Skip to content

Commit

Permalink
Add alert rules to istio-pilot based on the KF093 spec
Browse files Browse the repository at this point in the history
  • Loading branch information
rgildein committed Aug 15, 2024
1 parent 399f0b7 commit f8ac6b7
Showing 1 changed file with 24 additions and 0 deletions.
Original file line number Diff line number Diff line change
@@ -0,0 +1,24 @@
groups:
- name: KubeflowIstioPilotServices
rules:
- alert: KubeflowServiceDown
expr: up{} < 1
for: 5m
labels:
severity: critical
annotations:
summary: "{{ $labels.juju_charm }} service is Down ({{ $labels.juju_model }}/{{ $labels.juju_unit }})"
description: |
One or more targets of {{ $labels.juju_charm }} charm are down on unit {{ $labels.juju_model }}/{{ $labels.juju_unit }}.
LABELS = {{ $labels }}

- alert: KubeflowServiceIsNotStable
expr: avg_over_time(up{}[10m]) < 0.5
for: 0m
labels:
severity: warning
annotations:
summary: "{{ $labels.juju_charm }} service is not stable ({{ $labels.juju_model }}/{{ $labels.juju_unit }})"
description: |
{{ $labels.juju_charm }} unit {{ $labels.juju_model }}/{{ $labels.juju_unit }} has been unreachable at least 50% of the time over the last 10 minutes.
LABELS = {{ $labels }}

0 comments on commit f8ac6b7

Please sign in to comment.