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

jb update

Browse Source
This commit is contained in:
Jesse Bye
2020-09-30 14:04:09 -07:00
parent ad4462e506
commit f0755dcaa8
12 changed files with 2512 additions and 8125 deletions
Download Patch File Download Diff File Expand all files Collapse all files

284
manifests/prometheus-rules.yaml
View File

@@ -762,21 +762,17 @@ spec:
record: node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile
- name: kube-prometheus-node-recording.rules
rules:
- expr: sum(rate(node_cpu_seconds_total{mode!="idle",mode!="iowait"}[3m])) BY
(instance)
- expr: sum(rate(node_cpu_seconds_total{mode!="idle",mode!="iowait"}[3m])) BY (instance)
record: instance:node_cpu:rate:sum
- expr: sum(rate(node_network_receive_bytes_total[3m])) BY (instance)
record: instance:node_network_receive_bytes:rate:sum
- expr: sum(rate(node_network_transmit_bytes_total[3m])) BY (instance)
record: instance:node_network_transmit_bytes:rate:sum
- expr: sum(rate(node_cpu_seconds_total{mode!="idle",mode!="iowait"}[5m])) WITHOUT
(cpu, mode) / ON(instance) GROUP_LEFT() count(sum(node_cpu_seconds_total)
BY (instance, cpu)) BY (instance)
- expr: sum(rate(node_cpu_seconds_total{mode!="idle",mode!="iowait"}[5m])) WITHOUT (cpu, mode) / ON(instance) GROUP_LEFT() count(sum(node_cpu_seconds_total) BY (instance, cpu)) BY (instance)
record: instance:node_cpu:ratio
- expr: sum(rate(node_cpu_seconds_total{mode!="idle",mode!="iowait"}[5m]))
record: cluster:node_cpu:sum_rate5m
- expr: cluster:node_cpu_seconds_total:rate5m / count(sum(node_cpu_seconds_total)
BY (instance, cpu))
- expr: cluster:node_cpu_seconds_total:rate5m / count(sum(node_cpu_seconds_total) BY (instance, cpu))
record: cluster:node_cpu:ratio
- name: kube-prometheus-general.rules
rules:
@@ -788,9 +784,7 @@ spec:
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.
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.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubestatemetricslisterrors
summary: kube-state-metrics is experiencing errors in list operations.
expr: |
@@ -803,9 +797,7 @@ spec:
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.
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.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubestatemetricswatcherrors
summary: kube-state-metrics is experiencing errors in watch operations.
expr: |
@@ -820,9 +812,7 @@ spec:
rules:
- alert: NodeFilesystemSpaceFillingUp
annotations:
description: Filesystem on {{ $labels.device }} at {{ $labels.instance }}
has only {{ printf "%.2f" $value }}% available space left and is filling
up.
description: Filesystem on {{ $labels.device }} at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available space left and is filling up.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-nodefilesystemspacefillingup
summary: Filesystem is predicted to run out of space within the next 24 hours.
expr: |
@@ -838,9 +828,7 @@ spec:
severity: warning
- alert: NodeFilesystemSpaceFillingUp
annotations:
description: Filesystem on {{ $labels.device }} at {{ $labels.instance }}
has only {{ printf "%.2f" $value }}% available space left and is filling
up fast.
description: Filesystem on {{ $labels.device }} at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available space left and is filling up fast.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-nodefilesystemspacefillingup
summary: Filesystem is predicted to run out of space within the next 4 hours.
expr: |
@@ -856,8 +844,7 @@ spec:
severity: critical
- alert: NodeFilesystemAlmostOutOfSpace
annotations:
description: Filesystem on {{ $labels.device }} at {{ $labels.instance }}
has only {{ printf "%.2f" $value }}% available space left.
description: Filesystem on {{ $labels.device }} at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available space left.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-nodefilesystemalmostoutofspace
summary: Filesystem has less than 5% space left.
expr: |
@@ -871,8 +858,7 @@ spec:
severity: warning
- alert: NodeFilesystemAlmostOutOfSpace
annotations:
description: Filesystem on {{ $labels.device }} at {{ $labels.instance }}
has only {{ printf "%.2f" $value }}% available space left.
