Mirrors/rpi.carlosedp.cluster-monitoring
1
0
Fork 0
mirror of https://github.com/carlosedp/cluster-monitoring.git synced 2024-11-20 19:07:17 +01:00
Code Issues Projects Releases Wiki Activity

Update libs

Browse Source
This commit is contained in:
Carlos de Paula 2019-11-17 12:05:27 -03:00
parent b4d6ff0466
commit f857930874
13 changed files with 15830 additions and 3041 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

81
grafana-dashboards/traefik-dashboard.json
View File

@ -16,8 +16,8 @@
"editable": true,
"gnetId": 5851,
"graphTooltip": 0,
"id": 20,
"iteration": 1549118220486,
"id": 28,
"iteration": 1573760766760,
"links": [],
"panels": [
{
@ -74,6 +74,7 @@
"maxDataPoints": 100,
"nullPointMode": "connected",
"nullText": null,
"options": {},
"postfix": "",
"postfixFontSize": "50%",
"prefix": "",
@ -154,6 +155,7 @@
"maxDataPoints": 100,
"nullPointMode": "connected",
"nullText": null,
"options": {},
"postfix": "",
"postfixFontSize": "50%",
"prefix": "",
@ -234,6 +236,7 @@
"maxDataPoints": 100,
"nullPointMode": "connected",
"nullText": null,
"options": {},
"postfix": "",
"postfixFontSize": "50%",
"prefix": "",
@ -283,6 +286,7 @@
"dashes": false,
"datasource": "prometheus",
"fill": 2,
"fillGradient": 0,
"gridPos": {
"h": 7,
"w": 14,
@ -303,6 +307,9 @@
"linewidth": 2,
"links": [],
"nullPointMode": "null as zero",
"options": {
"dataLinks": []
},
"percentage": false,
"pointradius": 5,
"points": false,
@ -374,6 +381,7 @@
"dashes": false,
"datasource": "prometheus",
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 7,
"w": 24,
@ -396,6 +404,9 @@
"linewidth": 1,
"links": [],
"nullPointMode": "null",
"options": {
"dataLinks": []
},
"percentage": false,
"pointradius": 5,
"points": false,
@ -474,6 +485,7 @@
"dashes": false,
"datasource": "prometheus",
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 7,
"w": 24,
@ -496,6 +508,9 @@
"linewidth": 1,
"links": [],
"nullPointMode": "null",
"options": {
"dataLinks": []
},
"percentage": false,
"pointradius": 5,
"points": false,
@ -561,6 +576,7 @@
"dashes": false,
"datasource": "prometheus",
"fill": 7,
"fillGradient": 0,
"gridPos": {
"h": 7,
"w": 12,
@ -585,6 +601,9 @@
"linewidth": 1,
"links": [],
"nullPointMode": "null",
"options": {
"dataLinks": []
},
"percentage": false,
"pointradius": 5,
"points": false,
@ -650,6 +669,7 @@
"dashes": false,
"datasource": "prometheus",
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 7,
"w": 12,
@ -672,6 +692,9 @@
"linewidth": 1,
"links": [],
"nullPointMode": "null",
"options": {
"dataLinks": []
},
"percentage": false,
"pointradius": 5,
"points": false,
@ -750,6 +773,7 @@
"dashes": false,
"datasource": "prometheus",
"fill": 7,
"fillGradient": 0,
"gridPos": {
"h": 7,
"w": 12,
@ -774,6 +798,9 @@
"linewidth": 1,
"links": [],
"nullPointMode": "null",
"options": {
"dataLinks": []
},
"percentage": false,
"pointradius": 5,
"points": false,
@ -839,6 +866,7 @@
"dashes": false,
"datasource": "prometheus",
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 7,
"w": 12,
@ -861,6 +889,9 @@
"linewidth": 1,
"links": [],
"nullPointMode": "null",
"options": {
"dataLinks": []
},
"percentage": false,
"pointradius": 5,
"points": false,
@ -929,7 +960,7 @@
},
"id": 15,
"panels": [],
"title": "HTTP Codes stats",
"title": "HTTP Code stats",
"type": "row"
},
{
@ -939,6 +970,7 @@
"dashes": false,
"datasource": "prometheus",
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 9,
"w": 12,
@ -963,6 +995,9 @@
"linewidth": 1,
"links": [],
"nullPointMode": "null",
"options": {
"dataLinks": []
},
"percentage": false,
"pointradius": 5,
"points": false,
@ -1028,6 +1063,7 @@
"dashes": false,
"datasource": "prometheus",
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 9,
"w": 12,
@ -1050,6 +1086,9 @@
"linewidth": 1,
"links": [],
"nullPointMode": "null",
"options": {
"dataLinks": []
},
"percentage": false,
"pointradius": 5,
"points": false,
@ -1115,6 +1154,7 @@
"dashes": false,
"datasource": "prometheus",
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 9,
"w": 12,
@ -1139,6 +1179,9 @@
"linewidth": 1,
"links": [],
"nullPointMode": "null",
"options": {
"dataLinks": []
},
"percentage": false,
"pointradius": 5,
"points": false,
@ -1204,6 +1247,7 @@
"dashes": false,
"datasource": "prometheus",
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 9,
"w": 12,
@ -1227,6 +1271,9 @@
"linewidth": 1,
"links": [],
"nullPointMode": "null",
"options": {
"dataLinks": []
},
"percentage": false,
"pointradius": 5,
"points": false,
@ -1295,7 +1342,7 @@
},
"id": 35,
"panels": [],
"title": "Pods ressources",
"title": "Pod Resources",
"type": "row"
},
{
@ -1305,6 +1352,7 @@
"dashes": false,
"datasource": "prometheus",
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 9,
"w": 12,
@ -1327,6 +1375,9 @@
"linewidth": 1,
"links": [],
"nullPointMode": "null",
"options": {
"dataLinks": []
},
"percentage": false,
"pointradius": 5,
"points": false,
@ -1337,21 +1388,21 @@
"steppedLine": false,
"targets": [
{
"expr": "max(container_memory_usage_bytes{namespace=\"$namespace\", pod_name=~\"traefik-ingress-controller.*\"})",
"expr": "max(container_memory_usage_bytes{namespace=\"$namespace\", pod=~\"traefik-.*\"})",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "Max memory used",
"refId": "A"
},
{
"expr": "avg(kube_pod_container_resource_requests_memory_bytes{namespace=\"$namespace\", pod_name=~\"traefik-ingress-controller.*\"})",
"expr": "avg(kube_pod_container_resource_requests_memory_bytes{namespace=\"$namespace\", pod=~\"traefik-.*\"})",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "Requested memory usage",
"refId": "B"
},
{
"expr": "avg(kube_pod_container_resource_limits_memory_bytes{namespace=\"$namespace\", pod_name=~\"traefik-ingress-controller.*\"})",
"expr": "avg(kube_pod_container_resource_limits_memory_bytes{namespace=\"$namespace\", pod=~\"traefik-.*\"})",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "Limit memory usage",
@ -1406,6 +1457,7 @@
"dashes": false,
"datasource": "prometheus",
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 9,
"w": 12,
@ -1427,6 +1479,9 @@
"linewidth": 1,
"links": [],
"nullPointMode": "null",
"options": {
"dataLinks": []
},
"percentage": false,
"pointradius": 5,
"points": false,
@ -1437,21 +1492,21 @@
"steppedLine": false,
"targets": [
{
"expr": "max(rate(container_cpu_usage_seconds_total{namespace=\"$namespace\", pod_name=~\"traefik-ingress-controller.*\"}[1m]))",
"expr": "max(rate(container_cpu_usage_seconds_total{namespace=\"$namespace\", pod=~\"traefik-.*\"}[1m]))",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "Max cpu used",
"refId": "A"
},
{
"expr": "avg(kube_pod_container_resource_requests_cpu_cores{namespace=\"$namespace\", pod_name=~\"traefik-ingress-controller.*\"})",
"expr": "avg(kube_pod_container_resource_requests_cpu_cores{namespace=\"$namespace\", pod=~\"traefik-.*\"})",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "Requested cpu usage",
"refId": "B"
},
{
"expr": "avg(kube_pod_container_resource_limits_cpu_cores{namespace=\"$namespace\", pod_name=~\"traefik-ingress-controller.*\"})",
"expr": "avg(kube_pod_container_resource_limits_cpu_cores{namespace=\"$namespace\", pod=~\"traefik-.*\"})",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "Limit cpu usage",
@ -1500,7 +1555,7 @@
}
}
],
"schemaVersion": 16,
"schemaVersion": 19,
"style": "dark",
"tags": [
"traefik"
@ -1564,7 +1619,7 @@
]
},
"time": {
"from": "now-3h",
"from": "now-30m",
"to": "now"
},
"timepicker": {
@ -1595,5 +1650,5 @@
"timezone": "",
"title": "Traefik",
"uid": "000000113",
"version": 3
"version": 1
}

