Files
infra/ansible/playbooks/grimmory-update.yml
T
DmitryandClaude Sonnet 5 5e27ba2513 fix: update playbooks read the backup VMID from the registry; drop client-side prune
The *-update.yml playbooks hard-coded the pre-migration VMIDs, so after cutover
the "safety backup" ran against the stopped OLD container. Now the VMID comes
from homelab_services['<svc>'].vmid.

Also removes `--prune-backups keep-all=1` from the vzdump calls: retention is
PBS's job (prune-pbs), and the client-side flag needed Datastore.Modify/Prune
the ansible@pve token does not have, which made vzdump print "Backup ... failed"
and exit non-zero after a successful upload.

gitea-update.yml additionally splits the offsite backup (hosts: gitea) from its
audit (hosts: cloud-pc), matching the profile move into the container.
pve-*.yml imports pass pve_provisioning_enabled: false so the runtime update
path never re-enters container creation.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_012uoq5AVK8mkBgg83Mq6o5V
2026-09-03 07:05:56 +03:00

110 lines
3.2 KiB
YAML

---
- name: Create and verify Grimmory backup before update
hosts: grimmory
gather_facts: false
tasks:
- name: Create a fresh Grimmory offsite backup
ansible.builtin.command:
argv:
- systemctl
- start
- --wait
- homelab-restic-offsite-grimmory.service
changed_when: true
- name: Run Grimmory offsite backup audit
ansible.builtin.command:
argv:
- systemctl
- start
- --wait
- homelab-backup-audit-grimmory.service
changed_when: true
- name: Create a fresh Grimmory PBS backup
hosts: cloud-pc
gather_facts: false
vars:
grimmory_vmid: "{{ homelab_services['grimmory'].vmid }}"
tasks:
- name: Read Grimmory LXC config
ansible.builtin.command:
argv:
- pct
- config
- "{{ grimmory_vmid }}"
register: grimmory_pct_config
changed_when: false
- name: Assert registry VMID belongs to Grimmory
ansible.builtin.assert:
that:
- grimmory_pct_hostname_line != ""
- grimmory_pct_hostname == "grimmory"
fail_msg: >-
Refusing to run vzdump {{ grimmory_vmid }} because pct config
hostname is not grimmory:
{{ grimmory_pct_hostname_line | default('missing hostname line') }}
vars:
grimmory_pct_hostname_line: >-
{{ (grimmory_pct_config.stdout_lines | select('match', '^hostname:\\s+') | list | first | default('')) }}
grimmory_pct_hostname: >-
{{ grimmory_pct_hostname_line | regex_replace('^hostname:\\s*', '') }}
- name: Check for active Proxmox backup before Grimmory PBS backup
ansible.builtin.command: pgrep -x vzdump
register: grimmory_vzdump_preflight
changed_when: false
failed_when: false
- name: Require no active Proxmox backup before Grimmory PBS backup
ansible.builtin.assert:
that:
- grimmory_vzdump_preflight.rc != 0
fail_msg: >-
A Proxmox backup is already running on cloud-pc.
Retry after the existing backup completes.
- name: Create a fresh Grimmory PBS backup
ansible.builtin.command:
argv:
- vzdump
- "{{ grimmory_vmid }}"
- --storage
- pbs
- --mode
- snapshot
- --exclude-path
- /var/lib/docker/fuse-overlayfs/*/merged
- name: Run PBS backup audit on mini-pc
hosts: mini-pc
gather_facts: false
tasks:
- name: Run current PBS backup audit on mini-pc
ansible.builtin.command:
argv:
- systemctl
- start
- --wait
- homelab-backup-audit-pbs.service
changed_when: true
- import_playbook: pve-grimmory.yml
vars:
pve_provisioning_enabled: false
- name: Verify Grimmory public endpoint after update
hosts: ru-vps
gather_facts: false
tasks:
- name: Check Grimmory public health endpoint
ansible.builtin.uri:
url: https://books.ada-dev.ru/api/v1/healthcheck
status_code: 200
return_content: false
register: grimmory_public_health
retries: 24
delay: 5
until: grimmory_public_health.status == 200