description: Filesystem on {{ $labels.device }} at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available space left.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-nodefilesystemalmostoutofspace
summary: Filesystem has less than 3% space left.
expr: |
@@ -886,9 +872,7 @@ spec:
severity: critical
- alert: NodeFilesystemFilesFillingUp
annotations:
description: Filesystem on {{ $labels.device }} at {{ $labels.instance }}
has only {{ printf "%.2f" $value }}% available inodes left and is filling
up.
description: Filesystem on {{ $labels.device }} at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available inodes left and is filling up.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-nodefilesystemfilesfillingup
summary: Filesystem is predicted to run out of inodes within the next 24 hours.
expr: |
@@ -904,9 +888,7 @@ spec:
severity: warning
- alert: NodeFilesystemFilesFillingUp
annotations:
description: Filesystem on {{ $labels.device }} at {{ $labels.instance }}
has only {{ printf "%.2f" $value }}% available inodes left and is filling
up fast.
description: Filesystem on {{ $labels.device }} at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available inodes left and is filling up fast.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-nodefilesystemfilesfillingup
summary: Filesystem is predicted to run out of inodes within the next 4 hours.
expr: |
@@ -922,8 +904,7 @@ spec:
severity: critical
- alert: NodeFilesystemAlmostOutOfFiles
annotations:
description: Filesystem on {{ $labels.device }} at {{ $labels.instance }}
has only {{ printf "%.2f" $value }}% available inodes left.
description: Filesystem on {{ $labels.device }} at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available inodes left.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-nodefilesystemalmostoutoffiles
summary: Filesystem has less than 5% inodes left.
expr: |
@@ -937,8 +918,7 @@ spec:
severity: warning
- alert: NodeFilesystemAlmostOutOfFiles
annotations:
description: Filesystem on {{ $labels.device }} at {{ $labels.instance }}
has only {{ printf "%.2f" $value }}% available inodes left.
description: Filesystem on {{ $labels.device }} at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available inodes left.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-nodefilesystemalmostoutoffiles
summary: Filesystem has less than 3% inodes left.
expr: |
@@ -952,8 +932,7 @@ spec:
severity: critical
- alert: NodeNetworkReceiveErrs
annotations:
description: '{{ $labels.instance }} interface {{ $labels.device }} has encountered
{{ printf "%.0f" $value }} receive errors in the last two minutes.'
description: '{{ $labels.instance }} interface {{ $labels.device }} has encountered {{ printf "%.0f" $value }} receive errors in the last two minutes.'
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-nodenetworkreceiveerrs
summary: Network interface is reporting many receive errors.
expr: |
@@ -963,8 +942,7 @@ spec:
severity: warning
- alert: NodeNetworkTransmitErrs
annotations:
description: '{{ $labels.instance }} interface {{ $labels.device }} has encountered
{{ printf "%.0f" $value }} transmit errors in the last two minutes.'
description: '{{ $labels.instance }} interface {{ $labels.device }} has encountered {{ printf "%.0f" $value }} transmit errors in the last two minutes.'
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-nodenetworktransmiterrs
summary: Network interface is reporting many transmit errors.
expr: |
@@ -992,8 +970,7 @@ spec:
severity: warning
- alert: NodeClockSkewDetected
annotations:
message: Clock on {{ $labels.instance }} is out of sync by more than 300s.
Ensure NTP is configured correctly on this host.
message: Clock on {{ $labels.instance }} is out of sync by more than 300s. Ensure NTP is configured correctly on this host.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-nodeclockskewdetected
summary: Clock skew detected.
expr: |
@@ -1013,8 +990,7 @@ spec:
severity: warning
- alert: NodeClockNotSynchronising
annotations:
message: Clock on {{ $labels.instance }} is not synchronising. Ensure NTP
is configured on this host.
message: Clock on {{ $labels.instance }} is not synchronising. Ensure NTP is configured on this host.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-nodeclocknotsynchronising
summary: Clock not synchronising.
expr: |
@@ -1024,9 +1000,7 @@ spec:
severity: warning
- alert: NodeRAIDDegraded
annotations:
description: RAID array '{{ $labels.device }}' on {{ $labels.instance }} is
in degraded state due to one or more disks failures. Number of spare drives
is insufficient to fix issue automatically.
description: RAID array '{{ $labels.device }}' on {{ $labels.instance }} is in degraded state due to one or more disks failures. Number of spare drives is insufficient to fix issue automatically.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-noderaiddegraded
summary: RAID Array is degraded
expr: |
@@ -1036,8 +1010,7 @@ spec:
severity: critical
- alert: NodeRAIDDiskFailure
annotations:
description: At least one device in RAID array on {{ $labels.instance }} failed.