129
jsonnetfile.lock.json
View File

@ -1,54 +1,15 @@
{
"dependencies": [
{
"name": "kube-prometheus",
"name": "etcd-mixin",
"source": {
"git": {
"remote": "https://github.com/coreos/kube-prometheus",
"subdir": "jsonnet/kube-prometheus"
"remote": "https://github.com/coreos/etcd",
"subdir": "Documentation/etcd-mixin"
}
},
"version": "8405360a467a34fca34735d92c763ae38bfe5917"
},
{
"name": "ksonnet",
"source": {
"git": {
"remote": "https://github.com/ksonnet/ksonnet-lib",
"subdir": ""
}
},
"version": "0d2f82676817bbf9e4acf6495b2090205f323b9f"
},
{
"name": "kubernetes-mixin",
"source": {
"git": {
"remote": "https://github.com/kubernetes-monitoring/kubernetes-mixin",
"subdir": ""
}
},
"version": "acac6762be477a7ec16a96ae5222dd365568d87d"
},
{
"name": "grafonnet",
"source": {
"git": {
"remote": "https://github.com/grafana/grafonnet-lib",
"subdir": "grafonnet"
}
},
"version": "69bc267211790a1c3f4ea6e6211f3e8ffe22f987"
},
{
"name": "grafana-builder",
"source": {
"git": {
"remote": "https://github.com/kausalco/public",
"subdir": "grafana-builder"
}
},
"version": "1e4da2e3aa19d9880cf5ae07a5220bbd10c11083"
"version": "63dd73c1869f1784f907b922f61571176a2802e8",
"sum": "bkp18AxkOUYnVC15Gh9EoIi+mMAn0IT3hMzb8mlzpSw="
},
{
"name": "grafana",
@ -58,37 +19,63 @@
"subdir": "grafana"
}
},
"version": "c79fdb1f6cbd14a003f73d9a6f571f1cefc6638d"
"version": "539a90dbf63c812ad0194d8078dd776868a11c81",
"sum": "b8faWX1qqLGyN67sA36oRqYZ5HX+tHBRMPtrWRqIysE="
},
{
"name": "prometheus-operator",
"name": "grafana-builder",
"source": {
"git": {
"remote": "https://github.com/coreos/prometheus-operator",
"subdir": "jsonnet/prometheus-operator"
"remote": "https://github.com/grafana/jsonnet-libs",
"subdir": "grafana-builder"
}
},
"version": "908ee0372a9ac2c6574d589fdc56a4f3cb5f12d1"
"version": "250bf5499d81e5e77e1e5ed2242c89ad27485aec",
"sum": "ELsYwK+kGdzX1mee2Yy+/b2mdO4Y503BOCDkFzwmGbE="
},
{
"name": "etcd-mixin",
"name": "grafonnet",
"source": {
"git": {
"remote": "https://github.com/coreos/etcd",
"subdir": "Documentation/etcd-mixin"
"remote": "https://github.com/grafana/grafonnet-lib",
"subdir": "grafonnet"
}
},
"version": "f197ab45785dfe81a9e412affbdca7ff733dd5d0"
"version": "cb9e43f59558ff6338a76ae1806a0fb4b70b1b16",
"sum": "YIo2bziNlqzZtlnpLtoi9qa1aztcAX7j1UuKRjjEzVY="
},
{
"name": "prometheus",
"name": "ksonnet",
"source": {
"git": {
"remote": "https://github.com/prometheus/prometheus",
"subdir": "documentation/prometheus-mixin"
"remote": "https://github.com/ksonnet/ksonnet-lib",
"subdir": ""
}
},
"version": "81d284f806ef828e8f323088e00871fedd5a77c2"
"version": "0d2f82676817bbf9e4acf6495b2090205f323b9f",
"sum": "h28BXZ7+vczxYJ2sCt8JuR9+yznRtU/iA6DCpQUrtEg="
},
{
"name": "kube-prometheus",
"source": {
"git": {
"remote": "https://github.com/coreos/kube-prometheus",
"subdir": "jsonnet/kube-prometheus"
}
},
"version": "ce5fe790ee9f1772ad52d935b320d545c8f88722",
"sum": "AerKgmCkb6FsMAjPHqExxYSr6C/uYYq5qV9pAZULaxY="
},
{
"name": "kubernetes-mixin",
"source": {
"git": {
"remote": "https://github.com/kubernetes-monitoring/kubernetes-mixin",
"subdir": ""
}
},
"version": "23416282b86f75bff14bf94732c397764d7ba9db",
"sum": "NIE+/dQ5RelahRoLKLfxqAZEel8OTpDbDr1y05glb0E="
},
{
"name": "node-mixin",
@ -98,7 +85,30 @@
"subdir": "docs/node-mixin"
}
},
"version": "fb54f7f2e0c8e154768e63efffd9a4c161ed6931"
"version": "c4c5f1f062b141d0111b4068a52eb5917048b3ea",
"sum": "7vEamDTP9AApeiF4Zu9ZyXzDIs3rYHzwf9k7g8X+wsg="
},
{
"name": "prometheus",
"source": {
"git": {
"remote": "https://github.com/prometheus/prometheus",
"subdir": "documentation/prometheus-mixin"
}
},
"version": "23c0299d85bfeb5d9b59e994861553a25ca578e5",
"sum": "wSDLAXS5Xzla9RFRE2IW5mRToeRFULHb7dSYYBDfEsM="
},
{
"name": "prometheus-operator",
"source": {
"git": {
"remote": "https://github.com/coreos/prometheus-operator",
"subdir": "jsonnet/prometheus-operator"
}
},
"version": "8d44e0990230144177f97cf62ae4f43b1c4e3168",
"sum": "5U7/8MD3pF9O0YDTtUhg4vctkUBRVFxZxWUyhtNiBM8="
},
{
"name": "promgrafonnet",
@ -108,7 +118,8 @@
"subdir": "lib/promgrafonnet"
}
},
"version": "acac6762be477a7ec16a96ae5222dd365568d87d"
"version": "23416282b86f75bff14bf94732c397764d7ba9db",
"sum": "VhgBM39yv0f4bKv8VfGg4FXkg573evGDRalip9ypKbc="
}
]
}

728
manifests/0prometheus-operator-0alertmanagerCustomResourceDefinition.yaml
View File

