claude-home/ansible/playbooks/monthly-reboot.yml
Cal Corum 29a20fbe06
All checks were successful
Reindex Knowledge Base / reindex (push) Successful in 2s
feat: add monthly Proxmox maintenance reboot automation (#26)
Establishes a first-Sunday-of-the-month maintenance window orchestrated
by Ansible on LXC 304. Split into two playbooks to handle the self-reboot
paradox (the controller is a guest on the host being rebooted):

- monthly-reboot.yml: snapshots, tiered shutdown with per-guest polling,
  fire-and-forget host reboot
- post-reboot-startup.yml: controlled tiered startup with staggered delays,
  Pi-hole UDP DNS fix, validation, and snapshot cleanup

Also fixes onboot:1 on VM 109, LXC 221, LXC 223 and creates a recurring
Google Calendar event for the maintenance window.

Closes #26

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-03 23:33:59 -05:00

266 lines
9.6 KiB
YAML

---
# Monthly Proxmox Maintenance Reboot — Shutdown & Reboot
#
# Orchestrates a graceful shutdown of all guests in dependency order,
# then issues a fire-and-forget reboot to the Proxmox host.
#
# After the host reboots, LXC 304 auto-starts via onboot:1 and the
# post-reboot-startup.yml playbook runs automatically via the
# ansible-post-reboot.service systemd unit (triggered by @reboot).
#
# Schedule: 1st Sunday of each month, 08:00 UTC (3 AM ET)
# Controller: LXC 304 (ansible-controller) at 10.10.0.232
#
# Usage:
# # Dry run
# ansible-playbook /opt/ansible/playbooks/monthly-reboot.yml --check
#
# # Full execution
# ansible-playbook /opt/ansible/playbooks/monthly-reboot.yml
#
# # Shutdown only (skip the host reboot)
# ansible-playbook /opt/ansible/playbooks/monthly-reboot.yml --tags shutdown
#
# Note: VM 109 (homeassistant) is excluded from Ansible inventory
# (self-managed via HA Supervisor) but is included in pvesh start/stop.
- name: Pre-reboot health check and snapshots
hosts: pve-node
gather_facts: false
tags: [pre-reboot, shutdown]
tasks:
- name: Check Proxmox cluster health
ansible.builtin.command: pvesh get /cluster/status --output-format json
register: cluster_status
changed_when: false
- name: Get list of running QEMU VMs
ansible.builtin.shell: >
pvesh get /nodes/proxmox/qemu --output-format json |
python3 -c "import sys,json; [print(vm['vmid']) for vm in json.load(sys.stdin) if vm.get('status')=='running']"
register: running_vms
changed_when: false
- name: Get list of running LXC containers
ansible.builtin.shell: >
pvesh get /nodes/proxmox/lxc --output-format json |
python3 -c "import sys,json; [print(ct['vmid']) for ct in json.load(sys.stdin) if ct.get('status')=='running']"
register: running_lxcs
changed_when: false
- name: Display running guests
ansible.builtin.debug:
msg: "Running VMs: {{ running_vms.stdout_lines }} | Running LXCs: {{ running_lxcs.stdout_lines }}"
- name: Snapshot running VMs
ansible.builtin.command: >
pvesh create /nodes/proxmox/qemu/{{ item }}/snapshot
--snapname pre-maintenance-{{ lookup('pipe', 'date +%Y-%m-%d') }}
--description "Auto snapshot before monthly maintenance reboot"
loop: "{{ running_vms.stdout_lines }}"
when: running_vms.stdout_lines | length > 0
ignore_errors: true
- name: Snapshot running LXCs
ansible.builtin.command: >