Array '{{ $labels.device }}' needs attention and possibly a disk swap.
description: At least one device in RAID array on {{ $labels.instance }} failed. Array '{{ $labels.device }}' needs attention and possibly a disk swap.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-noderaiddiskfailure
summary: Failed device in RAID array
expr: |
@@ -1048,8 +1021,7 @@ spec:
rules:
- alert: PrometheusOperatorListErrors
annotations:
description: Errors while performing List operations in controller {{$labels.controller}}
in {{$labels.namespace}} namespace.
description: Errors while performing List operations in controller {{$labels.controller}} in {{$labels.namespace}} namespace.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-prometheusoperatorlisterrors
summary: Errors while performing list operations in controller.
expr: |
@@ -1059,8 +1031,7 @@ spec:
severity: warning
- alert: PrometheusOperatorWatchErrors
annotations:
description: Errors while performing watch operations in controller {{$labels.controller}}
in {{$labels.namespace}} namespace.
description: Errors while performing watch operations in controller {{$labels.controller}} in {{$labels.namespace}} namespace.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-prometheusoperatorwatcherrors
summary: Errors while performing watch operations in controller.
expr: |
@@ -1070,9 +1041,7 @@ spec:
severity: warning
- alert: PrometheusOperatorReconcileErrors
annotations:
description: '{{ $value | humanizePercentage }} of reconciling operations
failed for {{ $labels.controller }} controller in {{ $labels.namespace }}
namespace.'
description: '{{ $value | humanizePercentage }} of reconciling operations failed for {{ $labels.controller }} controller in {{ $labels.namespace }} namespace.'
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-prometheusoperatorreconcileerrors
summary: Errors while reconciling controller.
expr: |
@@ -1082,8 +1051,7 @@ spec:
severity: warning
- alert: PrometheusOperatorNodeLookupErrors
annotations:
description: Errors while reconciling Prometheus in {{ $labels.namespace }}
Namespace.
description: Errors while reconciling Prometheus in {{ $labels.namespace }} Namespace.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-prometheusoperatornodelookuperrors
summary: Errors while reconciling Prometheus.
expr: |
@@ -1095,8 +1063,7 @@ spec:
rules:
- alert: KubePodCrashLooping
annotations:
description: Pod {{ $labels.namespace }}/{{ $labels.pod }} ({{ $labels.container
}}) is restarting {{ printf "%.2f" $value }} times / 5 minutes.
description: Pod {{ $labels.namespace }}/{{ $labels.pod }} ({{ $labels.container }}) is restarting {{ printf "%.2f" $value }} times / 5 minutes.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubepodcrashlooping
summary: Pod is crash looping.
expr: |
@@ -1106,8 +1073,7 @@ 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://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubepodnotready
summary: Pod has been in a non-ready state for more than 15 minutes.
expr: |
@@ -1123,9 +1089,7 @@ 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://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubedeploymentgenerationmismatch
summary: Deployment generation mismatch due to possible roll-back
expr: |
@@ -1137,8 +1101,7 @@ 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://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubedeploymentreplicasmismatch
summary: Deployment has not matched the expected number of replicas.
expr: |
@@ -1156,8 +1119,7 @@ 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://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubestatefulsetreplicasmismatch
summary: Deployment has not matched the expected number of replicas.
expr: |
@@ -1175,9 +1137,7 @@ 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://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubestatefulsetgenerationmismatch
summary: StatefulSet generation mismatch due to possible roll-back
expr: |
@@ -1189,8 +1149,7 @@ 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://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubestatefulsetupdatenotrolledout
summary: StatefulSet update has not been rolled out.
expr: |
@@ -1216,8 +1175,7 @@ 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://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubedaemonsetrolloutstuck
summary: DaemonSet rollout is stuck.