@ -15,16 +15,16 @@ spec:
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/api-conventions.md#resources'
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/api-conventions.md#types-kinds'
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
spec:
description: 'AlertmanagerSpec is a specification of the desired behavior
of the Alertmanager cluster. More info: https://github.com/kubernetes/community/blob/master/contributors/devel/api-conventions.md#spec-and-status'
of the Alertmanager cluster. More info: https://github.com/kubernetes/community/blob/master/contributors/devel/sig-architecture/api-conventions.md#spec-and-status'
properties:
additionalPeers:
description: AdditionalPeers allows injecting a set of additional Alertmanagers
@ -626,6 +626,12 @@ spec:
items:
type: string
type: array
configSecret:
description: ConfigSecret is the name of a Kubernetes Secret in the
same namespace as the Alertmanager object, which contains configuration
for this Alertmanager instance. Defaults to 'alertmanager-<alertmanager-name>'
The secret is mounted into /etc/alertmanager/config.
type: string
containers:
description: Containers allows injecting additional containers. This
is meant to allow adding an authentication proxy to an Alertmanager
@ -1051,7 +1057,8 @@ spec:
successThreshold:
description: Minimum consecutive successes for the probe to
be considered successful after having failed. Defaults to
1. Must be 1 for liveness. Minimum value is 1.
1. Must be 1 for liveness and startup. Minimum value is
1.
format: int32
type: integer
tcpSocket:
@ -1203,7 +1210,8 @@ spec:
successThreshold:
description: Minimum consecutive successes for the probe to
be considered successful after having failed. Defaults to
1. Must be 1 for liveness. Minimum value is 1.
1. Must be 1 for liveness and startup. Minimum value is
1.
format: int32
type: integer
tcpSocket:
@ -1352,8 +1360,125 @@ spec:
and is only honored by servers that enable the WindowsGMSA
feature flag.
type: string
runAsUserName:
description: The UserName in Windows to run the entrypoint
of the container process. Defaults to the user specified
in image metadata if unspecified. May also be set in
PodSecurityContext. If set in both SecurityContext and
PodSecurityContext, the value specified in SecurityContext
takes precedence. This field is alpha-level and it is
only honored by servers that enable the WindowsRunAsUserName
feature flag.
type: string
type: object
type: object
startupProbe:
description: Probe describes a health check to be performed against
a container to determine whether it is alive or ready to receive
traffic.
properties:
exec:
description: ExecAction describes a "run in container" action.
properties:
command:
description: Command is the command line to execute inside
the container, the working directory for the command is
root ('/') in the container's filesystem. The command
is simply exec'd, it is not run inside a shell, so traditional
shell instructions ('|', etc) won't work. To use a shell,
you need to explicitly call out to that shell. Exit
status of 0 is treated as live/healthy and non-zero
is unhealthy.
items:
type: string
type: array
type: object
failureThreshold:
description: Minimum consecutive failures for the probe to
be considered failed after having succeeded. Defaults to
3. Minimum value is 1.
format: int32
type: integer
httpGet:
description: HTTPGetAction describes an action based on HTTP
Get requests.
properties:
host:
description: Host name to connect to, defaults to the
pod IP. You probably want to set "Host" in httpHeaders
instead.
type: string
httpHeaders:
description: Custom headers to set in the request. HTTP
allows repeated headers.
items:
description: HTTPHeader describes a custom header to
be used in HTTP probes
properties:
name:
description: The header field name
type: string
value:
description: The header field value
type: string
required:
- name
- value
type: object
type: array
path:
description: Path to access on the HTTP server.
type: string
port:
anyOf:
- type: string
- type: integer
scheme:
description: Scheme to use for connecting to the host.
Defaults to HTTP.
type: string
required:
- port
type: object
initialDelaySeconds:
description: 'Number of seconds after the container has started
before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes'
format: int32
type: integer
periodSeconds:
description: How often (in seconds) to perform the probe.
Default to 10 seconds. Minimum value is 1.
format: int32
type: integer
successThreshold:
description: Minimum consecutive successes for the probe to
be considered successful after having failed. Defaults to
1. Must be 1 for liveness and startup. Minimum value is
1.
format: int32
type: integer
tcpSocket:
description: TCPSocketAction describes an action based on
opening a socket
properties:
host:
description: 'Optional: Host name to connect to, defaults
to the pod IP.'
type: string
port:
anyOf:
- type: string
- type: integer
required:
- port
type: object
timeoutSeconds:
description: 'Number of seconds after which the probe times
out. Defaults to 1 second. Minimum value is 1. More info:
https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes'
format: int32
type: integer
type: object
stdin:
description: Whether this container should allocate a buffer for
stdin in the container runtime. If this is not set, reads from
@ -1918,7 +2043,8 @@ spec:
successThreshold:
description: Minimum consecutive successes for the probe to
be considered successful after having failed. Defaults to
1. Must be 1 for liveness. Minimum value is 1.
1. Must be 1 for liveness and startup. Minimum value is
1.
format: int32
type: integer
tcpSocket:
@ -2070,7 +2196,8 @@ spec:
successThreshold:
description: Minimum consecutive successes for the probe to
be considered successful after having failed. Defaults to
1. Must be 1 for liveness. Minimum value is 1.
1. Must be 1 for liveness and startup. Minimum value is
1.
format: int32
type: integer
tcpSocket:
@ -2219,8 +2346,125 @@ spec:
and is only honored by servers that enable the WindowsGMSA
feature flag.
type: string
runAsUserName:
description: The UserName in Windows to run the entrypoint
of the container process. Defaults to the user specified
in image metadata if unspecified. May also be set in
PodSecurityContext. If set in both SecurityContext and
PodSecurityContext, the value specified in SecurityContext
takes precedence. This field is alpha-level and it is
only honored by servers that enable the WindowsRunAsUserName
feature flag.
type: string
type: object
type: object
startupProbe:
description: Probe describes a health check to be performed against
a container to determine whether it is alive or ready to receive
traffic.
properties:
exec:
description: ExecAction describes a "run in container" action.
properties:
command:
description: Command is the command line to execute inside
the container, the working directory for the command is
root ('/') in the container's filesystem. The command
is simply exec'd, it is not run inside a shell, so traditional
shell instructions ('|', etc) won't work. To use a shell,
you need to explicitly call out to that shell. Exit
status of 0 is treated as live/healthy and non-zero
is unhealthy.
items:
type: string
type: array
type: object
failureThreshold:
description: Minimum consecutive failures for the probe to
be considered failed after having succeeded. Defaults to
3. Minimum value is 1.
format: int32
type: integer
httpGet:
description: HTTPGetAction describes an action based on HTTP
Get requests.
properties:
host:
description: Host name to connect to, defaults to the
pod IP. You probably want to set "Host" in httpHeaders
instead.
type: string
httpHeaders:
description: Custom headers to set in the request. HTTP
allows repeated headers.
items:
description: HTTPHeader describes a custom header to
be used in HTTP probes
properties:
name:
description: The header field name
type: string
value:
description: The header field value
type: string
required:
- name
- value
type: object
type: array
path:
description: Path to access on the HTTP server.
type: string
port:
anyOf:
- type: string
- type: integer
scheme:
description: Scheme to use for connecting to the host.
Defaults to HTTP.
type: string
required:
- port
type: object
initialDelaySeconds:
description: 'Number of seconds after the container has started
before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes'
format: int32
type: integer
periodSeconds:
description: How often (in seconds) to perform the probe.
Default to 10 seconds. Minimum value is 1.
format: int32
type: integer
successThreshold:
description: Minimum consecutive successes for the probe to
be considered successful after having failed. Defaults to
1. Must be 1 for liveness and startup. Minimum value is
1.
format: int32
type: integer
tcpSocket:
description: TCPSocketAction describes an action based on
opening a socket
properties:
host:
description: 'Optional: Host name to connect to, defaults
to the pod IP.'
type: string
port:
anyOf:
- type: string
- type: integer
required:
- port
type: object
timeoutSeconds:
description: 'Number of seconds after which the probe times
out. Defaults to 1 second. Minimum value is 1. More info:
https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes'
format: int32
type: integer
type: object
stdin:
description: Whether this container should allocate a buffer for
stdin in the container runtime. If this is not set, reads from
@ -2397,179 +2641,13 @@ spec:
If this field is specified and the generated name exists, the server will NOT return a 409 - instead, it will either return 201 Created or 500 with Reason ServerTimeout indicating a unique name could not be found in the time allotted, and the client should retry (optionally after the time indicated in the Retry-After header).
Applied only if Name is not specified. More info: https://git.k8s.io/community/contributors/devel/api-conventions.md#idempotency
Applied only if Name is not specified. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#idempotency
type: string
generation:
description: A sequence number representing a specific generation
of the desired state. Populated by the system. Read-only.
format: int64
type: integer
initializers:
description: Initializers tracks the progress of initialization.
properties:
pending:
description: Pending is a list of initializers that must execute
in order before this object is visible. When the last pending
initializer is removed, and no failing result is set, the
initializers struct will be set to nil and the object is considered
as initialized and visible to all clients.
items:
description: Initializer is information about an initializer
that has not yet completed.
properties:
name:
description: name of the process that is responsible for
initializing this object.
type: string
required:
- name
type: object
type: array
result:
description: Status is a return value for calls that don't return
other objects.
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/api-conventions.md#resources'
type: string
code:
description: Suggested HTTP return code for this status,
0 if not set.
format: int32
type: integer
details:
description: StatusDetails is a set of additional properties
that MAY be set by the server to provide additional information
about a response. The Reason field of a Status object
defines what attributes will be set. Clients must ignore
fields that do not match the defined type of each attribute,
and should assume that any attribute may be empty, invalid,
or under defined.
properties:
causes:
description: The Causes array includes more details
associated with the StatusReason failure. Not all
StatusReasons may provide detailed causes.
items:
description: StatusCause provides more information
about an api.Status failure, including cases when
multiple errors are encountered.
properties:
field:
description: |-
The field of the resource that has caused this error, as named by its JSON serialization. May include dot and postfix notation for nested attributes. Arrays are zero-indexed. Fields may appear more than once in an array of causes due to fields having multiple errors. Optional.
Examples:
"name" - the field "name" on the current resource
"items[0].name" - the field "name" on the first array entry in "items"
type: string
message:
description: A human-readable description of the
cause of the error. This field may be presented
as-is to a reader.
type: string
reason:
description: A machine-readable description of
the cause of the error. If this value is empty
there is no information available.
type: string
type: object
type: array
group:
description: The group attribute of the resource associated
with the status StatusReason.
type: string
kind:
description: 'The kind attribute of the resource associated
with the status StatusReason. On some operations may
differ from the requested resource Kind. More info:
