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

2
go.mod
View File

@@ -5,7 +5,7 @@ go 1.13
require (
github.com/Jeffail/gabs v1.2.0
github.com/alecthomas/units v0.0.0-20190924025748-f65c72e2690d // indirect
github.com/brancz/gojsontoyaml v0.0.0-20191212081931-bf2969bbd742
github.com/brancz/gojsontoyaml v0.0.0-20200602132005-3697ded27e8c
github.com/campoy/embedmd v1.0.0
github.com/google/go-jsonnet v0.16.1-0.20200703153429-aaf50f5b655f
github.com/googleapis/gnostic v0.0.0-20170729233727-0c5108395e2d // indirect

4
go.sum
View File

@@ -13,6 +13,8 @@ github.com/beorn7/perks v1.0.0/go.mod h1:KWe93zE9D1o94FZ5RNwFwVgaQK1VOXiVxmqh+Ce
github.com/beorn7/perks v1.0.1/go.mod h1:G2ZrVWU2WbWT9wwq4/hrbKbnv/1ERSJQ0ibhJ6rlkpw=
github.com/brancz/gojsontoyaml v0.0.0-20191212081931-bf2969bbd742 h1:PdvQdwUXiFnSmWsOJcBXLpyH3mJfP2FMPTT3J0i7+8o=
github.com/brancz/gojsontoyaml v0.0.0-20191212081931-bf2969bbd742/go.mod h1:IyUJYN1gvWjtLF5ZuygmxbnsAyP3aJS6cHzIuZY50B0=
github.com/brancz/gojsontoyaml v0.0.0-20200602132005-3697ded27e8c h1:hb6WqfcKQZlNx/vahy51SaIvKnoXD5609Nm0PC4msEM=
github.com/brancz/gojsontoyaml v0.0.0-20200602132005-3697ded27e8c/go.mod h1:+00lOjYXPgMfxHVPvg9GDtc3BX5Xh5aFpB4gMB8gfMo=
github.com/campoy/embedmd v1.0.0 h1:V4kI2qTJJLf4J29RzI/MAt2c3Bl4dQSYPuflzwFH2hY=
github.com/campoy/embedmd v1.0.0/go.mod h1:oxyr9RCiSXg0M3VJ3ks0UGfp98BpSSGr0kpiX3MzVl8=
github.com/cespare/xxhash/v2 v2.1.1/go.mod h1:VGX0DQ3Q6kWi7AoAeZDth3/j3BFtOZR5XLFGgcrjCOs=
@@ -168,6 +170,8 @@ gopkg.in/yaml.v2 v2.2.4 h1:/eiJrUcujPVeJ3xlSWaiNi3uSVmDGBK1pDHUHAnao1I=
gopkg.in/yaml.v2 v2.2.4/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
gopkg.in/yaml.v2 v2.2.5 h1:ymVxjfMaHvXD8RqPRmzHHsB3VvucivSkIAvJFDI5O3c=
gopkg.in/yaml.v2 v2.2.5/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
gopkg.in/yaml.v2 v2.3.0 h1:clyUAQHOM3G0M3f5vQj7LuJrETvjVot3Z5el9nffUtU=
gopkg.in/yaml.v2 v2.3.0/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
k8s.io/api v0.0.0-20190313235455-40a48860b5ab h1:DG9A67baNpoeweOy2spF1OWHhnVY5KR7/Ek/+U1lVZc=
k8s.io/api v0.0.0-20190313235455-40a48860b5ab/go.mod h1:iuAfoD4hCxJ8Onx9kaTIt30j7jUFS00AXQi6QMi99vA=
k8s.io/apimachinery v0.0.0-20190313205120-d7deff9243b1 h1:IS7K02iBkQXpCeieSiyJjGoLSdVOv2DbPaWHJ+ZtgKg=

