Alerts


/etc/prometheus/alerts/portalfull.yml > disk_alerts
DiskUsageCritical (0 active)
alert: DiskUsageCritical
expr: 100
  * (1 - (node_filesystem_avail_bytes{mountpoint="/"} / node_filesystem_size_bytes{mountpoint="/"}))
  > 90
for: 5m
labels:
  instance: portal-server
  severity: critical
annotations:
  description: Root filesystem usage is {{ $value | printf "%.2f" }}%, exceeding
    the 90% threshold.
  summary: Critical disk usage on portal-server
/etc/prometheus/alerts/up.yml > Up Checker
Host Down (0 active)
alert: Host
  Down
expr: up == 0
for: 5m
labels:
  severity: critical
annotations:
  description: Host {{ $labels.job }} has been unavailable for more than 5 minutes.
  summary: Host {{ $labels.instance }} is down