https://git.k8s.io/community/contributors/devel/api-conventions.md#types-kinds'
type: string
name:
description: The name attribute of the resource associated
with the status StatusReason (when there is a single
name which can be described).
type: string
retryAfterSeconds:
description: If specified, the time in seconds before
the operation should be retried. Some errors may indicate
the client must take an alternate action - for those
errors this field may indicate how long to wait before
taking the alternate action.
format: int32
type: integer
uid:
description: 'UID of the resource. (when there is a
single resource which can be described). More info:
http://kubernetes.io/docs/user-guide/identifiers#uids'
type: string
type: object
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/api-conventions.md#types-kinds'
type: string
message:
description: A human-readable description of the status
of this operation.
type: string
metadata:
description: ListMeta describes metadata that synthetic
resources must have, including lists and various status
objects. A resource may have only one of {ObjectMeta,
ListMeta}.
properties:
continue:
description: continue may be set if the user set a limit
on the number of items returned, and indicates that
the server has more data available. The value is opaque
and may be used to issue another request to the endpoint
that served this list to retrieve the next set of
available objects. Continuing a consistent list may
not be possible if the server configuration has changed
or more than a few minutes have passed. The resourceVersion
field returned when using this continue value will
be identical to the value in the first response, unless
you have received this token from an error message.
type: string
remainingItemCount:
description: |-
remainingItemCount is the number of subsequent items in the list which are not included in this list response. If the list request contained label or field selectors, then the number of remaining items is unknown and the field will be left unset and omitted during serialization. If the list is complete (either because it is not chunking or because this is the last chunk), then there are no more remaining items and this field will be left unset and omitted during serialization. Servers older than v1.15 do not set this field. The intended use of the remainingItemCount is *estimating* the size of a collection. Clients should not rely on the remainingItemCount to be set or to be exact.
This field is alpha and can be changed or removed without notice.
format: int64
type: integer
resourceVersion:
description: 'String that identifies the server''s internal
version of this object that can be used by clients
to determine when objects have changed. Value must
be treated as opaque by clients and passed unmodified
back to the server. Populated by the system. Read-only.
More info: https://git.k8s.io/community/contributors/devel/api-conventions.md#concurrency-control-and-consistency'
type: string
selfLink:
description: selfLink is a URL representing this object.
Populated by the system. Read-only.
type: string
type: object
reason:
description: A machine-readable description of why this
operation is in the "Failure" status. If this value is
empty there is no information available. A Reason clarifies
an HTTP status code but does not override it.
type: string
status:
description: 'Status of the operation. One of: "Success"
or "Failure". More info: https://git.k8s.io/community/contributors/devel/api-conventions.md#spec-and-status'
type: string
type: object
required:
- pending
type: object
labels:
description: 'Map of string keys and values that can be used to
organize and categorize (scope and select) objects. May match
@ -2577,10 +2655,13 @@ spec:
http://kubernetes.io/docs/user-guide/labels'
type: object
managedFields:
description: |-
ManagedFields maps workflow-id and version to the set of fields that are managed by that workflow. This is mostly for internal housekeeping, and users typically shouldn't need to set or understand this field. A workflow can be the user's name, a controller's name, or the name of a specific apply path like "ci-cd". The set of fields is always in the version that the workflow used when modifying the object.
This field is alpha and can be changed or removed without notice.
description: ManagedFields maps workflow-id and version to the set
of fields that are managed by that workflow. This is mostly for
internal housekeeping, and users typically shouldn't need to set
or understand this field. A workflow can be the user's name, a
controller's name, or the name of a specific apply path like "ci-cd".
The set of fields is always in the version that the workflow used
when modifying the object.
items:
description: ManagedFieldsEntry is a workflow-id, a FieldSet and
the group version of the resource that the fieldset applies
@ -2593,9 +2674,18 @@ spec:
to track the version of a field set because it cannot be
automatically converted.
type: string
fields:
description: 'Fields stores a set of fields in a data structure
like a Trie. To understand how this is used, see: https://github.com/kubernetes-sigs/structured-merge-diff'
fieldsType:
description: 'FieldsType is the discriminator for the different
fields format and version. There is currently only one possible
value: "FieldsV1"'
type: string
fieldsV1:
description: |-
FieldsV1 stores a set of fields in a data structure like a Trie, in JSON format.
Each key is either a '.' representing the field itself, and will always map to an empty set, or a string representing a sub-field or item. The string will follow one of these four formats: 'f:<name>', where <name> is the name of a field in a struct, or key in a map 'v:<value>', where <value> is the exact json formatted value of a list item 'i:<index>', where <index> is position of a item in a list 'k:<keys>', where <keys> is a map of a list item's key fields to their unique values If a key maps to an empty Fields value, the field that key represents is part of the set.
The exact format is defined in sigs.k8s.io/structured-merge-diff
type: object
manager:
description: Manager is an identifier of the workflow managing
@ -2654,7 +2744,7 @@ spec:
controller.
type: boolean
kind:
description: 'Kind of the referent. More info: https://git.k8s.io/community/contributors/devel/api-conventions.md#types-kinds'
description: 'Kind of the referent. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds'
type: string
name:
description: 'Name of the referent. More info: http://kubernetes.io/docs/user-guide/identifiers#names'
@ -2673,11 +2763,13 @@ spec:
description: |-
An opaque value that represents the internal version of this object that can be used by clients to determine when objects have changed. May be used for optimistic concurrency, change detection, and the watch operation on a resource or set of resources. Clients must treat these values as opaque and passed unmodified back to the server. They may only be valid for a particular resource or set of resources.
Populated by the system. Read-only. Value must be treated as opaque by clients and . More info: https://git.k8s.io/community/contributors/devel/api-conventions.md#concurrency-control-and-consistency
Populated by the system. Read-only. Value must be treated as opaque by clients and . More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#concurrency-control-and-consistency
type: string
selfLink:
description: SelfLink is a URL representing this object. Populated
by the system. Read-only.
description: |-
SelfLink is a URL representing this object. Populated by the system. Read-only.
DEPRECATED Kubernetes will stop propagating this field in 1.20 release and the field is planned to be removed in 1.21 release.
type: string
uid:
description: |-
@ -2835,6 +2927,15 @@ spec:
credential spec to use. This field is alpha-level and is only
honored by servers that enable the WindowsGMSA feature flag.
type: string
runAsUserName:
description: The UserName in Windows to run the entrypoint of
the container process. Defaults to the user specified in image
metadata if unspecified. May also be set in PodSecurityContext.
If set in both SecurityContext and PodSecurityContext, the
value specified in SecurityContext takes precedence. This
field is alpha-level and it is only honored by servers that
enable the WindowsRunAsUserName feature flag.
type: string
type: object
type: object
serviceAccountName:
@ -2872,13 +2973,13 @@ spec:
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/api-conventions.md#resources'
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/api-conventions.md#types-kinds'
More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds'
type: string
metadata:
description: ObjectMeta is metadata that all persisted resources
@ -2934,190 +3035,13 @@ spec:
If this field is specified and the generated name exists, the server will NOT return a 409 - instead, it will either return 201 Created or 500 with Reason ServerTimeout indicating a unique name could not be found in the time allotted, and the client should retry (optionally after the time indicated in the Retry-After header).
Applied only if Name is not specified. More info: https://git.k8s.io/community/contributors/devel/api-conventions.md#idempotency
Applied only if Name is not specified. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#idempotency
type: string
generation:
description: A sequence number representing a specific generation
of the desired state. Populated by the system. Read-only.
format: int64
type: integer
initializers:
description: Initializers tracks the progress of initialization.
properties:
pending:
description: Pending is a list of initializers that
must execute in order before this object is visible.
When the last pending initializer is removed, and
no failing result is set, the initializers struct
will be set to nil and the object is considered as
initialized and visible to all clients.
items:
description: Initializer is information about an initializer
that has not yet completed.
properties:
name:
description: name of the process that is responsible
for initializing this object.
type: string
required:
- name
type: object
type: array
result:
description: Status is a return value for calls that
don't return other objects.
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/api-conventions.md#resources'
type: string
code:
description: Suggested HTTP return code for this
status, 0 if not set.
format: int32
type: integer
details:
description: StatusDetails is a set of additional
properties that MAY be set by the server to provide
additional information about a response. The Reason
field of a Status object defines what attributes
will be set. Clients must ignore fields that do
not match the defined type of each attribute,
and should assume that any attribute may be empty,
invalid, or under defined.
properties:
causes:
description: The Causes array includes more
details associated with the StatusReason failure.
Not all StatusReasons may provide detailed
causes.
items:
description: StatusCause provides more information
about an api.Status failure, including cases
when multiple errors are encountered.
properties:
field:
description: |-
The field of the resource that has caused this error, as named by its JSON serialization. May include dot and postfix notation for nested attributes. Arrays are zero-indexed. Fields may appear more than once in an array of causes due to fields having multiple errors. Optional.
Examples:
"name" - the field "name" on the current resource
"items[0].name" - the field "name" on the first array entry in "items"
type: string
message:
description: A human-readable description
of the cause of the error. This field
may be presented as-is to a reader.
type: string
reason:
description: A machine-readable description
of the cause of the error. If this value
is empty there is no information available.
type: string
type: object
type: array
group:
description: The group attribute of the resource
associated with the status StatusReason.
type: string
kind:
description: 'The kind attribute of the resource
associated with the status StatusReason. On
some operations may differ from the requested
resource Kind. More info: https://git.k8s.io/community/contributors/devel/api-conventions.md#types-kinds'
type: string
name:
description: The name attribute of the resource
associated with the status StatusReason (when
there is a single name which can be described).
type: string
retryAfterSeconds:
description: If specified, the time in seconds
before the operation should be retried. Some
errors may indicate the client must take an
alternate action - for those errors this field
may indicate how long to wait before taking
the alternate action.
format: int32
type: integer
uid:
description: 'UID of the resource. (when there
is a single resource which can be described).
More info: http://kubernetes.io/docs/user-guide/identifiers#uids'