22
jsonnetfile.lock.json
View File

@@ -18,8 +18,8 @@
"subdir": "Documentation/etcd-mixin"
}
},
"version": "205a656cc58b32ab701c74297ce440bd517a680f",
"sum": "NhOkJWkO7ZO2DSE8Fvipcs7Hh2/GOCS0WjPPZU8OiaQ="
"version": "ab4cc3caef3d6a1bb7c8c9e79749357eafef42df",
"sum": "5awm+ZMs5J/nOFB+hLAb7hdeQxz/iIrls5hEZoEkXjM="
},
{
"source": {
@@ -28,8 +28,8 @@
"subdir": "grafonnet"
}
},
"version": "cc1626a1b4dee45c99b78ddd9714dfd5f5d7816e",
"sum": "nkgrtMYPCq/YB4r3mKyToepaLhicwWnxDdGIodPpzz0="
"version": "4ae0ba995612d3fe71bb74ec23a49815b6896817",
"sum": "J5CaYYEP02FleLx34/qgS+ckWUaxUaADlfnV7CriSo8="
},
{
"source": {
@@ -38,7 +38,7 @@
"subdir": "grafana-builder"
}
},
"version": "ecc83f569bbf56f2863e9c3cefa4487e3253aaa6",
"version": "b8cb0881befce313a6741489c6018662be663d5e",
"sum": "mD0zEP9FVFXeag7EaeS5OvUr2A9D6DQhGemoNn6+PLc="
},
{
@@ -79,7 +79,7 @@
"subdir": "jsonnet/kube-state-metrics"
}
},
"version": "2ebe4dffc52ee2d1ca5b6444be54bcf0dba5372a",
"version": "392f9249f808041612a8d3c5348fc48b64cece74",
"sum": "WJGwddC7KJnEN7CWGELiOHKam+vmv9XYkwrMCwmXi2M="
},
{
@@ -89,7 +89,7 @@
"subdir": "jsonnet/kube-state-metrics-mixin"
}
},
"version": "2ebe4dffc52ee2d1ca5b6444be54bcf0dba5372a",
"version": "392f9249f808041612a8d3c5348fc48b64cece74",
"sum": "Yf8mNAHrV1YWzrdV8Ry5dJ8YblepTGw3C0Zp10XIYLo="
},
{
@@ -99,7 +99,7 @@
"subdir": "jsonnet/mixin"
}
},
"version": "d7befd55020b3c040bea42fdb5b13d9f9d96474c",
"version": "fbd01683839aa408b31fa15fa1aa91c68f13d7ef",
"sum": "vqz67twCROf5kVgo/61luBOx25Mk7Okbt8YP+/7xjT0="
},
{
@@ -109,7 +109,7 @@
"subdir": "jsonnet/prometheus-operator"
}
},
"version": "a1eb8fd04f3cd2bfb11aee8943e0b3469ff2f199",
"version": "cd331ce9bb58bb926e391c6ae807621cb12cc29e",
"sum": "nM1eDP5vftqAeQSmVYzSBAh+lG0SN6zu46QiocQiVhk="
},
{
@@ -119,8 +119,8 @@
"subdir": "docs/node-mixin"
}
},
"version": "ff2ff3410f4ea8195e51f5fb8d84151684f91b3f",
"sum": "znDrZiHvvascm7Xuj3lTASIOfwX4Vmx7PELmKKw4YiI="
"version": "a3aaf63bb1262aada3cd9ca1fe59ffc3ea32e9e2",
"sum": "zpo4/qvCbAmfJXGjwrdzXcfsvg4fxZD6wi5af/kt+8g="
},
{
"source": {

2
manifests/grafana-dashboardDefinitions.yaml
View File

@@ -24367,7 +24367,7 @@ items:
"tableColumn": "",
"targets": [
{
"expr": "100 -\n(\n node_memory_MemAvailable_bytes{job=\"node-exporter\", instance=\"$instance\"}\n/\n node_memory_MemTotal_bytes{job=\"node-exporter\", instance=\"$instance\"}\n* 100\n)\n",
"expr": "100 -\n(\n avg(node_memory_MemAvailable_bytes{job=\"node-exporter\", instance=\"$instance\"})\n/\n avg(node_memory_MemTotal_bytes{job=\"node-exporter\", instance=\"$instance\"})\n* 100\n)\n",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "",

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

2921
manifests/setup/prometheus-operator-0alertmanagerCustomResourceDefinition.yaml
View File

File diff suppressed because it is too large Load Diff

130
manifests/setup/prometheus-operator-0podmonitorCustomResourceDefinition.yaml
View File

