46 @@
 ---
-
 - name: Download k3s binary x64
-  get_url:
+  ansible.builtin.get_url:
     url: https://github.com/k3s-io/k3s/releases/download/{{ k3s_version }}/k3s
     checksum: sha256:https://github.com/k3s-io/k3s/releases/download/{{ k3s_version }}/sha256sum-amd64.txt
     dest: /usr/local/bin/k3s
     owner: root
     group: root
-    mode: 0755
+    mode: "0755"
+  register: k3s_download_x64
+  retries: 5
+  delay: 10
+  until: k3s_download_x64 is succeeded
   when: ansible_facts.architecture == "x86_64"
 
 - name: Download k3s binary arm64
-  get_url:
+  ansible.builtin.get_url:
     url: https://github.com/k3s-io/k3s/releases/download/{{ k3s_version }}/k3s-arm64
     checksum: sha256:https://github.com/k3s-io/k3s/releases/download/{{ k3s_version }}/sha256sum-arm64.txt
     dest: /usr/local/bin/k3s
     owner: root
     group: root
-    mode: 0755
+    mode: "0755"
+  register: k3s_download_arm64
+  retries: 5
+  delay: 10
+  until: k3s_download_arm64 is succeeded
   when:
-    - ( ansible_facts.architecture is search("arm") and
-        ansible_facts.userspace_bits == "64" ) or
-      ansible_facts.architecture is search("aarch64")
+    - ( ansible_facts.architecture is search("arm") and ansible_facts.userspace_bits == "64" )
+      or ansible_facts.architecture is search("aarch64")
 
 - name: Download k3s binary armhf
-  get_url:
+  ansible.builtin.get_url:
     url: https://github.com/k3s-io/k3s/releases/download/{{ k3s_version }}/k3s-armhf
     checksum: sha256:https://github.com/k3s-io/k3s/releases/download/{{ k3s_version }}/sha256sum-arm.txt
     dest: /usr/local/bin/k3s
     owner: root
     group: root
-    mode: 0755
+    mode: "0755"
+  register: k3s_download_armhf
+  retries: 5
+  delay: 10
+  until: k3s_download_armhf is succeeded
   when:
     - ansible_facts.architecture is search("arm")
     - ansible_facts.userspace_bits == "32"

roles/k3s_agent/defaults/main.yml

@@ -0,0 +1,4 @@
+---
+extra_agent_args: ""
+group_name_master: master
+systemd_dir: /etc/systemd/system

roles/k3s_agent/meta/main.yml

@@ -0,0 +1,39 @@
+---
+argument_specs:
+  main:
+    short_description: Setup k3s agents
+    options:
+      apiserver_endpoint:
+        description: Virtual ip-address configured on each master
+        required: true
+
+      extra_agent_args:
+        description: Extra arguments for agents nodes
+
+      group_name_master:
+        description: Name of the master group
+        default: master
+
+      k3s_token:
+        description: Token used to communicate between masters
+
+      proxy_env:
+        type: dict
+        description:
+          - Internet proxy configurations.
+          - See https://docs.k3s.io/advanced#configuring-an-http-proxy for details
+        default: ~
+        options:
+          HTTP_PROXY:
+            description: HTTP internet proxy
+            required: true
+          HTTPS_PROXY:
+            description: HTTPS internet proxy
+            required: true
+          NO_PROXY:
+            description: Addresses that will not use the proxies
+            required: true
+
+      systemd_dir:
+        description: Path to systemd services
+        default: /etc/systemd/system

roles/k3s_agent/tasks/http_proxy.yml

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

roles/k3s_agent/tasks/main.yml

@@ -1,19 +1,35 @@
 ---
+- 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: Set fact for PXE-booted system
+      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
+  ansible.builtin.include_tasks: http_proxy.yml
   when: proxy_env is defined
 
-- name: Copy K3s service file
-  template:
-    src: "k3s.service.j2"
+- 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
-  systemd:
+- name: Manage k3s service
+  ansible.builtin.systemd:
     name: k3s-node
     daemon_reload: true
     state: restarted

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 }}
 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

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

roles/k3s_custom_registries/meta/main.yml

@@ -0,0 +1,20 @@
+---
+argument_specs:
+  main:
+    short_description: Configure the use of a custom container registry
+    options:
+      custom_registries_yaml:
+        description:
+          - YAML block defining custom registries.
+          - >
+            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.
+        required: true

roles/k3s_custom_registries/tasks/main.yml

@@ -1,17 +1,16 @@
 ---
-
 - name: Create directory /etc/rancher/k3s
-  file:
-    path: "/etc/{{ item }}"
+  ansible.builtin.file:
+    path: /etc/{{ item }}
     state: directory
-    mode: '0755'
+    mode: "0755"
   loop:
     - rancher
     - rancher/k3s
 
 - name: Insert registries into /etc/rancher/k3s/registries.yaml
-  blockinfile:
+  ansible.builtin.blockinfile:
     path: /etc/rancher/k3s/registries.yaml
     block: "{{ custom_registries_yaml }}"
-    mode: '0600'
+    mode: "0600"
     create: true

roles/k3s_server/defaults/main.yml

@@ -1,12 +1,30 @@
 ---
-# If you want to explicitly define an interface that ALL control nodes
-# should use to propagate the VIP, define it here. Otherwise, kube-vip
-# will determine the right interface automatically at runtime.
-kube_vip_iface: null
+extra_server_args: ""
+
+k3s_kubectl_binary: k3s kubectl
 
-# Name of the master group
 group_name_master: master
 
+kube_vip_arp: true
+kube_vip_iface:
+kube_vip_cloud_provider_tag_version: main
+kube_vip_tag_version: v0.7.2
+
+kube_vip_bgp: false
+kube_vip_bgp_routerid: 127.0.0.1
+kube_vip_bgp_as: "64513"
+kube_vip_bgp_peeraddress: 192.168.30.1
+kube_vip_bgp_peeras: "64512"
+
+kube_vip_bgp_peers: []
+kube_vip_bgp_peers_groups: ['k3s_master']
+
+metal_lb_controller_tag_version: v0.14.3
+metal_lb_speaker_tag_version: v0.14.3
+metal_lb_type: native
+
+retry_count: 20
+
 # yamllint disable rule:line-length
 server_init_args: >-
   {% if groups[group_name_master | default('master')] | length > 1 %}
@@ -17,4 +35,6 @@ server_init_args: >-
     {% endif %}
     --token {{ k3s_token }}
   {% endif %}
-  {{ extra_server_args | default('') }}
+  {{ extra_server_args }}
+
+systemd_dir: /etc/systemd/system

