mirror of
https://github.com/Alkatrazz24/Funk-lab.git
synced 2026-07-08 22:24:42 +02:00
Ansible roles: - node_exporter : déploie node_exporter v1.9.1 sur storage-01 et gpu-01 avec textfile collector + services systemd. ROCm activé sur gpu-01 uniquement via group_vars. Collecte métriques GPU via sysfs (temp, VRAM, utilisation) — pas de dépendance rocm-smi (remplacé dans ROCm 7.x) - alertmanager_webhook : service Python sur storage-01 (:9093/webhook) reçoit alertes AlertManager et les route vers ask-agent monitor → Hermes Playbooks: node_exporter + alertmanager_webhook ajoutés à storage-01 et gpu-01 Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
40 lines
1.1 KiB
YAML
40 lines
1.1 KiB
YAML
---
|
|
- name: Create webhook install directory
|
|
ansible.builtin.file:
|
|
path: "{{ webhook_install_dir }}"
|
|
state: directory
|
|
owner: "{{ webhook_user }}"
|
|
group: "{{ webhook_user }}"
|
|
mode: '0755'
|
|
|
|
- name: Deploy webhook script
|
|
ansible.builtin.copy:
|
|
src: webhook.py
|
|
dest: "{{ webhook_install_dir }}/webhook.py"
|
|
owner: "{{ webhook_user }}"
|
|
group: "{{ webhook_user }}"
|
|
mode: '0755'
|
|
notify: Restart alertmanager-webhook
|
|
|
|
- name: Deploy webhook systemd service
|
|
ansible.builtin.template:
|
|
src: alertmanager-webhook.service.j2
|
|
dest: /etc/systemd/system/alertmanager-webhook.service
|
|
mode: '0644'
|
|
notify: Restart alertmanager-webhook
|
|
|
|
- name: Enable and start alertmanager-webhook
|
|
ansible.builtin.systemd:
|
|
name: alertmanager-webhook
|
|
enabled: true
|
|
state: started
|
|
daemon_reload: true
|
|
|
|
- name: Open webhook port in nftables
|
|
ansible.builtin.lineinfile:
|
|
path: /etc/nftables.conf
|
|
insertafter: '# prometheus'
|
|
line: " tcp dport {{ webhook_port }} ip saddr 192.168.10.0/24 accept comment \"alertmanager-webhook\""
|
|
state: present
|
|
notify: Reload nftables
|
|
ignore_errors: true
|