easylinux/kube-prometheus
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

[bot] [main] Automated version update

Browse Source
This commit is contained in:
Prometheus Operator Bot
2022-04-04 07:42:34 +00:00
parent eb0fafd789
commit a16675bc0e
21 changed files with 105 additions and 68 deletions
Download Patch File Download Diff File Expand all files Collapse all files

25
manifests/kubernetesControlPlane-prometheusRule.yaml
View File

@@ -202,15 +202,16 @@ spec:
for: 15m
labels:
severity: warning
- alert: KubeJobCompletion
- alert: KubeJobNotCompleted
annotations:
description: Job {{ $labels.namespace }}/{{ $labels.job_name }} is taking
more than 12 hours to complete.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubejobcompletion
more than {{ "43200" | humanizeDuration }} to complete.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubejobnotcompleted
summary: Job did not complete in time
expr: |
kube_job_spec_completions{job="kube-state-metrics"} - kube_job_status_succeeded{job="kube-state-metrics"} > 0
for: 12h
time() - max by(namespace, job_name) (kube_job_status_start_time{job="kube-state-metrics"}
and
kube_job_status_active{job="kube-state-metrics"} > 0) > 43200
labels:
severity: warning
- alert: KubeJobFailed
@@ -451,9 +452,9 @@ spec:
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeclienterrors
summary: Kubernetes API server client is experiencing errors.
expr: |
(sum(rate(rest_client_requests_total{code=~"5.."}[5m])) by (instance, job, namespace)
(sum(rate(rest_client_requests_total{code=~"5.."}[5m])) by (cluster, instance, job, namespace)
/
sum(rate(rest_client_requests_total[5m])) by (instance, job, namespace))
sum(rate(rest_client_requests_total[5m])) by (cluster, instance, job, namespace))
> 0.01
for: 15m
labels:
@@ -612,11 +613,11 @@ spec:
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubelettoomanypods
summary: Kubelet is running at capacity.
expr: |
count by(node) (
count by(cluster, node) (
(kube_pod_status_phase{job="kube-state-metrics",phase="Running"} == 1) * on(instance,pod,namespace,cluster) group_left(node) topk by(instance,pod,namespace,cluster) (1, kube_pod_info{job="kube-state-metrics"})
)
/
max by(node) (
max by(cluster, node) (
kube_node_status_capacity{job="kube-state-metrics",resource="pods"} != 1
) > 0.95
for: 15m
@@ -629,7 +630,7 @@ spec:
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubenodereadinessflapping
summary: Node readiness status is flapping.
expr: |
sum(changes(kube_node_status_condition{status="true",condition="Ready"}[15m])) by (node) > 2
sum(changes(kube_node_status_condition{status="true",condition="Ready"}[15m])) by (cluster, node) > 2
for: 15m
labels:
severity: warning
@@ -1391,8 +1392,8 @@ spec:
- name: node.rules
rules:
- expr: |
topk by(namespace, pod) (1,
max by (node, namespace, pod) (
topk by(cluster, namespace, pod) (1,
max by (cluster, node, namespace, pod) (
label_replace(kube_pod_info{job="kube-state-metrics",node!=""}, "pod", "$1", "pod", "(.*)")
))
record: 'node_namespace_pod:kube_pod_info:'