roles/k3s_server/meta/main.yml

@@ -0,0 +1,135 @@
+---
+argument_specs:
+  main:
+    short_description: Setup k3s servers
+    options:
+      apiserver_endpoint:
+        description: Virtual ip-address configured on each master
+        required: true
+
+      cilium_bgp:
+        description:
+          - Enable cilium BGP control plane for LB services and pod cidrs.
+          - Disables the use of MetalLB.
+        type: bool
+        default: ~
+
+      cilium_iface:
+        description: The network interface used for when Cilium is enabled
+        default: ~
+
+      extra_server_args:
+        description: Extra arguments for server nodes
+        default: ""
+
+      group_name_master:
+        description: Name of the master group
+        default: master
+
+      k3s_create_kubectl_symlink:
+        description: Create the kubectl -> k3s symlink
+        default: false
+        type: bool
+
+      k3s_create_crictl_symlink:
+        description: Create the crictl -> k3s symlink
+        default: false
+        type: bool
+
+      kube_vip_arp:
+        description: Enables kube-vip ARP broadcasts
+        default: true
+        type: bool
+
+      kube_vip_bgp:
+        description: Enables kube-vip BGP peering
+        default: false
+        type: bool
+
+      kube_vip_bgp_routerid:
+        description: Defines the router ID for the kube-vip BGP server
+        default: "127.0.0.1"
+
+      kube_vip_bgp_as:
+        description: Defines the AS for the kube-vip BGP server
+        default: "64513"
+
+      kube_vip_bgp_peeraddress:
+        description: Defines the address for the kube-vip BGP peer
+        default: "192.168.30.1"
+
+      kube_vip_bgp_peeras:
+        description: Defines the AS for the kube-vip BGP peer
+        default: "64512"
+
+      kube_vip_bgp_peers:
+        description: List of BGP peer ASN & address pairs
+        default: []
+
+      kube_vip_bgp_peers_groups:
+        description: Inventory group in which to search for additional kube_vip_bgp_peers parameters to merge.
+        default: ['k3s_master']
+
+      kube_vip_iface:
+        description:
+          - Explicitly define an interface that ALL control nodes
+          - should use to propagate the VIP, define it here.
+          - Otherwise, kube-vip will determine the right interface
+          - automatically at runtime.
+        default: ~
+
+      kube_vip_tag_version:
+        description: Image tag for kube-vip
+        default: v0.7.2
+
+      kube_vip_cloud_provider_tag_version:
+        description: Tag for kube-vip-cloud-provider manifest when enabled
+        default: main
+
+      kube_vip_lb_ip_range:
+        description: IP range for kube-vip load balancer
+        default: ~
+
+      metal_lb_controller_tag_version:
+        description: Image tag for MetalLB
+        default: v0.14.3
+
+      metal_lb_speaker_tag_version:
+        description: Image tag for MetalLB
+        default: v0.14.3
+
+      metal_lb_type:
+        choices:
+          - frr
+          - native
+        default: native
+        description: Use FRR mode or native. Valid values are `frr` and `native`
+
+      proxy_env:
+        type: dict
+        description:
+          - Internet proxy configurations.
+          - See https://docs.k3s.io/advanced#configuring-an-http-proxy for details
+        default: ~
+        options:
+          HTTP_PROXY:
+            description: HTTP internet proxy
+            required: true
+          HTTPS_PROXY:
+            description: HTTPS internet proxy
+            required: true
+          NO_PROXY:
+            description: Addresses that will not use the proxies
+            required: true
+
+      retry_count:
+        description: Amount of retries when verifying that nodes joined
+        type: int
+        default: 20
+
+      server_init_args:
+        description: Arguments for server nodes
+
+      systemd_dir:
+        description: Path to systemd services
+        default: /etc/systemd/system

roles/k3s_server/tasks/fetch_k3s_init_logs.yml

@@ -4,10 +4,110 @@
 
 - name: Fetch k3s-init.service logs
   ansible.builtin.command:
-    cmd: journalctl --all --unit=k3s-init.service
+    cmd: >-
+      timeout --signal=TERM --kill-after=5s 30s journalctl --no-pager
+      --unit=k3s-init.service --since=-30min --lines=5000
   changed_when: false
+  failed_when: false
+  no_log: true
   register: k3s_init_log
 
+- name: Fetch k3s-init.service status
+  ansible.builtin.command:
+    cmd: >-
+      timeout --signal=TERM --kill-after=5s 15s systemctl status
+      k3s-init.service --no-pager --full
+  changed_when: false
+  failed_when: false
+  no_log: true
+  register: k3s_init_status
+
+- name: Fetch IP address state
+  ansible.builtin.command:
+    cmd: ip -br address
+  changed_when: false
+  failed_when: false
+  no_log: true
+  register: k3s_ip_address_state
+
+- name: Fetch IP link state
+  ansible.builtin.command:
+    cmd: ip -br link
+  changed_when: false
+  failed_when: false
+  no_log: true
+  register: k3s_ip_link_state
+
+- name: Fetch IP route state
+  ansible.builtin.command:
+    cmd: ip route show
+  changed_when: false
+  failed_when: false
+  no_log: true
+  register: k3s_ip_route_state
+
+- name: Fetch IP neighbor state
+  ansible.builtin.command:
+    cmd: ip neigh show
+  changed_when: false
+  failed_when: false
+  no_log: true
+  register: k3s_ip_neighbor_state
+
+- name: Fetch IP rule state
+  ansible.builtin.command:
+    cmd: ip rule show
+  changed_when: false
+  failed_when: false
+  no_log: true
+  register: k3s_ip_rule_state
+
+- name: Fetch listening TCP sockets
+  ansible.builtin.command:
+    cmd: ss -ltn
+  changed_when: false
+  failed_when: false
+  no_log: true
+  register: k3s_tcp_listener_state
+
+- name: Fetch guest firewall service state
+  ansible.builtin.service_facts:
+  no_log: true
+  register: k3s_service_facts
+
+- name: Fetch input firewall rules
+  ansible.builtin.command:
+    cmd: iptables -S INPUT
+  changed_when: false
+  failed_when: false
+  no_log: true
+  register: k3s_input_firewall_rules
+
+- name: Ping the primary Kubernetes API address from {{ ansible_hostname }}
+  ansible.builtin.command:
+    argv:
+      - ping
+      - -c
+      - "1"
+      - -W
+      - "1"
+      - "{{ hostvars[groups[group_name_master | default('master')][0]].k3s_node_ip | split(',') | first }}"
+  changed_when: false
+  failed_when: false
+  no_log: true
+  register: k3s_primary_api_ping
+
+- name: Probe primary Kubernetes API from {{ ansible_hostname }}
+  ansible.builtin.wait_for:
+    host: "{{ hostvars[groups[group_name_master | default('master')][0]].k3s_node_ip | split(',') | first }}"
+    port: 6443
+    connect_timeout: 1
+    timeout: 2
+  changed_when: false
+  failed_when: false
+  no_log: true
+  register: k3s_primary_api_probe
+
 - name: Create {{ log_destination }}
   delegate_to: localhost
   run_once: true
@@ -23,6 +123,58 @@
   ansible.builtin.template:
     src: content.j2
     dest: "{{ log_destination }}/k3s-init@{{ ansible_hostname }}.log"
-    mode: 0644
+    mode: "0644"
   vars:
-    content: "{{ k3s_init_log.stdout }}"
+    content: |
+      === k3s-init.service status ===
+      {{ k3s_init_status.stdout | regex_replace('--token(?:=| +)[^ ]+', '--token ***') }}
+
+      === k3s-init.service journal ===
+      {{ k3s_init_log.stdout | regex_replace('--token(?:=| +)[^ ]+', '--token ***') }}
+
+- name: Store network diagnostics to {{ log_destination }}
+  delegate_to: localhost
+  become: false
+  ansible.builtin.template:
+    src: content.j2
+    dest: "{{ log_destination }}/network@{{ ansible_hostname }}.log"
+    mode: "0644"
+  vars:
+    content: |
+      === ip -br address ===
+      {{ k3s_ip_address_state.stdout }}
+
+      === ip -br link ===
+      {{ k3s_ip_link_state.stdout }}
+
+      === ip route show ===
+      {{ k3s_ip_route_state.stdout }}
+
+      === ip neigh show ===
+      {{ k3s_ip_neighbor_state.stdout }}
+
+      === ip rule show ===
+      {{ k3s_ip_rule_state.stdout }}
+
+      === ss -ltn ===
+      {{ k3s_tcp_listener_state.stdout }}
+
+      === guest firewall services ===
+      firewalld={{ k3s_service_facts.ansible_facts.services.get('firewalld.service', {}).get('state', 'not-found') }}
+      nftables={{ k3s_service_facts.ansible_facts.services.get('nftables.service', {}).get('state', 'not-found') }}
+      ufw={{ k3s_service_facts.ansible_facts.services.get('ufw.service', {}).get('state', 'not-found') }}
+
+      === iptables -S INPUT ===
+      rc={{ k3s_input_firewall_rules.rc }}
+      {{ k3s_input_firewall_rules.stdout }}
+      {{ k3s_input_firewall_rules.stderr }}
+
+      === primary API ping ===
+      rc={{ k3s_primary_api_ping.rc }}
+      {{ k3s_primary_api_ping.stdout }}
+      {{ k3s_primary_api_ping.stderr }}
+
+      === primary API probe ===
+      failed={{ k3s_primary_api_probe.failed | default(false) }}
+      elapsed={{ k3s_primary_api_probe.elapsed | default('unknown') }}
+      msg={{ k3s_primary_api_probe.msg | default('connected') }}

roles/k3s_server/tasks/http_proxy.yml

@@ -1,18 +1,16 @@
 ---
-
 - name: Create k3s.service.d directory
-  file:
-    path: '{{ systemd_dir }}/k3s.service.d'
+  ansible.builtin.file:
+    path: "{{ systemd_dir }}/k3s.service.d"
     state: directory
     owner: root
     group: root
-    mode: '0755'
-
+    mode: "0755"
 