type: string
type: object
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/api-conventions.md#types-kinds'
type: string
message:
description: A human-readable description of the
status of this operation.
type: string
metadata:
description: ListMeta describes metadata that synthetic
resources must have, including lists and various
status objects. A resource may have only one of
{ObjectMeta, ListMeta}.
properties:
continue:
description: continue may be set if the user
set a limit on the number of items returned,
and indicates that the server has more data
available. The value is opaque and may be
used to issue another request to the endpoint
that served this list to retrieve the next
set of available objects. Continuing a consistent
list may not be possible if the server configuration
has changed or more than a few minutes have
passed. The resourceVersion field returned
when using this continue value will be identical
to the value in the first response, unless
you have received this token from an error
message.
type: string
remainingItemCount:
description: |-
remainingItemCount is the number of subsequent items in the list which are not included in this list response. If the list request contained label or field selectors, then the number of remaining items is unknown and the field will be left unset and omitted during serialization. If the list is complete (either because it is not chunking or because this is the last chunk), then there are no more remaining items and this field will be left unset and omitted during serialization. Servers older than v1.15 do not set this field. The intended use of the remainingItemCount is *estimating* the size of a collection. Clients should not rely on the remainingItemCount to be set or to be exact.
This field is alpha and can be changed or removed without notice.
format: int64
type: integer
resourceVersion:
description: 'String that identifies the server''s
internal version of this object that can be
used by clients to determine when objects
have changed. Value must be treated as opaque
by clients and passed unmodified back to the
server. Populated by the system. Read-only.
More info: https://git.k8s.io/community/contributors/devel/api-conventions.md#concurrency-control-and-consistency'
type: string
selfLink:
description: selfLink is a URL representing
this object. Populated by the system. Read-only.
type: string
type: object
reason:
description: A machine-readable description of why
this operation is in the "Failure" status. If
this value is empty there is no information available.
A Reason clarifies an HTTP status code but does
not override it.
type: string
status:
description: 'Status of the operation. One of: "Success"
or "Failure". More info: https://git.k8s.io/community/contributors/devel/api-conventions.md#spec-and-status'
type: string
type: object
required:
- pending
type: object
labels:
description: 'Map of string keys and values that can be
used to organize and categorize (scope and select) objects.
@ -3125,10 +3049,14 @@ spec:
More info: http://kubernetes.io/docs/user-guide/labels'
type: object
managedFields:
description: |-
ManagedFields maps workflow-id and version to the set of fields that are managed by that workflow. This is mostly for internal housekeeping, and users typically shouldn't need to set or understand this field. A workflow can be the user's name, a controller's name, or the name of a specific apply path like "ci-cd". The set of fields is always in the version that the workflow used when modifying the object.
This field is alpha and can be changed or removed without notice.
description: ManagedFields maps workflow-id and version
to the set of fields that are managed by that workflow.
This is mostly for internal housekeeping, and users typically
shouldn't need to set or understand this field. A workflow
can be the user's name, a controller's name, or the name
of a specific apply path like "ci-cd". The set of fields
is always in the version that the workflow used when modifying
the object.
items:
description: ManagedFieldsEntry is a workflow-id, a FieldSet
and the group version of the resource that the fieldset
@ -3141,10 +3069,18 @@ spec:
field. It is necessary to track the version of a
field set because it cannot be automatically converted.
type: string
fields:
description: 'Fields stores a set of fields in a data
structure like a Trie. To understand how this is
used, see: https://github.com/kubernetes-sigs/structured-merge-diff'
fieldsType:
description: 'FieldsType is the discriminator for
the different fields format and version. There is
currently only one possible value: "FieldsV1"'
type: string
fieldsV1:
description: |-
FieldsV1 stores a set of fields in a data structure like a Trie, in JSON format.
Each key is either a '.' representing the field itself, and will always map to an empty set, or a string representing a sub-field or item. The string will follow one of these four formats: 'f:<name>', where <name> is the name of a field in a struct, or key in a map 'v:<value>', where <value> is the exact json formatted value of a list item 'i:<index>', where <index> is position of a item in a list 'k:<keys>', where <keys> is a map of a list item's key fields to their unique values If a key maps to an empty Fields value, the field that key represents is part of the set.
The exact format is defined in sigs.k8s.io/structured-merge-diff
type: object
manager:
description: Manager is an identifier of the workflow
@ -3208,7 +3144,7 @@ spec:
managing controller.
type: boolean
kind:
description: 'Kind of the referent. More info: https://git.k8s.io/community/contributors/devel/api-conventions.md#types-kinds'
description: 'Kind of the referent. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds'
type: string
name:
description: 'Name of the referent. More info: http://kubernetes.io/docs/user-guide/identifiers#names'
@ -3227,11 +3163,13 @@ spec:
description: |-
An opaque value that represents the internal version of this object that can be used by clients to determine when objects have changed. May be used for optimistic concurrency, change detection, and the watch operation on a resource or set of resources. Clients must treat these values as opaque and passed unmodified back to the server. They may only be valid for a particular resource or set of resources.
Populated by the system. Read-only. Value must be treated as opaque by clients and . More info: https://git.k8s.io/community/contributors/devel/api-conventions.md#concurrency-control-and-consistency
Populated by the system. Read-only. Value must be treated as opaque by clients and . More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#concurrency-control-and-consistency
type: string
selfLink:
description: SelfLink is a URL representing this object.
Populated by the system. Read-only.
description: |-
SelfLink is a URL representing this object. Populated by the system. Read-only.
DEPRECATED Kubernetes will stop propagating this field in 1.20 release and the field is planned to be removed in 1.21 release.
type: string
uid:
description: |-
@ -3597,7 +3535,7 @@ spec:
properties:
monitors:
description: 'Required: Monitors is a collection of Ceph monitors
More info: https://releases.k8s.io/HEAD/examples/volumes/cephfs/README.md#how-to-use-it'
More info: https://examples.k8s.io/volumes/cephfs/README.md#how-to-use-it'
items:
type: string
type: array
@ -3608,11 +3546,11 @@ spec:
readOnly:
description: 'Optional: Defaults to false (read/write). ReadOnly
here will force the ReadOnly setting in VolumeMounts. More
info: https://releases.k8s.io/HEAD/examples/volumes/cephfs/README.md#how-to-use-it'
info: https://examples.k8s.io/volumes/cephfs/README.md#how-to-use-it'
type: boolean
secretFile:
description: 'Optional: SecretFile is the path to key ring
for User, default is /etc/ceph/user.secret More info: https://releases.k8s.io/HEAD/examples/volumes/cephfs/README.md#how-to-use-it'
for User, default is /etc/ceph/user.secret More info: https://examples.k8s.io/volumes/cephfs/README.md#how-to-use-it'
type: string
secretRef:
description: LocalObjectReference contains enough information
@ -3625,7 +3563,7 @@ spec:
type: object
user:
description: 'Optional: User is the rados user name, default
is admin More info: https://releases.k8s.io/HEAD/examples/volumes/cephfs/README.md#how-to-use-it'
is admin More info: https://examples.k8s.io/volumes/cephfs/README.md#how-to-use-it'
type: string
required:
- monitors
@ -3640,12 +3578,12 @@ spec:
description: 'Filesystem type to mount. Must be a filesystem
type supported by the host operating system. Examples: "ext4",
"xfs", "ntfs". Implicitly inferred to be "ext4" if unspecified.
More info: https://releases.k8s.io/HEAD/examples/mysql-cinder-pd/README.md'
More info: https://examples.k8s.io/mysql-cinder-pd/README.md'
type: string
readOnly:
description: 'Optional: Defaults to false (read/write). ReadOnly
here will force the ReadOnly setting in VolumeMounts. More
info: https://releases.k8s.io/HEAD/examples/mysql-cinder-pd/README.md'
info: https://examples.k8s.io/mysql-cinder-pd/README.md'
type: boolean
secretRef:
description: LocalObjectReference contains enough information
@ -3657,8 +3595,8 @@ spec:
type: string
type: object
volumeID:
description: 'volume id used to identify the volume in cinder
More info: https://releases.k8s.io/HEAD/examples/mysql-cinder-pd/README.md'
description: 'volume id used to identify the volume in cinder.
More info: https://examples.k8s.io/mysql-cinder-pd/README.md'
type: string
required:
- volumeID
@ -3981,16 +3919,16 @@ spec:
properties:
endpoints:
description: 'EndpointsName is the endpoint name that details
Glusterfs topology. More info: https://releases.k8s.io/HEAD/examples/volumes/glusterfs/README.md#create-a-pod'
Glusterfs topology. More info: https://examples.k8s.io/volumes/glusterfs/README.md#create-a-pod'
type: string
path:
description: 'Path is the Glusterfs volume path. More info:
https://releases.k8s.io/HEAD/examples/volumes/glusterfs/README.md#create-a-pod'
https://examples.k8s.io/volumes/glusterfs/README.md#create-a-pod'
type: string
readOnly:
description: 'ReadOnly here will force the Glusterfs volume
to be mounted with read-only permissions. Defaults to false.
More info: https://releases.k8s.io/HEAD/examples/volumes/glusterfs/README.md#create-a-pod'
More info: https://examples.k8s.io/volumes/glusterfs/README.md#create-a-pod'
type: boolean
required:
- endpoints
@ -4437,24 +4375,24 @@ spec:
https://kubernetes.io/docs/concepts/storage/volumes#rbd'
type: string
image:
description: 'The rados image name. More info: https://releases.k8s.io/HEAD/examples/volumes/rbd/README.md#how-to-use-it'
description: 'The rados image name. More info: https://examples.k8s.io/volumes/rbd/README.md#how-to-use-it'
type: string
keyring:
description: 'Keyring is the path to key ring for RBDUser.
Default is /etc/ceph/keyring. More info: https://releases.k8s.io/HEAD/examples/volumes/rbd/README.md#how-to-use-it'
Default is /etc/ceph/keyring. More info: https://examples.k8s.io/volumes/rbd/README.md#how-to-use-it'
type: string
monitors:
description: 'A collection of Ceph monitors. More info: https://releases.k8s.io/HEAD/examples/volumes/rbd/README.md#how-to-use-it'
description: 'A collection of Ceph monitors. More info: https://examples.k8s.io/volumes/rbd/README.md#how-to-use-it'
items:
type: string
type: array
pool:
description: 'The rados pool name. Default is rbd. More info:
https://releases.k8s.io/HEAD/examples/volumes/rbd/README.md#how-to-use-it'
https://examples.k8s.io/volumes/rbd/README.md#how-to-use-it'
type: string
readOnly:
description: 'ReadOnly here will force the ReadOnly setting
in VolumeMounts. Defaults to false. More info: https://releases.k8s.io/HEAD/examples/volumes/rbd/README.md#how-to-use-it'
in VolumeMounts. Defaults to false. More info: https://examples.k8s.io/volumes/rbd/README.md#how-to-use-it'
type: boolean
secretRef:
description: LocalObjectReference contains enough information
@ -4467,7 +4405,7 @@ spec:
type: object
user:
description: 'The rados user name. Default is admin. More
info: https://releases.k8s.io/HEAD/examples/volumes/rbd/README.md#how-to-use-it'
info: https://examples.k8s.io/volumes/rbd/README.md#how-to-use-it'
type: string
required:
- monitors
@ -4654,7 +4592,7 @@ spec:
status:
description: 'AlertmanagerStatus is the most recent observed status of the
Alertmanager cluster. Read-only. Not included when requesting from the
apiserver, only from the Prometheus Operator API itself. More info: https://github.com/kubernetes/community/blob/master/contributors/devel/api-conventions.md#spec-and-status'
apiserver, only from the Prometheus Operator API itself. More info: https://github.com/kubernetes/community/blob/master/contributors/devel/sig-architecture/api-conventions.md#spec-and-status'
properties:
availableReplicas:
description: Total number of available pods (ready for at least minReadySeconds)

