Add monitoring replacement baseline

This commit is contained in:
2026-05-17 11:22:38 +02:00
parent 0c308ff352
commit c95fa601f0
10 changed files with 490 additions and 5 deletions
+49
View File
@@ -0,0 +1,49 @@
groups:
- name: homelab-availability
rules:
- alert: HomelabEndpointDown
expr: probe_success{job="blackbox-http"} == 0
for: 2m
labels:
severity: critical
annotations:
summary: "{{ $labels.instance }} is not reachable"
description: "Blackbox probe failed for {{ $labels.instance }}."
- alert: HomelabEndpointSlow
expr: probe_duration_seconds{job="blackbox-http"} > 5
for: 5m
labels:
severity: warning
annotations:
summary: "{{ $labels.instance }} is slow"
description: "Blackbox probe duration is above 5 seconds for {{ $labels.instance }}."
- name: homelab-host
rules:
- alert: HomelabDiskAlmostFull
expr: 100 * (1 - node_filesystem_avail_bytes{fstype!~"tmpfs|overlay"} / node_filesystem_size_bytes{fstype!~"tmpfs|overlay"}) > 85
for: 10m
labels:
severity: warning
annotations:
summary: "Disk usage high on {{ $labels.mountpoint }}"
description: "{{ $labels.mountpoint }} is above 85% used."
- alert: HomelabHighMemoryUsage
expr: 100 * (1 - node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes) > 90
for: 10m
labels:
severity: warning
annotations:
summary: "Memory usage high"
description: "Host memory usage is above 90%."
- alert: HomelabTraefik5xx
expr: sum(rate(traefik_service_requests_total{code=~"5.."}[5m])) by (service) > 0
for: 2m
labels:
severity: warning
annotations:
summary: "Traefik 5xx responses for {{ $labels.service }}"
description: "Traefik reports 5xx responses for {{ $labels.service }}."