 - name: Copy K3s http_proxy conf file
-  template:
-    src: "http_proxy.conf.j2"
+  ansible.builtin.template:
+    src: http_proxy.conf.j2
     dest: "{{ systemd_dir }}/k3s.service.d/http_proxy.conf"
     owner: root
     group: root
-    mode: '0755'
+    mode: "0755"

roles/k3s_server/tasks/join_master.yml

@@ -0,0 +1,34 @@
+---
+- name: Verify primary Kubernetes API reachability from {{ joining_master }}
+  ansible.builtin.wait_for:
+    host: >-
+      {{ hostvars[groups[group_name_master | default('master')][0]].k3s_node_ip
+      | split(',') | first }}
+    port: 6443
+    connect_timeout: 2
+    timeout: 30
+  delegate_to: "{{ joining_master }}"
+
+- name: Join transient k3s-init service for {{ joining_master }}
+  ansible.builtin.command:
+    cmd: >-
+      systemd-run -p RestartSec=2 -p Restart=on-failure
+      -p Delegate=yes -p TasksMax=infinity -p KillMode=process
+      -p LimitNOFILE=1048576 -p LimitNPROC=infinity -p LimitCORE=infinity
+      --unit=k3s-init
+      k3s server {{ hostvars[joining_master].k3s_server_init_args }}
+    creates: "{{ systemd_dir }}/k3s-init.service"
+  delegate_to: "{{ joining_master }}"
+  no_log: true
+
+- name: Wait for primary registration of {{ joining_master }}
+  ansible.builtin.command:
+    cmd: >-
+      {{ k3s_kubectl_binary | default('k3s kubectl') }} get node
+      {{ hostvars[joining_master].ansible_hostname }}
+  delegate_to: "{{ groups[group_name_master | default('master')][0] }}"
+  register: joined_master
+  until: joined_master.rc == 0
+  retries: "{{ retry_count | default(20) }}"
+  delay: 2
+  changed_when: false

roles/k3s_server/tasks/kube-vip.yml

@@ -0,0 +1,27 @@
+---
+- name: Create manifests directory on first master
+  ansible.builtin.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
+  ansible.builtin.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

@@ -1,166 +1,234 @@
 ---
-
 - name: Stop k3s-init
-  systemd:
+  ansible.builtin.systemd:
     name: k3s-init
     state: stopped
   failed_when: false
 
 # k3s-init won't work if the port is already in use
 - name: Stop k3s
-  systemd:
+  ansible.builtin.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
+  ansible.builtin.command: systemctl reset-failed k3s-init
   failed_when: false
   changed_when: false
 
 - name: Deploy K3s http_proxy conf
-  include_tasks: http_proxy.yml
+  ansible.builtin.include_tasks: http_proxy.yml
   when: proxy_env is defined
 
 - name: Deploy vip manifest
-  include_tasks: vip.yml
-
+  ansible.builtin.include_tasks: vip.yml
 - name: Deploy metallb manifest
-  include_tasks: metallb.yml
+  ansible.builtin.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: Init cluster inside the transient k3s-init service
-  command:
-    cmd: "systemd-run -p RestartSec=2 \
-                      -p Restart=on-failure \
-                      --unit=k3s-init \
-                      k3s server {{ server_init_args }}"
-    creates: "{{ systemd_dir }}/k3s-init.service"
+- name: Deploy kube-vip manifest
+  ansible.builtin.include_tasks: kube-vip.yml
+  tags: kubevip
+  when: kube_vip_lb_ip_range is defined
 
-- name: Verification
+- name: Initialize and verify the K3s control plane
+  any_errors_fatal: true
   when: not ansible_check_mode
   block:
-    - name: Verify that all nodes actually joined (check k3s-init.service if this fails)
-      command:
-        cmd: k3s kubectl get nodes -l "node-role.kubernetes.io/master=true" -o=jsonpath="{.items[*].metadata.name}"
-      register: nodes
-      until: nodes.rc == 0 and (nodes.stdout.split() | length) == (groups[group_name_master | default('master')] | length)  # yamllint disable-line rule:line-length
+    - name: Materialize per-host server initialization arguments
+      ansible.builtin.set_fact:
+        k3s_server_init_args: "{{ server_init_args }}"
+      no_log: true
+      when: groups[group_name_master | default('master')] | length > 1
+
+    - name: Orchestrate control-plane initialization from the first master
+      when: inventory_hostname == groups[group_name_master | default('master')][0]
+      block:
+        - name: Init the first master inside the transient k3s-init service
+          ansible.builtin.command:
+            cmd: >-
+              systemd-run -p RestartSec=2 -p Restart=on-failure
+              -p Delegate=yes -p TasksMax=infinity -p KillMode=process
+              -p LimitNOFILE=1048576 -p LimitNPROC=infinity -p LimitCORE=infinity
+              --unit=k3s-init k3s server {{ server_init_args }}
+            creates: "{{ systemd_dir }}/k3s-init.service"
+          no_log: true
+
+        - name: Wait for the first master Kubernetes API
+          ansible.builtin.command:
+            cmd: "{{ k3s_kubectl_binary | default('k3s kubectl') }} get --raw=/readyz"
+          register: first_master_api
+          until: first_master_api.rc == 0
           retries: "{{ retry_count | default(20) }}"
-      delay: 10
+          delay: 2
+          changed_when: false
+
+        - name: Verify the first master API listener on its node address
+          ansible.builtin.wait_for:
+            host: >-
+              {{ hostvars[groups[group_name_master | default('master')][0]].k3s_node_ip
+              | split(',') | first }}
+            port: 6443
+            connect_timeout: 2
+            timeout: "{{ retry_count | default(20) * 2 }}"
+
+        - name: Join additional masters one at a time
+          ansible.builtin.include_tasks: join_master.yml
+          loop: "{{ groups[group_name_master | default('master')][1:] }}"
+          loop_control:
+            loop_var: joining_master
+          when: groups[group_name_master | default('master')] | length > 1
+
+        - name: Verify that all expected control-plane nodes registered
+          ansible.builtin.command:
+            cmd: >-
+              {{ k3s_kubectl_binary | default('k3s kubectl') }} get nodes
+              -o=jsonpath='{.items[*].metadata.name}'
+          register: nodes
+          until:
+            - nodes.rc == 0
+            - expected_control_plane_names | difference(nodes.stdout.split()) | length == 0
+          retries: "{{ retry_count | default(20) }}"
+          delay: 2
+          changed_when: false
+          vars:
+            expected_control_plane_names: >-
+              {{
+                groups[group_name_master | default('master')]
+                | map('extract', hostvars, 'ansible_hostname')
+                | list
+              }}
+
+        - name: Wait for K3s bootstrap CRDs to become established
+          ansible.builtin.command:
+            cmd: >-
+              {{ k3s_kubectl_binary | default('k3s kubectl') }} wait
+              --for=condition=Established --timeout=5s
+              crd/addons.k3s.cattle.io
+              crd/helmcharts.helm.cattle.io
+              crd/helmchartconfigs.helm.cattle.io
+          register: bootstrap_crds
+          until: bootstrap_crds.rc == 0
+          retries: "{{ retry_count | default(20) }}"
+          delay: 2
           changed_when: false
   always:
     - name: Save logs of k3s-init.service
-      include_tasks: fetch_k3s_init_logs.yml
+      ansible.builtin.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:
+      ansible.builtin.systemd:
         name: k3s-init
         state: stopped
       failed_when: false
 
 - name: Copy K3s service file
   register: k3s_service
-  template:
-    src: "k3s.service.j2"
+  ansible.builtin.template:
+    src: k3s.service.j2
     dest: "{{ systemd_dir }}/k3s.service"
     owner: root
     group: root
-    mode: 0644
+    mode: "0644"
 
