Operations and observability for sifaka NAS (#135)
## Summary - Add `smartctl_exporter` Docker container to sifaka for SMART disk health monitoring - Formalize existing `node_exporter` container under Ansible management - Route both exporters through Caddy L4 TCP proxy (`nas.ops.eblu.me:9100`, `nas.ops.eblu.me:9633`), replacing the hardcoded LAN IP in Prometheus - Create "Sifaka Disk Health" Grafana dashboard (health status, temperature, wear indicators, lifetime) - Introduce `ansible/playbooks/sifaka.yml` and `mise run provision-sifaka` — first Ansible playbook for the NAS - Shared exporter port variables in `group_vars/all.yml` to avoid duplication between Caddy and sifaka roles ## Prerequisites before deploy - [ ] Enable SSH on sifaka (DSM Control Panel > Terminal & SNMP) - [ ] Verify `ssh eblume@sifaka 'docker ps'` works - [ ] Run `mise run provision-sifaka` to deploy containers - [ ] Run `mise run provision-indri -- --tags caddy` to add L4 routes - [ ] `argocd app sync prometheus` + `argocd app sync grafana-config` ## Test plan - [ ] Verify smartctl_exporter metrics: `curl http://nas.ops.eblu.me:9633/metrics` - [ ] Verify Prometheus targets page shows both sifaka jobs as UP - [ ] Verify Grafana "Sifaka Disk Health" dashboard loads with data 🤖 Generated with [Claude Code](https://claude.com/claude-code) Reviewed-on: https://forge.ops.eblu.me/eblume/blumeops/pulls/135
This commit is contained in:
parent
4ee643a81d
commit
85e36cd807
15 changed files with 538 additions and 9 deletions
|
|
@ -1,2 +0,0 @@
|
|||
---
|
||||
ansible_managed: "Managed by ansible - do not edit. Source: ssh://forgejo@forge.ops.eblu.me:2222/eblume/blumeops.git"
|
||||
6
ansible/inventory/group_vars/all.yml
Normal file
6
ansible/inventory/group_vars/all.yml
Normal file
|
|
@ -0,0 +1,6 @@
|
|||
---
|
||||
ansible_managed: "Managed by ansible - do not edit. Source: ssh://forgejo@forge.ops.eblu.me:2222/eblume/blumeops.git"
|
||||
|
||||
# Sifaka NAS exporter ports — shared by caddy (indri) and sifaka_exporters roles
|
||||
sifaka_node_exporter_port: 9100
|
||||
sifaka_smartctl_exporter_port: 9633
|
||||
3
ansible/inventory/host_vars/sifaka.yml
Normal file
3
ansible/inventory/host_vars/sifaka.yml
Normal file
|
|
@ -0,0 +1,3 @@
|
|||
---
|
||||
ansible_user: eblume
|
||||
ansible_python_interpreter: /usr/bin/python3
|
||||
7
ansible/playbooks/sifaka.yml
Normal file
7
ansible/playbooks/sifaka.yml
Normal file
|
|
@ -0,0 +1,7 @@
|
|||
---
|
||||
- name: Configure sifaka
|
||||
hosts: nas
|
||||
|
||||
roles:
|
||||
- role: sifaka_exporters
|
||||
tags: sifaka_exporters
|
||||
|
|
@ -84,3 +84,7 @@ caddy_tcp_services:
|
|||
backend: "localhost:2200" # Forgejo SSH
|
||||
- port: 5432
|
||||
backend: "pg.tail8d86e.ts.net:5432" # PostgreSQL
|
||||
- port: "{{ sifaka_node_exporter_port }}"
|
||||
backend: "sifaka:{{ sifaka_node_exporter_port }}" # Sifaka node_exporter
|
||||
- port: "{{ sifaka_smartctl_exporter_port }}"
|
||||
backend: "sifaka:{{ sifaka_smartctl_exporter_port }}" # Sifaka smartctl_exporter
|
||||
|
|
|
|||
15
ansible/roles/sifaka_exporters/defaults/main.yml
Normal file
15
ansible/roles/sifaka_exporters/defaults/main.yml
Normal file
|
|
@ -0,0 +1,15 @@
|
|||
---
|
||||
# Docker images for Prometheus exporters on sifaka NAS
|
||||
# Ports are defined in group_vars/all.yml (shared with caddy role)
|
||||
sifaka_exporters_docker: /volume1/@appstore/ContainerManager/usr/bin/docker
|
||||
sifaka_exporters_node_exporter_image: "prom/node-exporter:latest"
|
||||
sifaka_exporters_node_exporter_name: "prom-node-exporter-1"
|
||||
sifaka_exporters_smartctl_exporter_image: "prometheuscommunity/smartctl-exporter:latest"
|
||||
sifaka_exporters_smartctl_exporter_name: "smartctl-exporter"
|
||||
|
||||
# Synology uses /dev/sata* instead of /dev/sd* — smartctl can't auto-detect them
|
||||
sifaka_exporters_smartctl_devices:
|
||||
- /dev/sata1
|
||||
- /dev/sata2
|
||||
- /dev/sata3
|
||||
- /dev/sata4
|
||||
12
ansible/roles/sifaka_exporters/handlers/main.yml
Normal file
12
ansible/roles/sifaka_exporters/handlers/main.yml
Normal file
|
|
@ -0,0 +1,12 @@
|
|||
---
|
||||
- name: Restart node_exporter
|
||||
ansible.builtin.command: "{{ sifaka_exporters_docker }} restart {{ sifaka_exporters_node_exporter_name }}"
|
||||
become: true
|
||||
listen: Restart node_exporter
|
||||
changed_when: true
|
||||
|
||||
- name: Restart smartctl_exporter
|
||||
