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

@@ -15,10 +15,6 @@ exclude_paths:
   - molecule/**/prepare.yml
   - molecule/**/reset.yml
 
-  # Scenario verify inputs are plain variable files, not playbooks. They are
-  # loaded as vars, not executed, so ansible-lint must not treat them as plays.
-  - molecule/**/verify-vars.yml
-
   # The file was generated by galaxy ansible - don't mess with it.
   - galaxy.yml
 

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

@@ -73,11 +73,10 @@ write_prewarm_vagrantfile() {
     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' \
+      '    virtualbox.memory = 512' \
+      '    virtualbox.cpus = 1' \
       '  end' \
       'end'
   } > "$destination"

.github/scripts/test-cilium-bgp-manifest.py

@@ -1,134 +0,0 @@
-#!/usr/bin/env python3
-"""Render the Cilium BGP CRD template and assert it uses the v2 API.
-
-This is a manifest-only regression test used where no real BGP peer is
-available. It renders roles/k3s_server_post/templates/cilium.crs.j2 with
-zero, one, and multiple neighbors, then checks that the output:
-  - never contains CiliumBGPPeeringPolicy or cilium.io/v2alpha1
-  - emits the Cilium v2 BGP resources
-  - emits deterministic DNS-safe peer and instance names
-  - advertises Pod CIDRs only when cilium_exportPodCIDR is true
-"""
-
-from __future__ import print_function
-
-import os
-import subprocess
-
-from jinja2 import Environment, FileSystemLoader, StrictUndefined
-
-
-def repo_root():
-    return subprocess.check_output(
-        ["git", "rev-parse", "--show-toplevel"], text=True
-    ).strip()
-
-
-def fail(message):
-    raise SystemExit("Cilium BGP manifest test failed: " + message)
-
-
-def render(env, extra_vars):
-    base_vars = {
-        "cilium_bgp_my_asn": "64513",
-        "cilium_bgp_peer_asn": "64512",
-        "cilium_bgp_peer_address": "192.168.30.1",
-        "cilium_exportPodCIDR": True,
-        "cilium_bgp_lb_cidr": "192.168.31.0/24",
-    }
-    base_vars.update(extra_vars)
-    template = env.get_template("cilium.crs.j2")
-    return template.render(**base_vars)
-
-
-def check_common(output):
-    if "cilium.io/v2alpha1" in output:
-        fail("rendered output still contains cilium.io/v2alpha1")
-    if "kind: CiliumBGPPeeringPolicy" in output:
-        fail("rendered output still contains CiliumBGPPeeringPolicy")
-    for kind in (
-        "CiliumBGPPeerConfig",
-        "CiliumBGPClusterConfig",
-        "CiliumBGPAdvertisement",
-        "CiliumLoadBalancerIPPool",
-    ):
-        if ("kind: " + kind) not in output:
-            fail("rendered output is missing kind: " + kind)
-
-
-def main():
-    root = repo_root()
-    template_dir = os.path.join(
-        root, "roles", "k3s_server_post", "templates"
-    )
-    env = Environment(
-        loader=FileSystemLoader(template_dir), undefined=StrictUndefined
-    )
-
-    # Zero neighbors -> fall back to the single default peer.
-    output = render(env, {"_cilium_bgp_neighbors": []})
-    check_common(output)
-    if "peer-64512-1" not in output:
-        fail("default single peer name was not rendered")
-    if "peerAddress: 192.168.30.1" not in output:
-        fail("default peer address was not rendered")
-    if 'advertisementType: "PodCIDR"' not in output:
-        fail("PodCIDR advertisement missing when exportPodCIDR is true")
-
-    # One neighbor via the merged list.
-    output = render(
-        env,
-        {"_cilium_bgp_neighbors": [{"peer_address": "10.0.0.1", "peer_asn": "65001"}]},
-    )
-    check_common(output)
-    if "peer-65001-1" not in output:
-        fail("single merged peer name was not rendered")
-    if "peerAddress: 10.0.0.1" not in output:
-        fail("single merged peer address was not rendered")
-
-    # Multiple neighbors.
-    output = render(
-        env,
-        {
-            "_cilium_bgp_neighbors": [
-                {"peer_address": "10.0.0.1", "peer_asn": "65001"},
-                {"peer_address": "10.0.0.2", "peer_asn": "65002"},
-            ]
-        },
-    )
-    check_common(output)
-    if "peer-65001-1" not in output or "peer-65002-2" not in output:
-        fail("multiple merged peer names were not rendered")
-    if "peerAddress: 10.0.0.2" not in output:
-        fail("second merged peer address was not rendered")
-
-    # exportPodCIDR false -> no PodCIDR advertisement, service remains.
-    output = render(
-        env, {"_cilium_bgp_neighbors": [], "cilium_exportPodCIDR": False}
-    )
-    check_common(output)
-    if 'advertisementType: "PodCIDR"' in output:
-        fail("PodCIDR advertisement present when exportPodCIDR is false")
-    if 'advertisementType: "Service"' not in output:
-        fail("Service advertisement missing when exportPodCIDR is false")
-
-    # Load balancer pools: CIDR and start/stop forms.
-    output = render(env, {"_cilium_bgp_neighbors": []})
-    if "cidr: 192.168.31.0/24" not in output:
-        fail("CIDR load balancer pool was not rendered")
-    output = render(
-        env,
-        {
-            "_cilium_bgp_neighbors": [],
-            "cilium_bgp_lb_cidr": "192.168.31.80-192.168.31.90",
-        },
-    )
-    check_common(output)
-    if "start: 192.168.31.80" not in output or "stop: 192.168.31.90" not in output:
-        fail("start/stop load balancer pool was not rendered")
-
-    print("Cilium BGP manifest regression test passed")
-
-
-if __name__ == "__main__":
-    main()

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

@@ -5,9 +5,6 @@ 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")"

.github/scripts/test-kube-vip-manifest.py

@@ -1,130 +0,0 @@
-#!/usr/bin/env python3
-"""Render the kube-vip DaemonSet template and assert env key correctness.
-
-kube-vip v1.2.2 reads `bgp_peers` and `vip_subnet`; it ignores the older
-`bgppeers` and `vip_cidr` names. This test proves the rendered manifest uses
-the keys the target image actually parses.
-"""
-
-from __future__ import print_function
-
-import os
-import subprocess
-
-from jinja2 import Environment, FileSystemLoader, StrictUndefined
-
-
-def repo_root():
-    return subprocess.check_output(
-        ["git", "rev-parse", "--show-toplevel"], text=True
-    ).strip()
-
-
-def fail(message):
-    raise SystemExit("kube-vip manifest test failed: " + message)
-
-
-def fake_ipsubnet(value):
-    # ansible.utils.ipsubnet -> network of the address as x.y.z.0/24
-    parts = value.split(".")
-    return ".".join(parts[:3]) + ".0/24"
-
-
-def fake_ipaddr(_value, expr=None):
-    # ansible.utils.ipaddr('prefix') -> prefix length
-    return "24"
-
-
-def fake_bool(value):
-    # Minimal stand-in for Ansible's truthiness filter used by the template.
-    if isinstance(value, bool):
-        return value
-    return str(value).lower() in ("1", "true", "yes", "on")
-
-
-def fake_map(seq, *args, **kwargs):
-    # Minimal stand-in for Ansible's map() filter in the two forms used by the
-    # template: map(attribute='x') on a list of dicts, and map('join', sep) on
-    # a list of sequences.
-    if "attribute" in kwargs:
-        return [item[kwargs["attribute"]] for item in seq]
-    if kwargs:
-        # e.g. map(default='x') not used here; ignore unknown kwargs.
-        return list(seq)
-    if args:
-        filter_name = args[0]
-        sep = args[1] if len(args) > 1 else ""
-        if filter_name == "join":
-            return [sep.join(str(x) for x in item) for item in seq]
-    return list(seq)
-
-
-def fake_zip(*seqs):
-    return list(zip(*seqs))
-
-
-def render(env, extra_vars):
-    base_vars = {
-        "apiserver_endpoint": "192.168.30.222",
-        "kube_vip_iface": "",
-        "kube_vip_arp": True,
-        "kube_vip_bgp": True,
-        "kube_vip_bgp_routerid": "127.0.0.1",
-        "_kube_vip_bgp_peers": [
-            {"peer_address": "192.168.30.1", "peer_asn": "64512"},
-            {"peer_address": "192.168.30.2", "peer_asn": "64513"},
-        ],
-        "kube_vip_tag_version": "v1.2.2",
-    }
-    base_vars.update(extra_vars)
-    template = env.get_template("vip.yaml.j2")
-    return template.render(**base_vars)
-
-
-def main():
-    root = repo_root()
-    template_dir = os.path.join(root, "roles", "k3s_server", "templates")
-    env = Environment(
-        loader=FileSystemLoader(template_dir), undefined=StrictUndefined
-    )
-    env.filters["ansible.utils.ipsubnet"] = fake_ipsubnet
-    env.filters["ansible.utils.ipaddr"] = fake_ipaddr
-    env.filters["bool"] = fake_bool
-    env.filters["map"] = fake_map
-    env.filters["zip"] = fake_zip
-
-    # Multi-peer BGP armed: must emit bgp_peers, never bgppeers.
-    output = render(env, {})
-    if "name: bgp_peers" not in output:
-        fail("rendered manifest is missing bgp_peers")
-    if "name: bgppeers" in output:
-        fail("rendered manifest still uses the ignored bgppeers key")
-    if "name: vip_subnet" not in output:
-        fail("rendered manifest is missing vip_subnet")
-    if "name: vip_cidr" in output:
-        fail("rendered manifest still uses the ignored vip_cidr key")
-    if "192.168.30.1:64512,192.168.30.2:64513" not in output:
-        fail("bgp_peers value is not comma-separated address:ASN entries")
-    if "ghcr.io/kube-vip/kube-vip:v1.2.2" not in output:
-        fail("kube-vip image tag is not v1.2.2")
-
-    # BGP enabled with no merged peers: single-peer fallback vars, no bgp_peers.
-    output = render(
-        env,
-        {
-            "_kube_vip_bgp_peers": [],
-            "kube_vip_bgp_as": "64513",
-            "kube_vip_bgp_peeraddress": "192.168.30.1",
-            "kube_vip_bgp_peeras": "64512",
-        },
-    )
-    if "name: bgp_as" not in output:
-        fail("single-peer bgp_as was not rendered")
-    if "name: bgp_peers" in output:
-        fail("bgp_peers present even though the peer list is empty")
-
-    print("kube-vip manifest regression test passed")
-
-
-if __name__ == "__main__":
-    main()