 - name: Enable and check K3s service
-  systemd:
+  ansible.builtin.systemd:
     name: k3s
     daemon_reload: true
     state: restarted
     enabled: true
 
 - name: Wait for node-token
-  wait_for:
+  ansible.builtin.wait_for:
     path: /var/lib/rancher/k3s/server/node-token
 
 - name: Register node-token file access mode
-  stat:
+  ansible.builtin.stat:
     path: /var/lib/rancher/k3s/server
   register: p
 
 - name: Change file access node-token
-  file:
+  ansible.builtin.file:
     path: /var/lib/rancher/k3s/server
-    mode: "g+rx,o+rx"
+    mode: g+rx,o+rx
 
 - name: Read node-token from master
-  slurp:
+  ansible.builtin.slurp:
     src: /var/lib/rancher/k3s/server/node-token
   register: node_token
 
 - name: Store Master node-token
-  set_fact:
+  ansible.builtin.set_fact:
     token: "{{ node_token.content | b64decode | regex_replace('\n', '') }}"
 
 - name: Restore node-token file access
-  file:
+  ansible.builtin.file:
     path: /var/lib/rancher/k3s/server
     mode: "{{ p.stat.mode }}"
 
 - name: Create directory .kube
-  file:
+  ansible.builtin.file:
     path: "{{ ansible_user_dir }}/.kube"
     state: directory
     owner: "{{ ansible_user_id }}"
-    mode: "u=rwx,g=rx,o="
+    mode: u=rwx,g=rx,o=
 
 - name: Copy config file to user home directory
-  copy:
+  ansible.builtin.copy:
     src: /etc/rancher/k3s/k3s.yaml
     dest: "{{ ansible_user_dir }}/.kube/config"
     remote_src: true
     owner: "{{ ansible_user_id }}"
-    mode: "u=rw,g=,o="
+    mode: u=rw,g=,o=
 
 - name: Configure kubectl cluster to {{ endpoint_url }}
-  command: >-
-    k3s kubectl config set-cluster default
+  ansible.builtin.command: >-
+    {{ k3s_kubectl_binary | default('k3s kubectl') }} config set-cluster default
       --server={{ endpoint_url }}
       --kubeconfig {{ ansible_user_dir }}/.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]
+# 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:
+  ansible.builtin.file:
     src: /usr/local/bin/k3s
     dest: /usr/local/bin/kubectl
     state: link
+  when: k3s_create_kubectl_symlink | default(true) | bool
 
 - name: Create crictl symlink
-  file:
+  ansible.builtin.file:
     src: /usr/local/bin/k3s
     dest: /usr/local/bin/crictl
     state: link
+  when: k3s_create_crictl_symlink | default(true) | bool
 
 - name: Get contents of manifests folder
-  find:
+  ansible.builtin.find:
     paths: /var/lib/rancher/k3s/server/manifests
     file_type: file
   register: k3s_server_manifests
 
 - name: Get sub dirs of manifests folder
-  find:
+  ansible.builtin.find:
     paths: /var/lib/rancher/k3s/server/manifests
     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:
+  ansible.builtin.file:
     path: "{{ item.path }}"
     state: absent
   with_items:

roles/k3s_server/tasks/metallb.yml

@@ -1,30 +1,30 @@
 ---
 - name: Create manifests directory on first master
-  file:
+  ansible.builtin.file:
     path: /var/lib/rancher/k3s/server/manifests
     state: directory
     owner: root
     group: root
-    mode: 0644
+    mode: "0644"
   when: ansible_hostname == hostvars[groups[group_name_master | default('master')][0]]['ansible_hostname']
 
 - name: "Download to first master: manifest for metallb-{{ metal_lb_type }}"
   ansible.builtin.get_url:
-    url: "https://raw.githubusercontent.com/metallb/metallb/{{ metal_lb_controller_tag_version }}/config/manifests/metallb-{{ metal_lb_type }}.yaml"  # noqa yaml[line-length]
-    dest: "/var/lib/rancher/k3s/server/manifests/metallb-crds.yaml"
+    url: https://raw.githubusercontent.com/metallb/metallb/{{ metal_lb_controller_tag_version }}/config/manifests/metallb-{{ metal_lb_type }}.yaml # noqa yaml[line-length]
+    dest: /var/lib/rancher/k3s/server/manifests/metallb-crds.yaml
     owner: root
     group: root
-    mode: 0644
+    mode: "0644"
   when: ansible_hostname == hostvars[groups[group_name_master | default('master')][0]]['ansible_hostname']
 
 - name: Set image versions in manifest for metallb-{{ metal_lb_type }}
   ansible.builtin.replace:
-    path: "/var/lib/rancher/k3s/server/manifests/metallb-crds.yaml"
+    path: /var/lib/rancher/k3s/server/manifests/metallb-crds.yaml
     regexp: "{{ item.change | ansible.builtin.regex_escape }}"
     replace: "{{ item.to }}"
   with_items:
-    - change: "metallb/speaker:{{ metal_lb_controller_tag_version }}"
-      to: "metallb/speaker:{{ metal_lb_speaker_tag_version }}"
+    - change: metallb/speaker:{{ metal_lb_controller_tag_version }}
+      to: metallb/speaker:{{ metal_lb_speaker_tag_version }}
   loop_control:
     label: "{{ item.change }} => {{ item.to }}"
   when: ansible_hostname == hostvars[groups[group_name_master | default('master')][0]]['ansible_hostname']

roles/k3s_server/tasks/vip.yml

@@ -1,27 +1,31 @@
 ---
+- name: Set _kube_vip_bgp_peers fact
+  ansible.builtin.set_fact:
+    _kube_vip_bgp_peers: "{{ lookup('community.general.merge_variables', '^kube_vip_bgp_peers__.+$', initial_value=kube_vip_bgp_peers, groups=kube_vip_bgp_peers_groups) }}"  # yamllint disable-line rule:line-length
+
 - name: Create manifests directory on first master
-  file:
+  ansible.builtin.file:
     path: /var/lib/rancher/k3s/server/manifests
     state: directory
     owner: root
     group: root
-    mode: 0644
+    mode: "0644"
   when: ansible_hostname == hostvars[groups[group_name_master | default('master')][0]]['ansible_hostname']
 
 - 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"
-    dest: "/var/lib/rancher/k3s/server/manifests/vip-rbac.yaml"
+    url: https://kube-vip.io/manifests/rbac.yaml
+    dest: /var/lib/rancher/k3s/server/manifests/vip-rbac.yaml
     owner: root
     group: root
-    mode: 0644
+    mode: "0644"
   when: ansible_hostname == hostvars[groups[group_name_master | default('master')][0]]['ansible_hostname']
 
 - name: Copy vip manifest to first master
-  template:
-    src: "vip.yaml.j2"
-    dest: "/var/lib/rancher/k3s/server/manifests/vip.yaml"
+  ansible.builtin.template:
+    src: vip.yaml.j2
+    dest: /var/lib/rancher/k3s/server/manifests/vip.yaml
     owner: root
     group: root
-    mode: 0644
+    mode: "0644"
   when: ansible_hostname == hostvars[groups[group_name_master | default('master')][0]]['ansible_hostname']