ansible.builtin.command: "{{ sifaka_exporters_docker }} restart {{ sifaka_exporters_smartctl_exporter_name }}"
|
||||
become: true
|
||||
listen: Restart smartctl_exporter
|
||||
changed_when: true
|
||||
91
ansible/roles/sifaka_exporters/tasks/main.yml
Normal file
91
ansible/roles/sifaka_exporters/tasks/main.yml
Normal file
|
|
@ -0,0 +1,91 @@
|
|||
---
|
||||
# Manage Prometheus exporter containers on sifaka NAS
|
||||
# Uses command module to avoid requiring docker Python SDK on Synology
|
||||
# Requires passwordless sudo for docker — see docs/reference/storage/sifaka.md
|
||||
|
||||
# --- node_exporter ---
|
||||
|
||||
- name: Pull node_exporter image
|
||||
ansible.builtin.command: "{{ sifaka_exporters_docker }} pull {{ sifaka_exporters_node_exporter_image }}"
|
||||
become: true
|
||||
register: sifaka_exporters_node_pull
|
||||
changed_when: "'Downloaded newer image' in sifaka_exporters_node_pull.stdout"
|
||||
|
||||
- name: Check if node_exporter container exists
|
||||
ansible.builtin.command: "{{ sifaka_exporters_docker }} inspect {{ sifaka_exporters_node_exporter_name }} --format {% raw %}'{{.Config.Image}}'{% endraw %}"
|
||||
become: true
|
||||
register: sifaka_exporters_node_inspect
|
||||
changed_when: false
|
||||
failed_when: false
|
||||
|
||||
- name: Remove node_exporter container if image changed
|
||||
ansible.builtin.command: "{{ sifaka_exporters_docker }} rm -f {{ sifaka_exporters_node_exporter_name }}"
|
||||
become: true
|
||||
when:
|
||||
- sifaka_exporters_node_inspect.rc == 0
|
||||
- sifaka_exporters_node_inspect.stdout != sifaka_exporters_node_exporter_image
|
||||
changed_when: true
|
||||
|
||||
- name: Start node_exporter container
|
||||
ansible.builtin.command:
|
||||
argv:
|
||||
- "{{ sifaka_exporters_docker }}"
|
||||
- run
|
||||
- -d
|
||||
- "--name={{ sifaka_exporters_node_exporter_name }}"
|
||||
- --restart=always
|
||||
- --net=host
|
||||
- "{{ sifaka_exporters_node_exporter_image }}"
|
||||
become: true
|
||||
register: sifaka_exporters_node_start
|
||||
when: >
|
||||
sifaka_exporters_node_inspect.rc != 0 or
|
||||
sifaka_exporters_node_inspect.stdout != sifaka_exporters_node_exporter_image
|
||||
changed_when: sifaka_exporters_node_start.rc == 0
|
||||
|
||||
# --- smartctl_exporter ---
|
||||
|
||||
- name: Pull smartctl_exporter image
|
||||
ansible.builtin.command: "{{ sifaka_exporters_docker }} pull {{ sifaka_exporters_smartctl_exporter_image }}"
|
||||
become: true
|
||||
register: sifaka_exporters_smartctl_pull
|
||||
changed_when: "'Downloaded newer image' in sifaka_exporters_smartctl_pull.stdout"
|
||||
|
||||
- name: Check if smartctl_exporter container exists
|
||||
ansible.builtin.command: "{{ sifaka_exporters_docker }} inspect {{ sifaka_exporters_smartctl_exporter_name }} --format {% raw %}'{{.Config.Image}}'{% endraw %}"
|
||||
become: true
|
||||
register: sifaka_exporters_smartctl_inspect
|
||||
changed_when: false
|
||||
failed_when: false
|
||||
|
||||
- name: Remove smartctl_exporter container if image changed
|
||||
ansible.builtin.command: "{{ sifaka_exporters_docker }} rm -f {{ sifaka_exporters_smartctl_exporter_name }}"
|
||||
become: true
|
||||
when:
|
||||
- sifaka_exporters_smartctl_inspect.rc == 0
|
||||
- sifaka_exporters_smartctl_inspect.stdout != sifaka_exporters_smartctl_exporter_image
|
||||
changed_when: true
|
||||
|
||||
- name: Build smartctl_exporter device arguments
|
||||
ansible.builtin.set_fact:
|
||||
sifaka_exporters_smartctl_device_args: >-
|
||||
{{ sifaka_exporters_smartctl_devices | map('regex_replace', '^(.*)$', '--smartctl.device=\1') | list }}
|
||||
|
||||
- name: Start smartctl_exporter container
|
||||
ansible.builtin.command:
|
||||
argv: >-
|
||||
{{ [
|
||||
sifaka_exporters_docker, 'run', '-d',
|
||||
'--name=' + sifaka_exporters_smartctl_exporter_name,
|
||||
'--restart=always',
|
||||
'--privileged',
|
||||
'--user=root',
|
||||
'-p', sifaka_smartctl_exporter_port | string + ':' + sifaka_smartctl_exporter_port | string,
|
||||
sifaka_exporters_smartctl_exporter_image
|
||||
] + sifaka_exporters_smartctl_device_args }}
|
||||
become: true
|
||||
register: sifaka_exporters_smartctl_start
|
||||
when: >
|
||||
sifaka_exporters_smartctl_inspect.rc != 0 or
|
||||
sifaka_exporters_smartctl_inspect.stdout != sifaka_exporters_smartctl_exporter_image
|
||||
changed_when: sifaka_exporters_smartctl_start.rc == 0
|
||||
Loading…
Add table
Add a link
Reference in a new issue