.github/scripts/test-metallb-remote-read.sh

@@ -1,29 +0,0 @@
-#!/usr/bin/env bash
-
-set -Eeuo pipefail
-
-repo_root="$(git rev-parse --show-toplevel)"
-metallb_task="$repo_root/roles/k3s_server/tasks/metallb.yml"
-
-# The speaker tag verification must read the rendered manifest on the managed
-# host with slurp. A controller-side lookup('ansible.builtin.file', ...) would
-# read from the Ansible control node, which does not have the file, and would
-# fail on every MetalLB scenario.
-grep -Fq -- 'ansible.builtin.slurp' "$metallb_task" || {
-  printf 'MetalLB speaker tag check does not use slurp on the managed host\n' >&2
-  exit 1
-}
-
-grep -Eq -- 'lookup\(.?ansible\.builtin\.file' "$metallb_task" && {
-  printf 'MetalLB speaker tag check uses a controller-side file lookup\n' >&2
-  exit 1
-}
-
-# The check must reference the full image reference, not just a bare version
-# string that could appear anywhere in the manifest.
-grep -Fq -- 'quay.io/metallb/speaker:' "$metallb_task" || {
-  printf 'MetalLB speaker tag check does not match the full image reference\n' >&2
-  exit 1
-}
-
-printf 'MetalLB remote manifest read regression test passed\n'

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

@@ -10,12 +10,12 @@ mock_bin="$fixture/bin"
 mock_state="$fixture/state"
 mock_home="$fixture/home"
 mock_vagrant_home="$fixture/vagrant-home"
-mock_box_dir="$mock_vagrant_home/boxes/bento-VAGRANTSLASH-ubuntu-26.04/202606.01.0/amd64/virtualbox"
+mock_box_dir="$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" "$mock_vbox_root"
-printf '%s\n' 'bento/ubuntu-26.04 202606.01.0 amd64' > "$lock_file"
+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" "$mock_bin/flock"
@@ -32,7 +32,6 @@ export MOCK_VBOX_ROOT="$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"
 
@@ -45,14 +44,7 @@ second_output="$fixture/second-output"
 third_output="$fixture/third-output"
 
 "$script" > "$first_output"
-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="$mock_master_root/bento_ubuntu-26.04-202606.01.0-amd64.uuid"
+mapping_file="$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"

.github/test-download-boxes.sh

@@ -17,29 +17,23 @@ trap 'rm -rf "$test_root"' EXIT
 printf '%s\n' \
     '#!/usr/bin/env bash' \
     'set -Eeuo pipefail' \
-    'printf "%s\n" bento/debian-13 bento/rockylinux-10.1 bento/ubuntu-26.04' \
+    'printf "%s\n" generic/debian12 generic/rocky9 generic/ubuntu2204' \
     >"$fake_bin/yq"
 
 printf '%s\n' \
     '#!/usr/bin/env bash' \
     'set -Eeuo pipefail' \
     'emit_box() {' \
-    '    case "$1" in' \
-    '        bento/debian-13) version=202510.26.0 ;;' \
-    '        bento/rockylinux-10.1) version=202512.01.0 ;;' \
-    '        bento/ubuntu-26.04) version=202606.01.0 ;;' \
-    '        *) printf "Unexpected box: %s\n" "$1" >&2; exit 1 ;;' \
-    '    esac' \
     '    printf "0,,box-name,%s\n" "$1"' \
     '    printf "0,,box-provider,virtualbox\n"' \
-    '    printf "0,,box-version,%s\n" "$version"' \
+    '    printf "0,,box-version,4.3.12\n"' \
     '    printf "0,,box-architecture,amd64\n"' \
     '}' \
     'if [[ "${1:-}" == box && "${2:-}" == list ]]; then' \
-    '    emit_box bento/debian-13' \
-    '    emit_box bento/rockylinux-10.1' \
+    '    emit_box generic/debian12' \
+    '    emit_box generic/rocky9' \
     '    if [[ "${FAKE_PRESENT_MODE:-all}" == all ]]; then' \
-    '        emit_box bento/ubuntu-26.04' \
+    '        emit_box generic/ubuntu2204' \
     '    fi' \
     'elif [[ "${1:-}" == box && "${2:-}" == add ]]; then' \
     '    printf "%s\n" "$*" >>"${FAKE_VAGRANT_LOG:?}"' \
@@ -61,13 +55,13 @@ PATH="$fake_bin:$PATH" \
     FAKE_VAGRANT_LOG="$fake_log" \
     "$repo_root/.github/download-boxes.sh" >"$output"
 grep -Fxq \
-    'box add --provider virtualbox --box-version 202606.01.0 --architecture amd64 bento/ubuntu-26.04' \
+    'box add --provider virtualbox --box-version 4.3.12 --architecture amd64 generic/ubuntu2204' \
     "$fake_log"
 
 incomplete_lock="$test_root/incomplete.lock"
 printf '%s\n' \
-    'bento/debian-13 202510.26.0 amd64' \
-    'bento/rockylinux-10.1 202512.01.0 amd64' \
+    'generic/debian12 4.3.12 amd64' \
+    'generic/rocky9 4.3.12 amd64' \
     >"$incomplete_lock"
 if PATH="$fake_bin:$PATH" \
     VAGRANT_BOX_LOCK_FILE="$incomplete_lock" \
@@ -77,14 +71,14 @@ if PATH="$fake_bin:$PATH" \
     exit 1
 fi
 grep -Fq 'Scenario boxes missing from the lock file:' "$output"
-grep -Fq 'bento/ubuntu-26.04' "$output"
+grep -Fq 'generic/ubuntu2204' "$output"
 
 duplicate_lock="$test_root/duplicate.lock"
 printf '%s\n' \
-    'bento/debian-13 202510.26.0 amd64' \
-    'bento/debian-13 202508.10.0 amd64' \
-    'bento/rockylinux-10.1 202512.01.0 amd64' \
-    'bento/ubuntu-26.04 202606.01.0 amd64' \
+    'generic/debian12 4.3.12 amd64' \
+    'generic/debian12 4.3.11 amd64' \
+    'generic/rocky9 4.3.12 amd64' \
+    'generic/ubuntu2204 4.3.12 amd64' \
     >"$duplicate_lock"
 if PATH="$fake_bin:$PATH" \
     VAGRANT_BOX_LOCK_FILE="$duplicate_lock" \

.github/vagrant-boxes.lock

@@ -1,4 +1,4 @@
 # box version architecture
-bento/debian-13 202510.26.0 amd64
-bento/rockylinux-10.1 202512.01.0 amd64
-bento/ubuntu-26.04 202606.01.0 amd64
+generic/debian12 4.3.12 amd64
+generic/rocky9 4.3.12 amd64
+generic/ubuntu2204 4.3.12 amd64

.github/workflows/ci.yml

@@ -2,8 +2,6 @@
 name: "CI"
 on:
   pull_request:
-    branches:
-      - master
     types:
       - opened
       - synchronize

.github/workflows/test.yml

@@ -88,7 +88,7 @@ jobs:
           trap stop_monitor EXIT
           /usr/bin/time -v -o "$timing_file" \
             molecule test --scenario-name ${{ matrix.scenario }}
-        timeout-minutes: 150
+        timeout-minutes: 90
         env:
           ANSIBLE_K3S_LOG_DIR: ${{ runner.temp }}/logs/k3s-ansible/${{ matrix.scenario }}
           ANSIBLE_SSH_RETRIES: 4

