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

update go-jsonnet for linter bugfix

Browse Source
This commit is contained in:
Haoyu Sun
2021-10-09 21:07:37 +02:00
parent 10c11d5019
commit 1e632d2ec8
17 changed files with 10070 additions and 3236 deletions
Download Patch File Download Diff File Expand all files Collapse all files

139
manifests/kubernetes-prometheusRule.yaml
View File

@@ -14,7 +14,8 @@ spec:
rules:
- alert: KubePodCrashLooping
annotations:
description: 'Pod {{ $labels.namespace }}/{{ $labels.pod }} ({{ $labels.container }}) is in waiting state (reason: "CrashLoopBackOff").'
description: 'Pod {{ $labels.namespace }}/{{ $labels.pod }} ({{ $labels.container
}}) is in waiting state (reason: "CrashLoopBackOff").'
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubepodcrashlooping
summary: Pod is crash looping.
expr: |
@@ -24,7 +25,8 @@ spec:
severity: warning
- alert: KubePodNotReady
annotations:
description: Pod {{ $labels.namespace }}/{{ $labels.pod }} has been in a non-ready state for longer than 15 minutes.
description: Pod {{ $labels.namespace }}/{{ $labels.pod }} has been in a non-ready
state for longer than 15 minutes.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubepodnotready
summary: Pod has been in a non-ready state for more than 15 minutes.
expr: |
@@ -40,7 +42,9 @@ spec:
severity: warning
- alert: KubeDeploymentGenerationMismatch
annotations:
description: Deployment generation for {{ $labels.namespace }}/{{ $labels.deployment }} does not match, this indicates that the Deployment has failed but has not been rolled back.
description: Deployment generation for {{ $labels.namespace }}/{{ $labels.deployment
}} does not match, this indicates that the Deployment has failed but has
not been rolled back.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubedeploymentgenerationmismatch
summary: Deployment generation mismatch due to possible roll-back
expr: |
@@ -52,7 +56,8 @@ spec:
severity: warning
- alert: KubeDeploymentReplicasMismatch
annotations:
description: Deployment {{ $labels.namespace }}/{{ $labels.deployment }} has not matched the expected number of replicas for longer than 15 minutes.
description: Deployment {{ $labels.namespace }}/{{ $labels.deployment }} has
not matched the expected number of replicas for longer than 15 minutes.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubedeploymentreplicasmismatch
summary: Deployment has not matched the expected number of replicas.
expr: |
@@ -70,7 +75,8 @@ spec:
severity: warning
- alert: KubeStatefulSetReplicasMismatch
annotations:
description: StatefulSet {{ $labels.namespace }}/{{ $labels.statefulset }} has not matched the expected number of replicas for longer than 15 minutes.
description: StatefulSet {{ $labels.namespace }}/{{ $labels.statefulset }}
has not matched the expected number of replicas for longer than 15 minutes.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubestatefulsetreplicasmismatch
summary: Deployment has not matched the expected number of replicas.
expr: |
@@ -88,7 +94,9 @@ spec:
severity: warning
- alert: KubeStatefulSetGenerationMismatch
annotations:
description: StatefulSet generation for {{ $labels.namespace }}/{{ $labels.statefulset }} does not match, this indicates that the StatefulSet has failed but has not been rolled back.
description: StatefulSet generation for {{ $labels.namespace }}/{{ $labels.statefulset
}} does not match, this indicates that the StatefulSet has failed but has
not been rolled back.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubestatefulsetgenerationmismatch
summary: StatefulSet generation mismatch due to possible roll-back
expr: |
@@ -100,7 +108,8 @@ spec:
severity: warning
- alert: KubeStatefulSetUpdateNotRolledOut
annotations:
description: StatefulSet {{ $labels.namespace }}/{{ $labels.statefulset }} update has not been rolled out.
description: StatefulSet {{ $labels.namespace }}/{{ $labels.statefulset }}
update has not been rolled out.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubestatefulsetupdatenotrolledout
summary: StatefulSet update has not been rolled out.
expr: |
@@ -126,7 +135,8 @@ spec:
severity: warning
- alert: KubeDaemonSetRolloutStuck
annotations:
description: DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset }} has not finished or progressed for at least 15 minutes.
description: DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset }} has
not finished or progressed for at least 15 minutes.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubedaemonsetrolloutstuck
summary: DaemonSet rollout is stuck.
expr: |
@@ -158,7 +168,8 @@ spec:
severity: warning
- alert: KubeContainerWaiting
annotations:
description: Pod {{ $labels.namespace }}/{{ $labels.pod }} container {{ $labels.container}} has been in waiting state for longer than 1 hour.
description: Pod {{ $labels.namespace }}/{{ $labels.pod }} container {{ $labels.container}}
has been in waiting state for longer than 1 hour.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubecontainerwaiting
summary: Pod container waiting longer than 1 hour
expr: |
@@ -168,7 +179,8 @@ spec:
severity: warning
- alert: KubeDaemonSetNotScheduled
annotations:
description: '{{ $value }} Pods of DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset }} are not scheduled.'
description: '{{ $value }} Pods of DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset
}} are not scheduled.'