expr: |
@@ -1249,8 +1207,7 @@ 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://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecontainerwaiting
summary: Pod container waiting longer than 1 hour
expr: |
@@ -1260,8 +1217,7 @@ 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://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubedaemonsetnotscheduled
summary: DaemonSet pods are not scheduled.
expr: |
@@ -1273,8 +1229,7 @@ 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://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubedaemonsetmisscheduled
summary: DaemonSet pods are misscheduled.
expr: |
@@ -1284,8 +1239,7 @@ 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://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubejobcompletion
summary: Job did not complete in time
expr: |
@@ -1295,8 +1249,7 @@ spec:
severity: warning
- alert: KubeJobFailed
annotations:
description: Job {{ $labels.namespace }}/{{ $labels.job_name }} failed to
complete.
description: Job {{ $labels.namespace }}/{{ $labels.job_name }} failed to complete.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubejobfailed
summary: Job failed to complete.
expr: |
@@ -1306,8 +1259,7 @@ spec:
severity: warning
- alert: KubeHpaReplicasMismatch
annotations:
description: HPA {{ $labels.namespace }}/{{ $labels.hpa }} has not matched
the desired number of replicas for longer than 15 minutes.
description: HPA {{ $labels.namespace }}/{{ $labels.hpa }} has not matched the desired number of replicas for longer than 15 minutes.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubehpareplicasmismatch
summary: HPA has not matched descired number of replicas.
expr: |
@@ -1321,8 +1273,7 @@ spec:
severity: warning
- alert: KubeHpaMaxedOut
annotations:
description: HPA {{ $labels.namespace }}/{{ $labels.hpa }} has been running
at max replicas for longer than 15 minutes.
description: HPA {{ $labels.namespace }}/{{ $labels.hpa }} has been running at max replicas for longer than 15 minutes.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubehpamaxedout
summary: HPA is running at max replicas
expr: |
@@ -1336,8 +1287,7 @@ spec:
rules:
- alert: KubeCPUOvercommit
annotations:
description: Cluster has overcommitted CPU resource requests for Pods and
cannot tolerate node failure.
description: Cluster has overcommitted CPU resource requests for Pods and cannot tolerate node failure.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecpuovercommit
summary: Cluster has overcommitted CPU resource requests.
expr: |
@@ -1351,8 +1301,7 @@ spec:
severity: warning
- alert: KubeMemoryOvercommit
annotations:
description: Cluster has overcommitted memory resource requests for Pods and
cannot tolerate node failure.
description: Cluster has overcommitted memory resource requests for Pods and cannot tolerate node failure.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubememoryovercommit
summary: Cluster has overcommitted memory resource requests.
expr: |
@@ -1394,8 +1343,7 @@ 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://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubequotaalmostfull
summary: Namespace quota is going to be full.
expr: |
@@ -1408,8 +1356,7 @@ 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://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubequotafullyused
summary: Namespace quota is fully used.
expr: |
@@ -1422,8 +1369,7 @@ 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://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubequotaexceeded
summary: Namespace quota has exceeded the limits.
expr: |
@@ -1436,9 +1382,7 @@ 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://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-cputhrottlinghigh
summary: Processes experience elevated CPU throttling.
expr: |
@@ -1453,9 +1397,7 @@ 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://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubepersistentvolumefillingup
summary: PersistentVolume is filling up.
expr: |
@@ -1468,10 +1410,7 @@ 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://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubepersistentvolumefillingup
summary: PersistentVolume is filling up.
expr: |
@@ -1487,8 +1426,7 @@ 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://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubepersistentvolumeerrors
summary: PersistentVolume is having issues with provisioning.
expr: |
@@ -1500,8 +1438,7 @@ 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://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeversionmismatch
summary: Different semantic versions of Kubernetes components running.
expr: |
@@ -1511,8 +1448,7 @@ 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://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeclienterrors
summary: Kubernetes API server client is experiencing errors.
expr: |
@@ -1585,8 +1521,7 @@ 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://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeclientcertificateexpiration
summary: Client certificate is about to expire.
expr: |
@@ -1595,8 +1530,7 @@ 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://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeclientcertificateexpiration
summary: Client certificate is about to expire.