.pre-commit-config.yaml

@@ -62,25 +62,3 @@ repos:
         language: system
         pass_filenames: false
         files: ^roles/k3s_server/tasks/(main|join_master)\.yml$|^\.github/scripts/test-k3s-server-bootstrap\.sh$
-      - id: cilium-bgp-manifest-test
-        name: Cilium BGP manifest test
-        entry: python3 .github/scripts/test-cilium-bgp-manifest.py
-        language: python
-        additional_dependencies:
-          - Jinja2>=3.1
-        pass_filenames: false
-        files: ^roles/k3s_server_post/templates/cilium\.crs\.j2$|^\.github/scripts/test-cilium-bgp-manifest\.py$
-      - id: kube-vip-manifest-test
-        name: kube-vip manifest test
-        entry: python3 .github/scripts/test-kube-vip-manifest.py
-        language: python
-        additional_dependencies:
-          - Jinja2>=3.1
-        pass_filenames: false
-        files: ^roles/k3s_server/templates/vip\.yaml\.j2$|^\.github/scripts/test-kube-vip-manifest\.py$
-      - id: metallb-remote-read-test
-        name: MetalLB remote read test
-        entry: .github/scripts/test-metallb-remote-read.sh
-        language: system
-        pass_filenames: false
-        files: ^roles/k3s_server/tasks/metallb\.yml$|^\.github/scripts/test-metallb-remote-read\.sh$

README.md

@@ -16,9 +16,9 @@ If you want more context on how this works, see:
 
 Build a Kubernetes cluster using Ansible with k3s. The goal is easily install a HA Kubernetes cluster on machines running:
 
-- [x] Debian (tested on version 13)
-- [x] Ubuntu (tested on version 26.04 LTS)
-- [x] Rocky (tested on version 10)
+- [x] Debian (tested on version 11)
+- [x] Ubuntu (tested on version 22.04)
+- [x] Rocky (tested on version 9)
 
 on processor architecture:
 
@@ -91,32 +91,6 @@ ansible-playbook reset.yml -i inventory/my-cluster/hosts.ini
 
 >You should also reboot these nodes due to the VIP not being destroyed
 
-## 🔁 Upgrading an existing cluster
-
-These version variables select the components used for a **fresh** installation.
-They are not a supported direct in-place upgrade path for an existing cluster.
-K3s, Calico, and Cilium each require staged upgrades for long-lived clusters.
-
-- **K3s**: do not jump an embedded-etcd cluster straight to Kubernetes 1.36.
-  Upgrade one Kubernetes minor version at a time. From the sample default
-  (`v1.30.2+k3s2`) the sequence is: the latest supported 1.30 patch, then 1.31,
-  1.32, a 1.33 patch that contains etcd 3.5.26 (for example `v1.33.7+k3s3`),
-  then 1.34, 1.35, and finally 1.36. Upgrade servers one at a time before
-  agents. Take backups and confirm cluster health at each step; this playbook
-  does not automate the upgrade, so those remain manual operational steps. See
-  [K3s manual upgrades](https://docs.k3s.io/upgrades/manual) and the
-  [v1.34 release notes](https://docs.k3s.io/release-notes/v1.34.X).
-- **Cilium**: upstream supports only consecutive minor upgrades. Update to the
-  latest patch of the current minor, then upgrade 1.17, 1.18, 1.19, and 1.20 in
-  order, reading each version's upgrade notes and running preflight checks.
-  Do not attempt a direct upgrade from an old Cilium to 1.20.
-- **Calico**: starting with 3.28 the v3 resource UID behavior changed. If you
-  have operators with OwnerReferences pointing to `projectcalico.org/v3`
-  resources, remove and recreate those references around an in-place upgrade.
-- **MetalLB**: this project installs application tag `v0.16.0`. A newer
-  chart-only tag such as `metallb-chart-0.16.1` is not an application or image
-  release and must not be used as the controller or speaker image tag.
-
 ## ⚙️ Kube Config
 
 To copy your `kube config` locally so that you can access your **Kubernetes** cluster run:
@@ -172,11 +146,11 @@ See the commands [here](https://technotim.com/posts/k3s-etcd-ansible/#testing-yo
 | `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 | `v1.2.2` | Not required | Image tag for kube-vip |
-| `k3s_server` | `kube_vip_cloud_provider_tag_version` | string | `v0.0.12` | Not required | Tag for kube-vip-cloud-provider manifest when enable |
+| `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 | `v0.16.0` | Not required | Image tag for MetalLB |
-| `k3s_server` | `metal_lb_speaker_tag_version` | string | `v0.16.0` | Not required | Image tag for MetalLB |
+| `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 |
@@ -188,7 +162,7 @@ See the commands [here](https://technotim.com/posts/k3s-etcd-ansible/#testing-yo
 | `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 | `v3.32.1` | Not required | Calico version tag |
+| `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 |
@@ -197,15 +171,14 @@ See the commands [here](https://technotim.com/posts/k3s-etcd-ansible/#testing-yo
 | `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_mode` | string | `native` | Not required | Inner-node communication mode (choices are `native` and `tunnel`; `routed` is a deprecated alias for `tunnel`) |
-| `k3s_server_post` | `cilium_tag` | string | `v1.20.0` | Not required | Cilium version tag |
-| `k3s_server_post` | `cilium_cli_tag` | string | `v0.19.7` | Not required | Cilium CLI version tag |
+| `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 | `v0.16.0` | Not required | Image tag for MetalLB |
+| `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 |

inventory/sample/group_vars/all.yml

@@ -1,5 +1,5 @@
 ---
-k3s_version: v1.36.2+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
@@ -13,14 +13,13 @@ 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: v3.32.1 # calico version tag
+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 are on the same subnet or use BGP, otherwise set tunnel
-cilium_tag: v1.20.0 # cilium version tag
-cilium_cli_tag: v0.19.7 # cilium cli version tag
+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
@@ -85,10 +84,10 @@ extra_agent_args: >-
   {{ extra_args }}
 
 # image tag for kube-vip
-kube_vip_tag_version: v1.2.2
+kube_vip_tag_version: v0.8.2
 
 # tag for kube-vip-cloud-provider manifest
-# kube_vip_cloud_provider_tag_version: "v0.0.12"
+# kube_vip_cloud_provider_tag_version: "main"
 
 # kube-vip ip range for load balancer
 # (uncomment to use kube-vip for services instead of MetalLB)
@@ -106,8 +105,8 @@ metal_lb_mode: layer2
 # metal_lb_bgp_peer_address: "192.168.30.1"
 
 # image tag for metal lb
-metal_lb_speaker_tag_version: v0.16.0
-metal_lb_controller_tag_version: v0.16.0
+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

molecule/calico/molecule.yml

@@ -5,9 +5,14 @@ driver:
   name: vagrant
 platforms:
   - name: control1
-    box: bento/ubuntu-26.04
+    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

molecule/calico/overrides.yml

@@ -1,14 +1,13 @@
 ---
 - name: Apply overrides
   hosts: all
-  serial: 1
   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' if 'eth1' in ansible_facts.interfaces else 'enp0s8' }}"
-        kube_vip_iface: "{{ 'eth1' if 'eth1' in ansible_facts.interfaces else 'enp0s8' }}"
+        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/calico/verify-vars.yml

@@ -1,6 +0,0 @@
----
-# Durable verify inputs for the calico (Calico CNI + MetalLB) scenario.
-verify_cni: calico
-verify_lb: metallb
-verify_lb_ip_range:
-  - 192.168.30.100-192.168.30.109

molecule/cilium/molecule.yml

@@ -5,9 +5,14 @@ driver:
   name: vagrant
 platforms:
   - name: control1
-    box: bento/ubuntu-26.04
+    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

molecule/cilium/overrides.yml

@@ -1,14 +1,13 @@
 ---
 - name: Apply overrides
   hosts: all
-  serial: 1
   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' if 'eth1' in ansible_facts.interfaces else 'enp0s8' }}"
-        kube_vip_iface: "{{ 'eth1' if 'eth1' in ansible_facts.interfaces else 'enp0s8' }}"
+        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/cilium/verify-vars.yml

@@ -1,6 +0,0 @@
----
-# Durable verify inputs for the cilium (Cilium CNI + MetalLB) scenario.
-verify_cni: cilium
-verify_lb: metallb
-verify_lb_ip_range:
-  - 192.168.30.110-192.168.30.119

molecule/default/create.yml

@@ -18,7 +18,12 @@
           - create_batches | map('length') | max <= 2
         fail_msg: Bounded create batches do not match the configured default platforms.
 
-    - name: Generate the complete Vagrant configuration # noqa fqcn[action]
+    - 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') }}"
@@ -27,18 +32,20 @@
         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: >-
           {{
-            [playbook_dir + '/../../.github/scripts/vagrant-up-timed.sh',
+            [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]

molecule/default/molecule.yml

@@ -8,7 +8,7 @@ driver:
   parallel: false
 platforms:
   - name: control1
-    box: bento/ubuntu-26.04
+    box: generic/ubuntu2204
     memory: 1024
     cpus: 2
     groups:
@@ -21,9 +21,14 @@ platforms:
     interfaces:
       - network_name: private_network
         ip: 192.168.30.38
+    config_options:
+      # We currently can not use public-key based authentication on Ubuntu 22.04,
+      # see: https://github.com/chef/bento/issues/1405
+      ssh.username: vagrant
+      ssh.password: vagrant
 
   - name: control2
-    box: bento/debian-13
+    box: generic/debian12
     memory: 1024
     cpus: 2
     groups:
@@ -36,7 +41,7 @@ platforms:
         ip: 192.168.30.39
 
   - name: control3
-    box: bento/rockylinux-10.1
+    box: generic/rocky9
     memory: 1024
     cpus: 2
     groups:
@@ -49,7 +54,7 @@ platforms:
         ip: 192.168.30.40
 
   - name: node1
-    box: bento/ubuntu-26.04
+    box: generic/ubuntu2204
     memory: 1024
     cpus: 2
     groups:
@@ -60,9 +65,14 @@ platforms:
     interfaces:
       - network_name: private_network
         ip: 192.168.30.41
+    config_options:
+      # We currently can not use public-key based authentication on Ubuntu 22.04,
+      # see: https://github.com/chef/bento/issues/1405
+      ssh.username: vagrant
+      ssh.password: vagrant
 
   - name: node2
-    box: bento/rockylinux-10.1
+    box: generic/rocky9
     memory: 1024
     cpus: 2
     groups:

molecule/default/overrides.yml

@@ -1,16 +1,15 @@
 ---
 - name: Apply overrides
   hosts: all
-  serial: 1
   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' if 'eth1' in ansible_facts.interfaces else 'enp0s8' }}"
+        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' if 'eth1' in ansible_facts.interfaces else 'enp0s8' }}"
+        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/verify-vars.yml

@@ -1,9 +0,0 @@
----
-# Durable verify inputs for the default (flannel + MetalLB) scenario.
-# These are plain inventory vars linked into the shared Molecule inventory so
-# the verify play can see them even though the converge play's set_fact values
-# are not persisted between the two Ansible processes.
-verify_cni: flannel
-verify_lb: metallb
-verify_lb_ip_range:
-  - 192.168.30.80-192.168.30.90

molecule/ipv6/molecule.yml

@@ -5,7 +5,7 @@ driver:
   name: vagrant
 platforms:
   - name: control1
-    box: bento/ubuntu-26.04
+    box: generic/ubuntu2204
     memory: 1024
     cpus: 2
     groups:
@@ -14,9 +14,14 @@ platforms:
     interfaces:
       - network_name: private_network
         ip: fdad:bad:ba55::de:11
+    config_options:
+      # We currently can not use public-key based authentication on Ubuntu 22.04,
+      # see: https://github.com/chef/bento/issues/1405
+      ssh.username: vagrant
+      ssh.password: vagrant
 
   - name: control2
-    box: bento/ubuntu-26.04
+    box: generic/ubuntu2204
     memory: 1024
     cpus: 2
     groups:
@@ -25,9 +30,14 @@ platforms:
     interfaces:
       - network_name: private_network
         ip: fdad:bad:ba55::de:12
+    config_options:
+      # We currently can not use public-key based authentication on Ubuntu 22.04,
+      # see: https://github.com/chef/bento/issues/1405
+      ssh.username: vagrant
+      ssh.password: vagrant
 
   - name: node1
-    box: bento/ubuntu-26.04
+    box: generic/ubuntu2204
     memory: 1024
     cpus: 2
     groups:
@@ -36,6 +46,11 @@ platforms:
     interfaces:
       - network_name: private_network
         ip: fdad:bad:ba55::de:21
+    config_options:
+      # We currently can not use public-key based authentication on Ubuntu 22.04,
+      # see: https://github.com/chef/bento/issues/1405
+      ssh.username: vagrant
+      ssh.password: vagrant
 provisioner:
   name: ansible
   env:

molecule/ipv6/overrides.yml

@@ -1,18 +1,17 @@
 ---
 - name: Apply overrides
   hosts: all
-  serial: 1
   tasks:
     - name: Override host variables (1/2)
       ansible.builtin.set_fact:
         # See:
         # https://github.com/flannel-io/flannel/blob/67d603aaf45ef80f5dd39f43714fc5e6f8a637eb/Documentation/troubleshooting.md#Vagrant
-        flannel_iface: "{{ 'eth1' if 'eth1' in ansible_facts.interfaces else 'enp0s8' }}"
+        flannel_iface: eth1
 
         # In this scenario, we have multiple interfaces that the VIP could be
         # broadcasted on. Since we have assigned a dedicated private network
         # here, let's make sure that it is used.
-        kube_vip_iface: "{{ 'eth1' if 'eth1' in ansible_facts.interfaces else 'enp0s8' }}"
+        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/ipv6/verify-vars.yml

@@ -1,7 +0,0 @@
----
-# Durable verify inputs for the ipv6 (flannel CNI + MetalLB) scenario.
-verify_cni: flannel
-verify_lb: metallb
-verify_lb_ip_range:
-  - fdad:bad:ba55::1b:0/112
-  - 192.168.123.80-192.168.123.90

molecule/kube-vip/molecule.yml

@@ -5,9 +5,14 @@ driver:
   name: vagrant
 platforms:
   - name: control1
-    box: bento/ubuntu-26.04
+    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

molecule/kube-vip/overrides.yml

@@ -1,14 +1,13 @@
 ---
 - name: Apply overrides
   hosts: all
-  serial: 1
   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' if 'eth1' in ansible_facts.interfaces else 'enp0s8' }}"
-        kube_vip_iface: "{{ 'eth1' if 'eth1' in ansible_facts.interfaces else 'enp0s8' }}"
+        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/kube-vip/verify-vars.yml

@@ -1,9 +0,0 @@
----
-# Durable verify inputs for the kube-vip (flannel CNI + kube-vip LB) scenario.
-verify_cni: flannel
-verify_lb: kube-vip
-# The kube-vip cloud provider tag is not defined in the linked sample group
-# vars (its sample entry is commented out), so it is supplied here.
-verify_kube_vip_cloud_provider_tag: v0.0.12
-verify_lb_ip_range:
-  - 192.168.30.110-192.168.30.119

molecule/resources/verify.yml

@@ -1,8 +1,5 @@
 ---
 - name: Verify
   hosts: all
-  vars_files:
-    - >-
-      {{ lookup("ansible.builtin.env", "MOLECULE_SCENARIO_DIRECTORY") }}/verify-vars.yml
   roles:
     - verify_from_outside

molecule/resources/verify_from_outside/tasks/main.yml

@@ -7,8 +7,6 @@
       ansible.builtin.import_tasks: kubecfg-fetch.yml
     - name: "TEST CASE: Get nodes"
       ansible.builtin.include_tasks: test/get-nodes.yml
-    - name: "TEST CASE: Verify components"
-      ansible.builtin.include_tasks: test/verify-components.yml
     - name: "TEST CASE: Deploy example"
       ansible.builtin.include_tasks: test/deploy-example.yml
   always:

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

@@ -32,86 +32,17 @@
         metallb_port: spec.ports[0].port
       register: nginx_services
 
-    - name: Wait for the load balancer address to be assigned
-      ansible.builtin.set_fact:
-        nginx_lb_ip: >-
-          {{
-            nginx_services.resources[0].status.loadBalancer.ingress[0].ip
-            if (nginx_services.resources | length > 0) and
-               (nginx_services.resources[0].status.loadBalancer.ingress is defined) and
-               (nginx_services.resources[0].status.loadBalancer.ingress | length > 0)
-            else ''
-          }}
-
-    - name: Retry until the load balancer service has an external IP
-      block:
-        - name: Refresh nginx service until it has an assigned address
-          kubernetes.core.k8s_info:
-            kind: service
-            name: nginx
-            namespace: "{{ testing_namespace }}"
-            kubeconfig: "{{ kubecfg_path }}"
-          register: nginx_lb_wait
-          until: >-
-            (nginx_lb_wait.resources | length > 0) and
-            (nginx_lb_wait.resources[0].status.loadBalancer.ingress is defined) and
-            (nginx_lb_wait.resources[0].status.loadBalancer.ingress | length > 0)
-          retries: 30
-          delay: 5
-
-        - name: Record the assigned load balancer address
-          ansible.builtin.set_fact:
-            nginx_lb_ip: >-
-              {{ nginx_lb_wait.resources[0].status.loadBalancer.ingress[0].ip }}
-
     - name: Assert that the nginx welcome page is available
       ansible.builtin.uri:
-        url: http://{{ nginx_lb_ip | ansible.utils.ipwrap }}:{{ port_ }}/
+        url: http://{{ ip | ansible.utils.ipwrap }}:{{ port_ }}/
         return_content: true
       register: result
       failed_when: "'Welcome to nginx!' not in result.content"
       vars:
+        ip: >-
+          {{ nginx_services.resources[0].status.loadBalancer.ingress[0].ip }}
         port_: >-
           {{ nginx_services.resources[0].spec.ports[0].port }}
-
-    - name: Initialize load balancer address range check
-      ansible.builtin.set_fact:
-        lb_addr_in_range: false
-        lb_ip_value: "{{ nginx_lb_ip }}"
-
-    - name: Check load balancer address against start-end pools
-      ansible.builtin.set_fact:
-        lb_addr_in_range: true
-      loop: "{{ verify_lb_ip_range }}"
-      loop_control:
-        label: "{{ item }}"
-      when:
-        - "'-' in item"
-        - "'/' not in item"
-        - >-
-          (lb_ip_value | ansible.utils.ipaddr('int') | int) >=
-          (item.split('-')[0] | ansible.utils.ipaddr('int') | int)
-        - >-
-          (lb_ip_value | ansible.utils.ipaddr('int') | int) <=
-          (item.split('-')[1] | ansible.utils.ipaddr('int') | int)
-
-    - name: Check load balancer address against CIDR pools
-      ansible.builtin.set_fact:
-        lb_addr_in_range: true
-      loop: "{{ verify_lb_ip_range }}"
-      loop_control:
-        label: "{{ item }}"
-      when:
-        - "'/' in item"
-        - (lb_ip_value | ansible.utils.ipaddr(item)) is string
-
-    - name: Assert that the load balancer address is within a configured pool
-      ansible.builtin.assert:
-        that: lb_addr_in_range
-        success_msg: "LoadBalancer address {{ lb_ip_value }} is in a configured range"
-        fail_msg: >-
-          LoadBalancer address {{ lb_ip_value }} is not in a configured
-          range {{ verify_lb_ip_range }}
   # 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.

