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

---
- name: Install baseline packages (guest agent, Longhorn/iscsi/nfs prereqs)
  ansible.builtin.apt:
    name: "{{ node_baseline_packages }}"
    state: present
    update_cache: true
    cache_valid_time: 3600

- name: Persist kernel modules for k3s/Cilium/Longhorn
  ansible.builtin.copy:
    dest: /etc/modules-load.d/k3s-cilium-longhorn.conf
    owner: root
    group: root
    mode: "0644"
    content: "{{ node_baseline_kernel_modules | join('\n') }}\n"

- name: Load kernel modules now
  community.general.modprobe:
    name: "{{ item }}"
    state: present
  loop: "{{ node_baseline_kernel_modules }}"

- name: Install sysctl tuning for k3s/Cilium
  ansible.builtin.copy:
    dest: /etc/sysctl.d/99-k3s-cilium.conf
    owner: root
    group: root
    mode: "0644"
    content: |
      net.bridge.bridge-nf-call-iptables  = 1
      net.bridge.bridge-nf-call-ip6tables = 1
      net.ipv4.ip_forward                 = 1
      net.ipv6.conf.all.forwarding        = 1
      fs.inotify.max_user_instances       = 8192
      fs.inotify.max_user_watches         = 524288
  notify: Reload sysctl

- name: Enable and start iscsid (Longhorn prerequisite)
  ansible.builtin.systemd:
    name: iscsid
    enabled: true
    state: started

# qemu-guest-agent binds to the virtio-serial channel /dev/virtio-ports/org.qemu.guest_agent.0,
# which Proxmox attaches only when the VM's `agent` option is enabled. Our tofu keeps agent
# DISABLED on purpose (enabling it makes `tofu apply` block up to 15m waiting for an agent the
# stock Debian cloud image hasn't installed yet — bpg gotcha). So we ENABLE the unit for the day
# a channel exists, but only START it when the channel is actually present — never fail the
# baseline over a missing hypervisor channel.
- name: Check whether the qemu guest-agent virtio channel is attached
  ansible.builtin.stat:
    path: /dev/virtio-ports/org.qemu.guest_agent.0
  register: node_baseline_qga_channel

- name: Enable qemu-guest-agent (start only when its virtio channel is present)
  ansible.builtin.systemd:
    name: qemu-guest-agent
    enabled: true
    state: "{{ 'started' if node_baseline_qga_channel.stat.exists else 'stopped' }}"

- name: Create ext4 filesystem on the Longhorn data disk (data-safe; skips if present)
  community.general.filesystem:
    fstype: ext4
    dev: "{{ node_baseline_longhorn_device }}"
    opts: "-L {{ node_baseline_longhorn_fs_label }}"

- name: Mount the Longhorn data disk
  ansible.posix.mount:
    path: "{{ node_baseline_longhorn_mount }}"
    src: "LABEL={{ node_baseline_longhorn_fs_label }}"
    fstype: ext4
    opts: "defaults,nofail,x-systemd.device-timeout=5s"
    state: mounted

- name: Disable swap now
  ansible.builtin.command: swapoff -a
  changed_when: false

- name: Neutralize swap entries in fstab (kubelet requires swap off)
  ansible.builtin.replace:
    path: /etc/fstab
    regexp: '^([^#].*\sswap\s.*)$'
    replace: '# \1  # disabled for k3s/kubelet'

# --- DNS resilience (ROOT-CAUSE FIX) -----------------------------------------
# The nodes shipped with a SINGLE upstream resolver — PiHole (node_baseline_dns_primary,
# 192.168.1.18) — set by cloud-init/netplan. PiHole answers the local `jackson.lan` zone
# instantly but its EXTERNAL/recursive resolution flaps (verified: 0/25 for public names
# like registry-1.docker.io/api.cloudflare.com while `gitea.jackson.lan` resolved 5/5).
# With one upstream that is a hard SPOF: BOTH containerd image pulls (`lookup
# registry-1.docker.io: Try again`) AND CoreDNS (`forward . /etc/resolv.conf`, so pods'
# external DNS — external-dns→Cloudflare, oauth, etc.) fail whenever PiHole's recursion is
# down. cert-manager already had to bypass it with public resolvers (DECISIONS-LOG Fix 5).
#
# FIX (additive, no policy bypass): keep PiHole PRIMARY (preserves `jackson.lan` + network
# ad-blocking) and ADD the pfSense gateway (node_baseline_dns_fallback, 192.168.1.1) as a
# FALLBACK. pfSense resolves the public zones reliably (verified). The resolver (glibc for
# containerd; CoreDNS `forward` health-checking for pods) fails over to the fallback when
# PiHole times out. A higher-priority netplan drop-in carries the change; cloud-init's
# 50-cloud-init.yaml is regenerated on rebuild, so tofu's `dns.servers` list is updated to
# match for provision-time parity (both layers converge on the same two servers).
# NOTE: the *underlying* PiHole external-recursion outage is a separate LAN-wide problem to
# investigate; this only makes the k3s nodes resilient to it.
- name: Deploy resilient DNS (PiHole primary + pfSense fallback) via netplan drop-in
  ansible.builtin.copy:
    dest: /etc/netplan/99-k3s-dns.yaml
    owner: root
    group: root
    mode: "0600"
    content: |
      # Managed by the Ansible node_baseline role — do not edit by hand.
      # Additive DNS redundancy for the k3s nodes (see roles/node_baseline/tasks/main.yml):
      # PiHole PRIMARY (local zone + ad-block), pfSense gateway FALLBACK (reliable external
      # recursion). Overrides the single nameserver from 50-cloud-init.yaml.
      network:
        version: 2
        ethernets:
          {{ node_baseline_primary_iface }}:
            nameservers:
              addresses: [{{ node_baseline_dns_primary }}, {{ node_baseline_dns_fallback }}]
              search: [{{ node_baseline_dns_search }}]
  notify: Apply netplan
  tags: [dns]