@@ -20,31 +20,24 @@ spec:
description: PodMonitor defines monitoring for a set of pods.
properties:
apiVersion:
description: 'APIVersion defines the versioned schema of this representation
of an object. Servers should convert recognized schemas to the latest
internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources'
description: 'APIVersion defines the versioned schema of this representation of an object. Servers should convert recognized schemas to the latest internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources'
type: string
kind:
description: 'Kind is a string value representing the REST resource this
object represents. Servers may infer this from the endpoint the client
submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds'
description: 'Kind is a string value representing the REST resource this object represents. Servers may infer this from the endpoint the client submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds'
type: string
metadata:
type: object
spec:
description: Specification of desired Pod selection for target discovery
by Prometheus.
description: Specification of desired Pod selection for target discovery by Prometheus.
properties:
jobLabel:
description: The label to use to retrieve the job name from.
type: string
namespaceSelector:
description: Selector to select which namespaces the Endpoints objects
are discovered from.
description: Selector to select which namespaces the Endpoints objects are discovered from.
properties:
any:
description: Boolean describing whether all namespaces are selected
in contrast to a list restricting them.
description: Boolean describing whether all namespaces are selected in contrast to a list restricting them.
type: boolean
matchNames:
description: List of namespace names.
@@ -55,63 +48,45 @@ spec:
podMetricsEndpoints:
description: A list of endpoints allowed as part of this PodMonitor.
items:
description: PodMetricsEndpoint defines a scrapeable endpoint of
a Kubernetes Pod serving Prometheus metrics.
description: PodMetricsEndpoint defines a scrapeable endpoint of a Kubernetes Pod serving Prometheus metrics.
properties:
honorLabels:
description: HonorLabels chooses the metric's labels on collisions
with target labels.
description: HonorLabels chooses the metric's labels on collisions with target labels.
type: boolean
honorTimestamps:
description: HonorTimestamps controls whether Prometheus respects
the timestamps present in scraped data.
description: HonorTimestamps controls whether Prometheus respects the timestamps present in scraped data.
type: boolean
interval:
description: Interval at which metrics should be scraped
type: string
metricRelabelings:
description: MetricRelabelConfigs to apply to samples before
ingestion.
description: MetricRelabelConfigs to apply to samples before ingestion.
items:
description: 'RelabelConfig allows dynamic rewriting of the
label set, being applied to samples before ingestion. It
defines `<metric_relabel_configs>`-section of Prometheus
configuration. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#metric_relabel_configs'
description: 'RelabelConfig allows dynamic rewriting of the label set, being applied to samples before ingestion. It defines `<metric_relabel_configs>`-section of Prometheus configuration. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#metric_relabel_configs'
properties:
action:
description: Action to perform based on regex matching.
Default is 'replace'
description: Action to perform based on regex matching. Default is 'replace'
type: string
modulus:
description: Modulus to take of the hash of the source
label values.
description: Modulus to take of the hash of the source label values.
format: int64
type: integer
regex:
description: Regular expression against which the extracted
value is matched. Default is '(.*)'
description: Regular expression against which the extracted value is matched. Default is '(.*)'
type: string
replacement:
description: Replacement value against which a regex replace
is performed if the regular expression matches. Regex
capture groups are available. Default is '$1'
description: Replacement value against which a regex replace is performed if the regular expression matches. Regex capture groups are available. Default is '$1'
type: string
separator:
description: Separator placed between concatenated source
label values. default is ';'.
description: Separator placed between concatenated source label values. default is ';'.
type: string
sourceLabels:
description: The source labels select values from existing
labels. Their content is concatenated using the configured
separator and matched against the configured regular
expression for the replace, keep, and drop actions.
description: The source labels select values from existing labels. Their content is concatenated using the configured separator and matched against the configured regular expression for the replace, keep, and drop actions.
items:
type: string
type: array
targetLabel:
description: Label to which the resulting value is written
in a replace action. It is mandatory for replace actions.
Regex capture groups are available.
description: Label to which the resulting value is written in a replace action. It is mandatory for replace actions. Regex capture groups are available.
type: string
type: object
type: array
@@ -126,56 +101,39 @@ spec:
description: HTTP path to scrape for metrics.
type: string
