XeLabs/awesome-prometheus-alerts
2
0
Fork 0
mirror of https://github.com/samber/awesome-prometheus-alerts.git synced 2026-06-26 19:37:27 +08:00
Code Issues Projects Releases Packages Wiki Activity

_data/rules.yml: Added missing jobs rules.

Browse source
This commit is contained in:
Jonathan Davies 2019-06-25 14:15:43 +01:00
parent dfe3bbb258
commit 7dedf12695
1 changed files with 21 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

22
_data/rules.yml
View file

@ -295,18 +295,38 @@ services:
- name: Kubernetes - name: Kubernetes
exporters: exporters:
- rules: - rules:
- name: KubeAPIServerDown
description: "Kubernetes API has disappeared from Prometheus target discovery."
query: 'absent(up{job="kubernetes-apiservers"}) == 1'
severity: critical
- name: KubeClientErrors - name: KubeClientErrors
description: "Kubernetes API server client '{{ $labels.job }}/{{ $labels.instance }}' is experiencing {{ printf \"%0.0f\" $value }}% errors.'" description: "Kubernetes API server client '{{ $labels.job }}/{{ $labels.instance }}' is experiencing {{ printf "%0.0f" $value }}% errors.'"
query: '(sum(rate(rest_client_requests_total{job=~"kubernetes-.*",code=~"5.."}[5m])) by (instance, job) / sum(rate(rest_client_requests_total[5m])) by (instance, job)) * 100 > 1' query: '(sum(rate(rest_client_requests_total{job=~"kubernetes-.*",code=~"5.."}[5m])) by (instance, job) / sum(rate(rest_client_requests_total[5m])) by (instance, job)) * 100 > 1'
severity: warning severity: warning
- name: KubeControllerManagerDown
description: "Kubernetes controller manager has disappeared from Prometheus target discovery."
query: 'absent(up{k8s-app="kubernetes-controller-manager"}) == 1'
severity: critical
- name: KubeNodeNotReady - name: KubeNodeNotReady
description: "{{ $labels.node }} has been unready for more than an hour." description: "{{ $labels.node }} has been unready for more than an hour."
query: 'kube_node_status_condition{condition="Ready",status="true"} == 0' query: 'kube_node_status_condition{condition="Ready",status="true"} == 0'
severity: warning severity: warning
- name: KubeSchedulerDown
description: "Kubernetes scheduler has disappeared from Prometheus target discovery."
query: 'absent(up{k8s-app="kubernetes-scheduler"}) == 1'
severity: critical
- name: KubeStateMetricsDown
description: "Kubernetes state metrics has disappeared from Prometheus target discovery."
query: 'absent(up{component="kube-state-metrics"}) == 1'
severity: critical
- name: KubeVersionMismatch - name: KubeVersionMismatch
description: "There are {{ $value }} different semantic versions of Kubernetes components running." description: "There are {{ $value }} different semantic versions of Kubernetes components running."
query: 'count(count by (gitVersion) (label_replace(kubernetes_build_info{job!="coredns"},"gitVersion","$1","gitVersion","(v[0-9]*.[0-9]*.[0-9]*).*"))) > 1' query: 'count(count by (gitVersion) (label_replace(kubernetes_build_info{job!="coredns"},"gitVersion","$1","gitVersion","(v[0-9]*.[0-9]*.[0-9]*).*"))) > 1'
severity: warning severity: warning
- name: KubeletDown
description: "Kubelet has disappeared from Prometheus target discovery."
query: 'absent(up{job="kubernetes-nodes"} == 1)'
severity: warning
- name: KubeletTooManyPods - name: KubeletTooManyPods
description: "Kubelet {{ $labels.instance }} is running {{ $value }} pods, close to the limit of 110." description: "Kubelet {{ $labels.instance }} is running {{ $value }} pods, close to the limit of 110."
query: 'kubelet_running_pod_count{job="kubernetes-nodes"} > (110 * 0.9)' query: 'kubelet_running_pod_count{job="kubernetes-nodes"} > (110 * 0.9)'