molecule/resources/verify_from_outside/tasks/test/verify-components.yml

@@ -1,313 +0,0 @@
----
-# Scenario-aware verification of cluster components and their live image tags.
-# Scenario identity (verify_cni / verify_lb) and expected address range come
-# from each scenario's verify-vars.yml, which is plain inventory data available
-# to the verify play. Converge-time set_fact values are not persisted between
-# the two Ansible processes, so they are never used here.
-- name: Verify cluster components report expected versions
-  block:
-    - name: Get all nodes with their kubelet versions
-      kubernetes.core.k8s_info:
-        kind: node
-        kubeconfig: "{{ kubecfg_path }}"
-      register: verify_nodes
-
-    - name: Assert each node reports the expected Kubernetes version
-      ansible.builtin.assert:
-        that: item.status.nodeInfo.kubeletVersion == k3s_version
-        success_msg: "{{ item.metadata.name }} reports {{ k3s_version }}"
-        fail_msg: >-
-          {{ item.metadata.name }} reports
-          {{ item.status.nodeInfo.kubeletVersion }},
-          expected {{ k3s_version }}
-      loop: "{{ verify_nodes.resources }}"
-      loop_control:
-        label: "{{ item.metadata.name }}"
-
-    - name: Verify Flannel is the active CNI
-      when: verify_cni == 'flannel'
-      block:
-        - name: Assert every node reports Ready
-          ansible.builtin.assert:
-            that: item.status.conditions
-              | selectattr('type', 'equalto', 'Ready')
-              | map(attribute='status') | first | default('') == 'True'
-            success_msg: "{{ item.metadata.name }} is Ready"
-            fail_msg: "{{ item.metadata.name }} is not Ready"
-          loop: "{{ verify_nodes.resources }}"
-          loop_control:
-            label: "{{ item.metadata.name }} ready"
-
-        - name: Get any Calico namespaces with Flannel enabled
-          kubernetes.core.k8s_info:
-            kind: Namespace
-            name: calico-system
-            kubeconfig: "{{ kubecfg_path }}"
-          register: flannel_calico_absent
-
-        - name: Assert there is no Calico system namespace
-          ansible.builtin.assert:
-            that: flannel_calico_absent.resources | length == 0
-            success_msg: "No Calico present with Flannel"
-            fail_msg: "A Calico namespace exists alongside Flannel"
-
-        - name: Get the Cilium namespace with Flannel enabled
-          kubernetes.core.k8s_info:
-            kind: Namespace
-            name: cilium
-            kubeconfig: "{{ kubecfg_path }}"
-          register: flannel_cilium
-
-        - name: Assert the Cilium namespace is absent
-          ansible.builtin.assert:
-            that: flannel_cilium.resources | length == 0
-            success_msg: "No Cilium present with Flannel"
-            fail_msg: "A Cilium namespace exists alongside Flannel"
-
-    - name: Verify Calico is the active CNI
-      when: verify_cni == 'calico'
-      block:
-        - name: Get the Calico node DaemonSet image
-          kubernetes.core.k8s_info:
-            kind: DaemonSet
-            name: calico-node
-            namespace: calico-system
-            kubeconfig: "{{ kubecfg_path }}"
-          register: calico_node_ds
-
-        - name: Assert the Calico node image uses the expected tag
-          ansible.builtin.assert:
-            that:
-              - calico_node_ds.resources | length == 1
-              - calico_node_image | regex_search(':' ~ calico_tag)
-            success_msg: "Calico node image uses tag {{ calico_tag }}"
-            fail_msg: >-
-              Calico node image {{ calico_node_image }},
-              expected {{ calico_tag }}
-          vars:
-            calico_node_image: "{{ calico_node_ds.resources[0].spec.template.spec.containers[0].image }}"
-
-        - name: Get Calico TigeraStatus for calico and apiserver
-          kubernetes.core.k8s_info:
-            api_version: operator.tigera.io/v1
-            kind: TigeraStatus
-            name: "{{ item }}"
-            kubeconfig: "{{ kubecfg_path }}"
-          register: calico_tigerastatus
-          loop:
-            - calico
-            - apiserver
-          loop_control:
-            label: "Tigerastatus/{{ item }}"
-
-        - name: Assert Calico TigeraStatus reports Available
-          ansible.builtin.assert:
-            that: >-
-              item.resources | length == 1 and
-              (item.resources[0].status.conditions
-               | selectattr('type', 'equalto', 'Available')
-               | map(attribute='status') | first | default('')) == 'True'
-            success_msg: "Tigerastatus {{ item.resources[0].metadata.name }} is Available"
-            fail_msg: "Tigerastatus is not Available"
-          loop: "{{ calico_tigerastatus.results }}"
-          loop_control:
-            label: "Tigerastatus Available"
-
-        - name: Get any Flannel DaemonSets with Calico enabled
-          kubernetes.core.k8s_info:
-            kind: DaemonSet
-            namespace: kube-flannel
-            kubeconfig: "{{ kubecfg_path }}"
-          register: no_flannel_ds
-
-        - name: Assert there are no Flannel DaemonSets
-          ansible.builtin.assert:
-            that: no_flannel_ds.resources | length == 0
-            success_msg: "No Flannel DaemonSet present with Calico"
-            fail_msg: "A Flannel DaemonSet exists alongside Calico"
-
-    - name: Verify Cilium is the active CNI
-      when: verify_cni == 'cilium'
-      block:
-        - name: Get the Cilium agent and operator images
-          kubernetes.core.k8s_info:
-            kind: "{{ item.kind }}"
-            name: "{{ item.name }}"
-            namespace: kube-system
-            kubeconfig: "{{ kubecfg_path }}"
-          register: cilium_info
-          loop:
-            - { kind: DaemonSet, name: cilium }
-            - { kind: Deployment, name: cilium-operator }
-          loop_control:
-            label: "{{ item.kind }}/{{ item.name }}"
-
-        - name: Assert Cilium agent and operator use the expected image tag
-          ansible.builtin.assert:
-            that:
-              - cilium_agent_image | regex_search(':' ~ cilium_tag)
-              - cilium_operator_image | regex_search(':' ~ cilium_tag)
-            success_msg: "Cilium agent and operator use {{ cilium_tag }}"
-            fail_msg: >-
-              Cilium agent {{ cilium_agent_image }},
-              operator {{ cilium_operator_image }},
-              expected {{ cilium_tag }}
-          vars:
-            cilium_agent_image: >-
-              {{ (cilium_info.results
-                  | selectattr('resources', 'defined')
-                  | map(attribute='resources')
-                  | list
-                  | map(attribute='0')
-                  | selectattr('kind', 'equalto', 'DaemonSet')
-                  | list)[0].spec.template.spec.containers[0].image }}
-            cilium_operator_image: >-
-              {{ (cilium_info.results
-                  | selectattr('resources', 'defined')
-                  | map(attribute='resources')
-                  | list
-                  | map(attribute='0')
-                  | selectattr('kind', 'equalto', 'Deployment')
-                  | list)[0].spec.template.spec.containers[0].image }}
-
-        - name: Get Hubble relay and UI deployments when enabled
-          kubernetes.core.k8s_info:
-            kind: Deployment
-            name: "{{ item }}"
-            namespace: kube-system
-            kubeconfig: "{{ kubecfg_path }}"
-          register: hubble_info
-          loop:
-            - hubble-relay
-            - hubble-ui
-          loop_control:
-            label: "Deployment/{{ item }}"
-          when: cilium_hubble | bool
-
-        - name: Assert Hubble components are Ready when enabled
-          ansible.builtin.assert:
-            that:
-              - item.resources | length == 1
-              - item.resources[0].status.readyReplicas | default(0) >= 1
-            success_msg: "Hubble deployment {{ item.resources[0].metadata.name }} is Ready"
-            fail_msg: "Hubble deployment is not Ready"
-          loop: "{{ hubble_info.results }}"
-          loop_control:
-            label: "Hubble deployment"
-          when: cilium_hubble | bool
-
-        - name: Get any Flannel DaemonSets with Cilium enabled
-          kubernetes.core.k8s_info:
-            kind: DaemonSet
-            namespace: kube-flannel
-            kubeconfig: "{{ kubecfg_path }}"
-          register: no_flannel_ds_cilium
-
-        - name: Assert there are no Flannel DaemonSets
-          ansible.builtin.assert:
-            that: no_flannel_ds_cilium.resources | length == 0
-            success_msg: "No Flannel DaemonSet present with Cilium"
-            fail_msg: "A Flannel DaemonSet exists alongside Cilium"
-
-    - name: Verify MetalLB is the active load balancer
-      when: verify_lb == 'metallb'
-      block:
-        - name: Get the MetalLB controller and speaker images
-          kubernetes.core.k8s_info:
-            kind: "{{ item.kind }}"
-            name: "{{ item.name }}"
-            namespace: metallb-system
-            kubeconfig: "{{ kubecfg_path }}"
-          register: metallb_info
-          loop:
-            - { kind: Deployment, name: controller }
-            - { kind: DaemonSet, name: speaker }
-          loop_control:
-            label: "{{ item.kind }}/{{ item.name }}"
-
-        - name: Assert MetalLB controller and speaker use the expected image tags
-          ansible.builtin.assert:
-            that:
-              - controller_image | regex_search(metal_lb_controller_tag_version)
-              - speaker_image | regex_search(metal_lb_speaker_tag_version)
-            success_msg: >-
-              MetalLB controller {{ metal_lb_controller_tag_version }},
-              speaker {{ metal_lb_speaker_tag_version }}
-            fail_msg: >-
-              MetalLB controller {{ controller_image }},
-              speaker {{ speaker_image }}
-          vars:
-            controller_image: >-
-              {{ (metallb_info.results
-                  | selectattr('resources', 'defined')
-                  | map(attribute='resources')
-                  | list
-                  | map(attribute='0')
-                  | selectattr('kind', 'equalto', 'Deployment')
-                  | list)[0].spec.template.spec.containers[0].image }}
-            speaker_image: >-
-              {{ (metallb_info.results
-                  | selectattr('resources', 'defined')
-                  | map(attribute='resources')
-                  | list
-                  | map(attribute='0')
-                  | selectattr('kind', 'equalto', 'DaemonSet')
-                  | list)[0].spec.template.spec.containers[0].image }}
-
-    - name: Verify kube-vip is the active load balancer
-      when: verify_lb == 'kube-vip'
-      block:
-        - name: Get the kube-vip and cloud provider images
-          kubernetes.core.k8s_info:
-            kind: "{{ item.kind }}"
-            name: "{{ item.name }}"
-            namespace: kube-system
-            kubeconfig: "{{ kubecfg_path }}"
-          register: kubevip_info
-          loop:
-            - { kind: DaemonSet, name: kube-vip-ds }
-            - { kind: Deployment, name: kube-vip-cloud-provider }
-          loop_control:
-            label: "{{ item.kind }}/{{ item.name }}"
-
-        - name: Assert the kube-vip and cloud provider image tags
-          ansible.builtin.assert:
-            that:
-              - kubevip_image | regex_search(':' ~ kube_vip_tag_version)
-              - cloud_provider_image | regex_search(verify_kube_vip_cloud_provider_tag)
-            success_msg: >-
-              kube-vip {{ kube_vip_tag_version }},
-              cloud provider {{ verify_kube_vip_cloud_provider_tag }}
-            fail_msg: >-
-              kube-vip {{ kubevip_image }},
-              cloud provider {{ cloud_provider_image }}
-          vars:
-            kubevip_image: >-
-              {{ (kubevip_info.results
-                  | selectattr('resources', 'defined')
-                  | map(attribute='resources')
-                  | list
-                  | map(attribute='0')
-                  | selectattr('kind', 'equalto', 'DaemonSet')
-                  | list)[0].spec.template.spec.containers[0].image }}
-            cloud_provider_image: >-
-              {{ (kubevip_info.results
-                  | selectattr('resources', 'defined')
-                  | map(attribute='resources')
-                  | list
-                  | map(attribute='0')
-                  | selectattr('kind', 'equalto', 'Deployment')
-                  | list)[0].spec.template.spec.containers[0].image }}
-
-        - name: Get the MetalLB namespace with kube-vip enabled
-          kubernetes.core.k8s_info:
-            kind: Namespace
-            name: metallb-system
-            kubeconfig: "{{ kubecfg_path }}"
-          register: metallb_absent
-
-        - name: Assert the MetalLB namespace does not exist
-          ansible.builtin.assert:
-            that: metallb_absent.resources | length == 0
-            success_msg: "MetalLB is not installed with kube-vip"
-            fail_msg: "MetalLB namespace exists alongside kube-vip"