8
manifests/0prometheus-operator-0podmonitorCustomResourceDefinition.yaml
View File

@ -15,12 +15,12 @@ spec:
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/api-conventions.md#resources'
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/api-conventions.md#types-kinds'
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
spec:
description: PodMonitorSpec contains specification parameters for a PodMonitor.
@ -52,6 +52,10 @@ spec:
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.
type: boolean
interval:
description: Interval at which metrics should be scraped
type: string

857
manifests/0prometheus-operator-0prometheusCustomResourceDefinition.yaml
View File

File diff suppressed because it is too large Load Diff

205
manifests/0prometheus-operator-0prometheusruleCustomResourceDefinition.yaml
View File

@ -15,12 +15,12 @@ spec:
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/api-conventions.md#resources'
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/api-conventions.md#types-kinds'
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:
description: ObjectMeta is metadata that all persisted resources must have,
@ -70,186 +70,26 @@ spec:
If this field is specified and the generated name exists, the server will NOT return a 409 - instead, it will either return 201 Created or 500 with Reason ServerTimeout indicating a unique name could not be found in the time allotted, and the client should retry (optionally after the time indicated in the Retry-After header).
Applied only if Name is not specified. More info: https://git.k8s.io/community/contributors/devel/api-conventions.md#idempotency
Applied only if Name is not specified. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#idempotency
type: string
generation:
description: A sequence number representing a specific generation of
the desired state. Populated by the system. Read-only.
format: int64
type: integer
initializers:
description: Initializers tracks the progress of initialization.
properties:
pending:
description: Pending is a list of initializers that must execute
in order before this object is visible. When the last pending
initializer is removed, and no failing result is set, the initializers
struct will be set to nil and the object is considered as initialized
and visible to all clients.
items:
description: Initializer is information about an initializer that
has not yet completed.
properties:
name:
description: name of the process that is responsible for initializing
this object.
type: string
required:
- name
type: object
type: array
result:
description: Status is a return value for calls that don't return
other objects.
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/api-conventions.md#resources'
type: string
code:
description: Suggested HTTP return code for this status, 0 if
not set.
format: int32
type: integer
details:
description: StatusDetails is a set of additional properties
that MAY be set by the server to provide additional information
about a response. The Reason field of a Status object defines
what attributes will be set. Clients must ignore fields that
do not match the defined type of each attribute, and should
assume that any attribute may be empty, invalid, or under
defined.
properties:
causes:
description: The Causes array includes more details associated
with the StatusReason failure. Not all StatusReasons may
provide detailed causes.
items:
description: StatusCause provides more information about
an api.Status failure, including cases when multiple
errors are encountered.
properties:
field:
description: |-
The field of the resource that has caused this error, as named by its JSON serialization. May include dot and postfix notation for nested attributes. Arrays are zero-indexed. Fields may appear more than once in an array of causes due to fields having multiple errors. Optional.
Examples:
"name" - the field "name" on the current resource
"items[0].name" - the field "name" on the first array entry in "items"
type: string
message:
description: A human-readable description of the cause
of the error. This field may be presented as-is
to a reader.
type: string
reason:
description: A machine-readable description of the
cause of the error. If this value is empty there
is no information available.
type: string
type: object
type: array
group:
description: The group attribute of the resource associated
with the status StatusReason.
type: string
kind:
description: 'The kind attribute of the resource associated
with the status StatusReason. On some operations may differ
from the requested resource Kind. More info: https://git.k8s.io/community/contributors/devel/api-conventions.md#types-kinds'
type: string
name:
description: The name attribute of the resource associated
with the status StatusReason (when there is a single name
which can be described).
type: string
retryAfterSeconds:
description: If specified, the time in seconds before the
operation should be retried. Some errors may indicate
the client must take an alternate action - for those errors
this field may indicate how long to wait before taking
the alternate action.
format: int32
type: integer
uid:
description: 'UID of the resource. (when there is a single
resource which can be described). More info: http://kubernetes.io/docs/user-guide/identifiers#uids'
type: string
type: object
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/api-conventions.md#types-kinds'
type: string
message:
description: A human-readable description of the status of this
operation.
type: string
metadata:
description: ListMeta describes metadata that synthetic resources
must have, including lists and various status objects. A resource
may have only one of {ObjectMeta, ListMeta}.
properties:
continue:
description: continue may be set if the user set a limit
on the number of items returned, and indicates that the
server has more data available. The value is opaque and
may be used to issue another request to the endpoint that
served this list to retrieve the next set of available
objects. Continuing a consistent list may not be possible
if the server configuration has changed or more than a
few minutes have passed. The resourceVersion field returned
when using this continue value will be identical to the
value in the first response, unless you have received
this token from an error message.
type: string
remainingItemCount:
description: |-
remainingItemCount is the number of subsequent items in the list which are not included in this list response. If the list request contained label or field selectors, then the number of remaining items is unknown and the field will be left unset and omitted during serialization. If the list is complete (either because it is not chunking or because this is the last chunk), then there are no more remaining items and this field will be left unset and omitted during serialization. Servers older than v1.15 do not set this field. The intended use of the remainingItemCount is *estimating* the size of a collection. Clients should not rely on the remainingItemCount to be set or to be exact.
This field is alpha and can be changed or removed without notice.
format: int64
type: integer
resourceVersion:
description: 'String that identifies the server''s internal
version of this object that can be used by clients to
determine when objects have changed. Value must be treated
as opaque by clients and passed unmodified back to the
server. Populated by the system. Read-only. More info:
https://git.k8s.io/community/contributors/devel/api-conventions.md#concurrency-control-and-consistency'
type: string
selfLink:
description: selfLink is a URL representing this object.
Populated by the system. Read-only.
type: string
type: object
reason:
description: A machine-readable description of why this operation
is in the "Failure" status. If this value is empty there is
no information available. A Reason clarifies an HTTP status
code but does not override it.
type: string
status:
description: 'Status of the operation. One of: "Success" or
"Failure". More info: https://git.k8s.io/community/contributors/devel/api-conventions.md#spec-and-status'
type: string
type: object
required:
- pending
type: object
labels:
description: 'Map of string keys and values that can be used to organize
and categorize (scope and select) objects. May match selectors of
replication controllers and services. More info: http://kubernetes.io/docs/user-guide/labels'
type: object
managedFields:
description: |-
ManagedFields maps workflow-id and version to the set of fields that are managed by that workflow. This is mostly for internal housekeeping, and users typically shouldn't need to set or understand this field. A workflow can be the user's name, a controller's name, or the name of a specific apply path like "ci-cd". The set of fields is always in the version that the workflow used when modifying the object.
This field is alpha and can be changed or removed without notice.
description: ManagedFields maps workflow-id and version to the set of
fields that are managed by that workflow. This is mostly for internal
housekeeping, and users typically shouldn't need to set or understand
this field. A workflow can be the user's name, a controller's name,
or the name of a specific apply path like "ci-cd". The set of fields
is always in the version that the workflow used when modifying the
object.
items:
description: ManagedFieldsEntry is a workflow-id, a FieldSet and the
group version of the resource that the fieldset applies to.
@ -261,9 +101,18 @@ spec:
the version of a field set because it cannot be automatically
converted.
type: string
fields:
description: 'Fields stores a set of fields in a data structure
like a Trie. To understand how this is used, see: https://github.com/kubernetes-sigs/structured-merge-diff'
fieldsType:
description: 'FieldsType is the discriminator for the different
fields format and version. There is currently only one possible
value: "FieldsV1"'
type: string
fieldsV1:
description: |-
FieldsV1 stores a set of fields in a data structure like a Trie, in JSON format.
Each key is either a '.' representing the field itself, and will always map to an empty set, or a string representing a sub-field or item. The string will follow one of these four formats: 'f:<name>', where <name> is the name of a field in a struct, or key in a map 'v:<value>', where <value> is the exact json formatted value of a list item 'i:<index>', where <index> is position of a item in a list 'k:<keys>', where <keys> is a map of a list item's key fields to their unique values If a key maps to an empty Fields value, the field that key represents is part of the set.
The exact format is defined in sigs.k8s.io/structured-merge-diff
type: object
manager:
description: Manager is an identifier of the workflow managing
@ -321,7 +170,7 @@ spec:
description: If true, this reference points to the managing controller.
type: boolean
kind:
description: 'Kind of the referent. More info: https://git.k8s.io/community/contributors/devel/api-conventions.md#types-kinds'
description: 'Kind of the referent. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds'
type: string
name:
description: 'Name of the referent. More info: http://kubernetes.io/docs/user-guide/identifiers#names'
@ -340,11 +189,13 @@ spec:
description: |-
An opaque value that represents the internal version of this object that can be used by clients to determine when objects have changed. May be used for optimistic concurrency, change detection, and the watch operation on a resource or set of resources. Clients must treat these values as opaque and passed unmodified back to the server. They may only be valid for a particular resource or set of resources.
Populated by the system. Read-only. Value must be treated as opaque by clients and . More info: https://git.k8s.io/community/contributors/devel/api-conventions.md#concurrency-control-and-consistency
Populated by the system. Read-only. Value must be treated as opaque by clients and . More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#concurrency-control-and-consistency
type: string
selfLink:
description: SelfLink is a URL representing this object. Populated by
the system. Read-only.
description: |-
SelfLink is a URL representing this object. Populated by the system. Read-only.
DEPRECATED Kubernetes will stop propagating this field in 1.20 release and the field is planned to be removed in 1.21 release.
type: string
uid:
description: |-

53
manifests/0prometheus-operator-0servicemonitorCustomResourceDefinition.yaml
View File

@ -15,12 +15,12 @@ spec:
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/api-conventions.md#resources'
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/api-conventions.md#types-kinds'
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
spec:
description: ServiceMonitorSpec contains specification parameters for a
@ -74,10 +74,31 @@ spec:
bearerTokenFile:
description: File to read bearer token for scraping targets.
type: string
bearerTokenSecret:
description: SecretKeySelector selects a key of a Secret.
properties:
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'
type: string
optional:
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.
type: boolean
honorTimestamps:
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
@ -199,18 +220,40 @@ spec:
tlsConfig:
description: TLSConfig specifies TLS configuration parameters.
properties:
ca: {}
caFile:
description: The CA cert to use for the targets.
description: Path to the CA cert in the Prometheus container
to use for the targets.
type: string
cert: {}
certFile:
description: The client cert file 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: The client key file for the targets.
description: Path to the client key file in the Prometheus
container for the targets.
type: string
keySecret:
description: SecretKeySelector selects a key of a Secret.
properties:
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'
type: string
optional:
description: Specify whether the Secret or its key must
be defined
type: boolean
required:
- key
type: object
serverName:
description: Used to verify the hostname for the targets.
type: string

13179
manifests/grafana-dashboardDefinitions.yaml
View File

File diff suppressed because it is too large Load Diff

36
manifests/grafana-deployment.yaml
View File

@ -45,6 +45,9 @@ spec:
- mountPath: /grafana-dashboard-definitions/0/apiserver
name: grafana-dashboard-apiserver
readOnly: false
- mountPath: /grafana-dashboard-definitions/0/cluster-total
name: grafana-dashboard-cluster-total
readOnly: false
- mountPath: /grafana-dashboard-definitions/0/controller-manager
name: grafana-dashboard-controller-manager
readOnly: false
@ -57,6 +60,9 @@ spec:
- mountPath: /grafana-dashboard-definitions/0/k8s-resources-namespace
name: grafana-dashboard-k8s-resources-namespace
readOnly: false
- mountPath: /grafana-dashboard-definitions/0/k8s-resources-node
name: grafana-dashboard-k8s-resources-node
readOnly: false
- mountPath: /grafana-dashboard-definitions/0/k8s-resources-pod
name: grafana-dashboard-k8s-resources-pod
readOnly: false
@ -72,6 +78,12 @@ spec:
- mountPath: /grafana-dashboard-definitions/0/kubernetes-cluster-dashboard
name: grafana-dashboard-kubernetes-cluster-dashboard
readOnly: false
- mountPath: /grafana-dashboard-definitions/0/namespace-by-pod
name: grafana-dashboard-namespace-by-pod
readOnly: false
- mountPath: /grafana-dashboard-definitions/0/namespace-by-workload
name: grafana-dashboard-namespace-by-workload
readOnly: false
- mountPath: /grafana-dashboard-definitions/0/node-cluster-rsrc-use
name: grafana-dashboard-node-cluster-rsrc-use
readOnly: false
@ -84,6 +96,9 @@ spec:
- mountPath: /grafana-dashboard-definitions/0/persistentvolumesusage
name: grafana-dashboard-persistentvolumesusage
readOnly: false
- mountPath: /grafana-dashboard-definitions/0/pod-total
name: grafana-dashboard-pod-total
readOnly: false
- mountPath: /grafana-dashboard-definitions/0/pods
name: grafana-dashboard-pods
readOnly: false
@ -105,6 +120,9 @@ spec:
- mountPath: /grafana-dashboard-definitions/0/statefulset
name: grafana-dashboard-statefulset
readOnly: false
- mountPath: /grafana-dashboard-definitions/0/workload-total
name: grafana-dashboard-workload-total
readOnly: false
- mountPath: /etc/grafana
name: grafana-config
readOnly: false
@ -126,6 +144,9 @@ spec:
- configMap:
name: grafana-dashboard-apiserver
name: grafana-dashboard-apiserver
- configMap:
name: grafana-dashboard-cluster-total
name: grafana-dashboard-cluster-total
- configMap:
name: grafana-dashboard-controller-manager
name: grafana-dashboard-controller-manager
@ -138,6 +159,9 @@ spec:
- configMap:
name: grafana-dashboard-k8s-resources-namespace
name: grafana-dashboard-k8s-resources-namespace
- configMap:
name: grafana-dashboard-k8s-resources-node
name: grafana-dashboard-k8s-resources-node
- configMap:
name: grafana-dashboard-k8s-resources-pod
name: grafana-dashboard-k8s-resources-pod
@ -153,6 +177,12 @@ spec:
- configMap:
name: grafana-dashboard-kubernetes-cluster-dashboard
name: grafana-dashboard-kubernetes-cluster-dashboard
- configMap:
name: grafana-dashboard-namespace-by-pod
name: grafana-dashboard-namespace-by-pod
- configMap:
name: grafana-dashboard-namespace-by-workload
name: grafana-dashboard-namespace-by-workload
- configMap:
name: grafana-dashboard-node-cluster-rsrc-use
name: grafana-dashboard-node-cluster-rsrc-use
@ -165,6 +195,9 @@ spec:
- configMap:
name: grafana-dashboard-persistentvolumesusage
name: grafana-dashboard-persistentvolumesusage
- configMap:
name: grafana-dashboard-pod-total
name: grafana-dashboard-pod-total
- configMap:
name: grafana-dashboard-pods
name: grafana-dashboard-pods
@ -186,6 +219,9 @@ spec:
- configMap:
name: grafana-dashboard-statefulset
name: grafana-dashboard-statefulset
- configMap:
name: grafana-dashboard-workload-total
name: grafana-dashboard-workload-total
- name: grafana-config
secret:
secretName: grafana-config