pvesh create /nodes/proxmox/lxc/{{ item }}/snapshot
--snapname pre-maintenance-{{ lookup('pipe', 'date +%Y-%m-%d') }}
--description "Auto snapshot before monthly maintenance reboot"
loop: "{{ running_lxcs.stdout_lines }}"
when: running_lxcs.stdout_lines | length > 0
ignore_errors: true
- name: "Shutdown Tier 4 — Media & Others"
hosts: pve-node
gather_facts: false
tags: [shutdown]
vars:
tier4_vms: [109]
# LXC 303 (mcp-gateway) is onboot=0 and operator-managed — not included here
tier4_lxcs: [221, 222, 223, 302]
tasks:
- name: Shutdown Tier 4 VMs
ansible.builtin.command: pvesh create /nodes/proxmox/qemu/{{ item }}/status/shutdown
loop: "{{ tier4_vms }}"
ignore_errors: true
- name: Shutdown Tier 4 LXCs
ansible.builtin.command: pvesh create /nodes/proxmox/lxc/{{ item }}/status/shutdown
loop: "{{ tier4_lxcs }}"
ignore_errors: true
- name: Wait for Tier 4 VMs to stop
ansible.builtin.shell: >
pvesh get /nodes/proxmox/qemu/{{ item }}/status/current --output-format json |
python3 -c "import sys,json; print(json.load(sys.stdin).get('status','unknown'))"
register: t4_vm_status
until: t4_vm_status.stdout.strip() == "stopped"
retries: 12
delay: 5
loop: "{{ tier4_vms }}"
ignore_errors: true
- name: Wait for Tier 4 LXCs to stop
ansible.builtin.shell: >
pvesh get /nodes/proxmox/lxc/{{ item }}/status/current --output-format json |
python3 -c "import sys,json; print(json.load(sys.stdin).get('status','unknown'))"
register: t4_lxc_status
until: t4_lxc_status.stdout.strip() == "stopped"
retries: 12
delay: 5
loop: "{{ tier4_lxcs }}"
ignore_errors: true
- name: "Shutdown Tier 3 — Applications"
hosts: pve-node
gather_facts: false
tags: [shutdown]
vars:
tier3_vms: [115, 110]
tier3_lxcs: [301]
tasks:
- name: Shutdown Tier 3 VMs
ansible.builtin.command: pvesh create /nodes/proxmox/qemu/{{ item }}/status/shutdown
loop: "{{ tier3_vms }}"
ignore_errors: true
- name: Shutdown Tier 3 LXCs
ansible.builtin.command: pvesh create /nodes/proxmox/lxc/{{ item }}/status/shutdown
loop: "{{ tier3_lxcs }}"
ignore_errors: true
- name: Wait for Tier 3 VMs to stop
ansible.builtin.shell: >
pvesh get /nodes/proxmox/qemu/{{ item }}/status/current --output-format json |
python3 -c "import sys,json; print(json.load(sys.stdin).get('status','unknown'))"
register: t3_vm_status
until: t3_vm_status.stdout.strip() == "stopped"
retries: 12
delay: 5
loop: "{{ tier3_vms }}"
ignore_errors: true
- name: Wait for Tier 3 LXCs to stop
ansible.builtin.shell: >
pvesh get /nodes/proxmox/lxc/{{ item }}/status/current --output-format json |
python3 -c "import sys,json; print(json.load(sys.stdin).get('status','unknown'))"
register: t3_lxc_status
until: t3_lxc_status.stdout.strip() == "stopped"
retries: 12
delay: 5
loop: "{{ tier3_lxcs }}"
ignore_errors: true
- name: "Shutdown Tier 2 — Infrastructure"
hosts: pve-node
gather_facts: false
tags: [shutdown]
vars:
tier2_vms: [106, 116]
tier2_lxcs: [225, 210, 227]
tasks:
- name: Shutdown Tier 2 VMs
ansible.builtin.command: pvesh create /nodes/proxmox/qemu/{{ item }}/status/shutdown
loop: "{{ tier2_vms }}"
ignore_errors: true
- name: Shutdown Tier 2 LXCs
ansible.builtin.command: pvesh create /nodes/proxmox/lxc/{{ item }}/status/shutdown
loop: "{{ tier2_lxcs }}"
