Fix playbook bugs from review, add Telegram alerts to health and service checks

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.

Claude-Session: https://claude.ai/code/session_01XEizHawueRXUcxQELRZ8kq
This commit is contained in:
Harwinder Sekhon
2026-09-06 23:06:18 -04:00
parent 0b7e136b24
commit 5aaa7020ac
21 changed files with 515 additions and 259 deletions
+49 -48
View File
@@ -1,73 +1,74 @@
---
- name: Build Dynamic Rocky Linux LXC Container
# Creates a Rocky Linux 9 container through the Proxmox API and starts it.
# Runs on the Semaphore host (localhost); proxmoxer must be importable by the
# Python that runs Ansible there.
#
# Extra vars (Semaphore environment / variable group):
# proxmox_api_user - e.g. root@pam (required)
# proxmox_api_password - that user's password (this, or a token)
# proxmox_api_token_id / proxmox_api_token_secret (API token instead of a password)
# proxmox_api_host - defaults to the pve entry in the inventory
#
# Optional: lxc_hostname, lxc_template, lxc_cores, lxc_memory, lxc_storage,
# lxc_disk_size, lxc_bridge, lxc_dns, target_node.
- name: Build a Rocky Linux LXC container
hosts: localhost
connection: local
gather_facts: false
vars:
# --- Container Specifications ---
lxc_hostname: "new_lxc"
lxc_template: "local:vztmpl/rockylinux-9-default_20240912_amd64.tar.xz"
proxmox_api_host: "{{ hostvars['pve'].ansible_host }}"
target_node: mini-pc
lxc_hostname: new-lxc # underscores are not valid in a hostname
lxc_template: local:vztmpl/rockylinux-9-default_20240912_amd64.tar.xz
lxc_cores: 2
lxc_memory: 1024
lxc_storage: "TB"
lxc_storage: TB
lxc_disk_size: 10
lxc_bridge: "vmbr0"
lxc_dns: "192.168.2.2"
target_node: "pve"
# --- Security & Access ---
lxc_bridge: vmbr0
lxc_dns: "{{ hostvars['pihole'].ansible_host }}"
lxc_ssh_key: "ssh-ed25519 AAAAC3NzaC1lZDI1NTE5AAAAINegitHaQG8i+s412h3wTWf/KvpeX1CEpYFva9MhHR+7 ansible-key"
module_defaults:
community.proxmox.proxmox:
api_host: "{{ proxmox_api_host }}"
api_user: "{{ proxmox_api_user }}"
api_password: "{{ proxmox_api_password | default(omit) }}"
api_token_id: "{{ proxmox_api_token_id | default(omit) }}"
api_token_secret: "{{ proxmox_api_token_secret | default(omit) }}"
validate_certs: false
timeout: 300 # template extraction takes longer than the 30 s default
tasks:
# ========================================================================
# NEW FIX: Auto-install missing dependencies into Semaphore's isolated venv
# ========================================================================
- name: Ensure Proxmox API dependencies are installed in Semaphore
ansible.builtin.shell: "{{ ansible_playbook_python }} -m pip install proxmoxer requests"
changed_when: false
# ========================================================================
- name: Ensure proxmoxer is available to the controller's Python
ansible.builtin.command: "{{ ansible_playbook_python }} -m pip install proxmoxer requests"
register: pip_install
changed_when: "'Successfully installed' in pip_install.stdout"
- name: Get the next available VMID from the Proxmox cluster
ansible.builtin.uri:
url: "https://{{ proxmox_api_host }}:8006/api2/json/cluster/nextid"
method: GET
headers:
Authorization: "PVEAPIToken {{ proxmox_api_user }}={{ proxmox_api_password }}"
validate_certs: false
return_content: true
register: nextid_response
- name: Extract the dynamic VMID from the API response
ansible.builtin.set_fact:
dynamic_vmid: "{{ nextid_response.json.data }}"
- name: Create the Rocky Linux LXC container
community.general.proxmox:
api_host: "{{ proxmox_api_host }}"
api_user: "{{ proxmox_api_user }}"
api_password: "{{ proxmox_api_password }}"
- name: Create the container (Proxmox assigns the next free VMID)
community.proxmox.proxmox:
node: "{{ target_node }}"
vmid: "{{ dynamic_vmid }}"
hostname: "{{ lxc_hostname }}"
ostemplate: "{{ lxc_template }}"
cores: "{{ lxc_cores }}"
memory: "{{ lxc_memory }}"
disk: "{{ lxc_storage }}:{{ lxc_disk_size }}"
netif: '{"net0":"name=eth0,bridge={{ lxc_bridge }},ip=dhcp"}'
netif:
net0: "name=eth0,bridge={{ lxc_bridge }},ip=dhcp"
nameserver: "{{ lxc_dns }}"
pubkey: "{{ lxc_ssh_key }}"
unprivileged: true
state: present
register: lxc_create
- name: Ensure the new LXC container is powered on
community.general.proxmox:
api_host: "{{ proxmox_api_host }}"
api_user: "{{ proxmox_api_user }}"
api_password: "{{ proxmox_api_password }}"
vmid: "{{ dynamic_vmid }}"
- name: Start the container
community.proxmox.proxmox:
vmid: "{{ lxc_create.vmid }}"
state: started
- name: Output the assigned VMID to the Semaphore UI logs
- name: Report
ansible.builtin.debug:
msg: "Successfully built {{ lxc_hostname }} (Rocky Linux 9) with dynamic ID: {{ dynamic_vmid }}"
msg: >-
Built {{ lxc_hostname }} (Rocky Linux 9) as VMID {{ lxc_create.vmid }} on {{ target_node }}.
Next: run discover_guests.yml with adopt=true, add it to inventories/all.yml, then bootstrap_lxc.yml.