port:
description: Name of the pod port this endpoint refers to. Mutually
exclusive with targetPort.
description: Name of the pod port this endpoint refers to. Mutually exclusive with targetPort.
type: string
proxyUrl:
description: ProxyURL eg http://proxyserver:2195 Directs scrapes
to proxy through this endpoint.
description: ProxyURL eg http://proxyserver:2195 Directs scrapes to proxy through this endpoint.
type: string
relabelings:
description: 'RelabelConfigs to apply to samples before ingestion.
More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#relabel_config'
description: 'RelabelConfigs to apply to samples before ingestion. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#relabel_config'
items:
description: 'RelabelConfig allows dynamic rewriting of the
label set, being applied to samples before ingestion. It
defines `<metric_relabel_configs>`-section of Prometheus
configuration. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#metric_relabel_configs'
description: 'RelabelConfig allows dynamic rewriting of the label set, being applied to samples before ingestion. It defines `<metric_relabel_configs>`-section of Prometheus configuration. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#metric_relabel_configs'
properties:
action:
description: Action to perform based on regex matching.
Default is 'replace'
description: Action to perform based on regex matching. Default is 'replace'
type: string
modulus:
description: Modulus to take of the hash of the source
label values.
description: Modulus to take of the hash of the source label values.
format: int64
type: integer
regex:
description: Regular expression against which the extracted
value is matched. Default is '(.*)'
description: Regular expression against which the extracted value is matched. Default is '(.*)'
type: string
replacement:
description: Replacement value against which a regex replace
is performed if the regular expression matches. Regex
capture groups are available. Default is '$1'
description: Replacement value against which a regex replace is performed if the regular expression matches. Regex capture groups are available. Default is '$1'
type: string
separator:
description: Separator placed between concatenated source
label values. default is ';'.
description: Separator placed between concatenated source label values. default is ';'.
type: string
sourceLabels:
description: The source labels select values from existing
labels. Their content is concatenated using the configured
separator and matched against the configured regular
expression for the replace, keep, and drop actions.
description: The source labels select values from existing labels. Their content is concatenated using the configured separator and matched against the configured regular expression for the replace, keep, and drop actions.
items:
type: string
type: array
targetLabel:
description: Label to which the resulting value is written
in a replace action. It is mandatory for replace actions.
Regex capture groups are available.
description: Label to which the resulting value is written in a replace action. It is mandatory for replace actions. Regex capture groups are available.
type: string
type: object
type: array
@@ -194,42 +152,30 @@ spec:
type: object
type: array
podTargetLabels:
description: PodTargetLabels transfers labels on the Kubernetes Pod
onto the target.
description: PodTargetLabels transfers labels on the Kubernetes Pod onto the target.
items:
type: string
type: array
sampleLimit:
description: SampleLimit defines per-scrape limit on number of scraped
samples that will be accepted.
description: SampleLimit defines per-scrape limit on number of scraped samples that will be accepted.
format: int64
type: integer
selector:
description: Selector to select Pod objects.
properties:
matchExpressions:
description: matchExpressions is a list of label selector requirements.
The requirements are ANDed.
description: matchExpressions is a list of label selector requirements. The requirements are ANDed.
items:
description: A label selector requirement is a selector that
contains values, a key, and an operator that relates the key
and values.
description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values.
properties:
key:
description: key is the label key that the selector applies
to.
description: key is the label key that the selector applies to.
type: string
operator:
description: operator represents a key's relationship to
a set of values. Valid operators are In, NotIn, Exists
and DoesNotExist.
description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist.
type: string
values:
description: values is an array of string values. If the
operator is In or NotIn, the values array must be non-empty.
If the operator is Exists or DoesNotExist, the values
array must be empty. This array is replaced during a strategic
merge patch.
description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch.
items:
type: string
type: array
@@ -241,11 +187,7 @@ spec:
matchLabels:
additionalProperties:
type: string
description: matchLabels is a map of {key,value} pairs. A single
{key,value} in the matchLabels map is equivalent to an element
of matchExpressions, whose key field is "key", the operator
is "In", and the values array contains only "value". The requirements
are ANDed.
description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed.
type: object
type: object
required:

100
manifests/setup/prometheus-operator-0probeCustomResourceDefinition.yaml
View File

@@ -20,37 +20,27 @@ spec:
description: Probe defines monitoring for a set of static targets or ingresses.
properties:
apiVersion:
description: 'APIVersion defines the versioned schema of this representation
of an object. Servers should convert recognized schemas to the latest
internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources'
description: 'APIVersion defines the versioned schema of this representation of an object. Servers should convert recognized schemas to the latest internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources'
type: string
kind:
description: 'Kind is a string value representing the REST resource this
object represents. Servers may infer this from the endpoint the client
submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds'
description: 'Kind is a string value representing the REST resource this object represents. Servers may infer this from the endpoint the client submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds'
type: string
metadata:
type: object
spec:
description: Specification of desired Ingress selection for target discovery
by Prometheus.
description: Specification of desired Ingress selection for target discovery by Prometheus.
properties:
interval:
description: Interval at which targets are probed using the configured
prober. If not specified Prometheus' global scrape interval is used.
description: Interval at which targets are probed using the configured prober. If not specified Prometheus' global scrape interval is used.
type: string
jobName:
description: The job name assigned to scraped metrics by default.
type: string
module:
description: 'The module to use for probing specifying how to probe
the target. Example module configuring in the blackbox exporter:
https://github.com/prometheus/blackbox_exporter/blob/master/example.yml'
description: 'The module to use for probing specifying how to probe the target. Example module configuring in the blackbox exporter: https://github.com/prometheus/blackbox_exporter/blob/master/example.yml'
type: string
prober:
description: Specification for the prober to use for probing targets.
The prober.URL parameter is required. Targets cannot be probed if
left empty.
description: Specification for the prober to use for probing targets. The prober.URL parameter is required. Targets cannot be probed if left empty.
properties:
path:
description: Path to collect metrics from. Defaults to `/probe`.
@@ -68,19 +58,16 @@ spec:
description: Timeout for scraping metrics from the Prometheus exporter.
type: string
targets:
description: Targets defines a set of static and/or dynamically discovered
targets to be probed using the prober.
description: Targets defines a set of static and/or dynamically discovered targets to be probed using the prober.
properties:
ingress:
description: Ingress defines the set of dynamically discovered
ingress objects which hosts are considered for probing.
description: Ingress defines the set of dynamically discovered ingress objects which hosts are considered for probing.
properties:
namespaceSelector:
description: Select Ingress objects by namespace.
properties:
any:
description: Boolean describing whether all namespaces
are selected in contrast to a list restricting them.
description: Boolean describing whether all namespaces are selected in contrast to a list restricting them.
type: boolean
matchNames:
description: List of namespace names.
@@ -89,48 +76,33 @@ spec:
type: array
type: object
relabelingConfigs:
description: 'RelabelConfigs to apply to samples before ingestion.
More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#relabel_config'
description: 'RelabelConfigs to apply to samples before ingestion. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#relabel_config'
items:
description: 'RelabelConfig allows dynamic rewriting of
the label set, being applied to samples before ingestion.
It defines `<metric_relabel_configs>`-section of Prometheus
configuration. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#metric_relabel_configs'
description: 'RelabelConfig allows dynamic rewriting of the label set, being applied to samples before ingestion. It defines `<metric_relabel_configs>`-section of Prometheus configuration. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#metric_relabel_configs'
properties:
action:
description: Action to perform based on regex matching.
Default is 'replace'
description: Action to perform based on regex matching. Default is 'replace'
type: string
modulus:
description: Modulus to take of the hash of the source
label values.
description: Modulus to take of the hash of the source label values.
format: int64
type: integer
regex:
description: Regular expression against which the extracted
value is matched. Default is '(.*)'
description: Regular expression against which the extracted value is matched. Default is '(.*)'
type: string
replacement:
description: Replacement value against which a regex
replace is performed if the regular expression matches.
Regex capture groups are available. Default is '$1'
description: Replacement value against which a regex replace is performed if the regular expression matches. Regex capture groups are available. Default is '$1'
type: string
separator:
description: Separator placed between concatenated source
label values. default is ';'.
description: Separator placed between concatenated source label values. default is ';'.
type: string
sourceLabels:
description: The source labels select values from existing
labels. Their content is concatenated using the configured
separator and matched against the configured regular
expression for the replace, keep, and drop actions.
description: The source labels select values from existing labels. Their content is concatenated using the configured separator and matched against the configured regular expression for the replace, keep, and drop actions.
items:
type: string
type: array
targetLabel:
description: Label to which the resulting value is written
in a replace action. It is mandatory for replace actions.
Regex capture groups are available.
description: Label to which the resulting value is written in a replace action. It is mandatory for replace actions. Regex capture groups are available.
type: string
type: object
type: array
@@ -138,29 +110,18 @@ spec:
description: Select Ingress objects by labels.
properties:
matchExpressions:
description: matchExpressions is a list of label selector
requirements. The requirements are ANDed.
description: matchExpressions is a list of label selector requirements. The requirements are ANDed.
items:
description: A label selector requirement is a selector
that contains values, a key, and an operator that
relates the key and values.
description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values.
properties:
key:
description: key is the label key that the selector
applies to.
description: key is the label key that the selector applies to.
type: string
operator:
description: operator represents a key's relationship
to a set of values. Valid operators are In, NotIn,
Exists and DoesNotExist.
description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist.
type: string
values:
description: values is an array of string values.
If the operator is In or NotIn, the values array
must be non-empty. If the operator is Exists or
DoesNotExist, the values array must be empty.
This array is replaced during a strategic merge
patch.
description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch.
items:
type: string
type: array
@@ -172,27 +133,20 @@ spec:
matchLabels:
additionalProperties:
type: string
description: matchLabels is a map of {key,value} pairs.
A single {key,value} in the matchLabels map is equivalent
to an element of matchExpressions, whose key field is
"key", the operator is "In", and the values array contains
only "value". The requirements are ANDed.
description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed.
type: object
type: object
type: object
staticConfig:
description: 'StaticConfig defines static targets which are considers
for probing. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#static_config.'
description: 'StaticConfig defines static targets which are considers for probing. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#static_config.'
properties:
labels:
additionalProperties:
type: string
description: Labels assigned to all metrics scraped from the
targets.
description: Labels assigned to all metrics scraped from the targets.
type: object
static:
description: Targets is a list of URLs to probe using the
configured prober.
description: Targets is a list of URLs to probe using the configured prober.
items:
type: string
type: array

3887
manifests/setup/prometheus-operator-0prometheusCustomResourceDefinition.yaml
View File

File diff suppressed because it is too large Load Diff

13
manifests/setup/prometheus-operator-0prometheusruleCustomResourceDefinition.yaml
View File

@@ -20,14 +20,10 @@ spec:
description: PrometheusRule defines alerting rules for a Prometheus instance
properties:
apiVersion:
description: 'APIVersion defines the versioned schema of this representation
of an object. Servers should convert recognized schemas to the latest
internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources'
description: 'APIVersion defines the versioned schema of this representation of an object. Servers should convert recognized schemas to the latest internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources'
type: string
kind:
description: 'Kind is a string value representing the REST resource this
object represents. Servers may infer this from the endpoint the client
submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds'
description: 'Kind is a string value representing the REST resource this object represents. Servers may infer this from the endpoint the client submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds'
type: string
metadata:
type: object
@@ -37,10 +33,7 @@ spec:
groups:
description: Content of Prometheus rule file
items:
description: 'RuleGroup is a list of sequentially evaluated recording
and alerting rules. Note: PartialResponseStrategy is only used
by ThanosRuler and will be ignored by Prometheus instances. Valid
values for this field are ''warn'' or ''abort''. More info: https://github.com/thanos-io/thanos/blob/master/docs/components/rule.md#partial-response'
description: 'RuleGroup is a list of sequentially evaluated recording and alerting rules. Note: PartialResponseStrategy is only used by ThanosRuler and will be ignored by Prometheus instances. Valid values for this field are ''warn'' or ''abort''. More info: https://github.com/thanos-io/thanos/blob/master/docs/components/rule.md#partial-response'
properties:
interval:
type: string