2
manifests/node-exporter-daemonset.yaml
View File

@ -61,7 +61,7 @@ spec:
resources:
limits:
cpu: 20m
memory: 60Mi
memory: 40Mi
requests:
cpu: 10m
memory: 20Mi

296
manifests/prometheus-rules.yaml
View File

@ -37,12 +37,8 @@ spec:
)
record: instance:node_memory_utilisation:ratio
- expr: |
(
rate(node_vmstat_pgpgin{job="node-exporter"}[1m])
+
rate(node_vmstat_pgpgout{job="node-exporter"}[1m])
)
record: instance:node_memory_swap_io_pages:rate1m
rate(node_vmstat_pgmajfault{job="node-exporter"}[1m])
record: instance:node_vmstat_pgmajfault:rate1m
- expr: |
rate(node_disk_io_time_seconds_total{job="node-exporter", device=~"nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+"}[1m])
record: instance_device:node_disk_io_time_seconds:rate1m
@ -69,6 +65,23 @@ spec:
rate(node_network_transmit_drop_total{job="node-exporter", device!="lo"}[1m])
)
record: instance:node_network_transmit_drop_excluding_lo:rate1m
- name: kube-apiserver.rules
rules:
- expr: |
histogram_quantile(0.99, sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver"}[5m])) without(instance, pod))
labels:
quantile: "0.99"
record: cluster_quantile:apiserver_request_duration_seconds:histogram_quantile
- expr: |
histogram_quantile(0.9, sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver"}[5m])) without(instance, pod))
labels:
quantile: "0.9"
record: cluster_quantile:apiserver_request_duration_seconds:histogram_quantile
- expr: |
histogram_quantile(0.5, sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver"}[5m])) without(instance, pod))
labels:
quantile: "0.5"
record: cluster_quantile:apiserver_request_duration_seconds:histogram_quantile
- name: k8s.rules
rules:
- expr: |
@ -77,21 +90,37 @@ spec:
- expr: |
sum by (namespace, pod, container) (
rate(container_cpu_usage_seconds_total{job="kubelet", image!="", container!="POD"}[5m])
)
record: namespace_pod_container:container_cpu_usage_seconds_total:sum_rate
) * on (namespace, pod) group_left(node) max by(namespace, pod, node) (kube_pod_info)
record: node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate
- expr: |
container_memory_working_set_bytes{job="kubelet", image!=""}
* on (namespace, pod) group_left(node) max by(namespace, pod, node) (kube_pod_info)
record: node_namespace_pod_container:container_memory_working_set_bytes
- expr: |
container_memory_rss{job="kubelet", image!=""}
* on (namespace, pod) group_left(node) max by(namespace, pod, node) (kube_pod_info)
record: node_namespace_pod_container:container_memory_rss
- expr: |
container_memory_cache{job="kubelet", image!=""}
* on (namespace, pod) group_left(node) max by(namespace, pod, node) (kube_pod_info)
record: node_namespace_pod_container:container_memory_cache
- expr: |
container_memory_swap{job="kubelet", image!=""}
* on (namespace, pod) group_left(node) max by(namespace, pod, node) (kube_pod_info)
record: node_namespace_pod_container:container_memory_swap
- expr: |
sum(container_memory_usage_bytes{job="kubelet", image!="", container!="POD"}) by (namespace)
record: namespace:container_memory_usage_bytes:sum
- expr: |
sum by (namespace, label_name) (
sum(kube_pod_container_resource_requests_memory_bytes{job="kube-state-metrics"} * on (endpoint, instance, job, namespace, pod, service) group_left(phase) (kube_pod_status_phase{phase=~"^(Pending|Running)$"} == 1)) by (namespace, pod)
sum(kube_pod_container_resource_requests_memory_bytes{job="kube-state-metrics"} * on (endpoint, instance, job, namespace, pod, service) group_left(phase) (kube_pod_status_phase{phase=~"Pending|Running"} == 1)) by (namespace, pod)
* on (namespace, pod)
group_left(label_name) kube_pod_labels{job="kube-state-metrics"}
)
record: namespace:kube_pod_container_resource_requests_memory_bytes:sum
- expr: |
sum by (namespace, label_name) (
sum(kube_pod_container_resource_requests_cpu_cores{job="kube-state-metrics"} * on (endpoint, instance, job, namespace, pod, service) group_left(phase) (kube_pod_status_phase{phase=~"^(Pending|Running)$"} == 1)) by (namespace, pod)
sum(kube_pod_container_resource_requests_cpu_cores{job="kube-state-metrics"} * on (endpoint, instance, job, namespace, pod, service) group_left(phase) (kube_pod_status_phase{phase=~"Pending|Running"} == 1)) by (namespace, pod)
* on (namespace, pod)
group_left(label_name) kube_pod_labels{job="kube-state-metrics"}
)
@ -176,23 +205,6 @@ spec:
labels:
quantile: "0.5"
record: cluster_quantile:scheduler_binding_duration_seconds:histogram_quantile
- name: kube-apiserver.rules
rules:
- expr: |
histogram_quantile(0.99, sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver"}[5m])) without(instance, pod))
labels:
quantile: "0.99"
record: cluster_quantile:apiserver_request_duration_seconds:histogram_quantile
- expr: |
histogram_quantile(0.9, sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver"}[5m])) without(instance, pod))
labels:
quantile: "0.9"
record: cluster_quantile:apiserver_request_duration_seconds:histogram_quantile
- expr: |
histogram_quantile(0.5, sum(rate(apiserver_request_duration_seconds_bucket{job="apiserver"}[5m])) without(instance, pod))
labels:
quantile: "0.5"
record: cluster_quantile:apiserver_request_duration_seconds:histogram_quantile
- name: node.rules
rules:
- expr: sum(min(kube_pod_info) by (node))
@ -208,8 +220,16 @@ spec:
))
record: node:node_num_cpu:sum
- expr: |
sum(node_memory_MemFree_bytes{job="node-exporter"} + node_memory_Cached_bytes{job="node-exporter"} + node_memory_Buffers_bytes{job="node-exporter"})
record: :node_memory_MemFreeCachedBuffers_bytes:sum
sum(
node_memory_MemAvailable_bytes{job="node-exporter"} or
(
node_memory_Buffers_bytes{job="node-exporter"} +
node_memory_Cached_bytes{job="node-exporter"} +
node_memory_MemFree_bytes{job="node-exporter"} +
node_memory_Slab_bytes{job="node-exporter"}
)
)
record: :node_memory_MemAvailable_bytes:sum
- name: kube-prometheus-node-recording.rules
rules:
- expr: sum(rate(node_cpu_seconds_total{mode!="idle",mode!="iowait"}[3m])) BY
@ -387,98 +407,6 @@ spec:
for: 1h
labels:
severity: warning
- name: kubernetes-absent
rules:
- alert: AlertmanagerDown
annotations:
message: Alertmanager has disappeared from Prometheus target discovery.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-alertmanagerdown
expr: |
absent(up{job="alertmanager-main",namespace="monitoring"} == 1)
for: 15m
labels:
severity: critical
- alert: CoreDNSDown
annotations:
message: CoreDNS has disappeared from Prometheus target discovery.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-corednsdown
expr: |
absent(up{job="kube-dns"} == 1)
for: 15m
labels:
severity: critical
- alert: KubeAPIDown
annotations:
message: KubeAPI has disappeared from Prometheus target discovery.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapidown
expr: |
absent(up{job="apiserver"} == 1)
for: 15m
labels:
severity: critical
- alert: KubeControllerManagerDown
annotations:
message: KubeControllerManager has disappeared from Prometheus target discovery.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecontrollermanagerdown
expr: |
absent(up{job="kube-controller-manager"} == 1)
for: 15m
labels:
severity: critical
- alert: KubeSchedulerDown
annotations:
message: KubeScheduler has disappeared from Prometheus target discovery.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeschedulerdown
expr: |
absent(up{job="kube-scheduler"} == 1)
for: 15m
labels:
severity: critical
- alert: KubeStateMetricsDown
annotations:
message: KubeStateMetrics has disappeared from Prometheus target discovery.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubestatemetricsdown
expr: |
absent(up{job="kube-state-metrics"} == 1)
for: 15m
labels:
severity: critical
- alert: KubeletDown
annotations:
message: Kubelet has disappeared from Prometheus target discovery.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletdown
expr: |
absent(up{job="kubelet"} == 1)
for: 15m
labels:
severity: critical
- alert: NodeExporterDown
annotations:
message: NodeExporter has disappeared from Prometheus target discovery.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-nodeexporterdown
expr: |
absent(up{job="node-exporter"} == 1)
for: 15m
labels:
severity: critical
- alert: PrometheusDown
annotations:
message: Prometheus has disappeared from Prometheus target discovery.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-prometheusdown
expr: |
absent(up{job="prometheus-k8s",namespace="monitoring"} == 1)
for: 15m
labels:
severity: critical
- alert: PrometheusOperatorDown
annotations:
message: PrometheusOperator has disappeared from Prometheus target discovery.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-prometheusoperatordown
expr: |
absent(up{job="prometheus-operator",namespace="monitoring"} == 1)
for: 15m
labels:
severity: critical
- name: kubernetes-apps
rules:
- alert: KubePodCrashLooping
@ -497,7 +425,7 @@ spec:
state for longer than 15 minutes.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubepodnotready
expr: |
