fix(k3s-server): stabilize single-server bootstrap

- delegate cgroups for transient K3s server units\n- verify inventory node registration without legacy role labels\n- wait for bootstrap CRDs before replacing the transient service

.ansible-lint

@@ -3,6 +3,7 @@ profile: production
 exclude_paths:
   # default paths
   - .cache/
+  - .ansible/
   - .github/
   - test/fixtures/formatting-before/
   - test/fixtures/formatting-prettier/
@@ -19,3 +20,8 @@ exclude_paths:
 
 skip_list:
   - 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/actionlint.yaml

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

.github/download-boxes.sh

@@ -1,42 +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}"
 
-yq --version
+MOLECULE_YML_PATH=("${GIT_ROOT}"/molecule/*/molecule.yml)
 
-# Define the path to the molecule.yml files
-MOLECULE_YML_PATH="${GIT_ROOT}/molecule/*/molecule.yml"
-
-# Extract and sort unique boxes from all molecule.yml files
-all_boxes=$(for file in $MOLECULE_YML_PATH; do
-    yq eval '.platforms[].box' "$file"
+# 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)
 
-echo all_boxes: "$all_boxes"
+if [[ ! -r "$LOCK_FILE" ]]; then
+    printf 'Vagrant box lock file is missing or unreadable: %s\n' "$LOCK_FILE" >&2
+    exit 1
+fi
 
-# Read the boxes that are currently present on the system (for the current provider)
+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 +1,210 @@
+#!/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' "$version"
+    printf '%s\n' \
+      '  config.vm.synced_folder ".", "/vagrant", disabled: true' \
+      '  config.vm.hostname = "k3s-ansible-box-prewarm"' \
+      '  config.vm.provider "virtualbox" do |virtualbox|' \
+      '    virtualbox.linked_clone = true' \
+      '    virtualbox.memory = 512' \
+      '    virtualbox.cpus = 1' \
+      '  end' \
+      'end'
+  } > "$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 +1,27 @@
+#!/usr/bin/env bash
+
+set -Eeuo pipefail
+
+printf '%s\n' "$*" >> "$MOCK_VAGRANT_LOG"
+case "${1:-}" in
+  up)
+    counter_file="$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 +1,81 @@
+#!/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="$fixture/vagrant.log"
+: > "$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" > "$first_output"
+mapping_file="$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@11bd71901bbe5b1630ceea73d27597364c9af683 # 4.2.2
+        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@0b93645e9fea7318ecaed2b359559ac225c90a2b # 5.3.0
+        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@6849a6489940f00c2f30c0fb92c6274307ccb58a # 4.1.2
+        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

@@ -5,6 +5,8 @@ on:
     types:
       - opened
       - synchronize
+      - reopened
+      - ready_for_review
     paths-ignore:
       - '**/.gitignore'
       - '**/FUNDING.yml'
@@ -16,12 +18,21 @@ on:
       - '**/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@11bd71901bbe5b1630ceea73d27597364c9af683 # 4.2.2
+        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@0b93645e9fea7318ecaed2b359559ac225c90a2b # 5.3.0
+        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@6849a6489940f00c2f30c0fb92c6274307ccb58a # 4.1.2
+        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@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@11bd71901bbe5b1630ceea73d27597364c9af683 # 4.2.2
+        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # 7.0.1
       - name: Ensure SHA pinned actions
-        uses: zgosalvez/github-actions-ensure-sha-pinned-actions@38608ef4fb69adae7f1eac6eeb88e67b7d083bfd # 3.0.16
+        uses: zgosalvez/github-actions-ensure-sha-pinned-actions@3db98c0363e2fa5df3e1c4c471777a7c10b24cc9 # 5.0.5
         with:
           allowlist: |
             aws-actions/

.github/workflows/test.yml

@@ -5,72 +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
           - calico
           - cilium
           - kube-vip
-      fail-fast: false
+          # - 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@11bd71901bbe5b1630ceea73d27597364c9af683 # 4.2.2
+        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # 7.0.1
         with:
-          ref: ${{ github.event.pull_request.head.sha }}
+          ref: ${{ github.event.pull_request.head.sha || github.sha }}
 
-      # these steps are necessary if not using ephemeral nodes
-      - name: Delete old Vagrant box versions
-        if: always() # do this even if a step before has failed
-        run: vagrant box prune --force
+      - name: Clean repository-owned resources before testing
+        run: ./.github/scripts/cleanup-runner-resources.sh --apply
 
-      - name: Remove all local Vagrant boxes
-        if: always() # do this even if a step before has failed
-        run: if vagrant box list 2>/dev/null; then vagrant box list | cut -f 1 -d ' ' | xargs -L 1 vagrant box remove -f 2>/dev/null && echo "All Vagrant boxes removed." || echo "No Vagrant boxes found."; else echo "No Vagrant boxes found."; fi
+      - name: Record host-only network baseline
+        run: ./.github/scripts/cleanup-runner-resources.sh --snapshot
 
