tommy
cfe95a3aef
Wazuh VM (vmid 109, .199) ran node-exporter v1.8.2 all along but was never in
Prometheus's scrape list -> its 2-month outage was invisible. Add 192.168.99.199:9100
to the node-exporter job; the existing NodeDown alert (up{job=node-exporter}==0, 2m,
critical -> ntfy) now covers it. Also mirror prometheus.yml into git for the first
time (only alert_rules.yml was tracked) to end live-only drift.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
63 lines
1.5 KiB
YAML
63 lines
1.5 KiB
YAML
global:
|
|
scrape_interval: 15s
|
|
evaluation_interval: 15s
|
|
|
|
rule_files:
|
|
- "alert_rules.yml"
|
|
|
|
alerting:
|
|
alertmanagers:
|
|
- static_configs:
|
|
- targets:
|
|
- "alertmanager:9093"
|
|
|
|
scrape_configs:
|
|
- job_name: prometheus
|
|
static_configs:
|
|
- targets: ["prometheus:9090"]
|
|
|
|
- job_name: alertmanager
|
|
static_configs:
|
|
- targets: ["alertmanager:9093"]
|
|
|
|
- job_name: node-exporter
|
|
static_configs:
|
|
- targets:
|
|
- "192.168.99.200:9100"
|
|
- "192.168.99.192:9100"
|
|
- "192.168.99.193:9100"
|
|
- "192.168.99.194:9100"
|
|
- "192.168.99.153:9100"
|
|
- "192.168.99.183:9100"
|
|
- "192.168.99.186:9100"
|
|
- "192.168.99.187:9100"
|
|
- "192.168.99.190:9100"
|
|
- "192.168.99.227:9100"
|
|
- "192.168.99.196:9100"
|
|
- "192.168.99.198:9100"
|
|
- "192.168.99.199:9100"
|
|
- "192.168.99.100:9100"
|
|
metric_relabel_configs:
|
|
- source_labels: [nodename]
|
|
regex: '0d869efa-prometheus-node-exporter'
|
|
target_label: nodename
|
|
replacement: haos
|
|
|
|
- job_name: nut
|
|
static_configs:
|
|
- targets: ['192.168.99.200']
|
|
metrics_path: /metrics
|
|
params:
|
|
target: ['192.168.99.200']
|
|
relabel_configs:
|
|
- target_label: __address__
|
|
replacement: '192.168.99.183:9995'
|
|
|
|
- job_name: cadvisor
|
|
static_configs:
|
|
- targets: ["cadvisor:8080"]
|
|
|
|
- job_name: crowdsec
|
|
static_configs:
|
|
- targets: ["192.168.99.186:6060"]
|