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubedaemonsetnotscheduled
summary: DaemonSet pods are not scheduled.
expr: |
@@ -180,7 +192,8 @@ spec:
severity: warning
- alert: KubeDaemonSetMisScheduled
annotations:
description: '{{ $value }} Pods of DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset }} are running where they are not supposed to run.'
description: '{{ $value }} Pods of DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset
}} are running where they are not supposed to run.'
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubedaemonsetmisscheduled
summary: DaemonSet pods are misscheduled.
expr: |
@@ -190,7 +203,8 @@ spec:
severity: warning
- alert: KubeJobCompletion
annotations:
description: Job {{ $labels.namespace }}/{{ $labels.job_name }} is taking more than 12 hours to complete.
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
summary: Job did not complete in time
expr: |
@@ -200,7 +214,8 @@ spec:
severity: warning
- alert: KubeJobFailed
annotations:
description: Job {{ $labels.namespace }}/{{ $labels.job_name }} failed to complete. Removing failed job after investigation should clear this alert.
description: Job {{ $labels.namespace }}/{{ $labels.job_name }} failed to
complete. Removing failed job after investigation should clear this alert.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubejobfailed
summary: Job failed to complete.
expr: |
@@ -210,7 +225,8 @@ spec:
severity: warning
- alert: KubeHpaReplicasMismatch
annotations:
description: HPA {{ $labels.namespace }}/{{ $labels.horizontalpodautoscaler }} has not matched the desired number of replicas for longer than 15 minutes.
description: HPA {{ $labels.namespace }}/{{ $labels.horizontalpodautoscaler }}
has not matched the desired number of replicas for longer than 15 minutes.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubehpareplicasmismatch
summary: HPA has not matched descired number of replicas.
expr: |
@@ -232,7 +248,8 @@ spec:
severity: warning
- alert: KubeHpaMaxedOut
annotations:
description: HPA {{ $labels.namespace }}/{{ $labels.horizontalpodautoscaler }} has been running at max replicas for longer than 15 minutes.
description: HPA {{ $labels.namespace }}/{{ $labels.horizontalpodautoscaler }}
has been running at max replicas for longer than 15 minutes.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubehpamaxedout
summary: HPA is running at max replicas
expr: |
@@ -246,7 +263,8 @@ spec:
rules:
- alert: KubeCPUOvercommit
annotations:
description: Cluster has overcommitted CPU resource requests for Pods by {{ $value }} CPU shares and cannot tolerate node failure.
description: Cluster has overcommitted CPU resource requests for Pods by {{
$value }} CPU shares and cannot tolerate node failure.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubecpuovercommit
summary: Cluster has overcommitted CPU resource requests.
expr: |
@@ -258,7 +276,8 @@ spec:
severity: warning
- alert: KubeMemoryOvercommit
annotations:
description: Cluster has overcommitted memory resource requests for Pods by {{ $value }} bytes and cannot tolerate node failure.
description: Cluster has overcommitted memory resource requests for Pods by
{{ $value }} bytes and cannot tolerate node failure.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubememoryovercommit
summary: Cluster has overcommitted memory resource requests.
expr: |
@@ -296,7 +315,8 @@ spec:
severity: warning
- alert: KubeQuotaAlmostFull
annotations:
description: Namespace {{ $labels.namespace }} is using {{ $value | humanizePercentage }} of its {{ $labels.resource }} quota.
description: Namespace {{ $labels.namespace }} is using {{ $value | humanizePercentage
}} of its {{ $labels.resource }} quota.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubequotaalmostfull
summary: Namespace quota is going to be full.
expr: |
@@ -309,7 +329,8 @@ spec:
severity: info
- alert: KubeQuotaFullyUsed
annotations:
description: Namespace {{ $labels.namespace }} is using {{ $value | humanizePercentage }} of its {{ $labels.resource }} quota.
description: Namespace {{ $labels.namespace }} is using {{ $value | humanizePercentage
}} of its {{ $labels.resource }} quota.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubequotafullyused
summary: Namespace quota is fully used.
expr: |
@@ -322,7 +343,8 @@ spec:
severity: info
- alert: KubeQuotaExceeded
annotations:
description: Namespace {{ $labels.namespace }} is using {{ $value | humanizePercentage }} of its {{ $labels.resource }} quota.
description: Namespace {{ $labels.namespace }} is using {{ $value | humanizePercentage
}} of its {{ $labels.resource }} quota.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubequotaexceeded
summary: Namespace quota has exceeded the limits.
expr: |
@@ -335,7 +357,9 @@ spec:
severity: warning
- alert: CPUThrottlingHigh
annotations:
description: '{{ $value | humanizePercentage }} throttling of CPU in namespace {{ $labels.namespace }} for container {{ $labels.container }} in pod {{ $labels.pod }}.'
description: '{{ $value | humanizePercentage }} throttling of CPU in namespace
{{ $labels.namespace }} for container {{ $labels.container }} in pod {{
$labels.pod }}.'