molecule/single_node/molecule.yml

@@ -5,9 +5,14 @@ driver:
   name: vagrant
 platforms:
   - name: control1
-    box: bento/ubuntu-26.04
+    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

molecule/single_node/overrides.yml

@@ -1,14 +1,13 @@
 ---
 - name: Apply overrides
   hosts: all
-  serial: 1
   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' if 'eth1' in ansible_facts.interfaces else 'enp0s8' }}"
-        kube_vip_iface: "{{ 'eth1' if 'eth1' in ansible_facts.interfaces else 'enp0s8' }}"
+        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/verify-vars.yml

@@ -1,6 +0,0 @@
----
-# Durable verify inputs for the single_node (flannel + MetalLB) scenario.
-verify_cni: flannel
-verify_lb: metallb
-verify_lb_ip_range:
-  - 192.168.30.91-192.168.30.99

roles/k3s_server/defaults/main.yml

@@ -7,8 +7,8 @@ group_name_master: master
 
 kube_vip_arp: true
 kube_vip_iface:
-kube_vip_cloud_provider_tag_version: v0.0.12
-kube_vip_tag_version: v1.2.2
+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
@@ -19,8 +19,8 @@ kube_vip_bgp_peeras: "64512"
 kube_vip_bgp_peers: []
 kube_vip_bgp_peers_groups: ['k3s_master']
 
-metal_lb_controller_tag_version: v0.16.0
-metal_lb_speaker_tag_version: v0.16.0
+metal_lb_controller_tag_version: v0.14.3
+metal_lb_speaker_tag_version: v0.14.3
 metal_lb_type: native
 
 retry_count: 20

roles/k3s_server/meta/main.yml

@@ -80,11 +80,11 @@ argument_specs:
 
       kube_vip_tag_version:
         description: Image tag for kube-vip
-        default: v1.2.2
+        default: v0.7.2
 
       kube_vip_cloud_provider_tag_version:
         description: Tag for kube-vip-cloud-provider manifest when enabled
-        default: v0.0.12
+        default: main
 
       kube_vip_lb_ip_range:
         description: IP range for kube-vip load balancer
@@ -92,11 +92,11 @@ argument_specs:
 
       metal_lb_controller_tag_version:
         description: Image tag for MetalLB
-        default: v0.16.0
+        default: v0.14.3
 
       metal_lb_speaker_tag_version:
         description: Image tag for MetalLB
-        default: v0.16.0
+        default: v0.14.3
 
       metal_lb_type:
         choices:

roles/k3s_server/tasks/kube-vip.yml

@@ -10,7 +10,7 @@
 
 - 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('v0.0.12') }}/manifest/kube-vip-cloud-controller.yaml # noqa yaml[line-length]
+    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

roles/k3s_server/tasks/metallb.yml

@@ -28,29 +28,3 @@
   loop_control:
     label: "{{ item.change }} => {{ item.to }}"
   when: ansible_hostname == hostvars[groups[group_name_master | default('master')][0]]['ansible_hostname']
-
-- name: Read back MetalLB manifest from first master
-  ansible.builtin.slurp:
-    src: /var/lib/rancher/k3s/server/manifests/metallb-crds.yaml
-  register: metallb_manifest
-  when: ansible_hostname == hostvars[groups[group_name_master | default('master')][0]]['ansible_hostname']
-
-- name: Check the MetalLB speaker image reference is present
-  ansible.builtin.set_fact:
-    metallb_manifest_has_speaker_tag: >-
-      {{
-        ('quay.io/metallb/speaker:' ~ metal_lb_speaker_tag_version) in
-        (metallb_manifest.content | default('') | b64decode)
-      }}
-  when: ansible_hostname == hostvars[groups[group_name_master | default('master')][0]]['ansible_hostname']
-
-- name: Fail if MetalLB speaker tag was not applied to the manifest
-  ansible.builtin.fail:
-    msg: >-
-      MetalLB speaker image reference
-      quay.io/metallb/speaker:{{ metal_lb_speaker_tag_version }}
-      was not found in the downloaded manifest. The upstream image
-      reference may have changed.
-  when:
-    - ansible_hostname == hostvars[groups[group_name_master | default('master')][0]]['ansible_hostname']
-    - not metallb_manifest_has_speaker_tag

roles/k3s_server/tasks/vip.yml

@@ -12,9 +12,9 @@
     mode: "0644"
   when: ansible_hostname == hostvars[groups[group_name_master | default('master')][0]]['ansible_hostname']
 