expr: |
@@ -1605,10 +1539,7 @@ spec:
severity: critical
- alert: AggregatedAPIErrors
annotations:
description: An aggregated API {{ $labels.name }}/{{ $labels.namespace }}
has reported errors. The number of errors have increased for it in the past
five minutes. High values indicate that the availability of the service
changes too often.
description: An aggregated API {{ $labels.name }}/{{ $labels.namespace }} has reported errors. The number of errors have increased for it in the past five minutes. High values indicate that the availability of the service changes too often.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-aggregatedapierrors
summary: An aggregated API has reported errors.
expr: |
@@ -1617,8 +1548,7 @@ 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://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-aggregatedapidown
summary: An aggregated API is down.
expr: |
@@ -1650,8 +1580,7 @@ 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://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubenodeunreachable
summary: Node is unreachable.
expr: |
@@ -1661,8 +1590,7 @@ 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://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubelettoomanypods
summary: Kubelet is running at capacity.
expr: |
@@ -1678,8 +1606,7 @@ spec:
severity: warning
- 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://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubenodereadinessflapping
summary: Node readiness status is flapping.
expr: |
@@ -1689,8 +1616,7 @@ 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://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletplegdurationhigh
summary: Kubelet Pod Lifecycle Event Generator is taking too long to relist.
expr: |
@@ -1700,8 +1626,7 @@ 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://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletpodstartuplatencyhigh
summary: Kubelet Pod startup latency is too high.
expr: |
@@ -1711,8 +1636,7 @@ 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://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletclientcertificateexpiration
summary: Kubelet client certificate is about to expire.
expr: |
@@ -1721,8 +1645,7 @@ 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://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletclientcertificateexpiration
summary: Kubelet client certificate is about to expire.
expr: |
@@ -1731,8 +1654,7 @@ 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://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletservercertificateexpiration
summary: Kubelet server certificate is about to expire.
expr: |
@@ -1741,8 +1663,7 @@ 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://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletservercertificateexpiration
summary: Kubelet server certificate is about to expire.
expr: |
@@ -1751,8 +1672,7 @@ 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://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletclientcertificaterenewalerrors
summary: Kubelet has failed to renew its client certificate.
expr: |
@@ -1762,8 +1682,7 @@ 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 ({{ $value | humanize }} errors in the last 5 minutes).
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletservercertificaterenewalerrors
summary: Kubelet has failed to renew its server certificate.
expr: |
@@ -1797,8 +1716,7 @@ spec:
rules:
- alert: KubeControllerManagerDown
annotations:
description: KubeControllerManager has disappeared from Prometheus target
discovery.
description: KubeControllerManager has disappeared from Prometheus target discovery.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecontrollermanagerdown
summary: Target disappeared from Prometheus target discovery.
expr: |
@@ -1810,8 +1728,7 @@ spec:
rules:
- alert: PrometheusBadConfig
annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has failed to
reload its configuration.
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has failed to reload its configuration.
summary: Failed Prometheus configuration reload.
expr: |
# Without max_over_time, failed scrapes could create false negatives, see
@@ -1822,10 +1739,8 @@ spec:
severity: critical
- alert: PrometheusNotificationQueueRunningFull
annotations:
description: Alert notification queue of Prometheus {{$labels.namespace}}/{{$labels.pod}}
is running full.
summary: Prometheus alert notification queue predicted to run full in less
than 30m.
description: Alert notification queue of Prometheus {{$labels.namespace}}/{{$labels.pod}} is running full.
summary: Prometheus alert notification queue predicted to run full in less than 30m.
expr: |
# Without min_over_time, failed scrapes could create false negatives, see
# https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.
@@ -1839,10 +1754,8 @@ spec:
severity: warning
- alert: PrometheusErrorSendingAlertsToSomeAlertmanagers
annotations:
description: '{{ printf "%.1f" $value }}% errors while sending alerts from
Prometheus {{$labels.namespace}}/{{$labels.pod}} to Alertmanager {{$labels.alertmanager}}.'
summary: Prometheus has encountered more than 1% errors sending alerts to
a specific Alertmanager.