ignore_errors: true
- name: Wait for Tier 2 VMs to stop
ansible.builtin.shell: >
pvesh get /nodes/proxmox/qemu/{{ item }}/status/current --output-format json |
python3 -c "import sys,json; print(json.load(sys.stdin).get('status','unknown'))"
register: t2_vm_status
until: t2_vm_status.stdout.strip() == "stopped"
retries: 12
delay: 5
loop: "{{ tier2_vms }}"
ignore_errors: true
- name: Wait for Tier 2 LXCs to stop
ansible.builtin.shell: >
pvesh get /nodes/proxmox/lxc/{{ item }}/status/current --output-format json |
python3 -c "import sys,json; print(json.load(sys.stdin).get('status','unknown'))"
register: t2_lxc_status
until: t2_lxc_status.stdout.strip() == "stopped"
retries: 12
delay: 5
loop: "{{ tier2_lxcs }}"
ignore_errors: true
- name: "Shutdown Tier 1 — Databases"
hosts: pve-node
gather_facts: false
tags: [shutdown]
vars:
tier1_vms: [112]
tasks:
- name: Shutdown database VMs
ansible.builtin.command: pvesh create /nodes/proxmox/qemu/{{ item }}/status/shutdown
loop: "{{ tier1_vms }}"
ignore_errors: true
- name: Wait for database VMs to stop (up to 90s)
ansible.builtin.shell: >
pvesh get /nodes/proxmox/qemu/{{ item }}/status/current --output-format json |
python3 -c "import sys,json; print(json.load(sys.stdin).get('status','unknown'))"
register: t1_vm_status
until: t1_vm_status.stdout.strip() == "stopped"
retries: 18
delay: 5
loop: "{{ tier1_vms }}"
ignore_errors: true
- name: Force stop database VMs if still running
ansible.builtin.shell: >
status=$(pvesh get /nodes/proxmox/qemu/{{ item }}/status/current --output-format json |
python3 -c "import sys,json; print(json.load(sys.stdin).get('status','unknown'))");
if [ "$status" = "running" ]; then
pvesh create /nodes/proxmox/qemu/{{ item }}/status/stop;
echo "Force stopped VM {{ item }}";
else
echo "VM {{ item }} already stopped";
fi
loop: "{{ tier1_vms }}"
register: force_stop_result
changed_when: force_stop_result.results | default([]) | selectattr('stdout', 'defined') | selectattr('stdout', 'search', 'Force stopped') | list | length > 0
- name: "Verify and reboot Proxmox host"
hosts: pve-node
gather_facts: false
tags: [reboot]
tasks:
- name: Verify all guests are stopped (excluding LXC 304)
ansible.builtin.shell: >
running_vms=$(pvesh get /nodes/proxmox/qemu --output-format json |
python3 -c "import sys,json; vms=[v for v in json.load(sys.stdin) if v.get('status')=='running']; print(len(vms))");
running_lxcs=$(pvesh get /nodes/proxmox/lxc --output-format json |
python3 -c "import sys,json; cts=[c for c in json.load(sys.stdin) if c.get('status')=='running' and c['vmid'] != 304]; print(len(cts))");
echo "Running VMs: $running_vms, Running LXCs: $running_lxcs";
if [ "$running_vms" != "0" ] || [ "$running_lxcs" != "0" ]; then exit 1; fi
register: verify_stopped
- name: Issue fire-and-forget reboot (controller will be killed)
ansible.builtin.shell: >
nohup bash -c 'sleep 10 && reboot' &>/dev/null &
echo "Reboot scheduled in 10 seconds"
register: reboot_issued
when: not ansible_check_mode
- name: Log reboot issued
ansible.builtin.debug:
msg: "{{ reboot_issued.stdout }} — Ansible process will terminate when host reboots. Post-reboot startup handled by ansible-post-reboot.service on LXC 304."