244
manifests/setup/prometheus-operator-0servicemonitorCustomResourceDefinition.yaml
View File

@@ -20,65 +20,50 @@ spec:
description: ServiceMonitor defines monitoring for a set of services.
properties:
apiVersion:
description: 'APIVersion defines the versioned schema of this representation
of an object. Servers should convert recognized schemas to the latest
internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources'
description: 'APIVersion defines the versioned schema of this representation of an object. Servers should convert recognized schemas to the latest internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources'
type: string
kind:
description: 'Kind is a string value representing the REST resource this
object represents. Servers may infer this from the endpoint the client
submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds'
description: 'Kind is a string value representing the REST resource this object represents. Servers may infer this from the endpoint the client submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds'
type: string
metadata:
type: object
spec:
description: Specification of desired Service selection for target discovery
by Prometheus.
description: Specification of desired Service selection for target discovery by Prometheus.
properties:
endpoints:
description: A list of endpoints allowed as part of this ServiceMonitor.
items:
description: Endpoint defines a scrapeable endpoint serving Prometheus
metrics.
description: Endpoint defines a scrapeable endpoint serving Prometheus metrics.
properties:
basicAuth:
description: 'BasicAuth allow an endpoint to authenticate over
basic authentication More info: https://prometheus.io/docs/operating/configuration/#endpoints'
description: 'BasicAuth allow an endpoint to authenticate over basic authentication More info: https://prometheus.io/docs/operating/configuration/#endpoints'
properties:
password:
description: The secret in the service monitor namespace
that contains the password for authentication.
description: The secret in the service monitor namespace that contains the password for authentication.
properties:
key:
description: The key of the secret to select from. Must
be a valid secret key.
description: The key of the secret to select from. Must be a valid secret key.
type: string
name:
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
TODO: Add other useful fields. apiVersion, kind, uid?'
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?'
type: string
optional:
description: Specify whether the Secret or its key must
be defined
description: Specify whether the Secret or its key must be defined
type: boolean
required:
- key
type: object
username:
description: The secret in the service monitor namespace
that contains the username for authentication.
description: The secret in the service monitor namespace that contains the username for authentication.
properties:
key:
description: The key of the secret to select from. Must
be a valid secret key.
description: The key of the secret to select from. Must be a valid secret key.
type: string
name:
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
TODO: Add other useful fields. apiVersion, kind, uid?'
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?'
type: string
optional:
description: Specify whether the Secret or its key must
be defined
description: Specify whether the Secret or its key must be defined
type: boolean
required:
- key
@@ -88,79 +73,57 @@ spec:
description: File to read bearer token for scraping targets.
type: string
bearerTokenSecret:
description: Secret to mount to read bearer token for scraping
targets. The secret needs to be in the same namespace as the
service monitor and accessible by the Prometheus Operator.
description: Secret to mount to read bearer token for scraping targets. The secret needs to be in the same namespace as the service monitor and accessible by the Prometheus Operator.
properties:
key:
description: The key of the secret to select from. Must
be a valid secret key.
description: The key of the secret to select from. Must be a valid secret key.
type: string
name:
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
TODO: Add other useful fields. apiVersion, kind, uid?'
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?'
type: string
optional:
description: Specify whether the Secret or its key must
be defined
description: Specify whether the Secret or its key must be defined
type: boolean
required:
- key
type: object
honorLabels:
description: HonorLabels chooses the metric's labels on collisions
with target labels.
description: HonorLabels chooses the metric's labels on collisions with target labels.
type: boolean
honorTimestamps:
description: HonorTimestamps controls whether Prometheus respects
the timestamps present in scraped data.
description: HonorTimestamps controls whether Prometheus respects the timestamps present in scraped data.
type: boolean
interval:
description: Interval at which metrics should be scraped
type: string
metricRelabelings:
description: MetricRelabelConfigs to apply to samples before
ingestion.
description: MetricRelabelConfigs to apply to samples before ingestion.
items:
description: 'RelabelConfig allows dynamic rewriting of the
label set, being applied to samples before ingestion. It
defines `<metric_relabel_configs>`-section of Prometheus
configuration. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#metric_relabel_configs'
description: 'RelabelConfig allows dynamic rewriting of the label set, being applied to samples before ingestion. It defines `<metric_relabel_configs>`-section of Prometheus configuration. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#metric_relabel_configs'
properties:
action:
description: Action to perform based on regex matching.
Default is 'replace'
description: Action to perform based on regex matching. Default is 'replace'
type: string
modulus:
description: Modulus to take of the hash of the source
label values.
description: Modulus to take of the hash of the source label values.
format: int64
type: integer
regex:
description: Regular expression against which the extracted
value is matched. Default is '(.*)'
description: Regular expression against which the extracted value is matched. Default is '(.*)'
