panxiao81
88a02ababa
Reorganize the brownfield repository, remove retired and generated artifacts, harden ignore rules, and record the GitOps/IaC redesign.
77 lines
3.0 KiB
YAML
77 lines
3.0 KiB
YAML
---
|
|
# Proxmox HA. Read roles/pve_ha/defaults/main.yml first — it explains why the
|
|
# resource list is short and why the watchdog choice is not cosmetic.
|
|
|
|
# --- Watchdog ---------------------------------------------------------------
|
|
# Done BEFORE registering resources: adding a resource arms fencing, and arming
|
|
# fencing on a software watchdog is the weakest configuration.
|
|
- name: Select the hardware watchdog module
|
|
ansible.builtin.lineinfile:
|
|
path: /etc/default/pve-ha-manager
|
|
regexp: '^#?\s*WATCHDOG_MODULE='
|
|
line: "WATCHDOG_MODULE={{ pve_ha_watchdog_module }}"
|
|
create: false
|
|
when: pve_ha_watchdog_module | length > 0
|
|
notify: reboot required for watchdog
|
|
tags: [ha, watchdog]
|
|
|
|
# watchdog-mux opens /dev/watchdog, which belongs to whichever watchdog registered
|
|
# FIRST. PVE loads softdog at boot, so it wins and the hardware module ends up as
|
|
# an unused watchdog1. Blacklisting softdog is what actually makes the hardware
|
|
# one take effect — setting WATCHDOG_MODULE alone does nothing.
|
|
- name: Blacklist softdog so the hardware watchdog claims /dev/watchdog
|
|
ansible.builtin.copy:
|
|
dest: /etc/modprobe.d/pve-ha-watchdog.conf
|
|
mode: "0644"
|
|
content: |
|
|
# Managed by ansible (roles/pve_ha). See that role for the reasoning.
|
|
# softdog cannot fence a frozen kernel; blacklisting it lets
|
|
# {{ pve_ha_watchdog_module }} register as watchdog0 and own /dev/watchdog.
|
|
blacklist softdog
|
|
when: pve_ha_watchdog_module | length > 0
|
|
notify: reboot required for watchdog
|
|
tags: [ha, watchdog]
|
|
|
|
# ⚠ NOT DONE LIVE ON PURPOSE. Swapping the watchdog on a running node means
|
|
# stopping watchdog-mux and unloading softdog while fencing is armed — get the
|
|
# order wrong and the node self-fences (reboots). The safe live procedure is
|
|
# documented in ../../README-ha.md; otherwise it simply takes effect on the next
|
|
# reboot, which is why the handler only WARNS rather than rebooting anything.
|
|
|
|
# --- Resources ---------------------------------------------------------------
|
|
- name: Read current HA resources
|
|
ansible.builtin.command: ha-manager status
|
|
register: pve_ha_status
|
|
changed_when: false
|
|
failed_when: false
|
|
run_once: true
|
|
tags: [ha]
|
|
|
|
- name: Register HA resources
|
|
ansible.builtin.command: >-
|
|
ha-manager add {{ item.sid }}
|
|
--state {{ item.state }}
|
|
--max_restart {{ item.max_restart }}
|
|
--max_relocate {{ item.max_relocate }}
|
|
loop: "{{ pve_ha_resources }}"
|
|
loop_control:
|
|
label: "{{ item.sid }}"
|
|
# `ha-manager add` errors if the resource already exists, so gate on the status
|
|
# output. This is what keeps a second run at changed=0.
|
|
when: "'service ' ~ item.sid not in (pve_ha_status.stdout | default(''))"
|
|
run_once: true
|
|
tags: [ha]
|
|
|
|
- name: Verify HA is armed and the resource is known
|
|
ansible.builtin.command: ha-manager status
|
|
register: pve_ha_verify
|
|
changed_when: false
|
|
run_once: true
|
|
tags: [ha]
|
|
|
|
- name: Show HA state
|
|
ansible.builtin.debug:
|
|
msg: "{{ pve_ha_verify.stdout_lines }}"
|
|
run_once: true
|
|
tags: [ha]
|