summaryrefslogtreecommitdiffstats
path: root/Prometheus/alerts/lysergic/wireguard_exporters.yml
blob: 87fecb69575387905453bbac51193c7ea6865345 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
groups:
- name: lysergic-wireguard_exporters
  rules:
  - alert: mercury-wireguard-down
    expr: wireguard_peer_last_handshake_seconds{device="wg0", instance="localhost:9586", job="wireguard-mercury", public_key="$WG0_PUBKEY"} - time() <- 125
    for: 10s
    labels:
      job: wireguard-mercury
      severity: CRITICAL
      project: LYSERGIC
    annotations:
      title: WireGuard {{ $labels.instance }} is down
      description: 'Failed to scrape {{ $labels.job }} on {{ $labels.instance}} for more than 2 minutes. Uplink to Psyched seems down. Affected services: Global infrastructure monitoring. Other outages might no longer be tracked. Urgent investigation is advised.'
  - alert: lysergic-wireguard-down
    expr: wireguard_peer_last_handshake_seconds{project="LYSERGIC",device!="wg1"} - time() <- 130
    for: 10s
    labels:
      job: wireguard-lysergic
      severity: CRITICAL
      project: LYSERGIC
    annotations:
      title: WireGuard Incident
      description: 'No handshakes for {{ $labels.device }} in {{ $labels.job }} on {{ $labels.instance}} have been exchanged for an extended amount of time. Critical services could be affected.'