feat(alerting): Add up alert rule with anti-flap and absence detection (

#147)
canonical · Oct 23, 2024 · 6da23c0 · 6da23c0
1 parent a144ec9
commit 6da23c0
Showing 1 changed file with 25 additions and 0 deletions.
diff --git a/src/prometheus_alert_rules/host_health.rules b/src/prometheus_alert_rules/host_health.rules
@@ -0,0 +1,25 @@
+groups:
+- name: HostHealth
+  rules:
+  - alert: HostDown
+    expr: up < 1
+    for: 5m
+    labels:
+      severity: critical
+    annotations:
+      summary: Host '{{labels.instance}}' is down.
+      description: >-
+        Host '{{ $labels.instance }}' is down.
+          VALUE = {{ $value }}
+          LABELS = {{ $labels }}
+  - alert: HostUnavailable
+    expr: absent(up)
+    for: 5m
+    labels:
+      severity: critical
+    annotations:
+      summary: Metrics not received from host '{{labels.instance}}'.
+      description: >-
+        The metrics endpoint for host '{{ $labels.instance }}' is unreachable.
+          VALUE = {{ $value }}
+          LABELS = {{ $labels }}