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 +27,9 @@ spec:
         - manager
         env:
         - name: vip_arp
-          value: "true"
+          value: "{{ 'true' if kube_vip_arp | default(true) | bool else 'false' }}"
+        - name: bgp_enable
+          value: "{{ 'true' if kube_vip_bgp | default(false) | bool else 'false' }}"
         - name: port
           value: "6443"
 {% if kube_vip_iface %}
@@ -43,7 +45,7 @@ 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
@@ -54,6 +56,29 @@ spec:
           value: "2"
         - name: address
           value: {{ apiserver_endpoint }}
+{% if kube_vip_bgp | default(false) | bool %}
+{% if kube_vip_bgp_routerid is defined %}
+        - name: bgp_routerid
+          value: "{{ kube_vip_bgp_routerid }}"
+{% endif %}
+{% if _kube_vip_bgp_peers | length > 0 %}
+        - name: bgppeers
+          value: "{{ _kube_vip_bgp_peers | map(attribute='peer_address') | zip(_kube_vip_bgp_peers| map(attribute='peer_asn')) | map('join', ',') | join(':') }}"  # yamllint disable-line rule:line-length
+{% else %}
+{% if kube_vip_bgp_as is defined %}
+        - name: bgp_as
+          value: "{{ kube_vip_bgp_as }}"
+{% endif %}
+{% if kube_vip_bgp_peeraddress is defined %}
+        - name: bgp_peeraddress
+          value: "{{ kube_vip_bgp_peeraddress }}"
+{% endif %}
+{% if kube_vip_bgp_peeras is defined %}
+        - name: bgp_peeras
+          value: "{{ kube_vip_bgp_peeras }}"
+{% endif %}
+{% endif %}
+{% endif %}
         image: ghcr.io/kube-vip/kube-vip:{{ kube_vip_tag_version }}
         imagePullPolicy: Always
         name: kube-vip

roles/k3s_server_post/defaults/main.yml

@@ -1,6 +1,32 @@
 ---
-# Timeout to wait for MetalLB services to come up
-metal_lb_available_timeout: 240s
+k3s_kubectl_binary: k3s kubectl
 
-# Name of the master group
+bpf_lb_algorithm: maglev
+bpf_lb_mode: hybrid
+
+calico_blockSize: 26  # noqa var-naming
+calico_ebpf: false
+calico_encapsulation: VXLANCrossSubnet
+calico_natOutgoing: Enabled  # noqa var-naming
+calico_nodeSelector: all()  # noqa var-naming
+calico_tag: v3.27.2
+
+cilium_bgp: false
+cilium_exportPodCIDR: true  # noqa var-naming
+cilium_bgp_my_asn: 64513
+cilium_bgp_peer_asn: 64512
+cilium_bgp_neighbors: []
+cilium_bgp_neighbors_groups: ['k3s_all']
+cilium_bgp_lb_cidr: 192.168.31.0/24
+cilium_hubble: true
+cilium_mode: native
+
+cluster_cidr: 10.52.0.0/16
+enable_bpf_masquerade: true
+kube_proxy_replacement: true
 group_name_master: master
+
+metal_lb_mode: layer2
+metal_lb_available_timeout: 240s
+metal_lb_controller_tag_version: v0.14.3
+metal_lb_ip_range: 192.168.30.80-192.168.30.90

roles/k3s_server_post/meta/main.yml

@@ -0,0 +1,153 @@
+---
+argument_specs:
+  main:
+    short_description: Configure k3s cluster
+    options:
+      apiserver_endpoint:
+        description: Virtual ip-address configured on each master
+        required: true
+
+      bpf_lb_algorithm:
+        description: BPF lb algorithm
+        default: maglev
+
+      bpf_lb_mode:
+        description: BPF lb mode
+        default: hybrid
+
+      calico_blockSize:
+        description: IP pool block size
+        type: int
+        default: 26
+
+      calico_ebpf:
+        description: Use eBPF dataplane instead of iptables
+        type: bool
+        default: false
+
+      calico_encapsulation:
+        description: IP pool encapsulation
+        default: VXLANCrossSubnet
+
+      calico_natOutgoing:
+        description: IP pool NAT outgoing
+        default: Enabled
+
+      calico_nodeSelector:
+        description: IP pool node selector
+        default: all()
+
+      calico_iface:
+        description: The network interface used for when Calico is enabled
+        default: ~
+
+      calico_tag:
+        description: Calico version tag
+        default: v3.27.2
+
+      cilium_bgp:
+        description:
+          - Enable cilium BGP control plane for LB services and pod cidrs.
+          - Disables the use of MetalLB.
+        type: bool
+        default: false
+
+      cilium_bgp_my_asn:
+        description: Local ASN for BGP peer
+        type: int
+        default: 64513
+
+      cilium_bgp_peer_asn:
+        description: BGP peer ASN
+        type: int
+        default: 64512
+
+      cilium_bgp_peer_address:
+        description: BGP peer address
+        default: ~
+
+      cilium_bgp_neighbors:
+        description: List of BGP peer ASN & address pairs
+        default: []
+
+      cilium_bgp_neighbors_groups:
+        description: Inventory group in which to search for additional cilium_bgp_neighbors parameters to merge.
+        default: ['k3s_all']
+
+      cilium_bgp_lb_cidr:
+        description: BGP load balancer IP range
+        default: 192.168.31.0/24
+
+      cilium_exportPodCIDR:
+        description: Export pod CIDR
+        type: bool
+        default: true
+
+      cilium_hubble:
+        description: Enable Cilium Hubble
+        type: bool
+        default: true
+
+      cilium_iface:
+        description: The network interface used for when Cilium is enabled
+        default: ~
+
+      cilium_mode:
+        description: Inner-node communication mode
+        default: native
+        choices:
+          - native
+          - routed
+
+      cluster_cidr:
+        description: Inner-cluster IP range
+        default: 10.52.0.0/16
+
+      enable_bpf_masquerade:
+        description: Use IP masquerading
+        type: bool
+        default: true
+
+      group_name_master:
+        description: Name of the master group
+        default: master
+
+      kube_proxy_replacement:
+        description: Replace the native kube-proxy with Cilium
+        type: bool
+        default: true
+
+      kube_vip_lb_ip_range:
+        description: IP range for kube-vip load balancer
+        default: ~
+
+      metal_lb_available_timeout:
+        description: Wait for MetalLB resources
+        default: 240s
+
+      metal_lb_ip_range:
+        description: MetalLB ip range for load balancer
+        default: 192.168.30.80-192.168.30.90
+
+      metal_lb_controller_tag_version:
+        description: Image tag for MetalLB
+        default: v0.14.3
+
+      metal_lb_mode:
+        description: Metallb mode
+        default: layer2
+        choices:
+          - bgp
+          - layer2
+
+      metal_lb_bgp_my_asn:
+        description: BGP ASN configurations
+        default: ~
+
+      metal_lb_bgp_peer_asn:
+        description: BGP peer ASN configurations
+        default: ~
+
+      metal_lb_bgp_peer_address:
+        description: BGP peer address
+        default: ~

roles/k3s_server_post/tasks/calico.yml

@@ -0,0 +1,120 @@
+---
+- 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
+      ansible.builtin.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: "{{ k3s_kubectl_binary | default('k3s 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: "{{ k3s_kubectl_binary | default('k3s 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
+      ansible.builtin.command: >-
+        {{ k3s_kubectl_binary | default('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: "{{ k3s_kubectl_binary | default('k3s 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: "{{ k3s_kubectl_binary | default('k3s 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
+      ansible.builtin.command: >-
+        {% if item.type == 'daemonset' %}
+        {{ k3s_kubectl_binary | default('k3s kubectl') }} wait pods
+        --namespace='{{ item.namespace }}'
+        --selector={{ item.selector }}
+        --for=condition=Ready
+        {% else %}
+        {{ k3s_kubectl_binary | default('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: >
+          {{ k3s_kubectl_binary | default('k3s 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 +1,256 @@
+---
+- 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
+      ansible.builtin.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
+      ansible.builtin.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
+      ansible.builtin.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_binary | default('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
+          ansible.builtin.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
+          ansible.builtin.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 }}
+        --helm-set autoDirectNodeRoutes={{ "true" if cilium_mode == "native" else "false" }}
+        --helm-set kubeProxyReplacement={{ kube_proxy_replacement }}
+        --helm-set bpf.masquerade={{ enable_bpf_masquerade }}
+        --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 }}
+        --helm-set bpf.loadBalancer.mode={{ bpf_lb_mode }}
+        {% 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
+      ansible.builtin.command: >-
+        {% if item.type == 'daemonset' %}
+        {{ k3s_kubectl_binary | default('k3s kubectl') }} wait pods
+        --namespace=kube-system
+        --selector='k8s-app=cilium'
+        --for=condition=Ready
+        {% else %}
+        {{ k3s_kubectl_binary | default('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: Set _cilium_bgp_neighbors fact
+          ansible.builtin.set_fact:
+            _cilium_bgp_neighbors: "{{ lookup('community.general.merge_variables', '^cilium_bgp_neighbors__.+$', initial_value=cilium_bgp_neighbors, groups=cilium_bgp_neighbors_groups) }}"  # yamllint disable-line rule:line-length
+
+        - 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: "{{ k3s_kubectl_binary | default('k3s 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_binary | default('k3s kubectl') }} get CiliumBGPPeeringPolicy.cilium.io"
+            - "{{ k3s_kubectl_binary | default('k3s kubectl') }} get CiliumLoadBalancerIPPool.cilium.io"
+          changed_when: false
+          loop_control:
+            label: "{{ item }}"

