Harwinder Sekhon
006103760f
Review fixes: - Availability plays: "ping_result is succeeded" is true for unreachable hosts, so offline hosts were added to reachable_hosts and failed the next play. Test reachability explicitly (7 playbooks). - bootstrap_lxc: vim-enhanced and mtr-tiny package names, enable CRB next to EPEL, add the root key without replacing authorized_keys, validate sshd_config edits and restart sshd only on change. - backup_docker: the command module does not expand $(...); fix rsync filter order and add --exclude=*; restart only the containers that were stopped, even when rsync fails; read the storage address from the inventory; keep semaphore and semaphore-db running. - new_lxc: community.general.proxmox no longer exists, use community.proxmox; node is mini-pc; valid hostname; password or token auth; let the module pick the VMID; longer timeout. - proxmox-backup: surface the vzdump exit code, let vzdump prune with keep-last, drop the rename/prune steps that globbed *.zstd. - time-region: chrony regex no longer comments out its own server line; /etc/localtime as a symlink; reuse facts across plays. - update_pihole_blocklists: FQCN, become: true, changed_when. - ansible.cfg gathering = smart; update_system only pings ubuntu/rocky. Telegram alerts: - health_check: filesystems above disk_warn_pct (default 80), excluding efivarfs, and offline hosts. - service_check: services not running. - One message per run from localhost, credentials from Semaphore (TELEGRAM_BOT_TOKEN / TELEGRAM_CHAT_ID), no_log on the send task, prints the alert text when Telegram is not configured. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01XEizHawueRXUcxQELRZ8kq
82 lines
3.1 KiB
YAML
82 lines
3.1 KiB
YAML
---
|
|
# vzdump of selected guests on the Proxmox host. vzdump prunes old dumps of
|
|
# each guest itself (keep-last), so nothing else touches the dump directory.
|
|
# Every run is appended to {{ backup_dir }}/proxmox_backup.log on the host.
|
|
#
|
|
# backup_mode "stop" shuts the guest down for the whole backup. Never list
|
|
# the guest that runs Semaphore with mode stop: the job would stop itself
|
|
# half way through. Use "snapshot" for that one (falls back to suspend on
|
|
# storage without snapshot support).
|
|
#
|
|
# Extra vars (optional):
|
|
# guests - list of { id, type, name }
|
|
# keep_last - dumps kept per guest (default 3)
|
|
# backup_mode - stop | snapshot | suspend (default stop)
|
|
# storage - target PVE storage id (default local)
|
|
# compression - zstd | gzip | lzo (default zstd)
|
|
|
|
- name: Backup selected Proxmox VMs and LXCs
|
|
hosts: proxmox
|
|
become: true
|
|
gather_facts: false
|
|
|
|
vars:
|
|
backup_dir: /var/lib/vz/dump
|
|
storage: local
|
|
compression: zstd
|
|
keep_last: 3
|
|
backup_mode: stop
|
|
guests:
|
|
# - { id: 104, type: lxc, name: courses }
|
|
- { id: 108, type: lxc, name: docker }
|
|
# - { id: 101, type: qemu, name: pnetlab }
|
|
|
|
tasks:
|
|
- name: Ensure the log directory exists
|
|
ansible.builtin.file:
|
|
path: "{{ backup_dir }}"
|
|
state: directory
|
|
mode: '0755'
|
|
|
|
- name: Run vzdump
|
|
ansible.builtin.shell: |
|
|
set -o pipefail
|
|
LOGFILE="{{ backup_dir }}/proxmox_backup.log"
|
|
START=$(date +%s)
|
|
echo "[$(date '+%Y-%m-%d %H:%M:%S')] START {{ item.name }} ({{ item.type }} {{ item.id }}) mode={{ backup_mode }}" >> "$LOGFILE"
|
|
OUTPUT=$(vzdump {{ item.id }} --mode {{ backup_mode }} --compress {{ compression }} \
|
|
--storage {{ storage }} --prune-backups keep-last={{ keep_last }} 2>&1)
|
|
STATUS=$?
|
|
DURATION=$(( $(date +%s) - START ))
|
|
if [ "$STATUS" -eq 0 ]; then
|
|
echo "[$(date '+%Y-%m-%d %H:%M:%S')] SUCCESS {{ item.name }} ({{ item.id }}) ${DURATION}s" >> "$LOGFILE"
|
|
echo "$OUTPUT" | grep -E 'archive file size|pruned|removing backup' || true
|
|
else
|
|
echo "[$(date '+%Y-%m-%d %H:%M:%S')] FAILURE {{ item.name }} ({{ item.id }}) ${DURATION}s" >> "$LOGFILE"
|
|
printf -- '---- vzdump output ----\n%s\n-----------------------\n' "$OUTPUT" >> "$LOGFILE"
|
|
echo "$OUTPUT" | tail -n 20
|
|
fi
|
|
exit "$STATUS"
|
|
args:
|
|
executable: /bin/bash
|
|
loop: "{{ guests }}"
|
|
loop_control:
|
|
label: "{{ item.name }} ({{ item.type }} {{ item.id }})"
|
|
changed_when: true
|
|
|
|
- name: List the dumps kept for each guest
|
|
ansible.builtin.command: pvesm list {{ storage }} --content backup --vmid {{ item.id }}
|
|
loop: "{{ guests }}"
|
|
loop_control:
|
|
label: "{{ item.name }} ({{ item.id }})"
|
|
register: dump_lists
|
|
changed_when: false
|
|
|
|
- name: Backup summary
|
|
ansible.builtin.debug:
|
|
msg: |
|
|
{% for r in dump_lists.results %}
|
|
{{ r.item.name }} ({{ r.item.type }} {{ r.item.id }}) - mode {{ backup_mode }}, keeping the last {{ keep_last }}:
|
|
{{ r.stdout }}
|
|
{% endfor %}
|