-- name: Copy kube-vip RBAC manifest to first master
-  ansible.builtin.template:
-    src: kube-vip-rbac.yaml.j2
+- name: Download vip rbac manifest to first master
+  ansible.builtin.get_url:
+    url: https://kube-vip.io/manifests/rbac.yaml
     dest: /var/lib/rancher/k3s/server/manifests/vip-rbac.yaml
     owner: root
     group: root

roles/k3s_server/templates/kube-vip-rbac.yaml.j2

@@ -1,48 +0,0 @@
-# Repository-owned kube-vip RBAC derived from the official v1.2.2
-# `kube-vip manifest rbac` output (run with `--inCluster`).
-# Source: https://github.com/kube-vip/kube-vip/blob/v1.2.2/pkg/kubevip/config_generator.go
-# Permissions are kept exactly as broad as the upstream manifest.
-apiVersion: v1
-kind: ServiceAccount
-metadata:
-  name: kube-vip
-  namespace: kube-system
----
-apiVersion: rbac.authorization.k8s.io/v1
-kind: ClusterRole
-metadata:
-  annotations:
-    rbac.authorization.kubernetes.io/autoupdate: "true"
-  name: system:kube-vip-role
-rules:
-  - apiGroups: [""]
-    resources: ["services/status"]
-    verbs: ["update"]
-  - apiGroups: [""]
-    resources: ["services", "endpoints"]
-    verbs: ["list", "get", "watch", "update"]
-  - apiGroups: [""]
-    resources: ["nodes"]
-    verbs: ["list", "get", "watch", "update", "patch"]
-  - apiGroups: ["coordination.k8s.io"]
-    resources: ["leases"]
-    verbs: ["list", "get", "watch", "update", "create"]
-  - apiGroups: ["discovery.k8s.io"]
-    resources: ["endpointslices"]
-    verbs: ["list", "get", "watch", "update"]
-  - apiGroups: [""]
-    resources: ["pods"]
-    verbs: ["list"]
----
-apiVersion: rbac.authorization.k8s.io/v1
-kind: ClusterRoleBinding
-metadata:
-  name: system:kube-vip-binding
-roleRef:
-  apiGroup: rbac.authorization.k8s.io
-  kind: ClusterRole
-  name: system:kube-vip-role
-subjects:
-  - kind: ServiceAccount
-    name: kube-vip
-    namespace: kube-system

roles/k3s_server/templates/vip.yaml.j2

@@ -36,7 +36,7 @@ spec:
         - name: vip_interface
           value: {{ kube_vip_iface }}
 {% endif %}
-        - name: vip_subnet
+        - name: vip_cidr
           value: "{{ apiserver_endpoint | ansible.utils.ipsubnet | ansible.utils.ipaddr('prefix') }}"
         - name: cp_enable
           value: "true"
@@ -62,8 +62,8 @@ spec:
           value: "{{ kube_vip_bgp_routerid }}"
 {% endif %}
 {% if _kube_vip_bgp_peers | length > 0 %}
-        - name: bgp_peers
-          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
+        - 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

roles/k3s_server_post/defaults/main.yml

@@ -9,7 +9,7 @@ calico_ebpf: false
 calico_encapsulation: VXLANCrossSubnet
 calico_natOutgoing: Enabled  # noqa var-naming
 calico_nodeSelector: all()  # noqa var-naming
-calico_tag: v3.32.1
+calico_tag: v3.27.2
 
 cilium_bgp: false
 cilium_exportPodCIDR: true  # noqa var-naming
@@ -20,8 +20,6 @@ cilium_bgp_neighbors_groups: ['k3s_all']
 cilium_bgp_lb_cidr: 192.168.31.0/24
 cilium_hubble: true
 cilium_mode: native
-cilium_tag: v1.20.0
-cilium_cli_tag: v0.19.7
 
 cluster_cidr: 10.52.0.0/16
 enable_bpf_masquerade: true
@@ -30,5 +28,5 @@ group_name_master: master
 
 metal_lb_mode: layer2
 metal_lb_available_timeout: 240s
-metal_lb_controller_tag_version: v0.16.0
+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

@@ -43,7 +43,7 @@ argument_specs:
 
       calico_tag:
         description: Calico version tag
-        default: v3.32.1
+        default: v3.27.2
 
       cilium_bgp:
         description:
@@ -93,24 +93,12 @@ argument_specs:
         default: ~
 
       cilium_mode:
-        description:
-          - Inner-node communication mode.
-          - Cilium accepts `native` or `tunnel`. `routed` is accepted as a
-            legacy alias and is mapped to `tunnel` at install time.
+        description: Inner-node communication mode
         default: native
         choices:
           - native
-          - tunnel
           - routed
 
-      cilium_tag:
-        description: Cilium version tag
-        default: v1.20.0
-
-      cilium_cli_tag:
-        description: Cilium CLI version tag
-        default: v0.19.7
-
       cluster_cidr:
         description: Inner-cluster IP range
         default: 10.52.0.0/16
@@ -143,7 +131,7 @@ argument_specs:
 
       metal_lb_controller_tag_version:
         description: Image tag for MetalLB
-        default: v0.16.0
+        default: v0.14.3
 
       metal_lb_mode:
         description: Metallb mode

roles/k3s_server_post/tasks/calico.yml

@@ -11,14 +11,6 @@
         group: root
         mode: "0755"
 
-    - name: "Download to first master: Calico CRD bundle for {{ calico_tag }}"
-      ansible.builtin.get_url:
-        url: https://raw.githubusercontent.com/projectcalico/calico/{{ calico_tag }}/manifests/v1_crd_projectcalico_org.yaml # noqa yaml[line-length]
-        dest: /tmp/k3s/v1_crd_projectcalico_org.yaml
-        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
@@ -27,48 +19,6 @@
         group: root
         mode: "0755"
 
-    - name: Apply Calico CRD bundle with server-side apply
-      ansible.builtin.command: >-
-        {{ k3s_kubectl_binary | default('k3s kubectl') }}
-        apply --server-side --force-conflicts
-        -f /tmp/k3s/v1_crd_projectcalico_org.yaml
-      register: apply_crds
-      changed_when: >-
-        'created' in apply_crds.stdout or
-        'configured' in apply_crds.stdout or
-        'applied' in apply_crds.stdout
-      failed_when: apply_crds.rc != 0
-
-    - name: Apply Tigera Operator manifest idempotently with server-side apply
-      ansible.builtin.command: >-
-        {{ k3s_kubectl_binary | default('k3s kubectl') }}
-        apply --server-side --force-conflicts
-        -f /tmp/k3s/tigera-operator.yaml
-      register: apply_operator
-      changed_when: >-
-        'created' in apply_operator.stdout or
-        'configured' in apply_operator.stdout or
-        'applied' in apply_operator.stdout
-      failed_when: apply_operator.rc != 0
-
-    - name: Wait for Tigera Operator and managed CRDs to become available
-      ansible.builtin.command: >-
-        {{ k3s_kubectl_binary | default('k3s kubectl') }} wait {{ item.type }}/{{ item.name }}
-        {% if item.namespace is defined %}--namespace='{{ item.namespace }}'{% endif %}
-        --for=condition={{ item.condition }}
-        --timeout=30s
-      register: tigera_result
-      changed_when: false
-      until: tigera_result is succeeded
-      retries: 7
-      delay: 7
-      with_items:
-        - { name: tigera-operator, type: deployment, namespace: tigera-operator, condition: Available=True }
-        - { name: installations.operator.tigera.io, type: crd, condition: Established }
-        - { name: apiservers.operator.tigera.io, type: crd, condition: Established }
-      loop_control:
-        label: "{{ item.type }}/{{ item.name }}"
-
     - name: Copy Calico custom resources manifest to first master
       ansible.builtin.template:
         src: calico.crs.j2
@@ -77,16 +27,53 @@
         group: root
         mode: "0755"
 
-    - name: Apply Calico custom resources
+    - 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') }}
-        apply -f /tmp/k3s/custom-resources.yaml
-      register: apply_cr
-      changed_when: >-
-        'configured' in apply_cr.stdout or
-        'created' in apply_cr.stdout or
-        'unchanged' in apply_cr.stdout
-      failed_when: apply_cr.rc != 0
+        {{ 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: >-
@@ -104,8 +91,8 @@
       register: cr_result
       changed_when: false
       until: cr_result is succeeded
-      retries: 60
-      delay: 10
+      retries: 30
+      delay: 7
       with_items:
         - { name: calico-typha, type: deployment, namespace: calico-system }
         - { name: calico-kube-controllers, type: deployment, namespace: calico-system }
@@ -117,40 +104,10 @@
           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 }}"
 