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/cputhrottlinghigh
summary: Processes experience elevated CPU throttling.
expr: |
@@ -350,7 +374,9 @@ spec:
rules:
- alert: KubePersistentVolumeFillingUp
annotations:
description: The PersistentVolume claimed by {{ $labels.persistentvolumeclaim }} in Namespace {{ $labels.namespace }} is only {{ $value | humanizePercentage }} free.
description: The PersistentVolume claimed by {{ $labels.persistentvolumeclaim
}} in Namespace {{ $labels.namespace }} is only {{ $value | humanizePercentage
}} free.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubepersistentvolumefillingup
summary: PersistentVolume is filling up.
expr: |
@@ -368,7 +394,10 @@ spec:
severity: critical
- alert: KubePersistentVolumeFillingUp
annotations:
description: Based on recent sampling, the PersistentVolume claimed by {{ $labels.persistentvolumeclaim }} in Namespace {{ $labels.namespace }} is expected to fill up within four days. Currently {{ $value | humanizePercentage }} is available.
description: Based on recent sampling, the PersistentVolume claimed by {{
$labels.persistentvolumeclaim }} in Namespace {{ $labels.namespace }} is
expected to fill up within four days. Currently {{ $value | humanizePercentage
}} is available.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubepersistentvolumefillingup
summary: PersistentVolume is filling up.
expr: |
@@ -388,7 +417,8 @@ spec:
severity: warning
- alert: KubePersistentVolumeErrors
annotations:
description: The persistent volume {{ $labels.persistentvolume }} has status {{ $labels.phase }}.
description: The persistent volume {{ $labels.persistentvolume }} has status
{{ $labels.phase }}.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubepersistentvolumeerrors
summary: PersistentVolume is having issues with provisioning.
expr: |
@@ -400,7 +430,8 @@ spec:
rules:
- alert: KubeVersionMismatch
annotations:
description: There are {{ $value }} different semantic versions of Kubernetes components running.
description: There are {{ $value }} different semantic versions of Kubernetes
components running.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeversionmismatch
summary: Different semantic versions of Kubernetes components running.
expr: |
@@ -410,7 +441,8 @@ spec:
severity: warning
- alert: KubeClientErrors
annotations:
description: Kubernetes API server client '{{ $labels.job }}/{{ $labels.instance }}' is experiencing {{ $value | humanizePercentage }} errors.'
description: Kubernetes API server client '{{ $labels.job }}/{{ $labels.instance
}}' is experiencing {{ $value | humanizePercentage }} errors.'
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeclienterrors
summary: Kubernetes API server client is experiencing errors.
expr: |
@@ -483,7 +515,8 @@ 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 the 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: |
@@ -492,7 +525,8 @@ 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 the 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: |
@@ -501,7 +535,9 @@ spec:
severity: critical
- alert: AggregatedAPIErrors
annotations:
description: An aggregated API {{ $labels.name }}/{{ $labels.namespace }} has reported errors. It has appeared unavailable {{ $value | humanize }} times averaged over the past 10m.
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.
expr: |
@@ -510,7 +546,8 @@ spec:
severity: warning
- alert: AggregatedAPIDown
annotations:
description: An aggregated API {{ $labels.name }}/{{ $labels.namespace }} has been only {{ $value | humanize }}% available over the last 10m.
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.
expr: |
@@ -530,9 +567,11 @@ spec:
severity: critical
- alert: KubeAPITerminatedRequests
annotations:
description: The apiserver has terminated {{ $value | humanizePercentage }} of its incoming requests.
description: The 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 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
@@ -552,7 +591,8 @@ spec:
severity: warning
- alert: KubeNodeUnreachable
annotations:
description: '{{ $labels.node }} is unreachable and some workloads may be rescheduled.'
description: '{{ $labels.node }} is unreachable and some workloads may be
rescheduled.'
