feat: monitoring — node_exporter + ROCm sysfs collector + alertmanager webhook

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>
This commit is contained in:
alkatrazz 2026-05-13 21:01:03 +02:00
parent 857351bcf9
commit 92a882aa94
15 changed files with 354 additions and 2 deletions

View file

@ -0,0 +1,86 @@
---
- name: Create node_exporter user
ansible.builtin.user:
name: "{{ node_exporter_user }}"
shell: /sbin/nologin
create_home: false
system: true
state: present
- name: Create textfile collector directory
ansible.builtin.file:
path: "{{ node_exporter_textfile_dir }}"
state: directory
owner: "{{ node_exporter_user }}"
group: "{{ node_exporter_user }}"
mode: '0755'
- name: Download node_exporter
ansible.builtin.get_url:
url: "https://github.com/prometheus/node_exporter/releases/download/v{{ node_exporter_version }}/node_exporter-{{ node_exporter_version }}.linux-amd64.tar.gz"
dest: "/tmp/node_exporter-{{ node_exporter_version }}.tar.gz"
mode: '0644'
- name: Extract node_exporter
ansible.builtin.unarchive:
src: "/tmp/node_exporter-{{ node_exporter_version }}.tar.gz"
dest: /tmp/
remote_src: true
creates: "/tmp/node_exporter-{{ node_exporter_version }}.linux-amd64/node_exporter"
- name: Install node_exporter binary
ansible.builtin.copy:
src: "/tmp/node_exporter-{{ node_exporter_version }}.linux-amd64/node_exporter"
dest: /usr/local/bin/node_exporter
owner: root
group: root
mode: '0755'
remote_src: true
- name: Deploy node_exporter systemd service
ansible.builtin.template:
src: node_exporter.service.j2
dest: /etc/systemd/system/node_exporter.service
mode: '0644'
notify: Restart node_exporter
- name: Enable and start node_exporter
ansible.builtin.systemd:
name: node_exporter
enabled: true
state: started
daemon_reload: true
- name: Open node_exporter port in nftables
ansible.builtin.lineinfile:
path: /etc/nftables.conf
insertafter: '# prometheus'
line: " tcp dport {{ node_exporter_port }} accept comment \"node_exporter\""
state: present
notify: Reload nftables
ignore_errors: true
- name: Deploy ROCm scraper script
ansible.builtin.template:
src: rocm_scraper.sh.j2
dest: /usr/local/bin/rocm_scraper.sh
mode: '0755'
when: rocm_exporter_enabled
- name: Deploy ROCm scraper service + timer
ansible.builtin.template:
src: "{{ item }}.j2"
dest: "/etc/systemd/system/{{ item }}"
mode: '0644'
loop:
- rocm_scraper.service
- rocm_scraper.timer
when: rocm_exporter_enabled
- name: Enable ROCm scraper timer
ansible.builtin.systemd:
name: rocm_scraper.timer
enabled: true
state: started
daemon_reload: true
when: rocm_exporter_enabled