-    # The Calico API server is an optional add-on for managing Calico policy via
-    # kubectl (the projectcalico.org/v3 Kubernetes API). It is not required for
-    # Calico CNI data plane operation and does not reconcile on K3s with recent
-    # Calico releases, so it is treated as best-effort here.
-    - name: Wait for the optional Calico API server (best effort)
-      ansible.builtin.command: >-
-        {{ k3s_kubectl_binary | default('k3s kubectl') }} wait deployment/calico-apiserver
-        --namespace=calico-apiserver --for=condition=Available --timeout=30s
-      register: cr_apiserver
-      changed_when: false
-      until: cr_apiserver is succeeded
-      retries: 30
-      delay: 10
-      ignore_errors: true
-
-    - name: Verify Calico TigeraStatus reports Available
-      ansible.builtin.command: >-
-        {{ k3s_kubectl_binary | default('k3s kubectl') }}
-        get tigerastatus {{ item }}
-        -o jsonpath='{.status.conditions[?(@.type=="Available")].status}'
-      register: tigera_status
-      changed_when: false
-      until: tigera_status.stdout | trim == 'True'
-      retries: 30
-      delay: 7
-      failed_when: tigera_status.rc != 0 or (tigera_status.stdout | trim) != 'True'
-      with_items:
-        - calico
-      loop_control:
-        label: "tigerastatus/{{ item }}"
-
     - name: Patch Felix configuration for eBPF mode
       ansible.builtin.command:
         cmd: >

roles/k3s_server_post/tasks/cilium.yml

@@ -30,13 +30,26 @@
           }}
       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 pinned Cilium CLI version
+    - name: Log latest stable Cilium CLI version
       ansible.builtin.debug:
-        msg: "Pinned Cilium CLI version: {{ cilium_cli_tag }}"
+        msg: "Latest Cilium CLI version: {{ cli_ver.stdout }}"
 
     - name: Determine if Cilium CLI needs installation or update
       ansible.builtin.set_fact:
@@ -44,7 +57,7 @@
           {{
             cilium_cli_installed.rc != 0 or
             (cilium_cli_installed.rc == 0 and
-            installed_cli_version != cilium_cli_tag)
+            installed_cli_version != cli_ver.stdout)
           }}
 
     - name: Install or update Cilium CLI
@@ -65,7 +78,7 @@
             - .tar.gz
             - .tar.gz.sha256sum
           vars:
-            cilium_base_url: https://github.com/cilium/cilium-cli/releases/download/{{ cilium_cli_tag }}
+            cilium_base_url: https://github.com/cilium/cilium-cli/releases/download/{{ cli_ver.stdout }}
 
         - name: Verify the downloaded tarball
           ansible.builtin.shell: |
@@ -143,13 +156,6 @@
               Target Cilium version: {{ cilium_tag }},
               Update needed: {{ cilium_needs_update }}
 
-    - name: Map the legacy routed mode to Cilium tunnel mode
-      ansible.builtin.set_fact:
-        # Cilium 1.20 accepts `native` or `tunnel`. `routed` was the name used
-        # by older releases and is kept only as a backward-compatible alias.
-        cilium_routing_mode: >-
-          {{ 'tunnel' if cilium_mode == 'routed' else cilium_mode }}
-
     - name: Install Cilium
       ansible.builtin.command: >-
         {% if cilium_installed.rc != 0 %}
@@ -161,13 +167,13 @@
         --helm-set operator.replicas="1"
         {{ '--helm-set devices=' + cilium_iface if cilium_iface != 'auto' else '' }}
         --helm-set ipam.operator.clusterPoolIPv4PodCIDRList={{ cluster_cidr }}
-        {% if cilium_routing_mode == "native" or (cilium_bgp and cilium_exportPodCIDR != 'false') %}
+        {% 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_routing_mode }}
-        --helm-set autoDirectNodeRoutes={{ "true" if cilium_routing_mode == "native" else "false" }}
+        --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") }}
@@ -175,8 +181,8 @@
         --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 loadBalancer.algorithm={{ bpf_lb_algorithm }}
-        --helm-set loadBalancer.mode={{ bpf_lb_mode }}
+        --helm-set bpf.loadBalancer.algorithm={{ bpf_lb_algorithm }}
+        --helm-set bpf.loadBalancer.mode={{ bpf_lb_mode }}
         {% endif %}
       environment:
         KUBECONFIG: "{{ ansible_user_dir }}/.kube/config"
@@ -212,16 +218,6 @@
       when: >-
         not item.check_hubble | default(false) or (item.check_hubble | default(false) and cilium_hubble)
 
-    - name: Wait for Cilium status to be healthy
-      ansible.builtin.command: cilium status --wait
-      environment:
-        KUBECONFIG: "{{ ansible_user_dir }}/.kube/config"
-      register: cilium_status
-      changed_when: false
-      until: cilium_status.rc == 0
-      retries: 30
-      delay: 7
-
     - name: Configure Cilium BGP
       when: cilium_bgp
       block:
@@ -237,38 +233,23 @@
             group: root
             mode: "0755"
 
-        - name: Preflight validate rendered BGP manifests against installed CRDs
-          ansible.builtin.command: >-
-            {{ k3s_kubectl_binary | default('k3s kubectl') }}
-            apply --dry-run=server -f /tmp/k3s/cilium-bgp.yaml
-          register: preflight_cr
-          changed_when: false
-          failed_when: preflight_cr.rc != 0
-
         - name: Apply BGP manifests
-          ansible.builtin.command: >-
-            {{ k3s_kubectl_binary | default('k3s kubectl') }}
-            apply -f /tmp/k3s/cilium-bgp.yaml
+          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: apply_cr.rc != 0
+          failed_when: "'is invalid' in apply_cr.stderr"
+          ignore_errors: true
 
-        - name: Remove deprecated CiliumBGPPeeringPolicy after v2 resources are accepted
-          ansible.builtin.command: >-
-            {{ k3s_kubectl_binary | default('k3s kubectl') }}
-            delete CiliumBGPPeeringPolicy.cilium.io 01-bgp-peering-policy
-          register: delete_old_policy
-          changed_when: "'deleted' in delete_old_policy.stdout"
-          # The policy (and possibly its CRD) may already be absent; this is
-          # intentionally tolerated, not a command whose failure must be hidden.
-          failed_when: false
+        - 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 CiliumBGPClusterConfig.cilium.io"
-            - "{{ k3s_kubectl_binary | default('k3s kubectl') }} get CiliumBGPPeerConfig.cilium.io"
-            - "{{ k3s_kubectl_binary | default('k3s kubectl') }} get CiliumBGPAdvertisement.cilium.io"
+            - "{{ 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:

roles/k3s_server_post/tasks/metallb.yml

@@ -85,9 +85,17 @@
 
 - name: Set metallb webhook service name
   ansible.builtin.set_fact:
-    # Inspected the v0.16.0 manifest: the newer webhook Service name is used
-    # by every supported MetalLB release, so the old pre-0.14.4 branch is gone.
-    metallb_webhook_service_name: metallb-webhook-service
+    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
   ansible.builtin.command: >-

roles/k3s_server_post/templates/cilium.crs.j2

@@ -1,84 +1,40 @@
-# Cilium BGP Control Plane v2 resources.
-# Replace the deprecated v2alpha1 CiliumBGPPeeringPolicy that was removed
-# in Cilium 1.19.
-{% set _cilium_default_peer = {'peer_address': cilium_bgp_peer_address, 'peer_asn': cilium_bgp_peer_asn} %}
-{% set _cilium_peers = _cilium_bgp_neighbors if _cilium_bgp_neighbors | length > 0 else [_cilium_default_peer] %}
-apiVersion: cilium.io/v2
-kind: CiliumBGPPeerConfig
+apiVersion: "cilium.io/v2alpha1"
+kind: CiliumBGPPeeringPolicy
 metadata:
-  name: cilium-peer
-spec:
-  # Matches the timers and multihop used by the previous v2alpha1 policy.
-  ebgpMultihop: 10
-  timers:
-    connectRetryTimeSeconds: 120
-    holdTimeSeconds: 90
-    keepAliveTimeSeconds: 30
-  gracefulRestart:
-    enabled: true
-    restartTimeSeconds: 120
-  families:
-    - afi: ipv4
-      safi: unicast
-      advertisements:
-        matchLabels:
-          advertise: "bgp"
----
-apiVersion: cilium.io/v2
-kind: CiliumBGPClusterConfig
-metadata:
-  name: cilium-bgp
-spec:
-  # Explicitly select every node so the BGP instance runs across the cluster.
-  nodeSelector:
-    matchExpressions:
-      - key: somekey
-        operator: NotIn
-        values: ['never-used-value']
-  bgpInstances:
-    - name: "instance-{{ cilium_bgp_my_asn }}"
-      localASN: {{ cilium_bgp_my_asn }}
-      peers:
-{% for peer in _cilium_peers %}
-        - name: "peer-{{ peer.peer_asn }}-{{ loop.index }}"
-          peerASN: {{ peer.peer_asn }}
-          peerAddress: {{ peer.peer_address }}
-          peerConfigRef:
-            name: cilium-peer
+ 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 %}
-{% if cilium_exportPodCIDR %}
----
-apiVersion: cilium.io/v2
-kind: CiliumBGPAdvertisement
-metadata:
-  name: cilium-pod-cidrs
-  labels:
-    advertise: "bgp"
-spec:
-  advertisements:
-    - advertisementType: "PodCIDR"
+{% 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/v2
-kind: CiliumBGPAdvertisement
-metadata:
-  name: cilium-lb-services
-  labels:
-    advertise: "bgp"
-spec:
-  advertisements:
-    - advertisementType: "Service"
-      service:
-        addresses:
-          - LoadBalancerIP
-      # Advertise all Services carrying an ingress address from the pool.
-      selector:
-        matchExpressions:
-          - key: somekey
-            operator: NotIn
-            values: ['never-used-value']
----
-apiVersion: cilium.io/v2
+apiVersion: "cilium.io/v2alpha1"
 kind: CiliumLoadBalancerIPPool
 metadata:
   name: "01-lb-pool"