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

chore: version update after fixing k8s-resources-workloads-namespace query

Browse Source
This commit is contained in:
yaacine
2021-11-25 13:25:24 +01:00
parent 974b37e620
commit acced5a95d
5 changed files with 140 additions and 36 deletions
Download Patch File Download Diff File Expand all files Collapse all files

50
manifests/kubernetes-prometheusRule.yaml
View File

@@ -294,9 +294,9 @@ spec:
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubecpuquotaovercommit
summary: Cluster has overcommitted CPU resource requests.
expr: |
sum(kube_resourcequota{job="kube-state-metrics", type="hard", resource="cpu"})
sum(min without(resource) (kube_resourcequota{job="kube-state-metrics", type="hard", resource=~"(cpu|requests.cpu)"}))
/
sum(kube_node_status_allocatable{resource="cpu"})
sum(kube_node_status_allocatable{resource="cpu", job="kube-state-metrics"})
> 1.5
for: 5m
labels:
@@ -307,9 +307,9 @@ spec:
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubememoryquotaovercommit
summary: Cluster has overcommitted memory resource requests.
expr: |
sum(kube_resourcequota{job="kube-state-metrics", type="hard", resource="memory"})
sum(min without(resource) (kube_resourcequota{job="kube-state-metrics", type="hard", resource=~"(memory|requests.memory)"}))
/
sum(kube_node_status_allocatable{resource="memory",job="kube-state-metrics"})
sum(kube_node_status_allocatable{resource="memory", job="kube-state-metrics"})
> 1.5
for: 5m
labels:
@@ -390,6 +390,8 @@ spec:
kubelet_volume_stats_used_bytes{job="kubelet", metrics_path="/metrics"} > 0
unless on(namespace, persistentvolumeclaim)
kube_persistentvolumeclaim_access_mode{ access_mode="ReadOnlyMany"} == 1
unless on(namespace, persistentvolumeclaim)
kube_persistentvolumeclaim_labels{label_excluded_from_alerts="true"} == 1
for: 1m
labels:
severity: critical
@@ -413,6 +415,8 @@ spec:
predict_linear(kubelet_volume_stats_available_bytes{job="kubelet", metrics_path="/metrics"}[6h], 4 * 24 * 3600) < 0
unless on(namespace, persistentvolumeclaim)
kube_persistentvolumeclaim_access_mode{ access_mode="ReadOnlyMany"} == 1
unless on(namespace, persistentvolumeclaim)
kube_persistentvolumeclaim_labels{label_excluded_from_alerts="true"} == 1
for: 1h
labels:
severity: warning
@@ -516,8 +520,8 @@ spec:
rules:
- alert: KubeClientCertificateExpiration
annotations:
description: A client certificate used to authenticate to the apiserver is
expiring in less than 7.0 days.
description: A client certificate used to authenticate to kubernetes apiserver
is expiring in less than 7.0 days.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeclientcertificateexpiration
summary: Client certificate is about to expire.
expr: |
@@ -526,31 +530,31 @@ spec:
severity: warning
- alert: KubeClientCertificateExpiration
annotations:
description: A client certificate used to authenticate to the apiserver is
expiring in less than 24.0 hours.
description: A client certificate used to authenticate to kubernetes apiserver
is expiring in less than 24.0 hours.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeclientcertificateexpiration
summary: Client certificate is about to expire.
expr: |
apiserver_client_certificate_expiration_seconds_count{job="apiserver"} > 0 and on(job) histogram_quantile(0.01, sum by (job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job="apiserver"}[5m]))) < 86400
labels:
severity: critical
- alert: AggregatedAPIErrors
- alert: KubeAggregatedAPIErrors
annotations:
description: An aggregated API {{ $labels.name }}/{{ $labels.namespace }}
has reported errors. It has appeared unavailable {{ $value | humanize }}
times averaged over the past 10m.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/aggregatedapierrors
summary: An aggregated API has reported errors.
description: Kubernetes aggregated API {{ $labels.name }}/{{ $labels.namespace
}} has reported errors. It has appeared unavailable {{ $value | humanize
}} times averaged over the past 10m.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeaggregatedapierrors
summary: Kubernetes aggregated API has reported errors.
expr: |
sum by(name, namespace)(increase(aggregator_unavailable_apiservice_total[10m])) > 4
labels:
severity: warning
- alert: AggregatedAPIDown
- alert: KubeAggregatedAPIDown
annotations:
description: An aggregated API {{ $labels.name }}/{{ $labels.namespace }}
has been only {{ $value | humanize }}% available over the last 10m.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/aggregatedapidown
summary: An aggregated API is down.
description: Kubernetes aggregated API {{ $labels.name }}/{{ $labels.namespace
}} has been only {{ $value | humanize }}% available over the last 10m.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeaggregatedapidown
summary: Kubernetes aggregated API is down.
expr: |
(1 - max by(name, namespace)(avg_over_time(aggregator_unavailable_apiservice[10m]))) * 100 < 85
for: 5m
@@ -568,11 +572,11 @@ spec:
severity: critical
- alert: KubeAPITerminatedRequests
annotations:
description: The apiserver has terminated {{ $value | humanizePercentage }}
of its incoming requests.
description: The kubernetes apiserver has terminated {{ $value | humanizePercentage
}} of its incoming requests.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeapiterminatedrequests
summary: The apiserver has terminated {{ $value | humanizePercentage }} of
its incoming requests.
summary: The kubernetes apiserver has terminated {{ $value | humanizePercentage
}} of its incoming requests.
expr: |
sum(rate(apiserver_request_terminations_total{job="apiserver"}[10m])) / ( sum(rate(apiserver_request_total{job="apiserver"}[10m])) + sum(rate(apiserver_request_terminations_total{job="apiserver"}[10m])) ) > 0.20
for: 5m