roles/k3s_server_post/tasks/main.yml

@@ -1,9 +1,20 @@
 ---
+- name: Deploy calico
+  ansible.builtin.include_tasks: calico.yml
+  tags: calico
+  when: calico_iface is defined and cilium_iface is not defined
+
+- name: Deploy cilium
+  ansible.builtin.include_tasks: cilium.yml
+  tags: cilium
+  when: cilium_iface is defined
+
 - name: Deploy metallb pool
-  include_tasks: metallb.yml
+  ansible.builtin.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:
+  ansible.builtin.file:
     path: /tmp/k3s
     state: absent

roles/k3s_server_post/tasks/metallb.yml

@@ -1,32 +1,53 @@
 ---
 - name: Create manifests directory for temp configuration
-  file:
+  ansible.builtin.file:
     path: /tmp/k3s
     state: directory
     owner: "{{ ansible_user_id }}"
-    mode: 0755
+    mode: "0755"
   with_items: "{{ groups[group_name_master | default('master')] }}"
   run_once: true
 
+- name: Delete outdated metallb replicas
+  ansible.builtin.shell: |-
+    set -o pipefail
+
+    REPLICAS=$({{ k3s_kubectl_binary | default('k3s kubectl') }} --namespace='metallb-system' get replicasets \
+      -l 'component=controller,app=metallb' \
+      -o jsonpath='{.items[0].spec.template.spec.containers[0].image}, {.items[0].metadata.name}' 2>/dev/null || true)
+    REPLICAS_SETS=$(echo ${REPLICAS} | grep -v '{{ metal_lb_controller_tag_version }}' | sed -e "s/^.*\s//g")
+    if [ -n "${REPLICAS_SETS}" ] ; then
+      for REPLICAS in "${REPLICAS_SETS}"
+      do
+        {{ k3s_kubectl_binary | default('k3s kubectl') }} --namespace='metallb-system' \
+          delete rs "${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"
-    dest: "/tmp/k3s/metallb-crs.yaml"
+  ansible.builtin.template:
+    src: metallb.crs.j2
+    dest: /tmp/k3s/metallb-crs.yaml
     owner: "{{ ansible_user_id }}"
-    mode: 0755
+    mode: "0755"
   with_items: "{{ groups[group_name_master | default('master')] }}"
   run_once: true
 
 - name: Test metallb-system namespace
-  command: >-
-    k3s kubectl -n metallb-system
+  ansible.builtin.command: >-
+    {{ k3s_kubectl_binary | default('k3s kubectl') }} -n metallb-system
   changed_when: false
   with_items: "{{ groups[group_name_master | default('master')] }}"
   run_once: true
 
 - name: Wait for MetalLB resources
-  command: >-
-    k3s kubectl wait {{ item.resource }}
+  ansible.builtin.command: >-
+    {{ k3s_kubectl_binary | default('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 %}
@@ -62,16 +83,30 @@
   loop_control:
     label: "{{ item.description }}"
 
+- name: Set metallb webhook service name
+  ansible.builtin.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
+  ansible.builtin.command: >-
+    {{ k3s_kubectl_binary | default('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
 
 - name: Apply metallb CRs
-  command: >-
-    k3s kubectl apply -f /tmp/k3s/metallb-crs.yaml
+  ansible.builtin.command: >-
+    {{ k3s_kubectl_binary | default('k3s kubectl') }} apply -f /tmp/k3s/metallb-crs.yaml
     --timeout='{{ metal_lb_available_timeout }}'
   register: this
   changed_when: false
@@ -80,8 +115,8 @@
   retries: 5
 
 - name: Test metallb-system resources for Layer 2 configuration
-  command: >-
-    k3s kubectl -n metallb-system get {{ item }}
+  ansible.builtin.command: >-
+    {{ k3s_kubectl_binary | default('k3s kubectl') }} -n metallb-system get {{ item }}
   changed_when: false
   run_once: true
   when: metal_lb_mode == "layer2"
@@ -90,8 +125,8 @@
     - L2Advertisement
 
 - name: Test metallb-system resources for BGP configuration
-  command: >-
-    k3s kubectl -n metallb-system get {{ item }}
+  ansible.builtin.command: >-
+    {{ k3s_kubectl_binary | default('k3s kubectl') }} -n metallb-system get {{ item }}
   changed_when: false
   run_once: true
   when: metal_lb_mode == "bgp"

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 }}
+      cidr: {{ cluster_cidr }}
+      encapsulation: {{ calico_encapsulation }}
+      natOutgoing: {{ calico_natOutgoing }}
+      nodeSelector: {{ calico_nodeSelector }}
+    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 +1,48 @@
+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
+{% if _cilium_bgp_neighbors | length > 0 %}
+{% for item in _cilium_bgp_neighbors %}
+    - peerAddress: '{{ item.peer_address + "/32"}}'
+      peerASN: {{ item.peer_asn }}
+      eBGPMultihopTTL: 10
+      connectRetryTimeSeconds: 120
+      holdTimeSeconds: 90
+      keepAliveTimeSeconds: 30
+      gracefulRestart:
+        enabled: true
+        restartTimeSeconds: 120
+{% endfor %}
+{% else %}
+    - peerAddress: '{{ cilium_bgp_peer_address + "/32"}}'
+      peerASN: {{ cilium_bgp_peer_asn }}
+      eBGPMultihopTTL: 10
+      connectRetryTimeSeconds: 120
+      holdTimeSeconds: 90
+      keepAliveTimeSeconds: 30
+      gracefulRestart:
+        enabled: true
+        restartTimeSeconds: 120
+{% endif %}
+   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

@@ -1,5 +1,6 @@
 ---
 - name: Reboot server
   become: true
-  reboot:
+  ansible.builtin.reboot:
+    reboot_command: "{{ custom_reboot_command | default(omit) }}"
   listen: reboot server

roles/lxc/meta/main.yml

@@ -0,0 +1,8 @@
+---
+argument_specs:
+  main:
+    short_description: Configure LXC
+    options:
+      custom_reboot_command:
+        default: ~
+        description: Command to run on reboot

roles/lxc/tasks/main.yml

@@ -1,20 +1,20 @@
 ---
 - name: Check for rc.local file
-  stat:
+  ansible.builtin.stat:
     path: /etc/rc.local
   register: rcfile
 
 - name: Create rc.local if needed
-  lineinfile:
+  ansible.builtin.lineinfile:
     path: /etc/rc.local
     line: "#!/bin/sh -e"
     create: true
     insertbefore: BOF
-    mode: "u=rwx,g=rx,o=rx"
+    mode: u=rwx,g=rx,o=rx
   when: not rcfile.stat.exists
 
 - name: Write rc.local file
-  blockinfile:
+  ansible.builtin.blockinfile:
     path: /etc/rc.local
     content: "{{ lookup('template', 'templates/rc.local.j2') }}"
     state: present

roles/prereq/defaults/main.yml

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

roles/prereq/meta/main.yml

@@ -0,0 +1,7 @@
+---
+argument_specs:
+  main:
+    short_description: Prerequisites
+    options:
+      system_timezone:
+        description: Timezone to be set on all nodes

roles/prereq/tasks/main.yml

@@ -34,10 +34,10 @@
   tags: sysctl
 
 - name: Add br_netfilter to /etc/modules-load.d/
-  copy:
-    content: "br_netfilter"
+  ansible.builtin.copy:
+    content: br_netfilter
     dest: /etc/modules-load.d/br_netfilter.conf
-    mode: "u=rw,g=,o="
+    mode: u=rw,g=,o=
   when: ansible_os_family == "RedHat"
 
