home-network-k3s-impl/infra/ansible/roles/k3s_server/tasks/main.yml

---
# Install k3s as an HA server (embedded etcd) with Cilium-required components
# disabled (ADR-0001, docs/02 stage 3 "Cluster-join"). The primary runs
# --cluster-init; secondaries join it with the shared node-token.

- name: Download the k3s install script
  ansible.builtin.get_url:
    url: "{{ k3s_install_url }}"
    dest: "{{ k3s_install_script }}"
    mode: "0755"

# --node-ip uses k3s_node_ip (the real 192.168.1.x), NOT ansible_host — the latter is
# now the pfSense NAT SSH target (192.168.2.102:225x) and must not be advertised to k3s.
- name: Compose the common k3s server flags
  ansible.builtin.set_fact:
    k3s_common_args: >-
      server
      --flannel-backend=none
      --disable-kube-proxy
      --disable-network-policy
      --disable={{ k3s_disable }}
      --write-kubeconfig-mode=644
      {% for san in k3s_tls_sans %}--tls-san={{ san }} {% endfor %}
      --node-ip={{ k3s_node_ip }}

# On an ALREADY-installed cluster the install task above is idempotent (creates:
# k3s.yaml) and won't re-apply new --tls-san flags. Persist the SAN list in
# /etc/rancher/k3s/config.yaml, which a running k3s reads on the next restart —
# it then regenerates the serving cert when the SAN set changes. Apply the
# restart ROLLING, one node at a time (kube-vip keeps the API reachable; etcd
# quorum holds at 2/3). See playbooks note: run with `serial: 1`.
- name: Write /etc/rancher/k3s/config.yaml with the tls-san list
  ansible.builtin.copy:
    dest: /etc/rancher/k3s/config.yaml
    owner: root
    group: root
    mode: "0600"
    content: |
      # Managed by Ansible (roles/k3s_server). Read by k3s in addition to the
      # systemd unit flags; tls-san entries are merged into the serving cert.
      tls-san:
      {% for san in k3s_tls_sans %}
        - "{{ san }}"
      {% endfor %}
  notify: Restart k3s

# --- primary: found the cluster --------------------------------------------
- name: Install k3s primary (cluster-init, embedded etcd)
  ansible.builtin.command:
    cmd: "{{ k3s_install_script }} {{ k3s_common_args }} --cluster-init"
    creates: /etc/rancher/k3s/k3s.yaml
  environment:
    INSTALL_K3S_VERSION: "{{ k3s_version }}"
  when: k3s_server_mode == 'primary'

- name: Wait for the k3s node-token to exist (primary)
  ansible.builtin.wait_for:
    path: /var/lib/rancher/k3s/server/token
    timeout: 180
  when: k3s_server_mode == 'primary'

- name: Read the k3s node-token (primary)
  ansible.builtin.slurp:
    src: /var/lib/rancher/k3s/server/token
  register: k3s_token_raw
  when: k3s_server_mode == 'primary'

- name: Publish the node-token as a fact for secondaries (primary)
  ansible.builtin.set_fact:
    k3s_node_token: "{{ k3s_token_raw.content | b64decode | trim }}"
  when: k3s_server_mode == 'primary'

# --- secondaries: obtain the join token, then join the existing cluster -----
# Fetch the token straight from the primary via delegate_to, falling back to it
# only when the primary play didn't publish the fact this run. This makes a
# single-node rejoin (`--limit k3s-dev-N`, primary NOT in the batch) self-
# contained — delegate_to still reaches the primary even when it isn't a play
# target, so the join no longer depends on a fact an earlier play had to set.
# T-1.5 finding F2 (see DECISIONS-LOG.md).
- name: Fetch the k3s node-token directly from the primary (secondary)
  ansible.builtin.slurp:
    src: /var/lib/rancher/k3s/server/token
  delegate_to: "{{ groups['k3s_primary'][0] }}"
  register: k3s_primary_token_raw
  when:
    - k3s_server_mode == 'secondary'
    - hostvars[groups['k3s_primary'][0]].k3s_node_token is not defined

- name: Resolve the join token (secondary)
  ansible.builtin.set_fact:
    k3s_join_token: >-
      {{ hostvars[groups['k3s_primary'][0]].k3s_node_token
         | default(k3s_primary_token_raw.content | b64decode | trim, true) }}
  when: k3s_server_mode == 'secondary'

- name: Install k3s secondary (join as server)
  ansible.builtin.command:
    cmd: >-
      {{ k3s_install_script }} {{ k3s_common_args }}
      --server https://{{ k3s_api_host }}:{{ k3s_api_port }}
    creates: /etc/rancher/k3s/k3s.yaml
  environment:
    INSTALL_K3S_VERSION: "{{ k3s_version }}"
    K3S_TOKEN: "{{ k3s_join_token }}"
  when: k3s_server_mode == 'secondary'

- name: Wait for the k3s API to be serving locally
  ansible.builtin.wait_for:
    host: "127.0.0.1"
    port: "{{ k3s_api_port }}"
    timeout: 180