description: '{{ printf "%.1f" $value }}% errors while sending alerts from Prometheus {{$labels.namespace}}/{{$labels.pod}} to Alertmanager {{$labels.alertmanager}}.'
summary: Prometheus has encountered more than 1% errors sending alerts to a specific Alertmanager.
expr: |
(
rate(prometheus_notifications_errors_total{job="prometheus-k8s",namespace="monitoring"}[5m])
@@ -1856,8 +1769,7 @@ spec:
severity: warning
- alert: PrometheusErrorSendingAlertsToAnyAlertmanager
annotations:
description: '{{ printf "%.1f" $value }}% minimum errors while sending alerts
from Prometheus {{$labels.namespace}}/{{$labels.pod}} to any Alertmanager.'
description: '{{ printf "%.1f" $value }}% minimum errors while sending alerts from Prometheus {{$labels.namespace}}/{{$labels.pod}} to any Alertmanager.'
summary: Prometheus encounters more than 3% errors sending alerts to any Alertmanager.
expr: |
min without(alertmanager) (
@@ -1872,8 +1784,7 @@ spec:
severity: critical
- alert: PrometheusNotConnectedToAlertmanagers
annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} is not connected
to any Alertmanagers.
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} is not connected to any Alertmanagers.
summary: Prometheus is not connected to any Alertmanagers.
expr: |
# Without max_over_time, failed scrapes could create false negatives, see
@@ -1884,8 +1795,7 @@ spec:
severity: warning
- alert: PrometheusTSDBReloadsFailing
annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has detected
{{$value | humanize}} reload failures over the last 3h.
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has detected {{$value | humanize}} reload failures over the last 3h.
summary: Prometheus has issues reloading blocks from disk.
expr: |
increase(prometheus_tsdb_reloads_failures_total{job="prometheus-k8s",namespace="monitoring"}[3h]) > 0
@@ -1894,8 +1804,7 @@ spec:
severity: warning
- alert: PrometheusTSDBCompactionsFailing
annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has detected
{{$value | humanize}} compaction failures over the last 3h.
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has detected {{$value | humanize}} compaction failures over the last 3h.
summary: Prometheus has issues compacting blocks.
expr: |
increase(prometheus_tsdb_compactions_failed_total{job="prometheus-k8s",namespace="monitoring"}[3h]) > 0
@@ -1904,8 +1813,7 @@ spec:
severity: warning
- alert: PrometheusNotIngestingSamples
annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} is not ingesting
samples.
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} is not ingesting samples.
summary: Prometheus is not ingesting samples.
expr: |
rate(prometheus_tsdb_head_samples_appended_total{job="prometheus-k8s",namespace="monitoring"}[5m]) <= 0
@@ -1914,9 +1822,7 @@ spec:
severity: warning
- alert: PrometheusDuplicateTimestamps
annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} is dropping
{{ printf "%.4g" $value }} samples/s with different values but duplicated
timestamp.
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} is dropping {{ printf "%.4g" $value }} samples/s with different values but duplicated timestamp.
summary: Prometheus is dropping samples with duplicate timestamps.
expr: |
rate(prometheus_target_scrapes_sample_duplicate_timestamp_total{job="prometheus-k8s",namespace="monitoring"}[5m]) > 0
@@ -1925,8 +1831,7 @@ spec:
severity: warning
- alert: PrometheusOutOfOrderTimestamps
annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} is dropping
{{ printf "%.4g" $value }} samples/s with timestamps arriving out of order.
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} is dropping {{ printf "%.4g" $value }} samples/s with timestamps arriving out of order.
summary: Prometheus drops samples with out-of-order timestamps.
expr: |
rate(prometheus_target_scrapes_sample_out_of_order_total{job="prometheus-k8s",namespace="monitoring"}[5m]) > 0
@@ -1935,9 +1840,7 @@ spec:
severity: warning
- alert: PrometheusRemoteStorageFailures
annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} failed to send
{{ printf "%.1f" $value }}% of the samples to {{ $labels.remote_name}}:{{
$labels.url }}
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} failed to send {{ printf "%.1f" $value }}% of the samples to {{ $labels.remote_name}}:{{ $labels.url }}
summary: Prometheus fails to send samples to remote storage.
expr: |
(
@@ -1956,9 +1859,7 @@ spec:
severity: critical
- alert: PrometheusRemoteWriteBehind
annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} remote write
is {{ printf "%.1f" $value }}s behind for {{ $labels.remote_name}}:{{ $labels.url
}}.
