feat: track machine skew/not synchronising

bdossantos · Feb 26, 2021 · daa7773 · daa7773
1 parent 57c15da
commit daa7773
Showing 1 changed file with 20 additions and 0 deletions.
diff --git a/rules/clock.yml b/rules/clock.yml
@@ -0,0 +1,20 @@
+---
+groups:
+  - name: clock
+    rules:
+      - alert: HostClockSkew
+        expr: (node_timex_offset_seconds > 0.05 and deriv(node_timex_offset_seconds[5m]) >= 0) or (node_timex_offset_seconds < -0.05 and deriv(node_timex_offset_seconds[5m]) <= 0)
+        for: 2m
+        labels:
+          severity: page
+        annotations:
+          summary: Host clock skew (instance {{ $labels.instance }})
+          description: "Clock skew detected. Clock is out of sync.\n  VALUE = {{ $value }}\n  LABELS: {{ $labels }}"
+      - alert: HostClockNotSynchronising
+        expr: min_over_time(node_timex_sync_status[1m]) == 0 and node_timex_maxerror_seconds >= 16
+        for: 2m
+        labels:
+          severity: page
+        annotations:
+          summary: Host clock not synchronising (instance {{ $labels.instance }})
+          description: "Clock not synchronising.\n  VALUE = {{ $value }}\n  LABELS: {{ $labels }}"