type: string
replacement:
description: Replacement value against which a regex replace
is performed if the regular expression matches. Regex
capture groups are available. Default is '$1'
description: Replacement value against which a regex replace is performed if the regular expression matches. Regex capture groups are available. Default is '$1'
type: string
separator:
description: Separator placed between concatenated source
label values. default is ';'.
description: Separator placed between concatenated source label values. default is ';'.
type: string
sourceLabels:
description: The source labels select values from existing
labels. Their content is concatenated using the configured
separator and matched against the configured regular
expression for the replace, keep, and drop actions.
description: The source labels select values from existing labels. Their content is concatenated using the configured separator and matched against the configured regular expression for the replace, keep, and drop actions.
items:
type: string
type: array
targetLabel:
description: Label to which the resulting value is written
in a replace action. It is mandatory for replace actions.
Regex capture groups are available.
description: Label to which the resulting value is written in a replace action. It is mandatory for replace actions. Regex capture groups are available.
type: string
type: object
type: array
@@ -175,56 +138,39 @@ spec:
description: HTTP path to scrape for metrics.
type: string
port:
description: Name of the service port this endpoint refers to.
Mutually exclusive with targetPort.
description: Name of the service port this endpoint refers to. Mutually exclusive with targetPort.
type: string
proxyUrl:
description: ProxyURL eg http://proxyserver:2195 Directs scrapes
to proxy through this endpoint.
description: ProxyURL eg http://proxyserver:2195 Directs scrapes to proxy through this endpoint.
type: string
relabelings:
description: 'RelabelConfigs to apply to samples before scraping.
More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#relabel_config'
description: 'RelabelConfigs to apply to samples before scraping. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#relabel_config'
items:
description: 'RelabelConfig allows dynamic rewriting of the
label set, being applied to samples before ingestion. It
defines `<metric_relabel_configs>`-section of Prometheus
configuration. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#metric_relabel_configs'
description: 'RelabelConfig allows dynamic rewriting of the label set, being applied to samples before ingestion. It defines `<metric_relabel_configs>`-section of Prometheus configuration. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#metric_relabel_configs'
properties:
action:
description: Action to perform based on regex matching.
Default is 'replace'
description: Action to perform based on regex matching. Default is 'replace'
type: string
modulus:
description: Modulus to take of the hash of the source
label values.
description: Modulus to take of the hash of the source label values.
format: int64
type: integer
regex:
description: Regular expression against which the extracted
value is matched. Default is '(.*)'
description: Regular expression against which the extracted value is matched. Default is '(.*)'
type: string
replacement:
description: Replacement value against which a regex replace
is performed if the regular expression matches. Regex
capture groups are available. Default is '$1'
description: Replacement value against which a regex replace is performed if the regular expression matches. Regex capture groups are available. Default is '$1'
type: string
separator:
description: Separator placed between concatenated source
label values. default is ';'.
description: Separator placed between concatenated source label values. default is ';'.
type: string
sourceLabels:
description: The source labels select values from existing
labels. Their content is concatenated using the configured
separator and matched against the configured regular
expression for the replace, keep, and drop actions.
description: The source labels select values from existing labels. Their content is concatenated using the configured separator and matched against the configured regular expression for the replace, keep, and drop actions.
items:
type: string
type: array
targetLabel:
description: Label to which the resulting value is written
in a replace action. It is mandatory for replace actions.
Regex capture groups are available.
description: Label to which the resulting value is written in a replace action. It is mandatory for replace actions. Regex capture groups are available.
type: string
type: object
type: array
@@ -238,32 +184,25 @@ spec:
anyOf:
- type: integer
- type: string
description: Name or number of the target port of the Pod behind
the Service, the port must be specified with container port
property. Mutually exclusive with port.
description: Name or number of the target port of the Pod behind the Service, the port must be specified with container port property. Mutually exclusive with port.
x-kubernetes-int-or-string: true
tlsConfig:
description: TLS configuration to use when scraping the endpoint
properties:
ca:
description: Stuct containing the CA cert to use for the
targets.
description: Stuct containing the CA cert to use for the targets.
properties:
configMap:
description: ConfigMap containing data to use for the
targets.
description: ConfigMap containing data to use for the targets.
properties:
key:
description: The key to select.
type: string
name:
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
TODO: Add other useful fields. apiVersion, kind,
uid?'
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?'
type: string
optional:
description: Specify whether the ConfigMap or its
key must be defined
description: Specify whether the ConfigMap or its key must be defined
type: boolean
required:
- key
@@ -272,45 +211,35 @@ spec:
description: Secret containing data to use for the targets.
properties:
key:
description: The key of the secret to select from. Must
be a valid secret key.
description: The key of the secret to select from. Must be a valid secret key.
type: string
name:
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
TODO: Add other useful fields. apiVersion, kind,
uid?'
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?'
type: string
optional:
description: Specify whether the Secret or its key
must be defined
description: Specify whether the Secret or its key must be defined
type: boolean
required:
- key
type: object
type: object
caFile:
description: Path to the CA cert in the Prometheus container
to use for the targets.
description: Path to the CA cert in the Prometheus container to use for the targets.
type: string
cert:
description: Struct containing the client cert file for
the targets.
description: Struct containing the client cert file for the targets.
properties:
configMap:
description: ConfigMap containing data to use for the
targets.
description: ConfigMap containing data to use for the targets.
properties:
key:
description: The key to select.
type: string
name:
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
TODO: Add other useful fields. apiVersion, kind,
uid?'
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?'
type: string
optional:
description: Specify whether the ConfigMap or its
key must be defined
description: Specify whether the ConfigMap or its key must be defined
type: boolean
required:
- key
@@ -319,48 +248,38 @@ spec:
description: Secret containing data to use for the targets.
properties:
key:
description: The key of the secret to select from. Must
be a valid secret key.
description: The key of the secret to select from. Must be a valid secret key.
type: string
name:
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
TODO: Add other useful fields. apiVersion, kind,
uid?'
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?'
type: string
optional:
description: Specify whether the Secret or its key
must be defined
description: Specify whether the Secret or its key must be defined
type: boolean
required:
- key
type: object
type: object
certFile:
description: Path to the client cert file in the Prometheus
container for the targets.
description: Path to the client cert file in the Prometheus container for the targets.
type: string
insecureSkipVerify:
description: Disable target certificate validation.
type: boolean
keyFile:
description: Path to the client key file in the Prometheus
container for the targets.
description: Path to the client key file in the Prometheus container for the targets.
type: string
keySecret:
description: Secret containing the client key file for the
targets.
description: Secret containing the client key file for the targets.
properties:
key:
description: The key of the secret to select from. Must
be a valid secret key.
description: The key of the secret to select from. Must be a valid secret key.
type: string
name:
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
TODO: Add other useful fields. apiVersion, kind, uid?'
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?'
type: string
optional:
description: Specify whether the Secret or its key must
be defined
description: Specify whether the Secret or its key must be defined
type: boolean
required:
- key
@@ -375,12 +294,10 @@ spec:
description: The label to use to retrieve the job name from.
type: string
namespaceSelector:
description: Selector to select which namespaces the Endpoints objects
are discovered from.
description: Selector to select which namespaces the Endpoints objects are discovered from.
properties:
any:
description: Boolean describing whether all namespaces are selected
in contrast to a list restricting them.
description: Boolean describing whether all namespaces are selected in contrast to a list restricting them.
type: boolean
matchNames:
description: List of namespace names.
@@ -389,42 +306,30 @@ spec:
type: array
type: object
podTargetLabels:
description: PodTargetLabels transfers labels on the Kubernetes Pod
onto the target.
description: PodTargetLabels transfers labels on the Kubernetes Pod onto the target.
items:
type: string
type: array
sampleLimit:
description: SampleLimit defines per-scrape limit on number of scraped
samples that will be accepted.
description: SampleLimit defines per-scrape limit on number of scraped samples that will be accepted.
format: int64
type: integer
selector:
description: Selector to select Endpoints objects.
properties:
matchExpressions:
description: matchExpressions is a list of label selector requirements.
The requirements are ANDed.
description: matchExpressions is a list of label selector requirements. The requirements are ANDed.
items:
description: A label selector requirement is a selector that
contains values, a key, and an operator that relates the key
and values.
description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values.
properties:
key:
description: key is the label key that the selector applies
to.
description: key is the label key that the selector applies to.
type: string
operator:
description: operator represents a key's relationship to
a set of values. Valid operators are In, NotIn, Exists
and DoesNotExist.
description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist.
type: string
values:
description: values is an array of string values. If the
operator is In or NotIn, the values array must be non-empty.
If the operator is Exists or DoesNotExist, the values
array must be empty. This array is replaced during a strategic
merge patch.
description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch.
items:
type: string
type: array
@@ -436,16 +341,11 @@ spec:
matchLabels:
additionalProperties:
type: string
description: matchLabels is a map of {key,value} pairs. A single
{key,value} in the matchLabels map is equivalent to an element
of matchExpressions, whose key field is "key", the operator
is "In", and the values array contains only "value". The requirements
are ANDed.
description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed.
type: object
type: object
targetLabels:
description: TargetLabels transfers labels on the Kubernetes Service
onto the target.
description: TargetLabels transfers labels on the Kubernetes Service onto the target.
items:
type: string
type: array

3028
manifests/setup/prometheus-operator-0thanosrulerCustomResourceDefinition.yaml
View File

File diff suppressed because it is too large Load Diff