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} remote write is {{ printf "%.1f" $value }}s behind for {{ $labels.remote_name}}:{{ $labels.url }}.
summary: Prometheus remote write is behind.
expr: |
# Without max_over_time, failed scrapes could create false negatives, see
@@ -1974,13 +1875,8 @@ spec:
severity: critical
- alert: PrometheusRemoteWriteDesiredShards
annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} remote write
desired shards calculation wants to run {{ $value }} shards for queue {{
$labels.remote_name}}:{{ $labels.url }}, which is more than the max of {{
printf `prometheus_remote_storage_shards_max{instance="%s",job="prometheus-k8s",namespace="monitoring"}`
$labels.instance | query | first | value }}.
summary: Prometheus remote write desired shards calculation wants to run more
than configured max shards.
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} remote write desired shards calculation wants to run {{ $value }} shards for queue {{ $labels.remote_name}}:{{ $labels.url }}, which is more than the max of {{ printf `prometheus_remote_storage_shards_max{instance="%s",job="prometheus-k8s",namespace="monitoring"}` $labels.instance | query | first | value }}.
summary: Prometheus remote write desired shards calculation wants to run more than configured max shards.
expr: |
# Without max_over_time, failed scrapes could create false negatives, see
# https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.
@@ -1994,8 +1890,7 @@ spec:
severity: warning
- alert: PrometheusRuleFailures
annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has failed to
evaluate {{ printf "%.0f" $value }} rules in the last 5m.
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has failed to evaluate {{ printf "%.0f" $value }} rules in the last 5m.
summary: Prometheus is failing rule evaluations.
expr: |
increase(prometheus_rule_evaluation_failures_total{job="prometheus-k8s",namespace="monitoring"}[5m]) > 0
@@ -2004,8 +1899,7 @@ spec:
severity: critical
- alert: PrometheusMissingRuleEvaluations
annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has missed {{
printf "%.0f" $value }} rule group evaluations in the last 5m.
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has missed {{ printf "%.0f" $value }} rule group evaluations in the last 5m.
summary: Prometheus is missing rule evaluations due to slow rule group evaluation.
expr: |
increase(prometheus_rule_group_iterations_missed_total{job="prometheus-k8s",namespace="monitoring"}[5m]) > 0
@@ -2028,8 +1922,7 @@ spec:
severity: critical
- alert: AlertmanagerFailedReload
annotations:
message: Reloading Alertmanager's configuration has failed for {{ $labels.namespace
}}/{{ $labels.pod}}.
message: Reloading Alertmanager's configuration has failed for {{ $labels.namespace }}/{{ $labels.pod}}.
expr: |
alertmanager_config_last_reload_successful{job="alertmanager-main",namespace="monitoring"} == 0
for: 10m
@@ -2049,10 +1942,8 @@ spec:
rules:
- alert: TargetDown
annotations:
message: '{{ printf "%.4g" $value }}% of the {{ $labels.job }}/{{ $labels.service
}} targets in {{ $labels.namespace }} namespace are down.'
expr: 100 * (count(up == 0) BY (job, namespace, service) / count(up) BY (job,
namespace, service)) > 10
message: '{{ printf "%.4g" $value }}% of the {{ $labels.job }}/{{ $labels.service }} targets in {{ $labels.namespace }} namespace are down.'
expr: 100 * (count(up == 0) BY (job, namespace, service) / count(up) BY (job, namespace, service)) > 10
for: 10m
labels:
severity: warning
@@ -2071,8 +1962,7 @@ spec:
rules:
- alert: NodeNetworkInterfaceFlapping
annotations:
message: Network interface "{{ $labels.device }}" changing it's up status
often on node-exporter {{ $labels.namespace }}/{{ $labels.pod }}"
message: Network interface "{{ $labels.device }}" changing it's up status often on node-exporter {{ $labels.namespace }}/{{ $labels.pod }}"
expr: |
changes(node_network_up{job="node-exporter",device!~"veth.+"}[2m]) > 2
for: 2m