 - name: Load br_netfilter
@@ -59,11 +59,11 @@
   tags: sysctl
 
 - name: Add /usr/local/bin to sudo secure_path
-  lineinfile:
-    line: 'Defaults    secure_path = {{ secure_path[ansible_os_family] }}'
-    regexp: "Defaults(\\s)*secure_path(\\s)*="
+  ansible.builtin.lineinfile:
+    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'
+    validate: visudo -cf %s
   when: ansible_os_family in [ "RedHat", "Suse" ]

roles/proxmox_lxc/handlers/main.yml

@@ -2,12 +2,12 @@
 - name: Reboot containers
   block:
     - name: Get container ids from filtered files
-      set_fact:
+      ansible.builtin.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 }}"
+      ansible.builtin.command: pct reboot {{ item }}
       loop: "{{ proxmox_lxc_filtered_ids }}"
       changed_when: true
       listen: reboot containers

roles/proxmox_lxc/meta/main.yml

@@ -0,0 +1,9 @@
+---
+argument_specs:
+  main:
+    short_description: Proxmox LXC settings
+    options:
+      proxmox_lxc_ct_ids:
+        description: Proxmox container ID list
+        type: list
+        required: true

roles/proxmox_lxc/tasks/main.yml

@@ -1,44 +1,43 @@
 ---
 - name: Check for container files that exist on this host
-  stat:
-    path: "/etc/pve/lxc/{{ item }}.conf"
+  ansible.builtin.stat:
+    path: /etc/pve/lxc/{{ item }}.conf
   loop: "{{ proxmox_lxc_ct_ids }}"
   register: stat_results
 
 - name: Filter out files that do not exist
-  set_fact:
-    proxmox_lxc_filtered_files:
-      '{{ stat_results.results | rejectattr("stat.exists", "false") | map(attribute="stat.path") }}'
+  ansible.builtin.set_fact:
+    proxmox_lxc_filtered_files: '{{ stat_results.results | rejectattr("stat.exists", "false") | map(attribute="stat.path") }}' # noqa yaml[line-length]
 
 # https://gist.github.com/triangletodd/02f595cd4c0dc9aac5f7763ca2264185
 - name: Ensure lxc config has the right apparmor profile
-  lineinfile:
+  ansible.builtin.lineinfile:
     dest: "{{ item }}"
-    regexp: "^lxc.apparmor.profile"
+    regexp: ^lxc.apparmor.profile
     line: "lxc.apparmor.profile: unconfined"
   loop: "{{ proxmox_lxc_filtered_files }}"
   notify: reboot containers
 
 - name: Ensure lxc config has the right cgroup
-  lineinfile:
+  ansible.builtin.lineinfile:
     dest: "{{ item }}"
-    regexp: "^lxc.cgroup.devices.allow"
+    regexp: ^lxc.cgroup.devices.allow
     line: "lxc.cgroup.devices.allow: a"
   loop: "{{ proxmox_lxc_filtered_files }}"
   notify: reboot containers
 
 - name: Ensure lxc config has the right cap drop
-  lineinfile:
+  ansible.builtin.lineinfile:
     dest: "{{ item }}"
-    regexp: "^lxc.cap.drop"
+    regexp: ^lxc.cap.drop
     line: "lxc.cap.drop: "
   loop: "{{ proxmox_lxc_filtered_files }}"
   notify: reboot containers
 
 - name: Ensure lxc config has the right mounts
-  lineinfile:
+  ansible.builtin.lineinfile:
     dest: "{{ item }}"
-    regexp: "^lxc.mount.auto"
+    regexp: ^lxc.mount.auto
     line: 'lxc.mount.auto: "proc:rw sys:rw"'
   loop: "{{ proxmox_lxc_filtered_files }}"
   notify: reboot containers

roles/raspberrypi/handlers/main.yml

@@ -1,4 +1,5 @@
 ---
 - name: Reboot
-  reboot:
+  ansible.builtin.reboot:
+    reboot_command: "{{ custom_reboot_command | default(omit) }}"
   listen: reboot

roles/raspberrypi/meta/main.yml

@@ -0,0 +1,10 @@
+---
+argument_specs:
+  main:
+    short_description: Adjust some Raspberry Pi specific requisites
+    options:
+      state:
+        default: present
+        description:
+          - Indicates whether the k3s prerequisites for Raspberry Pi should be
+          - set up (possible values are `present` and `absent`)

roles/raspberrypi/tasks/main.yml

@@ -1,44 +1,51 @@
 ---
 - name: Test for raspberry pi /proc/cpuinfo
-  command: grep -E "Raspberry Pi|BCM2708|BCM2709|BCM2835|BCM2836" /proc/cpuinfo
+  ansible.builtin.command: grep -E "Raspberry Pi|BCM2708|BCM2709|BCM2835|BCM2836" /proc/cpuinfo
   register: grep_cpuinfo_raspberrypi
   failed_when: false
   changed_when: false
 
 - name: Test for raspberry pi /proc/device-tree/model
-  command: grep -E "Raspberry Pi" /proc/device-tree/model
+  ansible.builtin.command: grep -E "Raspberry Pi" /proc/device-tree/model
   register: grep_device_tree_model_raspberrypi
   failed_when: false
   changed_when: false
 
 - name: Set raspberry_pi fact to true
-  set_fact:
+  ansible.builtin.set_fact:
     raspberry_pi: true
-  when:
-    grep_cpuinfo_raspberrypi.rc == 0 or grep_device_tree_model_raspberrypi.rc == 0
+  when: grep_cpuinfo_raspberrypi.rc == 0 or grep_device_tree_model_raspberrypi.rc == 0
 
 - name: Set detected_distribution to Raspbian (ARM64 on Raspbian, Debian Buster/Bullseye/Bookworm)
-  set_fact:
+  ansible.builtin.set_fact:
     detected_distribution: Raspbian
   vars:
     allowed_descriptions:
       - "[Rr]aspbian.*"
-      - "Debian.*buster"
-      - "Debian.*bullseye"
-      - "Debian.*bookworm"
+      - 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 Bookworm)
+  ansible.builtin.set_fact:
+    detected_distribution: Raspbian
+  when:
+    - ansible_facts.architecture is search("aarch64")
+    - raspberry_pi|default(false)
+    - ansible_facts.lsb.description|default("") is match("Debian.*bookworm")
+
 - name: Set detected_distribution_major_version
-  set_fact:
+  ansible.builtin.set_fact:
     detected_distribution_major_version: "{{ ansible_facts.lsb.major_release }}"
   when:
     - detected_distribution | default("") == "Raspbian"
 
 - name: Execute OS related tasks on the Raspberry Pi - {{ action_ }}
-  include_tasks: "{{ item }}"
+  ansible.builtin.include_tasks: "{{ item }}"
   with_first_found:
     - "{{ action_ }}/{{ detected_distribution }}-{{ detected_distribution_major_version }}.yml"
     - "{{ action_ }}/{{ detected_distribution }}.yml"

roles/raspberrypi/tasks/setup/Raspbian.yml

@@ -1,19 +1,39 @@
 ---
+- name: Test for cmdline path
+  ansible.builtin.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
+  ansible.builtin.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
-    regexp: '^((?!.*\bcgroup_enable=cpuset cgroup_memory=1 cgroup_enable=memory\b).*)$'
-    line: '\1 cgroup_enable=cpuset cgroup_memory=1 cgroup_enable=memory'
+  ansible.builtin.lineinfile:
+    path: "{{ cmdline_path }}"
+    regexp: ^((?!.*\bcgroup_enable=cpuset cgroup_memory=1 cgroup_enable=memory\b).*)$
+    line: \1 cgroup_enable=cpuset cgroup_memory=1 cgroup_enable=memory
     backrefs: true
   notify: reboot
 
 - name: Install iptables
-  apt:
+  ansible.builtin.apt:
     name: iptables
     state: present
 
 - name: Flush iptables before changing to iptables-legacy
-  iptables:
+  ansible.builtin.iptables:
     flush: true
 
 - name: Changing to iptables-legacy

roles/raspberrypi/tasks/setup/Rocky.yml

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

roles/raspberrypi/tasks/setup/Ubuntu.yml

@@ -1,13 +1,14 @@
 ---
 - name: Enable cgroup via boot commandline if not already enabled for Ubuntu on a Raspberry Pi
-  lineinfile:
+  ansible.builtin.lineinfile:
     path: /boot/firmware/cmdline.txt
     backrefs: true
-    regexp: '^((?!.*\bcgroup_enable=cpuset cgroup_memory=1 cgroup_enable=memory\b).*)$'
-    line: '\1 cgroup_enable=cpuset cgroup_memory=1 cgroup_enable=memory'
+    regexp: ^((?!.*\bcgroup_enable=cpuset cgroup_memory=1 cgroup_enable=memory\b).*)$
+    line: \1 cgroup_enable=cpuset cgroup_memory=1 cgroup_enable=memory
   notify: reboot
 
 - name: Install linux-modules-extra-raspi
-  apt:
+  ansible.builtin.apt:
     name: linux-modules-extra-raspi
     state: present
+  when: ansible_distribution_version is version('24.04', '<')

roles/raspberrypi/tasks/teardown/Ubuntu.yml

@@ -1,5 +1,6 @@
 ---
 - name: Remove linux-modules-extra-raspi
-  apt:
+  ansible.builtin.apt:
     name: linux-modules-extra-raspi
     state: absent
+  when: ansible_distribution_version is version('24.04', '<')

roles/reset/defaults/main.yml

@@ -0,0 +1,2 @@
+---
+systemd_dir: /etc/systemd/system

roles/reset/meta/main.yml

@@ -0,0 +1,8 @@
+---
+argument_specs:
+  main:
+    short_description: Reset all nodes
+    options:
+      systemd_dir:
+        description: Path to systemd services
+        default: /etc/systemd/system

roles/reset/tasks/main.yml

@@ -1,6 +1,6 @@
 ---
 - name: Disable services
-  systemd:
+  ansible.builtin.systemd:
     name: "{{ item }}"
     state: stopped
     enabled: false
@@ -12,12 +12,12 @@
 
 - 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"
+  ansible.builtin.command: pkill -9 -f "k3s/data/[^/]+/bin/containerd-shim-runc"
+  changed_when: pkill_containerd_shim_runc.rc == 0
   failed_when: false
 
 - name: Umount k3s filesystems
-  include_tasks: umount_with_children.yml
+  ansible.builtin.include_tasks: umount_with_children.yml
   with_items:
     - /run/k3s
     - /var/lib/kubelet
@@ -30,7 +30,7 @@
     loop_var: mounted_fs
 
 - name: Remove service files, binaries and data
-  file:
+  ansible.builtin.file:
     name: "{{ item }}"
     state: absent
   with_items:
@@ -45,9 +45,10 @@
     - /var/lib/rancher/k3s
     - /var/lib/rancher/
     - /var/lib/cni/
+    - /etc/cni/net.d
 
 - name: Remove K3s http_proxy files
-  file:
+  ansible.builtin.file:
     name: "{{ item }}"
     state: absent
   with_items:
@@ -58,22 +59,22 @@
   when: proxy_env is defined
 
 - name: Reload daemon_reload
-  systemd:
+  ansible.builtin.systemd:
     daemon_reload: true
 
 - name: Remove tmp directory used for manifests
-  file:
+  ansible.builtin.file:
     path: /tmp/k3s
     state: absent
 
 - name: Check if rc.local exists
-  stat:
+  ansible.builtin.stat:
     path: /etc/rc.local
   register: rcfile
 
 - name: Remove rc.local modifications for proxmox lxc containers
   become: true
-  blockinfile:
+  ansible.builtin.blockinfile:
     path: /etc/rc.local
     content: "{{ lookup('template', 'templates/rc.local.j2') }}"
     create: false
@@ -82,14 +83,14 @@
 
 - name: Check rc.local for cleanup
   become: true
-  slurp:
+  ansible.builtin.slurp:
     src: /etc/rc.local
   register: rcslurp
   when: proxmox_lxc_configure and rcfile.stat.exists
 
 - name: Cleanup rc.local if we only have a Shebang line
   become: true
-  file:
+  ansible.builtin.file:
     path: /etc/rc.local
     state: absent
   when: proxmox_lxc_configure and rcfile.stat.exists and ((rcslurp.content | b64decode).splitlines() | length) <= 1

roles/reset/tasks/umount_with_children.yml

@@ -1,6 +1,6 @@
 ---
 - name: Get the list of mounted filesystems
-  shell: set -o pipefail && cat /proc/mounts | awk '{ print $2}' | grep -E "^{{ mounted_fs }}"
+  ansible.builtin.shell: set -o pipefail && cat /proc/mounts | awk '{ print $2}' | grep -E "^{{ mounted_fs }}"
   register: get_mounted_filesystems
   args:
     executable: /bin/bash
@@ -12,5 +12,4 @@
   ansible.posix.mount:
     path: "{{ item }}"
     state: unmounted
-  with_items:
-    "{{ get_mounted_filesystems.stdout_lines | reverse | list }}"
+  with_items: "{{ get_mounted_filesystems.stdout_lines | reverse | list }}"

roles/reset_proxmox_lxc/meta/main.yml

@@ -0,0 +1,9 @@
+---
+argument_specs:
+  main:
+    short_description: Proxmox LXC settings
+    options:
+      proxmox_lxc_ct_ids:
+        description: Proxmox container ID list
+        type: list
+        required: true

roles/reset_proxmox_lxc/tasks/main.yml

@@ -1,46 +1,45 @@
 ---
 - name: Check for container files that exist on this host
-  stat:
-    path: "/etc/pve/lxc/{{ item }}.conf"
+  ansible.builtin.stat:
+    path: /etc/pve/lxc/{{ item }}.conf
   loop: "{{ proxmox_lxc_ct_ids }}"
   register: stat_results
 
 - name: Filter out files that do not exist
-  set_fact:
-    proxmox_lxc_filtered_files:
-      '{{ stat_results.results | rejectattr("stat.exists", "false") | map(attribute="stat.path") }}'
+  ansible.builtin.set_fact:
+    proxmox_lxc_filtered_files: '{{ stat_results.results | rejectattr("stat.exists", "false") | map(attribute="stat.path") }}' # noqa yaml[line-length]
 
 - name: Remove LXC apparmor profile
-  lineinfile:
+  ansible.builtin.lineinfile:
     dest: "{{ item }}"
-    regexp: "^lxc.apparmor.profile"
+    regexp: ^lxc.apparmor.profile
     line: "lxc.apparmor.profile: unconfined"
     state: absent
   loop: "{{ proxmox_lxc_filtered_files }}"
   notify: reboot containers
 
 - name: Remove lxc cgroups
-  lineinfile:
+  ansible.builtin.lineinfile:
     dest: "{{ item }}"
-    regexp: "^lxc.cgroup.devices.allow"
+    regexp: ^lxc.cgroup.devices.allow
     line: "lxc.cgroup.devices.allow: a"
     state: absent
   loop: "{{ proxmox_lxc_filtered_files }}"
   notify: reboot containers
 
 - name: Remove lxc cap drop
-  lineinfile:
+  ansible.builtin.lineinfile:
     dest: "{{ item }}"
-    regexp: "^lxc.cap.drop"
+    regexp: ^lxc.cap.drop
     line: "lxc.cap.drop: "
     state: absent
   loop: "{{ proxmox_lxc_filtered_files }}"
   notify: reboot containers
 
 - name: Remove lxc mounts
-  lineinfile:
+  ansible.builtin.lineinfile:
     dest: "{{ item }}"
-    regexp: "^lxc.mount.auto"
+    regexp: ^lxc.mount.auto
     line: 'lxc.mount.auto: "proc:rw sys:rw"'
     state: absent
   loop: "{{ proxmox_lxc_filtered_files }}"

site.yml

@@ -1,4 +1,13 @@
 ---
+- 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)
+      ansible.builtin.assert:
+        that: ansible_version.full is version_compare('2.11', '>=')
+        msg: >
+          "Ansible is out of date. See here for more info: https://docs.technotim.com/posts/ansible-automation/"
+
 - name: Prepare Proxmox cluster
   hosts: proxmox
   gather_facts: true
@@ -46,3 +55,14 @@
   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']