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubenodeunreachable
summary: Node is unreachable.
expr: |
@@ -562,7 +602,8 @@ spec:
severity: warning
- alert: KubeletTooManyPods
annotations:
description: Kubelet '{{ $labels.node }}' is running at {{ $value | humanizePercentage }} of its Pod capacity.
description: Kubelet '{{ $labels.node }}' is running at {{ $value | humanizePercentage
}} of its Pod capacity.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubelettoomanypods
summary: Kubelet is running at capacity.
expr: |
@@ -578,7 +619,8 @@ spec:
severity: info
- alert: KubeNodeReadinessFlapping
annotations:
description: The readiness status of node {{ $labels.node }} has changed {{ $value }} times in the last 15 minutes.
description: The readiness status of node {{ $labels.node }} has changed {{
$value }} times in the last 15 minutes.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubenodereadinessflapping
summary: Node readiness status is flapping.
expr: |
@@ -588,7 +630,8 @@ spec:
severity: warning
- alert: KubeletPlegDurationHigh
annotations:
description: The Kubelet Pod Lifecycle Event Generator has a 99th percentile duration of {{ $value }} seconds on node {{ $labels.node }}.
description: The Kubelet Pod Lifecycle Event Generator has a 99th percentile
duration of {{ $value }} seconds on node {{ $labels.node }}.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeletplegdurationhigh
summary: Kubelet Pod Lifecycle Event Generator is taking too long to relist.
expr: |
@@ -598,7 +641,8 @@ spec:
severity: warning
- alert: KubeletPodStartUpLatencyHigh
annotations:
description: Kubelet Pod startup 99th percentile latency is {{ $value }} seconds on node {{ $labels.node }}.
description: Kubelet Pod startup 99th percentile latency is {{ $value }} seconds
on node {{ $labels.node }}.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeletpodstartuplatencyhigh
summary: Kubelet Pod startup latency is too high.
expr: |
@@ -608,7 +652,8 @@ spec:
severity: warning
- alert: KubeletClientCertificateExpiration
annotations:
description: Client certificate for Kubelet on node {{ $labels.node }} expires in {{ $value | humanizeDuration }}.
description: Client certificate for Kubelet on node {{ $labels.node }} expires
in {{ $value | humanizeDuration }}.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeletclientcertificateexpiration
summary: Kubelet client certificate is about to expire.
expr: |
@@ -617,7 +662,8 @@ spec:
severity: warning
- alert: KubeletClientCertificateExpiration
annotations:
description: Client certificate for Kubelet on node {{ $labels.node }} expires in {{ $value | humanizeDuration }}.
description: Client certificate for Kubelet on node {{ $labels.node }} expires
in {{ $value | humanizeDuration }}.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeletclientcertificateexpiration
summary: Kubelet client certificate is about to expire.
expr: |
@@ -626,7 +672,8 @@ spec:
severity: critical
- alert: KubeletServerCertificateExpiration
annotations:
description: Server certificate for Kubelet on node {{ $labels.node }} expires in {{ $value | humanizeDuration }}.
description: Server certificate for Kubelet on node {{ $labels.node }} expires
in {{ $value | humanizeDuration }}.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeletservercertificateexpiration
summary: Kubelet server certificate is about to expire.
expr: |
@@ -635,7 +682,8 @@ spec:
severity: warning
- alert: KubeletServerCertificateExpiration
annotations:
description: Server certificate for Kubelet on node {{ $labels.node }} expires in {{ $value | humanizeDuration }}.
description: Server certificate for Kubelet on node {{ $labels.node }} expires
in {{ $value | humanizeDuration }}.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeletservercertificateexpiration
summary: Kubelet server certificate is about to expire.
expr: |
@@ -644,7 +692,8 @@ spec:
severity: critical
- alert: KubeletClientCertificateRenewalErrors
annotations:
description: Kubelet on node {{ $labels.node }} has failed to renew its client certificate ({{ $value | humanize }} errors in the last 5 minutes).
description: Kubelet on node {{ $labels.node }} has failed to renew its client
certificate ({{ $value | humanize }} errors in the last 5 minutes).
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeletclientcertificaterenewalerrors
summary: Kubelet has failed to renew its client certificate.
expr: |
@@ -654,7 +703,8 @@ spec:
severity: warning
- alert: KubeletServerCertificateRenewalErrors
annotations:
description: Kubelet on node {{ $labels.node }} has failed to renew its server certificate ({{ $value | humanize }} errors in the last 5 minutes).
description: Kubelet on node {{ $labels.node }} has failed to renew its server
certificate ({{ $value | humanize }} errors in the last 5 minutes).
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeletservercertificaterenewalerrors
summary: Kubelet has failed to renew its server certificate.
expr: |
@@ -688,7 +738,8 @@ spec:
rules:
- alert: KubeControllerManagerDown
annotations:
description: KubeControllerManager has disappeared from Prometheus target discovery.
description: KubeControllerManager has disappeared from Prometheus target
discovery.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubecontrollermanagerdown
summary: Target disappeared from Prometheus target discovery.
expr: |