-      - name: Remove all Virtualbox VMs
-        if: always() # do this even if a step before has failed
-        run: VBoxManage list vms | awk -F'"' '{print $2}' | xargs -I {} VBoxManage unregistervm --delete "{}"
-
-      - name: Remove all Virtualbox HDs
-        if: always() # do this even if a step before has failed
-        run: VBoxManage list hdds | awk -F':' '/^UUID:/ {print $2}' | xargs -I {} VBoxManage closemedium disk "{}" --delete
-
-      - name: Remove all Virtualbox Networks
-        if: always() # do this even if a step before has failed
-        run: VBoxManage list hostonlyifs | grep '^Name:' | awk '{print $2}' | grep '^vboxnet' | xargs -I {} VBoxManage hostonlyif remove {}
-
-      - name: Remove Virtualbox network config
-        if: always() # do this even if a step before has failed
-        run: sudo rm /etc/vbox/networks.conf || true
-
-      - name: Configure VirtualBox
-        run: |-
-          sudo mkdir -p /etc/vbox
-          cat <<EOF | sudo tee -a /etc/vbox/networks.conf > /dev/null
-          * 192.168.30.0/24
-          * fdad:bad:ba55::/64
-          EOF
+      - name: Check nested VirtualBox platform
+        run: |
+          set -Eeuo pipefail
+          grep -Eq 'vmx|svm' /proc/cpuinfo
+          test -c /dev/kvm
+          test -c /dev/vboxdrv
+          VBoxManage --version
+          vagrant --version
+          test -r /etc/vbox/networks.conf
+          test "$(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@0b93645e9fea7318ecaed2b359559ac225c90a2b # 5.3.0
+        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@6849a6489940f00c2f30c0fb92c6274307ccb58a # 4.1.2
+        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"
@@ -82,7 +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 }}
@@ -90,37 +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: if vagrant box list 2>/dev/null; then vagrant box list | cut -f 1 -d ' ' | xargs -L 1 vagrant box remove -f 2>/dev/null && echo "All Vagrant boxes removed." || echo "No Vagrant boxes found."; else echo "No Vagrant boxes found."; fi
-
-      - name: Remove all Virtualbox VMs
-        if: always() # do this even if a step before has failed
-        run: VBoxManage list vms | awk -F'"' '{print $2}' | xargs -I {} VBoxManage unregistervm --delete "{}"
-
-      - name: Remove all Virtualbox HDs
-        if: always() # do this even if a step before has failed
-        run: VBoxManage list hdds | awk -F':' '/^UUID:/ {print $2}' | xargs -I {} VBoxManage closemedium disk "{}" --delete
-
-      - name: Remove all Virtualbox Networks
-        if: always() # do this even if a step before has failed
-        run: VBoxManage list hostonlyifs | grep '^Name:' | awk '{print $2}' | grep '^vboxnet' | xargs -I {} VBoxManage hostonlyif remove {}
-
-      - name: Remove Virtualbox network config
-        if: always() # do this even if a step before has failed
-        run: sudo rm /etc/vbox/networks.conf || true
+      - name: 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@b4b15b8c7c6ac21ea08fcf65892d2ee8f75cf882 # 4.4.3
+        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
-          overwrite: true
+          if-no-files-found: warn
+          retention-days: 14

.gitignore

@@ -1,4 +1,6 @@
 .env/
 *.log
 ansible.cfg
+.ansible/
 kubeconfig
+zIgnore/

.pre-commit-config.yaml

@@ -20,6 +20,9 @@ repos:
     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: v0.9.0.6
     hooks:
@@ -33,3 +36,29 @@ repos:
     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$|^\.github/scripts/test-k3s-server-bootstrap\.sh$

molecule/calico/overrides.yml

@@ -7,6 +7,7 @@
         # 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

molecule/cilium/overrides.yml

@@ -7,6 +7,7 @@
         # 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

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

@@ -3,6 +3,9 @@ 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
@@ -11,6 +14,10 @@ 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
@@ -27,6 +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
@@ -38,6 +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
@@ -49,6 +60,8 @@ 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
@@ -65,6 +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
@@ -74,6 +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/kube-vip/overrides.yml

@@ -7,6 +7,7 @@
         # 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

molecule/single_node/overrides.yml

@@ -7,6 +7,7 @@
         # 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

roles/download/tasks/main.yml

@@ -7,6 +7,10 @@
     owner: root
     group: root
     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
@@ -17,6 +21,10 @@
     owner: root
     group: root
     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")
@@ -29,6 +37,10 @@
     owner: root
     group: root
     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_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
@@ -25,4 +125,56 @@
     dest: "{{ log_destination }}/k3s-init@{{ ansible_hostname }}.log"
     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/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/main.yml

@@ -34,21 +34,86 @@
   tags: kubevip
   when: kube_vip_lb_ip_range is defined
 
-- name: Init cluster inside the transient k3s-init service
-  ansible.builtin.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: 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)
+    - 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: "{{ k3s_kubectl_binary | default('k3s kubectl') }} get nodes -l 'node-role.kubernetes.io/master=true' -o=jsonpath='{.items[*].metadata.name}'" # yamllint disable-line rule:line-length
-      register: nodes
-      until: nodes.rc == 0 and (nodes.stdout.split() | length) == (groups[group_name_master | default('master')] | length) # yamllint disable-line rule:line-length
+            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