1
0
Fork 0
mirror of https://github.com/monitoring-mixins/website.git synced 2024-12-15 17:50:48 +00:00
monitoring-mixins-website/assets/kube-state-metrics/alerts.yaml
2023-05-13 03:19:29 +00:00

55 lines
2.3 KiB
YAML

groups:
- name: kube-state-metrics
rules:
- alert: KubeStateMetricsListErrors
annotations:
description: kube-state-metrics is experiencing errors at an elevated rate in
list operations. This is likely causing it to not be able to expose metrics
about Kubernetes objects correctly or at all.
summary: kube-state-metrics is experiencing errors in list operations.
expr: |
(sum(rate(kube_state_metrics_list_total{job="kube-state-metrics",result="error"}[5m])) by (cluster)
/
sum(rate(kube_state_metrics_list_total{job="kube-state-metrics"}[5m])) by (cluster))
> 0.01
for: 15m
labels:
severity: critical
- alert: KubeStateMetricsWatchErrors
annotations:
description: kube-state-metrics is experiencing errors at an elevated rate in
watch operations. This is likely causing it to not be able to expose metrics
about Kubernetes objects correctly or at all.
summary: kube-state-metrics is experiencing errors in watch operations.
expr: |
(sum(rate(kube_state_metrics_watch_total{job="kube-state-metrics",result="error"}[5m])) by (cluster)
/
sum(rate(kube_state_metrics_watch_total{job="kube-state-metrics"}[5m])) by (cluster))
> 0.01
for: 15m
labels:
severity: critical
- alert: KubeStateMetricsShardingMismatch
annotations:
description: kube-state-metrics pods are running with different --total-shards
configuration, some Kubernetes objects may be exposed multiple times or not
exposed at all.
summary: kube-state-metrics sharding is misconfigured.
expr: |
stdvar (kube_state_metrics_total_shards{job="kube-state-metrics"}) by (cluster) != 0
for: 15m
labels:
severity: critical
- alert: KubeStateMetricsShardsMissing
annotations:
description: kube-state-metrics shards are missing, some Kubernetes objects
are not being exposed.
summary: kube-state-metrics shards are missing.
expr: |
2^max(kube_state_metrics_total_shards{job="kube-state-metrics"}) by (cluster) - 1
-
sum( 2 ^ max by (cluster, shard_ordinal) (kube_state_metrics_shard_ordinal{job="kube-state-metrics"}) ) by (cluster)
!= 0
for: 15m
labels:
severity: critical