|
/etc/prometheus/alert_rules.yml > Instances
|
alert: InstanceDown
expr: up == 0
for: 1m
labels:
severity: critical
annotations:
description: '{{ $labels.instance }} of job {{ $labels.job }} has been down for
more than 1 minutes.'
summary: Instance {{ $labels.instance }} down
|
|
/etc/prometheus/alert_rules.yml > system-alerts
|
| Labels |
State |
Active Since |
Value |
|
alertname="HighCPUUsage"
instance="localhost:9100"
severity="warning"
|
firing |
2026-09-08 22:00:22.466325293 +0000 UTC |
58.69449259896663 |
| Annotations |
- description
- CPU usage is above 50% for more than 5 minutes
- summary
- High CPU usage on localhost:9100
|
|
| Labels |
State |
Active Since |
Value |
|
alertname="LowMemoryAvailable"
instance="localhost:9100"
job="node"
severity="critical"
|
firing |
2026-09-08 22:11:52.466325293 +0000 UTC |
0.21724564957515802 |
| Annotations |
- description
- Less than 25% memory available
- summary
- Low memory available on localhost:9100
|
|
|
|
|
|