sum by (namespace, pod) (kube_pod_status_phase{job="kube-state-metrics", phase=~"Failed|Pending|Unknown"} * on(namespace, pod) group_left(owner_kind) kube_pod_owner{owner_kind!="Job"}) > 0
sum by (namespace, pod) (max by(namespace, pod) (kube_pod_status_phase{job="kube-state-metrics", phase=~"Failed|Pending|Unknown"}) * on(namespace, pod) group_left(owner_kind) max by(namespace, pod, owner_kind) (kube_pod_owner{owner_kind!="Job"})) > 0
for: 15m
labels:
severity: critical
@ -583,6 +511,16 @@ spec:
for: 15m
labels:
severity: critical
- alert: KubeContainerWaiting
annotations:
message: 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
expr: |
sum by (namespace, pod, container) (kube_pod_container_status_waiting_reason{job="kube-state-metrics"}) > 0
for: 1h
labels:
severity: warning
- alert: KubeDaemonSetNotScheduled
annotations:
message: '{{ $value }} Pods of DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset
@ -773,7 +711,7 @@ spec:
) < 0.15
and
predict_linear(kubelet_volume_stats_available_bytes{job="kubelet"}[6h], 4 * 24 * 3600) < 0
for: 5m
for: 1h
labels:
severity: critical
- alert: KubePersistentVolumeErrors
@ -788,15 +726,6 @@ spec:
severity: critical
- name: kubernetes-system
rules:
- alert: KubeNodeNotReady
annotations:
message: '{{ $labels.node }} has been unready for more than 15 minutes.'
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubenodenotready
expr: |
kube_node_status_condition{job="kube-state-metrics",condition="Ready",status="true"} == 0
for: 15m
labels:
severity: warning
- alert: KubeVersionMismatch
annotations:
message: There are {{ $value }} different semantic versions of Kubernetes
@ -820,23 +749,15 @@ spec:
for: 15m
labels:
severity: warning
- alert: KubeletTooManyPods
annotations:
message: 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
expr: |
max(max(kubelet_running_pod_count{job="kubelet"}) by(instance) * on(instance) group_left(node) kubelet_node_name{job="kubelet"}) by(node) / max(kube_node_status_capacity_pods{job="kube-state-metrics"}) by(node) > 0.95
for: 15m
labels:
severity: warning
- name: kubernetes-system-apiserver
rules:
- alert: KubeAPILatencyHigh
annotations:
message: The API server has a 99th percentile latency of {{ $value }} seconds
for {{ $labels.verb }} {{ $labels.resource }}.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapilatencyhigh
expr: |
cluster_quantile:apiserver_request_duration_seconds:histogram_quantile{job="apiserver",quantile="0.99",subresource!="log",verb!~"^(?:LIST|WATCH|WATCHLIST|PROXY|CONNECT)$"} > 1
cluster_quantile:apiserver_request_duration_seconds:histogram_quantile{job="apiserver",quantile="0.99",subresource!="log",verb!~"LIST|WATCH|WATCHLIST|PROXY|CONNECT"} > 1
for: 10m
labels:
severity: warning
@ -846,7 +767,7 @@ spec:
for {{ $labels.verb }} {{ $labels.resource }}.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapilatencyhigh
expr: |
cluster_quantile:apiserver_request_duration_seconds:histogram_quantile{job="apiserver",quantile="0.99",subresource!="log",verb!~"^(?:LIST|WATCH|WATCHLIST|PROXY|CONNECT)$"} > 4
cluster_quantile:apiserver_request_duration_seconds:histogram_quantile{job="apiserver",quantile="0.99",subresource!="log",verb!~"LIST|WATCH|WATCHLIST|PROXY|CONNECT"} > 4
for: 10m
labels:
severity: critical
@ -856,7 +777,7 @@ spec:
}} of requests.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapierrorshigh
expr: |
sum(rate(apiserver_request_total{job="apiserver",code=~"^(?:5..)$"}[5m]))
sum(rate(apiserver_request_total{job="apiserver",code=~"5.."}[5m]))
/
sum(rate(apiserver_request_total{job="apiserver"}[5m])) > 0.03
for: 10m
@ -868,7 +789,7 @@ spec:
}} of requests.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapierrorshigh
expr: |
sum(rate(apiserver_request_total{job="apiserver",code=~"^(?:5..)$"}[5m]))
sum(rate(apiserver_request_total{job="apiserver",code=~"5.."}[5m]))
/
sum(rate(apiserver_request_total{job="apiserver"}[5m])) > 0.01
for: 10m
@ -881,7 +802,7 @@ spec:
}}.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapierrorshigh
expr: |
sum(rate(apiserver_request_total{job="apiserver",code=~"^(?:5..)$"}[5m])) by (resource,subresource,verb)
sum(rate(apiserver_request_total{job="apiserver",code=~"5.."}[5m])) by (resource,subresource,verb)
/
sum(rate(apiserver_request_total{job="apiserver"}[5m])) by (resource,subresource,verb) > 0.10
for: 10m
@ -894,7 +815,7 @@ spec:
}}.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapierrorshigh
expr: |
sum(rate(apiserver_request_total{job="apiserver",code=~"^(?:5..)$"}[5m])) by (resource,subresource,verb)
sum(rate(apiserver_request_total{job="apiserver",code=~"5.."}[5m])) by (resource,subresource,verb)
/
sum(rate(apiserver_request_total{job="apiserver"}[5m])) by (resource,subresource,verb) > 0.05
for: 10m
@ -918,6 +839,75 @@ spec:
apiserver_client_certificate_expiration_seconds_count{job="apiserver"} > 0 and histogram_quantile(0.01, sum by (job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job="apiserver"}[5m]))) < 86400
labels:
severity: critical
- alert: KubeAPIDown
annotations:
message: KubeAPI has disappeared from Prometheus target discovery.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapidown
expr: |
absent(up{job="apiserver"} == 1)
for: 15m
labels:
severity: critical
- name: kubernetes-system-kubelet
rules:
- alert: KubeNodeNotReady
annotations:
message: '{{ $labels.node }} has been unready for more than 15 minutes.'
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubenodenotready
expr: |
kube_node_status_condition{job="kube-state-metrics",condition="Ready",status="true"} == 0
for: 15m
labels:
severity: warning
- alert: KubeNodeUnreachable
annotations:
message: '{{ $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
expr: |
kube_node_spec_taint{job="kube-state-metrics",key="node.kubernetes.io/unreachable",effect="NoSchedule"} == 1
labels:
severity: warning
- alert: KubeletTooManyPods
annotations:
message: Kubelet '{{ $labels.node }}' is running at {{ $value | humanizePercentage
}} of its Pod capacity.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubelettoomanypods
expr: |
max(max(kubelet_running_pod_count{job="kubelet"}) by(instance) * on(instance) group_left(node) kubelet_node_name{job="kubelet"}) by(node) / max(kube_node_status_capacity_pods{job="kube-state-metrics"}) by(node) > 0.95
for: 15m
labels:
severity: warning
- alert: KubeletDown
annotations:
message: Kubelet has disappeared from Prometheus target discovery.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletdown
expr: |
absent(up{job="kubelet"} == 1)
for: 15m
labels:
severity: critical
- name: kubernetes-system-scheduler
rules:
- alert: KubeSchedulerDown
annotations:
message: KubeScheduler has disappeared from Prometheus target discovery.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeschedulerdown
expr: |
absent(up{job="kube-scheduler"} == 1)
for: 15m
labels:
severity: critical
- name: kubernetes-system-controller-manager
rules:
- alert: KubeControllerManagerDown
annotations:
message: KubeControllerManager has disappeared from Prometheus target discovery.
runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecontrollermanagerdown
expr: |
absent(up{job="kube-controller-manager"} == 1)
for: 15m
labels:
severity: critical
- name: prometheus
rules:
- alert: PrometheusBadConfig
@ -1085,8 +1075,8 @@ spec:
- alert: PrometheusRemoteWriteDesiredShards
annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} remote write
desired shards calculation wants to run {{ printf $value }} shards, which
is more than the max of {{ printf `prometheus_remote_storage_shards_max{instance="%s",job="prometheus-k8s",namespace="monitoring"}`
desired shards calculation wants to run {{ $value }} shards, 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.
@ -1095,7 +1085,7 @@ spec:
# https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.
(
max_over_time(prometheus_remote_storage_shards_desired{job="prometheus-k8s",namespace="monitoring"}[5m])
> on(job, instance) group_right
>
max_over_time(prometheus_remote_storage_shards_max{job="prometheus-k8s",namespace="monitoring"}[5m])
)
for: 15m
@ -1155,8 +1145,8 @@ spec:
rules:
- alert: TargetDown
annotations:
message: '{{ printf "%.4g" $value }}% of the {{ $labels.job }} targets are
down.'
message: '{{ printf "%.4g" $value }}% of the {{ $labels.job }} 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

13
manifests/prometheus-serviceMonitorKubelet.yaml
View File

@ -10,12 +10,25 @@ spec:
- bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token
interval: 30s
port: http-metrics
relabelings:
- sourceLabels:
- __metrics_path__
targetLabel: metrics_path
scheme: http
- bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token
honorLabels: true
interval: 30s
metricRelabelings:
- action: drop
regex: container_(network_tcp_usage_total|network_udp_usage_total|tasks_state|cpu_load_average_10s)
sourceLabels:
- __name__
path: /metrics/cadvisor
port: http-metrics
relabelings:
- sourceLabels:
- __metrics_path__
targetLabel: metrics_path
scheme: http
jobLabel: k8s-app
namespaceSelector: