kube-prometheus
Signed-off-by: Martyn Ranyard <m@rtyn.berlin>
This commit is contained in:
parent
6e7f842efb
commit
4ce267de84
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
|
|
@ -0,0 +1,702 @@
|
|||
apiVersion: apiextensions.k8s.io/v1
|
||||
kind: CustomResourceDefinition
|
||||
metadata:
|
||||
annotations:
|
||||
controller-gen.kubebuilder.io/version: v0.11.1
|
||||
argocd.argoproj.io/sync-wave: '0'
|
||||
creationTimestamp: null
|
||||
name: podmonitors.monitoring.coreos.com
|
||||
spec:
|
||||
group: monitoring.coreos.com
|
||||
names:
|
||||
categories:
|
||||
- prometheus-operator
|
||||
kind: PodMonitor
|
||||
listKind: PodMonitorList
|
||||
plural: podmonitors
|
||||
shortNames:
|
||||
- pmon
|
||||
singular: podmonitor
|
||||
scope: Namespaced
|
||||
versions:
|
||||
- name: v1
|
||||
schema:
|
||||
openAPIV3Schema:
|
||||
description: PodMonitor defines monitoring for a set of pods.
|
||||
properties:
|
||||
apiVersion:
|
||||
description: 'APIVersion defines the versioned schema of this representation
|
||||
of an object. Servers should convert recognized schemas to the latest
|
||||
internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources'
|
||||
type: string
|
||||
kind:
|
||||
description: 'Kind is a string value representing the REST resource
|
||||
this object represents. Servers may infer this from the endpoint the
|
||||
client submits requests to. Cannot be updated. In CamelCase. More
|
||||
info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds'
|
||||
type: string
|
||||
metadata:
|
||||
type: object
|
||||
spec:
|
||||
description: Specification of desired Pod selection for target discovery
|
||||
by Prometheus.
|
||||
properties:
|
||||
attachMetadata:
|
||||
description: Attaches node metadata to discovered targets. Requires
|
||||
Prometheus v2.35.0 and above.
|
||||
properties:
|
||||
node:
|
||||
description: When set to true, Prometheus must have permissions
|
||||
to get Nodes.
|
||||
type: boolean
|
||||
type: object
|
||||
jobLabel:
|
||||
description: The label to use to retrieve the job name from.
|
||||
type: string
|
||||
labelLimit:
|
||||
description: Per-scrape limit on number of labels that will be accepted
|
||||
for a sample. Only valid in Prometheus versions 2.27.0 and newer.
|
||||
format: int64
|
||||
type: integer
|
||||
labelNameLengthLimit:
|
||||
description: Per-scrape limit on length of labels name that will
|
||||
be accepted for a sample. Only valid in Prometheus versions 2.27.0
|
||||
and newer.
|
||||
format: int64
|
||||
type: integer
|
||||
labelValueLengthLimit:
|
||||
description: Per-scrape limit on length of labels value that will
|
||||
be accepted for a sample. Only valid in Prometheus versions 2.27.0
|
||||
and newer.
|
||||
format: int64
|
||||
type: integer
|
||||
namespaceSelector:
|
||||
description: Selector to select which namespaces the Endpoints objects
|
||||
are discovered from.
|
||||
properties:
|
||||
any:
|
||||
description: Boolean describing whether all namespaces are selected
|
||||
in contrast to a list restricting them.
|
||||
type: boolean
|
||||
matchNames:
|
||||
description: List of namespace names to select from.
|
||||
items:
|
||||
type: string
|
||||
type: array
|
||||
type: object
|
||||
podMetricsEndpoints:
|
||||
description: A list of endpoints allowed as part of this PodMonitor.
|
||||
items:
|
||||
description: PodMetricsEndpoint defines a scrapeable endpoint
|
||||
of a Kubernetes Pod serving Prometheus metrics.
|
||||
properties:
|
||||
authorization:
|
||||
description: Authorization section for this endpoint
|
||||
properties:
|
||||
credentials:
|
||||
description: Selects a key of a Secret in the namespace
|
||||
that contains the credentials for authentication.
|
||||
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
|
||||
TODO: Add other useful fields. apiVersion, kind,
|
||||
uid?'
|
||||
type: string
|
||||
optional:
|
||||
description: Specify whether the Secret or its key
|
||||
must be defined
|
||||
type: boolean
|
||||
required:
|
||||
- key
|
||||
type: object
|
||||
x-kubernetes-map-type: atomic
|
||||
type:
|
||||
description: "Defines the authentication type. The value\
|
||||
\ is case-insensitive. \n \"Basic\" is not a supported\
|
||||
\ value. \n Default: \"Bearer\""
|
||||
type: string
|
||||
type: object
|
||||
basicAuth:
|
||||
description: 'BasicAuth allow an endpoint to authenticate
|
||||
over basic authentication. More info: https://prometheus.io/docs/operating/configuration/#endpoint'
|
||||
properties:
|
||||
password:
|
||||
description: The secret in the service monitor namespace
|
||||
that contains the password for authentication.
|
||||
properties:
|
||||
key:
|
||||
description: The key of the secret to select from. Must
|
||||
be a valid secret key.
|
||||
type: string
|
||||
name:
|
||||
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
|
||||
TODO: Add other useful fields. apiVersion, kind,
|
||||
uid?'
|
||||
type: string
|
||||
optional:
|
||||
description: Specify whether the Secret or its key
|
||||
must be defined
|
||||
type: boolean
|
||||
required:
|
||||
- key
|
||||
type: object
|
||||
x-kubernetes-map-type: atomic
|
||||
username:
|
||||
description: The secret in the service monitor namespace
|
||||
that contains the username for authentication.
|
||||
properties:
|
||||
key:
|
||||
description: The key of the secret to select from. Must
|
||||
be a valid secret key.
|
||||
type: string
|
||||
name:
|
||||
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
|
||||
TODO: Add other useful fields. apiVersion, kind,
|
||||
uid?'
|
||||
type: string
|
||||
optional:
|
||||
description: Specify whether the Secret or its key
|
||||
must be defined
|
||||
type: boolean
|
||||
required:
|
||||
- key
|
||||
type: object
|
||||
x-kubernetes-map-type: atomic
|
||||
type: object
|
||||
bearerTokenSecret:
|
||||
description: Secret to mount to read bearer token for scraping
|
||||
targets. The secret needs to be in the same namespace as
|
||||
the pod monitor and accessible by the Prometheus Operator.
|
||||
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
|
||||
TODO: Add other useful fields. apiVersion, kind, uid?'
|
||||
type: string
|
||||
optional:
|
||||
description: Specify whether the Secret or its key must
|
||||
be defined
|
||||
type: boolean
|
||||
required:
|
||||
- key
|
||||
type: object
|
||||
x-kubernetes-map-type: atomic
|
||||
enableHttp2:
|
||||
description: Whether to enable HTTP2.
|
||||
type: boolean
|
||||
filterRunning:
|
||||
description: 'Drop pods that are not running. (Failed, Succeeded).
|
||||
Enabled by default. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle/#pod-phase'
|
||||
type: boolean
|
||||
followRedirects:
|
||||
description: FollowRedirects configures whether scrape requests
|
||||
follow HTTP 3xx redirects.
|
||||
type: boolean
|
||||
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 If
|
||||
not specified Prometheus' global scrape interval is used.
|
||||
pattern: ^(0|(([0-9]+)y)?(([0-9]+)w)?(([0-9]+)d)?(([0-9]+)h)?(([0-9]+)m)?(([0-9]+)s)?(([0-9]+)ms)?)$
|
||||
type: string
|
||||
metricRelabelings:
|
||||
description: MetricRelabelConfigs to apply to samples before
|
||||
ingestion.
|
||||
items:
|
||||
description: "RelabelConfig allows dynamic rewriting of\
|
||||
\ the label set for targets, alerts, scraped samples and\
|
||||
\ remote write samples. \n More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#relabel_config"
|
||||
properties:
|
||||
action:
|
||||
default: replace
|
||||
description: "Action to perform based on the regex matching.\
|
||||
\ \n `Uppercase` and `Lowercase` actions require Prometheus\
|
||||
\ >= v2.36.0. `DropEqual` and `KeepEqual` actions\
|
||||
\ require Prometheus >= v2.41.0. \n Default: \"Replace\""
|
||||
enum:
|
||||
- replace
|
||||
- Replace
|
||||
- keep
|
||||
- Keep
|
||||
- drop
|
||||
- Drop
|
||||
- hashmod
|
||||
- HashMod
|
||||
- labelmap
|
||||
- LabelMap
|
||||
- labeldrop
|
||||
- LabelDrop
|
||||
- labelkeep
|
||||
- LabelKeep
|
||||
- lowercase
|
||||
- Lowercase
|
||||
- uppercase
|
||||
- Uppercase
|
||||
- keepequal
|
||||
- KeepEqual
|
||||
- dropequal
|
||||
- DropEqual
|
||||
type: string
|
||||
modulus:
|
||||
description: "Modulus to take of the hash of the source\
|
||||
\ label values. \n Only applicable when the action\
|
||||
\ is `HashMod`."
|
||||
format: int64
|
||||
type: integer
|
||||
regex:
|
||||
description: Regular expression against which the extracted
|
||||
value is matched.
|
||||
type: string
|
||||
replacement:
|
||||
description: "Replacement value against which a Replace\
|
||||
\ action is performed if the regular expression matches.\
|
||||
\ \n Regex capture groups are available."
|
||||
type: string
|
||||
separator:
|
||||
description: Separator is the string between concatenated
|
||||
SourceLabels.
|
||||
type: string
|
||||
sourceLabels:
|
||||
description: The source labels select values from existing
|
||||
labels. Their content is concatenated using the configured
|
||||
Separator and matched against the configured regular
|
||||
expression.
|
||||
items:
|
||||
description: LabelName is a valid Prometheus label
|
||||
name which may only contain ASCII letters, numbers,
|
||||
as well as underscores.
|
||||
pattern: ^[a-zA-Z_][a-zA-Z0-9_]*$
|
||||
type: string
|
||||
type: array
|
||||
targetLabel:
|
||||
description: "Label to which the resulting string is\
|
||||
\ written in a replacement. \n It is mandatory for\
|
||||
\ `Replace`, `HashMod`, `Lowercase`, `Uppercase`,\
|
||||
\ `KeepEqual` and `DropEqual` actions. \n Regex capture\
|
||||
\ groups are available."
|
||||
type: string
|
||||
type: object
|
||||
type: array
|
||||
oauth2:
|
||||
description: OAuth2 for the URL. Only valid in Prometheus
|
||||
versions 2.27.0 and newer.
|
||||
properties:
|
||||
clientId:
|
||||
description: The secret or configmap containing the OAuth2
|
||||
client id
|
||||
properties:
|
||||
configMap:
|
||||
description: ConfigMap containing data to use for
|
||||
the targets.
|
||||
properties:
|
||||
key:
|
||||
description: The key to select.
|
||||
type: string
|
||||
name:
|
||||
description: 'Name of the referent. More info:
|
||||
https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
|
||||
TODO: Add other useful fields. apiVersion, kind,
|
||||
uid?'
|
||||
type: string
|
||||
optional:
|
||||
description: Specify whether the ConfigMap or
|
||||
its key must be defined
|
||||
type: boolean
|
||||
required:
|
||||
- key
|
||||
type: object
|
||||
x-kubernetes-map-type: atomic
|
||||
secret:
|
||||
description: Secret containing data to use for the
|
||||
targets.
|
||||
properties:
|
||||
key:
|
||||
description: The key of the secret to select from. Must
|
||||
be a valid secret key.
|
||||
type: string
|
||||
name:
|
||||
description: 'Name of the referent. More info:
|
||||
https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
|
||||
TODO: Add other useful fields. apiVersion, kind,
|
||||
uid?'
|
||||
type: string
|
||||
optional:
|
||||
description: Specify whether the Secret or its
|
||||
key must be defined
|
||||
type: boolean
|
||||
required:
|
||||
- key
|
||||
type: object
|
||||
x-kubernetes-map-type: atomic
|
||||
type: object
|
||||
clientSecret:
|
||||
description: The secret containing the OAuth2 client 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
|
||||
TODO: Add other useful fields. apiVersion, kind,
|
||||
uid?'
|
||||
type: string
|
||||
optional:
|
||||
description: Specify whether the Secret or its key
|
||||
must be defined
|
||||
type: boolean
|
||||
required:
|
||||
- key
|
||||
type: object
|
||||
x-kubernetes-map-type: atomic
|
||||
endpointParams:
|
||||
additionalProperties:
|
||||
type: string
|
||||
description: Parameters to append to the token URL
|
||||
type: object
|
||||
scopes:
|
||||
description: OAuth2 scopes used for the token request
|
||||
items:
|
||||
type: string
|
||||
type: array
|
||||
tokenUrl:
|
||||
description: The URL to fetch the token from
|
||||
minLength: 1
|
||||
type: string
|
||||
required:
|
||||
- clientId
|
||||
- clientSecret
|
||||
- tokenUrl
|
||||
type: object
|
||||
params:
|
||||
additionalProperties:
|
||||
items:
|
||||
type: string
|
||||
type: array
|
||||
description: Optional HTTP URL parameters
|
||||
type: object
|
||||
path:
|
||||
description: HTTP path to scrape for metrics. If empty, Prometheus
|
||||
uses the default value (e.g. `/metrics`).
|
||||
type: string
|
||||
port:
|
||||
description: Name of the pod port this endpoint refers to.
|
||||
Mutually exclusive with targetPort.
|
||||
type: string
|
||||
proxyUrl:
|
||||
description: ProxyURL eg http://proxyserver:2195 Directs scrapes
|
||||
to proxy through this endpoint.
|
||||
type: string
|
||||
relabelings:
|
||||
description: 'RelabelConfigs to apply to samples before scraping.
|
||||
Prometheus Operator automatically adds relabelings for a
|
||||
few standard Kubernetes fields. The original scrape job''s
|
||||
name is available via the `__tmp_prometheus_job_name` label.
|
||||
More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#relabel_config'
|
||||
items:
|
||||
description: "RelabelConfig allows dynamic rewriting of\
|
||||
\ the label set for targets, alerts, scraped samples and\
|
||||
\ remote write samples. \n More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#relabel_config"
|
||||
properties:
|
||||
action:
|
||||
default: replace
|
||||
description: "Action to perform based on the regex matching.\
|
||||
\ \n `Uppercase` and `Lowercase` actions require Prometheus\
|
||||
\ >= v2.36.0. `DropEqual` and `KeepEqual` actions\
|
||||
\ require Prometheus >= v2.41.0. \n Default: \"Replace\""
|
||||
enum:
|
||||
- replace
|
||||
- Replace
|
||||
- keep
|
||||
- Keep
|
||||
- drop
|
||||
- Drop
|
||||
- hashmod
|
||||
- HashMod
|
||||
- labelmap
|
||||
- LabelMap
|
||||
- labeldrop
|
||||
- LabelDrop
|
||||
- labelkeep
|
||||
- LabelKeep
|
||||
- lowercase
|
||||
- Lowercase
|
||||
- uppercase
|
||||
- Uppercase
|
||||
- keepequal
|
||||
- KeepEqual
|
||||
- dropequal
|
||||
- DropEqual
|
||||
type: string
|
||||
modulus:
|
||||
description: "Modulus to take of the hash of the source\
|
||||
\ label values. \n Only applicable when the action\
|
||||
\ is `HashMod`."
|
||||
format: int64
|
||||
type: integer
|
||||
regex:
|
||||
description: Regular expression against which the extracted
|
||||
value is matched.
|
||||
type: string
|
||||
replacement:
|
||||
description: "Replacement value against which a Replace\
|
||||
\ action is performed if the regular expression matches.\
|
||||
\ \n Regex capture groups are available."
|
||||
type: string
|
||||
separator:
|
||||
description: Separator is the string between concatenated
|
||||
SourceLabels.
|
||||
type: string
|
||||
sourceLabels:
|
||||
description: The source labels select values from existing
|
||||
labels. Their content is concatenated using the configured
|
||||
Separator and matched against the configured regular
|
||||
expression.
|
||||
items:
|
||||
description: LabelName is a valid Prometheus label
|
||||
name which may only contain ASCII letters, numbers,
|
||||
as well as underscores.
|
||||
pattern: ^[a-zA-Z_][a-zA-Z0-9_]*$
|
||||
type: string
|
||||
type: array
|
||||
targetLabel:
|
||||
description: "Label to which the resulting string is\
|
||||
\ written in a replacement. \n It is mandatory for\
|
||||
\ `Replace`, `HashMod`, `Lowercase`, `Uppercase`,\
|
||||
\ `KeepEqual` and `DropEqual` actions. \n Regex capture\
|
||||
\ groups are available."
|
||||
type: string
|
||||
type: object
|
||||
type: array
|
||||
scheme:
|
||||
description: HTTP scheme to use for scraping. `http` and `https`
|
||||
are the expected values unless you rewrite the `__scheme__`
|
||||
label via relabeling. If empty, Prometheus uses the default
|
||||
value `http`.
|
||||
enum:
|
||||
- http
|
||||
- https
|
||||
type: string
|
||||
scrapeTimeout:
|
||||
description: Timeout after which the scrape is ended If not
|
||||
specified, the Prometheus global scrape interval is used.
|
||||
pattern: ^(0|(([0-9]+)y)?(([0-9]+)w)?(([0-9]+)d)?(([0-9]+)h)?(([0-9]+)m)?(([0-9]+)s)?(([0-9]+)ms)?)$
|
||||
type: string
|
||||
targetPort:
|
||||
anyOf:
|
||||
- type: integer
|
||||
- type: string
|
||||
description: 'Deprecated: Use ''port'' instead.'
|
||||
x-kubernetes-int-or-string: true
|
||||
tlsConfig:
|
||||
description: TLS configuration to use when scraping the endpoint.
|
||||
properties:
|
||||
ca:
|
||||
description: Certificate authority used when verifying
|
||||
server certificates.
|
||||
properties:
|
||||
configMap:
|
||||
description: ConfigMap containing data to use for
|
||||
the targets.
|
||||
properties:
|
||||
key:
|
||||
description: The key to select.
|
||||
type: string
|
||||
name:
|
||||
description: 'Name of the referent. More info:
|
||||
https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
|
||||
TODO: Add other useful fields. apiVersion, kind,
|
||||
uid?'
|
||||
type: string
|
||||
optional:
|
||||
description: Specify whether the ConfigMap or
|
||||
its key must be defined
|
||||
type: boolean
|
||||
required:
|
||||
- key
|
||||
type: object
|
||||
x-kubernetes-map-type: atomic
|
||||
secret:
|
||||
description: Secret containing data to use for the
|
||||
targets.
|
||||
properties:
|
||||
key:
|
||||
description: The key of the secret to select from. Must
|
||||
be a valid secret key.
|
||||
type: string
|
||||
name:
|
||||
description: 'Name of the referent. More info:
|
||||
https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
|
||||
TODO: Add other useful fields. apiVersion, kind,
|
||||
uid?'
|
||||
type: string
|
||||
optional:
|
||||
description: Specify whether the Secret or its
|
||||
key must be defined
|
||||
type: boolean
|
||||
required:
|
||||
- key
|
||||
type: object
|
||||
x-kubernetes-map-type: atomic
|
||||
type: object
|
||||
cert:
|
||||
description: Client certificate to present when doing
|
||||
client-authentication.
|
||||
properties:
|
||||
configMap:
|
||||
description: ConfigMap containing data to use for
|
||||
the targets.
|
||||
properties:
|
||||
key:
|
||||
description: The key to select.
|
||||
type: string
|
||||
name:
|
||||
description: 'Name of the referent. More info:
|
||||
https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
|
||||
TODO: Add other useful fields. apiVersion, kind,
|
||||
uid?'
|
||||
type: string
|
||||
optional:
|
||||
description: Specify whether the ConfigMap or
|
||||
its key must be defined
|
||||
type: boolean
|
||||
required:
|
||||
- key
|
||||
type: object
|
||||
x-kubernetes-map-type: atomic
|
||||
secret:
|
||||
description: Secret containing data to use for the
|
||||
targets.
|
||||
properties:
|
||||
key:
|
||||
description: The key of the secret to select from. Must
|
||||
be a valid secret key.
|
||||
type: string
|
||||
name:
|
||||
description: 'Name of the referent. More info:
|
||||
https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
|
||||
TODO: Add other useful fields. apiVersion, kind,
|
||||
uid?'
|
||||
type: string
|
||||
optional:
|
||||
description: Specify whether the Secret or its
|
||||
key must be defined
|
||||
type: boolean
|
||||
required:
|
||||
- key
|
||||
type: object
|
||||
x-kubernetes-map-type: atomic
|
||||
type: object
|
||||
insecureSkipVerify:
|
||||
description: Disable target certificate validation.
|
||||
type: boolean
|
||||
keySecret:
|
||||
description: Secret containing the client key file for
|
||||
the targets.
|
||||
properties:
|
||||
key:
|
||||
description: The key of the secret to select from. Must
|
||||
be a valid secret key.
|
||||
type: string
|
||||
name:
|
||||
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
|
||||
TODO: Add other useful fields. apiVersion, kind,
|
||||
uid?'
|
||||
type: string
|
||||
optional:
|
||||
description: Specify whether the Secret or its key
|
||||
must be defined
|
||||
type: boolean
|
||||
required:
|
||||
- key
|
||||
type: object
|
||||
x-kubernetes-map-type: atomic
|
||||
serverName:
|
||||
description: Used to verify the hostname for the targets.
|
||||
type: string
|
||||
type: object
|
||||
type: object
|
||||
type: array
|
||||
podTargetLabels:
|
||||
description: PodTargetLabels transfers labels on the Kubernetes
|
||||
Pod onto the target.
|
||||
items:
|
||||
type: string
|
||||
type: array
|
||||
sampleLimit:
|
||||
description: SampleLimit defines per-scrape limit on number of scraped
|
||||
samples that will be accepted.
|
||||
format: int64
|
||||
type: integer
|
||||
selector:
|
||||
description: Selector to select Pod objects.
|
||||
properties:
|
||||
matchExpressions:
|
||||
description: matchExpressions is a list of label selector requirements.
|
||||
The requirements are ANDed.
|
||||
items:
|
||||
description: A label selector requirement is a selector that
|
||||
contains values, a key, and an operator that relates the
|
||||
key and values.
|
||||
properties:
|
||||
key:
|
||||
description: key is the label key that the selector applies
|
||||
to.
|
||||
type: string
|
||||
operator:
|
||||
description: operator represents a key's relationship
|
||||
to a set of values. Valid operators are In, NotIn, Exists
|
||||
and DoesNotExist.
|
||||
type: string
|
||||
values:
|
||||
description: values is an array of string values. If the
|
||||
operator is In or NotIn, the values array must be non-empty.
|
||||
If the operator is Exists or DoesNotExist, the values
|
||||
array must be empty. This array is replaced during a
|
||||
strategic merge patch.
|
||||
items:
|
||||
type: string
|
||||
type: array
|
||||
required:
|
||||
- key
|
||||
- operator
|
||||
type: object
|
||||
type: array
|
||||
matchLabels:
|
||||
additionalProperties:
|
||||
type: string
|
||||
description: matchLabels is a map of {key,value} pairs. A single
|
||||
{key,value} in the matchLabels map is equivalent to an element
|
||||
of matchExpressions, whose key field is "key", the operator
|
||||
is "In", and the values array contains only "value". The requirements
|
||||
are ANDed.
|
||||
type: object
|
||||
type: object
|
||||
x-kubernetes-map-type: atomic
|
||||
targetLimit:
|
||||
description: TargetLimit defines a limit on the number of scraped
|
||||
targets that will be accepted.
|
||||
format: int64
|
||||
type: integer
|
||||
required:
|
||||
- podMetricsEndpoints
|
||||
- selector
|
||||
type: object
|
||||
required:
|
||||
- spec
|
||||
type: object
|
||||
served: true
|
||||
storage: true
|
||||
|
|
@ -0,0 +1,736 @@
|
|||
apiVersion: apiextensions.k8s.io/v1
|
||||
kind: CustomResourceDefinition
|
||||
metadata:
|
||||
annotations:
|
||||
controller-gen.kubebuilder.io/version: v0.11.1
|
||||
argocd.argoproj.io/sync-wave: '0'
|
||||
creationTimestamp: null
|
||||
name: probes.monitoring.coreos.com
|
||||
spec:
|
||||
group: monitoring.coreos.com
|
||||
names:
|
||||
categories:
|
||||
- prometheus-operator
|
||||
kind: Probe
|
||||
listKind: ProbeList
|
||||
plural: probes
|
||||
shortNames:
|
||||
- prb
|
||||
singular: probe
|
||||
scope: Namespaced
|
||||
versions:
|
||||
- name: v1
|
||||
schema:
|
||||
openAPIV3Schema:
|
||||
description: Probe defines monitoring for a set of static targets or ingresses.
|
||||
properties:
|
||||
apiVersion:
|
||||
description: 'APIVersion defines the versioned schema of this representation
|
||||
of an object. Servers should convert recognized schemas to the latest
|
||||
internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources'
|
||||
type: string
|
||||
kind:
|
||||
description: 'Kind is a string value representing the REST resource
|
||||
this object represents. Servers may infer this from the endpoint the
|
||||
client submits requests to. Cannot be updated. In CamelCase. More
|
||||
info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds'
|
||||
type: string
|
||||
metadata:
|
||||
type: object
|
||||
spec:
|
||||
description: Specification of desired Ingress selection for target discovery
|
||||
by Prometheus.
|
||||
properties:
|
||||
authorization:
|
||||
description: Authorization section for this endpoint
|
||||
properties:
|
||||
credentials:
|
||||
description: Selects a key of a Secret in the namespace that
|
||||
contains the credentials for authentication.
|
||||
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
|
||||
TODO: Add other useful fields. apiVersion, kind, uid?'
|
||||
type: string
|
||||
optional:
|
||||
description: Specify whether the Secret or its key must
|
||||
be defined
|
||||
type: boolean
|
||||
required:
|
||||
- key
|
||||
type: object
|
||||
x-kubernetes-map-type: atomic
|
||||
type:
|
||||
description: "Defines the authentication type. The value is\
|
||||
\ case-insensitive. \n \"Basic\" is not a supported value.\
|
||||
\ \n Default: \"Bearer\""
|
||||
type: string
|
||||
type: object
|
||||
basicAuth:
|
||||
description: 'BasicAuth allow an endpoint to authenticate over basic
|
||||
authentication. More info: https://prometheus.io/docs/operating/configuration/#endpoint'
|
||||
properties:
|
||||
password:
|
||||
description: The secret in the service monitor namespace that
|
||||
contains the password for authentication.
|
||||
properties:
|
||||
key:
|
||||
description: The key of the secret to select from. Must
|
||||
be a valid secret key.
|
||||
type: string
|
||||
name:
|
||||
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
|
||||
TODO: Add other useful fields. apiVersion, kind, uid?'
|
||||
type: string
|
||||
optional:
|
||||
description: Specify whether the Secret or its key must
|
||||
be defined
|
||||
type: boolean
|
||||
required:
|
||||
- key
|
||||
type: object
|
||||
x-kubernetes-map-type: atomic
|
||||
username:
|
||||
description: The secret in the service monitor namespace that
|
||||
contains the username for authentication.
|
||||
properties:
|
||||
key:
|
||||
description: The key of the secret to select from. Must
|
||||
be a valid secret key.
|
||||
type: string
|
||||
name:
|
||||
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
|
||||
TODO: Add other useful fields. apiVersion, kind, uid?'
|
||||
type: string
|
||||
optional:
|
||||
description: Specify whether the Secret or its key must
|
||||
be defined
|
||||
type: boolean
|
||||
required:
|
||||
- key
|
||||
type: object
|
||||
x-kubernetes-map-type: atomic
|
||||
type: object
|
||||
bearerTokenSecret:
|
||||
description: Secret to mount to read bearer token for scraping targets.
|
||||
The secret needs to be in the same namespace as the probe and
|
||||
accessible by the Prometheus Operator.
|
||||
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
|
||||
TODO: Add other useful fields. apiVersion, kind, uid?'
|
||||
type: string
|
||||
optional:
|
||||
description: Specify whether the Secret or its key must be defined
|
||||
type: boolean
|
||||
required:
|
||||
- key
|
||||
type: object
|
||||
x-kubernetes-map-type: atomic
|
||||
interval:
|
||||
description: Interval at which targets are probed using the configured
|
||||
prober. If not specified Prometheus' global scrape interval is
|
||||
used.
|
||||
pattern: ^(0|(([0-9]+)y)?(([0-9]+)w)?(([0-9]+)d)?(([0-9]+)h)?(([0-9]+)m)?(([0-9]+)s)?(([0-9]+)ms)?)$
|
||||
type: string
|
||||
jobName:
|
||||
description: The job name assigned to scraped metrics by default.
|
||||
type: string
|
||||
labelLimit:
|
||||
description: Per-scrape limit on number of labels that will be accepted
|
||||
for a sample. Only valid in Prometheus versions 2.27.0 and newer.
|
||||
format: int64
|
||||
type: integer
|
||||
labelNameLengthLimit:
|
||||
description: Per-scrape limit on length of labels name that will
|
||||
be accepted for a sample. Only valid in Prometheus versions 2.27.0
|
||||
and newer.
|
||||
format: int64
|
||||
type: integer
|
||||
labelValueLengthLimit:
|
||||
description: Per-scrape limit on length of labels value that will
|
||||
be accepted for a sample. Only valid in Prometheus versions 2.27.0
|
||||
and newer.
|
||||
format: int64
|
||||
type: integer
|
||||
metricRelabelings:
|
||||
description: MetricRelabelConfigs to apply to samples before ingestion.
|
||||
items:
|
||||
description: "RelabelConfig allows dynamic rewriting of the label\
|
||||
\ set for targets, alerts, scraped samples and remote write\
|
||||
\ samples. \n More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#relabel_config"
|
||||
properties:
|
||||
action:
|
||||
default: replace
|
||||
description: "Action to perform based on the regex matching.\
|
||||
\ \n `Uppercase` and `Lowercase` actions require Prometheus\
|
||||
\ >= v2.36.0. `DropEqual` and `KeepEqual` actions require\
|
||||
\ Prometheus >= v2.41.0. \n Default: \"Replace\""
|
||||
enum:
|
||||
- replace
|
||||
- Replace
|
||||
- keep
|
||||
- Keep
|
||||
- drop
|
||||
- Drop
|
||||
- hashmod
|
||||
- HashMod
|
||||
- labelmap
|
||||
- LabelMap
|
||||
- labeldrop
|
||||
- LabelDrop
|
||||
- labelkeep
|
||||
- LabelKeep
|
||||
- lowercase
|
||||
- Lowercase
|
||||
- uppercase
|
||||
- Uppercase
|
||||
- keepequal
|
||||
- KeepEqual
|
||||
- dropequal
|
||||
- DropEqual
|
||||
type: string
|
||||
modulus:
|
||||
description: "Modulus to take of the hash of the source label\
|
||||
\ values. \n Only applicable when the action is `HashMod`."
|
||||
format: int64
|
||||
type: integer
|
||||
regex:
|
||||
description: Regular expression against which the extracted
|
||||
value is matched.
|
||||
type: string
|
||||
replacement:
|
||||
description: "Replacement value against which a Replace action\
|
||||
\ is performed if the regular expression matches. \n Regex\
|
||||
\ capture groups are available."
|
||||
type: string
|
||||
separator:
|
||||
description: Separator is the string between concatenated
|
||||
SourceLabels.
|
||||
type: string
|
||||
sourceLabels:
|
||||
description: The source labels select values from existing
|
||||
labels. Their content is concatenated using the configured
|
||||
Separator and matched against the configured regular expression.
|
||||
items:
|
||||
description: LabelName is a valid Prometheus label name
|
||||
which may only contain ASCII letters, numbers, as well
|
||||
as underscores.
|
||||
pattern: ^[a-zA-Z_][a-zA-Z0-9_]*$
|
||||
type: string
|
||||
type: array
|
||||
targetLabel:
|
||||
description: "Label to which the resulting string is written\
|
||||
\ in a replacement. \n It is mandatory for `Replace`, `HashMod`,\
|
||||
\ `Lowercase`, `Uppercase`, `KeepEqual` and `DropEqual`\
|
||||
\ actions. \n Regex capture groups are available."
|
||||
type: string
|
||||
type: object
|
||||
type: array
|
||||
module:
|
||||
description: 'The module to use for probing specifying how to probe
|
||||
the target. Example module configuring in the blackbox exporter:
|
||||
https://github.com/prometheus/blackbox_exporter/blob/master/example.yml'
|
||||
type: string
|
||||
oauth2:
|
||||
description: OAuth2 for the URL. Only valid in Prometheus versions
|
||||
2.27.0 and newer.
|
||||
properties:
|
||||
clientId:
|
||||
description: The secret or configmap containing the OAuth2 client
|
||||
id
|
||||
properties:
|
||||
configMap:
|
||||
description: ConfigMap containing data to use for the targets.
|
||||
properties:
|
||||
key:
|
||||
description: The key to select.
|
||||
type: string
|
||||
name:
|
||||
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
|
||||
TODO: Add other useful fields. apiVersion, kind, uid?'
|
||||
type: string
|
||||
optional:
|
||||
description: Specify whether the ConfigMap or its key
|
||||
must be defined
|
||||
type: boolean
|
||||
required:
|
||||
- key
|
||||
type: object
|
||||
x-kubernetes-map-type: atomic
|
||||
secret:
|
||||
description: Secret containing data to use for the targets.
|
||||
properties:
|
||||
key:
|
||||
description: The key of the secret to select from. Must
|
||||
be a valid secret key.
|
||||
type: string
|
||||
name:
|
||||
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
|
||||
TODO: Add other useful fields. apiVersion, kind, uid?'
|
||||
type: string
|
||||
optional:
|
||||
description: Specify whether the Secret or its key must
|
||||
be defined
|
||||
type: boolean
|
||||
required:
|
||||
- key
|
||||
type: object
|
||||
x-kubernetes-map-type: atomic
|
||||
type: object
|
||||
clientSecret:
|
||||
description: The secret containing the OAuth2 client 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
|
||||
TODO: Add other useful fields. apiVersion, kind, uid?'
|
||||
type: string
|
||||
optional:
|
||||
description: Specify whether the Secret or its key must
|
||||
be defined
|
||||
type: boolean
|
||||
required:
|
||||
- key
|
||||
type: object
|
||||
x-kubernetes-map-type: atomic
|
||||
endpointParams:
|
||||
additionalProperties:
|
||||
type: string
|
||||
description: Parameters to append to the token URL
|
||||
type: object
|
||||
scopes:
|
||||
description: OAuth2 scopes used for the token request
|
||||
items:
|
||||
type: string
|
||||
type: array
|
||||
tokenUrl:
|
||||
description: The URL to fetch the token from
|
||||
minLength: 1
|
||||
type: string
|
||||
required:
|
||||
- clientId
|
||||
- clientSecret
|
||||
- tokenUrl
|
||||
type: object
|
||||
prober:
|
||||
description: Specification for the prober to use for probing targets.
|
||||
The prober.URL parameter is required. Targets cannot be probed
|
||||
if left empty.
|
||||
properties:
|
||||
path:
|
||||
default: /probe
|
||||
description: Path to collect metrics from. Defaults to `/probe`.
|
||||
type: string
|
||||
proxyUrl:
|
||||
description: Optional ProxyURL.
|
||||
type: string
|
||||
scheme:
|
||||
description: HTTP scheme to use for scraping. `http` and `https`
|
||||
are the expected values unless you rewrite the `__scheme__`
|
||||
label via relabeling. If empty, Prometheus uses the default
|
||||
value `http`.
|
||||
enum:
|
||||
- http
|
||||
- https
|
||||
type: string
|
||||
url:
|
||||
description: Mandatory URL of the prober.
|
||||
type: string
|
||||
required:
|
||||
- url
|
||||
type: object
|
||||
sampleLimit:
|
||||
description: SampleLimit defines per-scrape limit on number of scraped
|
||||
samples that will be accepted.
|
||||
format: int64
|
||||
type: integer
|
||||
scrapeTimeout:
|
||||
description: Timeout for scraping metrics from the Prometheus exporter.
|
||||
If not specified, the Prometheus global scrape timeout is used.
|
||||
pattern: ^(0|(([0-9]+)y)?(([0-9]+)w)?(([0-9]+)d)?(([0-9]+)h)?(([0-9]+)m)?(([0-9]+)s)?(([0-9]+)ms)?)$
|
||||
type: string
|
||||
targetLimit:
|
||||
description: TargetLimit defines a limit on the number of scraped
|
||||
targets that will be accepted.
|
||||
format: int64
|
||||
type: integer
|
||||
targets:
|
||||
description: Targets defines a set of static or dynamically discovered
|
||||
targets to probe.
|
||||
properties:
|
||||
ingress:
|
||||
description: ingress defines the Ingress objects to probe and
|
||||
the relabeling configuration. If `staticConfig` is also defined,
|
||||
`staticConfig` takes precedence.
|
||||
properties:
|
||||
namespaceSelector:
|
||||
description: From which namespaces to select Ingress objects.
|
||||
properties:
|
||||
any:
|
||||
description: Boolean describing whether all namespaces
|
||||
are selected in contrast to a list restricting them.
|
||||
type: boolean
|
||||
matchNames:
|
||||
description: List of namespace names to select from.
|
||||
items:
|
||||
type: string
|
||||
type: array
|
||||
type: object
|
||||
relabelingConfigs:
|
||||
description: 'RelabelConfigs to apply to the label set of
|
||||
the target before it gets scraped. The original ingress
|
||||
address is available via the `__tmp_prometheus_ingress_address`
|
||||
label. It can be used to customize the probed URL. The
|
||||
original scrape job''s name is available via the `__tmp_prometheus_job_name`
|
||||
label. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#relabel_config'
|
||||
items:
|
||||
description: "RelabelConfig allows dynamic rewriting of\
|
||||
\ the label set for targets, alerts, scraped samples\
|
||||
\ and remote write samples. \n More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#relabel_config"
|
||||
properties:
|
||||
action:
|
||||
default: replace
|
||||
description: "Action to perform based on the regex\
|
||||
\ matching. \n `Uppercase` and `Lowercase` actions\
|
||||
\ require Prometheus >= v2.36.0. `DropEqual` and\
|
||||
\ `KeepEqual` actions require Prometheus >= v2.41.0.\
|
||||
\ \n Default: \"Replace\""
|
||||
enum:
|
||||
- replace
|
||||
- Replace
|
||||
- keep
|
||||
- Keep
|
||||
- drop
|
||||
- Drop
|
||||
- hashmod
|
||||
- HashMod
|
||||
- labelmap
|
||||
- LabelMap
|
||||
- labeldrop
|
||||
- LabelDrop
|
||||
- labelkeep
|
||||
- LabelKeep
|
||||
- lowercase
|
||||
- Lowercase
|
||||
- uppercase
|
||||
- Uppercase
|
||||
- keepequal
|
||||
- KeepEqual
|
||||
- dropequal
|
||||
- DropEqual
|
||||
type: string
|
||||
modulus:
|
||||
description: "Modulus to take of the hash of the source\
|
||||
\ label values. \n Only applicable when the action\
|
||||
\ is `HashMod`."
|
||||
format: int64
|
||||
type: integer
|
||||
regex:
|
||||
description: Regular expression against which the
|
||||
extracted value is matched.
|
||||
type: string
|
||||
replacement:
|
||||
description: "Replacement value against which a Replace\
|
||||
\ action is performed if the regular expression\
|
||||
\ matches. \n Regex capture groups are available."
|
||||
type: string
|
||||
separator:
|
||||
description: Separator is the string between concatenated
|
||||
SourceLabels.
|
||||
type: string
|
||||
sourceLabels:
|
||||
description: The source labels select values from
|
||||
existing labels. Their content is concatenated using
|
||||
the configured Separator and matched against the
|
||||
configured regular expression.
|
||||
items:
|
||||
description: LabelName is a valid Prometheus label
|
||||
name which may only contain ASCII letters, numbers,
|
||||
as well as underscores.
|
||||
pattern: ^[a-zA-Z_][a-zA-Z0-9_]*$
|
||||
type: string
|
||||
type: array
|
||||
targetLabel:
|
||||
description: "Label to which the resulting string\
|
||||
\ is written in a replacement. \n It is mandatory\
|
||||
\ for `Replace`, `HashMod`, `Lowercase`, `Uppercase`,\
|
||||
\ `KeepEqual` and `DropEqual` actions. \n Regex\
|
||||
\ capture groups are available."
|
||||
type: string
|
||||
type: object
|
||||
type: array
|
||||
selector:
|
||||
description: Selector to select the Ingress objects.
|
||||
properties:
|
||||
matchExpressions:
|
||||
description: matchExpressions is a list of label selector
|
||||
requirements. The requirements are ANDed.
|
||||
items:
|
||||
description: A label selector requirement is a selector
|
||||
that contains values, a key, and an operator that
|
||||
relates the key and values.
|
||||
properties:
|
||||
key:
|
||||
description: key is the label key that the selector
|
||||
applies to.
|
||||
type: string
|
||||
operator:
|
||||
description: operator represents a key's relationship
|
||||
to a set of values. Valid operators are In,
|
||||
NotIn, Exists and DoesNotExist.
|
||||
type: string
|
||||
values:
|
||||
description: values is an array of string values.
|
||||
If the operator is In or NotIn, the values array
|
||||
must be non-empty. If the operator is Exists
|
||||
or DoesNotExist, the values array must be empty.
|
||||
This array is replaced during a strategic merge
|
||||
patch.
|
||||
items:
|
||||
type: string
|
||||
type: array
|
||||
required:
|
||||
- key
|
||||
- operator
|
||||
type: object
|
||||
type: array
|
||||
matchLabels:
|
||||
additionalProperties:
|
||||
type: string
|
||||
description: matchLabels is a map of {key,value} pairs.
|
||||
A single {key,value} in the matchLabels map is equivalent
|
||||
to an element of matchExpressions, whose key field
|
||||
is "key", the operator is "In", and the values array
|
||||
contains only "value". The requirements are ANDed.
|
||||
type: object
|
||||
type: object
|
||||
x-kubernetes-map-type: atomic
|
||||
type: object
|
||||
staticConfig:
|
||||
description: 'staticConfig defines the static list of targets
|
||||
to probe and the relabeling configuration. If `ingress` is
|
||||
also defined, `staticConfig` takes precedence. More info:
|
||||
https://prometheus.io/docs/prometheus/latest/configuration/configuration/#static_config.'
|
||||
properties:
|
||||
labels:
|
||||
additionalProperties:
|
||||
type: string
|
||||
description: Labels assigned to all metrics scraped from
|
||||
the targets.
|
||||
type: object
|
||||
relabelingConfigs:
|
||||
description: 'RelabelConfigs to apply to the label set of
|
||||
the targets before it gets scraped. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#relabel_config'
|
||||
items:
|
||||
description: "RelabelConfig allows dynamic rewriting of\
|
||||
\ the label set for targets, alerts, scraped samples\
|
||||
\ and remote write samples. \n More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#relabel_config"
|
||||
properties:
|
||||
action:
|
||||
default: replace
|
||||
description: "Action to perform based on the regex\
|
||||
\ matching. \n `Uppercase` and `Lowercase` actions\
|
||||
\ require Prometheus >= v2.36.0. `DropEqual` and\
|
||||
\ `KeepEqual` actions require Prometheus >= v2.41.0.\
|
||||
\ \n Default: \"Replace\""
|
||||
enum:
|
||||
- replace
|
||||
- Replace
|
||||
- keep
|
||||
- Keep
|
||||
- drop
|
||||
- Drop
|
||||
- hashmod
|
||||
- HashMod
|
||||
- labelmap
|
||||
- LabelMap
|
||||
- labeldrop
|
||||
- LabelDrop
|
||||
- labelkeep
|
||||
- LabelKeep
|
||||
- lowercase
|
||||
- Lowercase
|
||||
- uppercase
|
||||
- Uppercase
|
||||
- keepequal
|
||||
- KeepEqual
|
||||
- dropequal
|
||||
- DropEqual
|
||||
type: string
|
||||
modulus:
|
||||
description: "Modulus to take of the hash of the source\
|
||||
\ label values. \n Only applicable when the action\
|
||||
\ is `HashMod`."
|
||||
format: int64
|
||||
type: integer
|
||||
regex:
|
||||
description: Regular expression against which the
|
||||
extracted value is matched.
|
||||
type: string
|
||||
replacement:
|
||||
description: "Replacement value against which a Replace\
|
||||
\ action is performed if the regular expression\
|
||||
\ matches. \n Regex capture groups are available."
|
||||
type: string
|
||||
separator:
|
||||
description: Separator is the string between concatenated
|
||||
SourceLabels.
|
||||
type: string
|
||||
sourceLabels:
|
||||
description: The source labels select values from
|
||||
existing labels. Their content is concatenated using
|
||||
the configured Separator and matched against the
|
||||
configured regular expression.
|
||||
items:
|
||||
description: LabelName is a valid Prometheus label
|
||||
name which may only contain ASCII letters, numbers,
|
||||
as well as underscores.
|
||||
pattern: ^[a-zA-Z_][a-zA-Z0-9_]*$
|
||||
type: string
|
||||
type: array
|
||||
targetLabel:
|
||||
description: "Label to which the resulting string\
|
||||
\ is written in a replacement. \n It is mandatory\
|
||||
\ for `Replace`, `HashMod`, `Lowercase`, `Uppercase`,\
|
||||
\ `KeepEqual` and `DropEqual` actions. \n Regex\
|
||||
\ capture groups are available."
|
||||
type: string
|
||||
type: object
|
||||
type: array
|
||||
static:
|
||||
description: The list of hosts to probe.
|
||||
items:
|
||||
type: string
|
||||
type: array
|
||||
type: object
|
||||
type: object
|
||||
tlsConfig:
|
||||
description: TLS configuration to use when scraping the endpoint.
|
||||
properties:
|
||||
ca:
|
||||
description: Certificate authority used when verifying server
|
||||
certificates.
|
||||
properties:
|
||||
configMap:
|
||||
description: ConfigMap containing data to use for the targets.
|
||||
properties:
|
||||
key:
|
||||
description: The key to select.
|
||||
type: string
|
||||
name:
|
||||
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
|
||||
TODO: Add other useful fields. apiVersion, kind, uid?'
|
||||
type: string
|
||||
optional:
|
||||
description: Specify whether the ConfigMap or its key
|
||||
must be defined
|
||||
type: boolean
|
||||
required:
|
||||
- key
|
||||
type: object
|
||||
x-kubernetes-map-type: atomic
|
||||
secret:
|
||||
description: Secret containing data to use for the targets.
|
||||
properties:
|
||||
key:
|
||||
description: The key of the secret to select from. Must
|
||||
be a valid secret key.
|
||||
type: string
|
||||
name:
|
||||
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
|
||||
TODO: Add other useful fields. apiVersion, kind, uid?'
|
||||
type: string
|
||||
optional:
|
||||
description: Specify whether the Secret or its key must
|
||||
be defined
|
||||
type: boolean
|
||||
required:
|
||||
- key
|
||||
type: object
|
||||
x-kubernetes-map-type: atomic
|
||||
type: object
|
||||
cert:
|
||||
description: Client certificate to present when doing client-authentication.
|
||||
properties:
|
||||
configMap:
|
||||
description: ConfigMap containing data to use for the targets.
|
||||
properties:
|
||||
key:
|
||||
description: The key to select.
|
||||
type: string
|
||||
name:
|
||||
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
|
||||
TODO: Add other useful fields. apiVersion, kind, uid?'
|
||||
type: string
|
||||
optional:
|
||||
description: Specify whether the ConfigMap or its key
|
||||
must be defined
|
||||
type: boolean
|
||||
required:
|
||||
- key
|
||||
type: object
|
||||
x-kubernetes-map-type: atomic
|
||||
secret:
|
||||
description: Secret containing data to use for the targets.
|
||||
properties:
|
||||
key:
|
||||
description: The key of the secret to select from. Must
|
||||
be a valid secret key.
|
||||
type: string
|
||||
name:
|
||||
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
|
||||
TODO: Add other useful fields. apiVersion, kind, uid?'
|
||||
type: string
|
||||
optional:
|
||||
description: Specify whether the Secret or its key must
|
||||
be defined
|
||||
type: boolean
|
||||
required:
|
||||
- key
|
||||
type: object
|
||||
x-kubernetes-map-type: atomic
|
||||
type: object
|
||||
insecureSkipVerify:
|
||||
description: Disable target certificate validation.
|
||||
type: boolean
|
||||
keySecret:
|
||||
description: Secret containing the client key file for the targets.
|
||||
properties:
|
||||
key:
|
||||
description: The key of the secret to select from. Must
|
||||
be a valid secret key.
|
||||
type: string
|
||||
name:
|
||||
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
|
||||
TODO: Add other useful fields. apiVersion, kind, uid?'
|
||||
type: string
|
||||
optional:
|
||||
description: Specify whether the Secret or its key must
|
||||
be defined
|
||||
type: boolean
|
||||
required:
|
||||
- key
|
||||
type: object
|
||||
x-kubernetes-map-type: atomic
|
||||
serverName:
|
||||
description: Used to verify the hostname for the targets.
|
||||
type: string
|
||||
type: object
|
||||
type: object
|
||||
required:
|
||||
- spec
|
||||
type: object
|
||||
served: true
|
||||
storage: true
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
|
|
@ -0,0 +1,133 @@
|
|||
apiVersion: apiextensions.k8s.io/v1
|
||||
kind: CustomResourceDefinition
|
||||
metadata:
|
||||
annotations:
|
||||
controller-gen.kubebuilder.io/version: v0.11.1
|
||||
argocd.argoproj.io/sync-wave: '0'
|
||||
creationTimestamp: null
|
||||
name: prometheusrules.monitoring.coreos.com
|
||||
spec:
|
||||
group: monitoring.coreos.com
|
||||
names:
|
||||
categories:
|
||||
- prometheus-operator
|
||||
kind: PrometheusRule
|
||||
listKind: PrometheusRuleList
|
||||
plural: prometheusrules
|
||||
shortNames:
|
||||
- promrule
|
||||
singular: prometheusrule
|
||||
scope: Namespaced
|
||||
versions:
|
||||
- name: v1
|
||||
schema:
|
||||
openAPIV3Schema:
|
||||
description: PrometheusRule defines recording and alerting rules for a Prometheus
|
||||
instance
|
||||
properties:
|
||||
apiVersion:
|
||||
description: 'APIVersion defines the versioned schema of this representation
|
||||
of an object. Servers should convert recognized schemas to the latest
|
||||
internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources'
|
||||
type: string
|
||||
kind:
|
||||
description: 'Kind is a string value representing the REST resource
|
||||
this object represents. Servers may infer this from the endpoint the
|
||||
client submits requests to. Cannot be updated. In CamelCase. More
|
||||
info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds'
|
||||
type: string
|
||||
metadata:
|
||||
type: object
|
||||
spec:
|
||||
description: Specification of desired alerting rule definitions for
|
||||
Prometheus.
|
||||
properties:
|
||||
groups:
|
||||
description: Content of Prometheus rule file
|
||||
items:
|
||||
description: RuleGroup is a list of sequentially evaluated recording
|
||||
and alerting rules.
|
||||
properties:
|
||||
interval:
|
||||
description: Interval determines how often rules in the group
|
||||
are evaluated.
|
||||
pattern: ^(0|(([0-9]+)y)?(([0-9]+)w)?(([0-9]+)d)?(([0-9]+)h)?(([0-9]+)m)?(([0-9]+)s)?(([0-9]+)ms)?)$
|
||||
type: string
|
||||
limit:
|
||||
description: Limit the number of alerts an alerting rule and
|
||||
series a recording rule can produce. Limit is supported
|
||||
starting with Prometheus >= 2.31 and Thanos Ruler >= 0.24.
|
||||
type: integer
|
||||
name:
|
||||
description: Name of the rule group.
|
||||
minLength: 1
|
||||
type: string
|
||||
partial_response_strategy:
|
||||
description: 'PartialResponseStrategy is only used by ThanosRuler
|
||||
and will be ignored by Prometheus instances. More info:
|
||||
https://github.com/thanos-io/thanos/blob/main/docs/components/rule.md#partial-response'
|
||||
pattern: ^(?i)(abort|warn)?$
|
||||
type: string
|
||||
rules:
|
||||
description: List of alerting and recording rules.
|
||||
items:
|
||||
description: 'Rule describes an alerting or recording rule
|
||||
See Prometheus documentation: [alerting](https://www.prometheus.io/docs/prometheus/latest/configuration/alerting_rules/)
|
||||
or [recording](https://www.prometheus.io/docs/prometheus/latest/configuration/recording_rules/#recording-rules)
|
||||
rule'
|
||||
properties:
|
||||
alert:
|
||||
description: Name of the alert. Must be a valid label
|
||||
value. Only one of `record` and `alert` must be set.
|
||||
type: string
|
||||
annotations:
|
||||
additionalProperties:
|
||||
type: string
|
||||
description: Annotations to add to each alert. Only
|
||||
valid for alerting rules.
|
||||
type: object
|
||||
expr:
|
||||
anyOf:
|
||||
- type: integer
|
||||
- type: string
|
||||
description: PromQL expression to evaluate.
|
||||
x-kubernetes-int-or-string: true
|
||||
for:
|
||||
description: Alerts are considered firing once they
|
||||
have been returned for this long.
|
||||
pattern: ^(0|(([0-9]+)y)?(([0-9]+)w)?(([0-9]+)d)?(([0-9]+)h)?(([0-9]+)m)?(([0-9]+)s)?(([0-9]+)ms)?)$
|
||||
type: string
|
||||
keep_firing_for:
|
||||
description: KeepFiringFor defines how long an alert
|
||||
will continue firing after the condition that triggered
|
||||
it has cleared.
|
||||
minLength: 1
|
||||
pattern: ^(0|(([0-9]+)y)?(([0-9]+)w)?(([0-9]+)d)?(([0-9]+)h)?(([0-9]+)m)?(([0-9]+)s)?(([0-9]+)ms)?)$
|
||||
type: string
|
||||
labels:
|
||||
additionalProperties:
|
||||
type: string
|
||||
description: Labels to add or overwrite.
|
||||
type: object
|
||||
record:
|
||||
description: Name of the time series to output to. Must
|
||||
be a valid metric name. Only one of `record` and `alert`
|
||||
must be set.
|
||||
type: string
|
||||
required:
|
||||
- expr
|
||||
type: object
|
||||
type: array
|
||||
required:
|
||||
- name
|
||||
type: object
|
||||
type: array
|
||||
x-kubernetes-list-map-keys:
|
||||
- name
|
||||
x-kubernetes-list-type: map
|
||||
type: object
|
||||
required:
|
||||
- spec
|
||||
type: object
|
||||
served: true
|
||||
storage: true
|
||||
File diff suppressed because it is too large
Load Diff
|
|
@ -0,0 +1,734 @@
|
|||
apiVersion: apiextensions.k8s.io/v1
|
||||
kind: CustomResourceDefinition
|
||||
metadata:
|
||||
annotations:
|
||||
controller-gen.kubebuilder.io/version: v0.11.1
|
||||
argocd.argoproj.io/sync-wave: '0'
|
||||
creationTimestamp: null
|
||||
name: servicemonitors.monitoring.coreos.com
|
||||
spec:
|
||||
group: monitoring.coreos.com
|
||||
names:
|
||||
categories:
|
||||
- prometheus-operator
|
||||
kind: ServiceMonitor
|
||||
listKind: ServiceMonitorList
|
||||
plural: servicemonitors
|
||||
shortNames:
|
||||
- smon
|
||||
singular: servicemonitor
|
||||
scope: Namespaced
|
||||
versions:
|
||||
- name: v1
|
||||
schema:
|
||||
openAPIV3Schema:
|
||||
description: ServiceMonitor defines monitoring for a set of services.
|
||||
properties:
|
||||
apiVersion:
|
||||
description: 'APIVersion defines the versioned schema of this representation
|
||||
of an object. Servers should convert recognized schemas to the latest
|
||||
internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources'
|
||||
type: string
|
||||
kind:
|
||||
description: 'Kind is a string value representing the REST resource
|
||||
this object represents. Servers may infer this from the endpoint the
|
||||
client submits requests to. Cannot be updated. In CamelCase. More
|
||||
info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds'
|
||||
type: string
|
||||
metadata:
|
||||
type: object
|
||||
spec:
|
||||
description: Specification of desired Service selection for target discovery
|
||||
by Prometheus.
|
||||
properties:
|
||||
attachMetadata:
|
||||
description: Attaches node metadata to discovered targets. Requires
|
||||
Prometheus v2.37.0 and above.
|
||||
properties:
|
||||
node:
|
||||
description: When set to true, Prometheus must have permissions
|
||||
to get Nodes.
|
||||
type: boolean
|
||||
type: object
|
||||
endpoints:
|
||||
description: A list of endpoints allowed as part of this ServiceMonitor.
|
||||
items:
|
||||
description: Endpoint defines a scrapeable endpoint serving Prometheus
|
||||
metrics.
|
||||
properties:
|
||||
authorization:
|
||||
description: Authorization section for this endpoint
|
||||
properties:
|
||||
credentials:
|
||||
description: Selects a key of a Secret in the namespace
|
||||
that contains the credentials for authentication.
|
||||
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
|
||||
TODO: Add other useful fields. apiVersion, kind,
|
||||
uid?'
|
||||
type: string
|
||||
optional:
|
||||
description: Specify whether the Secret or its key
|
||||
must be defined
|
||||
type: boolean
|
||||
required:
|
||||
- key
|
||||
type: object
|
||||
x-kubernetes-map-type: atomic
|
||||
type:
|
||||
description: "Defines the authentication type. The value\
|
||||
\ is case-insensitive. \n \"Basic\" is not a supported\
|
||||
\ value. \n Default: \"Bearer\""
|
||||
type: string
|
||||
type: object
|
||||
basicAuth:
|
||||
description: 'BasicAuth allow an endpoint to authenticate
|
||||
over basic authentication More info: https://prometheus.io/docs/operating/configuration/#endpoints'
|
||||
properties:
|
||||
password:
|
||||
description: The secret in the service monitor namespace
|
||||
that contains the password for authentication.
|
||||
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
|
||||
TODO: Add other useful fields. apiVersion, kind,
|
||||
uid?'
|
||||
type: string
|
||||
optional:
|
||||
description: Specify whether the Secret or its key
|
||||
must be defined
|
||||
type: boolean
|
||||
required:
|
||||
- key
|
||||
type: object
|
||||
x-kubernetes-map-type: atomic
|
||||
username:
|
||||
description: The secret in the service monitor namespace
|
||||
that contains the username for authentication.
|
||||
properties:
|
||||
key:
|
||||
description: The key of the secret to select from. Must
|
||||
be a valid secret key.
|
||||
type: string
|
||||
name:
|
||||
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
|
||||
TODO: Add other useful fields. apiVersion, kind,
|
||||
uid?'
|
||||
type: string
|
||||
optional:
|
||||
description: Specify whether the Secret or its key
|
||||
must be defined
|
||||
type: boolean
|
||||
required:
|
||||
- key
|
||||
type: object
|
||||
x-kubernetes-map-type: atomic
|
||||
type: object
|
||||
bearerTokenFile:
|
||||
description: File to read bearer token for scraping targets.
|
||||
type: string
|
||||
bearerTokenSecret:
|
||||
description: Secret to mount to read bearer token for scraping
|
||||
targets. The secret needs to be in the same namespace as
|
||||
the service monitor and accessible by the Prometheus Operator.
|
||||
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
|
||||
TODO: Add other useful fields. apiVersion, kind, uid?'
|
||||
type: string
|
||||
optional:
|
||||
description: Specify whether the Secret or its key must
|
||||
be defined
|
||||
type: boolean
|
||||
required:
|
||||
- key
|
||||
type: object
|
||||
x-kubernetes-map-type: atomic
|
||||
enableHttp2:
|
||||
description: Whether to enable HTTP2.
|
||||
type: boolean
|
||||
filterRunning:
|
||||
description: 'Drop pods that are not running. (Failed, Succeeded).
|
||||
Enabled by default. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle/#pod-phase'
|
||||
type: boolean
|
||||
followRedirects:
|
||||
description: FollowRedirects configures whether scrape requests
|
||||
follow HTTP 3xx redirects.
|
||||
type: boolean
|
||||
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 If
|
||||
not specified Prometheus' global scrape interval is used.
|
||||
pattern: ^(0|(([0-9]+)y)?(([0-9]+)w)?(([0-9]+)d)?(([0-9]+)h)?(([0-9]+)m)?(([0-9]+)s)?(([0-9]+)ms)?)$
|
||||
type: string
|
||||
metricRelabelings:
|
||||
description: MetricRelabelConfigs to apply to samples before
|
||||
ingestion.
|
||||
items:
|
||||
description: "RelabelConfig allows dynamic rewriting of\
|
||||
\ the label set for targets, alerts, scraped samples and\
|
||||
\ remote write samples. \n More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#relabel_config"
|
||||
properties:
|
||||
action:
|
||||
default: replace
|
||||
description: "Action to perform based on the regex matching.\
|
||||
\ \n `Uppercase` and `Lowercase` actions require Prometheus\
|
||||
\ >= v2.36.0. `DropEqual` and `KeepEqual` actions\
|
||||
\ require Prometheus >= v2.41.0. \n Default: \"Replace\""
|
||||
enum:
|
||||
- replace
|
||||
- Replace
|
||||
- keep
|
||||
- Keep
|
||||
- drop
|
||||
- Drop
|
||||
- hashmod
|
||||
- HashMod
|
||||
- labelmap
|
||||
- LabelMap
|
||||
- labeldrop
|
||||
- LabelDrop
|
||||
- labelkeep
|
||||
- LabelKeep
|
||||
- lowercase
|
||||
- Lowercase
|
||||
- uppercase
|
||||
- Uppercase
|
||||
- keepequal
|
||||
- KeepEqual
|
||||
- dropequal
|
||||
- DropEqual
|
||||
type: string
|
||||
modulus:
|
||||
description: "Modulus to take of the hash of the source\
|
||||
\ label values. \n Only applicable when the action\
|
||||
\ is `HashMod`."
|
||||
format: int64
|
||||
type: integer
|
||||
regex:
|
||||
description: Regular expression against which the extracted
|
||||
value is matched.
|
||||
type: string
|
||||
replacement:
|
||||
description: "Replacement value against which a Replace\
|
||||
\ action is performed if the regular expression matches.\
|
||||
\ \n Regex capture groups are available."
|
||||
type: string
|
||||
separator:
|
||||
description: Separator is the string between concatenated
|
||||
SourceLabels.
|
||||
type: string
|
||||
sourceLabels:
|
||||
description: The source labels select values from existing
|
||||
labels. Their content is concatenated using the configured
|
||||
Separator and matched against the configured regular
|
||||
expression.
|
||||
items:
|
||||
description: LabelName is a valid Prometheus label
|
||||
name which may only contain ASCII letters, numbers,
|
||||
as well as underscores.
|
||||
pattern: ^[a-zA-Z_][a-zA-Z0-9_]*$
|
||||
type: string
|
||||
type: array
|
||||
targetLabel:
|
||||
description: "Label to which the resulting string is\
|
||||
\ written in a replacement. \n It is mandatory for\
|
||||
\ `Replace`, `HashMod`, `Lowercase`, `Uppercase`,\
|
||||
\ `KeepEqual` and `DropEqual` actions. \n Regex capture\
|
||||
\ groups are available."
|
||||
type: string
|
||||
type: object
|
||||
type: array
|
||||
oauth2:
|
||||
description: OAuth2 for the URL. Only valid in Prometheus
|
||||
versions 2.27.0 and newer.
|
||||
properties:
|
||||
clientId:
|
||||
description: The secret or configmap containing the OAuth2
|
||||
client id
|
||||
properties:
|
||||
configMap:
|
||||
description: ConfigMap containing data to use for
|
||||
the targets.
|
||||
properties:
|
||||
key:
|
||||
description: The key to select.
|
||||
type: string
|
||||
name:
|
||||
description: 'Name of the referent. More info:
|
||||
https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
|
||||
TODO: Add other useful fields. apiVersion, kind,
|
||||
uid?'
|
||||
type: string
|
||||
optional:
|
||||
description: Specify whether the ConfigMap or
|
||||
its key must be defined
|
||||
type: boolean
|
||||
required:
|
||||
- key
|
||||
type: object
|
||||
x-kubernetes-map-type: atomic
|
||||
secret:
|
||||
description: Secret containing data to use for the
|
||||
targets.
|
||||
properties:
|
||||
key:
|
||||
description: The key of the secret to select from. Must
|
||||
be a valid secret key.
|
||||
type: string
|
||||
name:
|
||||
description: 'Name of the referent. More info:
|
||||
https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
|
||||
TODO: Add other useful fields. apiVersion, kind,
|
||||
uid?'
|
||||
type: string
|
||||
optional:
|
||||
description: Specify whether the Secret or its
|
||||
key must be defined
|
||||
type: boolean
|
||||
required:
|
||||
- key
|
||||
type: object
|
||||
x-kubernetes-map-type: atomic
|
||||
type: object
|
||||
clientSecret:
|
||||
description: The secret containing the OAuth2 client 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
|
||||
TODO: Add other useful fields. apiVersion, kind,
|
||||
uid?'
|
||||
type: string
|
||||
optional:
|
||||
description: Specify whether the Secret or its key
|
||||
must be defined
|
||||
type: boolean
|
||||
required:
|
||||
- key
|
||||
type: object
|
||||
x-kubernetes-map-type: atomic
|
||||
endpointParams:
|
||||
additionalProperties:
|
||||
type: string
|
||||
description: Parameters to append to the token URL
|
||||
type: object
|
||||
scopes:
|
||||
description: OAuth2 scopes used for the token request
|
||||
items:
|
||||
type: string
|
||||
type: array
|
||||
tokenUrl:
|
||||
description: The URL to fetch the token from
|
||||
minLength: 1
|
||||
type: string
|
||||
required:
|
||||
- clientId
|
||||
- clientSecret
|
||||
- tokenUrl
|
||||
type: object
|
||||
params:
|
||||
additionalProperties:
|
||||
items:
|
||||
type: string
|
||||
type: array
|
||||
description: Optional HTTP URL parameters
|
||||
type: object
|
||||
path:
|
||||
description: HTTP path to scrape for metrics. If empty, Prometheus
|
||||
uses the default value (e.g. `/metrics`).
|
||||
type: string
|
||||
port:
|
||||
description: Name of the service port this endpoint refers
|
||||
to. Mutually exclusive with targetPort.
|
||||
type: string
|
||||
proxyUrl:
|
||||
description: ProxyURL eg http://proxyserver:2195 Directs scrapes
|
||||
to proxy through this endpoint.
|
||||
type: string
|
||||
relabelings:
|
||||
description: 'RelabelConfigs to apply to samples before scraping.
|
||||
Prometheus Operator automatically adds relabelings for a
|
||||
few standard Kubernetes fields. The original scrape job''s
|
||||
name is available via the `__tmp_prometheus_job_name` label.
|
||||
More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#relabel_config'
|
||||
items:
|
||||
description: "RelabelConfig allows dynamic rewriting of\
|
||||
\ the label set for targets, alerts, scraped samples and\
|
||||
\ remote write samples. \n More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#relabel_config"
|
||||
properties:
|
||||
action:
|
||||
default: replace
|
||||
description: "Action to perform based on the regex matching.\
|
||||
\ \n `Uppercase` and `Lowercase` actions require Prometheus\
|
||||
\ >= v2.36.0. `DropEqual` and `KeepEqual` actions\
|
||||
\ require Prometheus >= v2.41.0. \n Default: \"Replace\""
|
||||
enum:
|
||||
- replace
|
||||
- Replace
|
||||
- keep
|
||||
- Keep
|
||||
- drop
|
||||
- Drop
|
||||
- hashmod
|
||||
- HashMod
|
||||
- labelmap
|
||||
- LabelMap
|
||||
- labeldrop
|
||||
- LabelDrop
|
||||
- labelkeep
|
||||
- LabelKeep
|
||||
- lowercase
|
||||
- Lowercase
|
||||
- uppercase
|
||||
- Uppercase
|
||||
- keepequal
|
||||
- KeepEqual
|
||||
- dropequal
|
||||
- DropEqual
|
||||
type: string
|
||||
modulus:
|
||||
description: "Modulus to take of the hash of the source\
|
||||
\ label values. \n Only applicable when the action\
|
||||
\ is `HashMod`."
|
||||
format: int64
|
||||
type: integer
|
||||
regex:
|
||||
description: Regular expression against which the extracted
|
||||
value is matched.
|
||||
type: string
|
||||
replacement:
|
||||
description: "Replacement value against which a Replace\
|
||||
\ action is performed if the regular expression matches.\
|
||||
\ \n Regex capture groups are available."
|
||||
type: string
|
||||
separator:
|
||||
description: Separator is the string between concatenated
|
||||
SourceLabels.
|
||||
type: string
|
||||
sourceLabels:
|
||||
description: The source labels select values from existing
|
||||
labels. Their content is concatenated using the configured
|
||||
Separator and matched against the configured regular
|
||||
expression.
|
||||
items:
|
||||
description: LabelName is a valid Prometheus label
|
||||
name which may only contain ASCII letters, numbers,
|
||||
as well as underscores.
|
||||
pattern: ^[a-zA-Z_][a-zA-Z0-9_]*$
|
||||
type: string
|
||||
type: array
|
||||
targetLabel:
|
||||
description: "Label to which the resulting string is\
|
||||
\ written in a replacement. \n It is mandatory for\
|
||||
\ `Replace`, `HashMod`, `Lowercase`, `Uppercase`,\
|
||||
\ `KeepEqual` and `DropEqual` actions. \n Regex capture\
|
||||
\ groups are available."
|
||||
type: string
|
||||
type: object
|
||||
type: array
|
||||
scheme:
|
||||
description: HTTP scheme to use for scraping. `http` and `https`
|
||||
are the expected values unless you rewrite the `__scheme__`
|
||||
label via relabeling. If empty, Prometheus uses the default
|
||||
value `http`.
|
||||
enum:
|
||||
- http
|
||||
- https
|
||||
type: string
|
||||
scrapeTimeout:
|
||||
description: Timeout after which the scrape is ended If not
|
||||
specified, the Prometheus global scrape timeout is used
|
||||
unless it is less than `Interval` in which the latter is
|
||||
used.
|
||||
pattern: ^(0|(([0-9]+)y)?(([0-9]+)w)?(([0-9]+)d)?(([0-9]+)h)?(([0-9]+)m)?(([0-9]+)s)?(([0-9]+)ms)?)$
|
||||
type: string
|
||||
targetPort:
|
||||
anyOf:
|
||||
- type: integer
|
||||
- type: string
|
||||
description: Name or number of the target port of the Pod
|
||||
behind the Service, the port must be specified with container
|
||||
port property. Mutually exclusive with port.
|
||||
x-kubernetes-int-or-string: true
|
||||
tlsConfig:
|
||||
description: TLS configuration to use when scraping the endpoint
|
||||
properties:
|
||||
ca:
|
||||
description: Certificate authority used when verifying
|
||||
server certificates.
|
||||
properties:
|
||||
configMap:
|
||||
description: ConfigMap containing data to use for
|
||||
the targets.
|
||||
properties:
|
||||
key:
|
||||
description: The key to select.
|
||||
type: string
|
||||
name:
|
||||
description: 'Name of the referent. More info:
|
||||
https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
|
||||
TODO: Add other useful fields. apiVersion, kind,
|
||||
uid?'
|
||||
type: string
|
||||
optional:
|
||||
description: Specify whether the ConfigMap or
|
||||
its key must be defined
|
||||
type: boolean
|
||||
required:
|
||||
- key
|
||||
type: object
|
||||
x-kubernetes-map-type: atomic
|
||||
secret:
|
||||
description: Secret containing data to use for the
|
||||
targets.
|
||||
properties:
|
||||
key:
|
||||
description: The key of the secret to select from. Must
|
||||
be a valid secret key.
|
||||
type: string
|
||||
name:
|
||||
description: 'Name of the referent. More info:
|
||||
https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
|
||||
TODO: Add other useful fields. apiVersion, kind,
|
||||
uid?'
|
||||
type: string
|
||||
optional:
|
||||
description: Specify whether the Secret or its
|
||||
key must be defined
|
||||
type: boolean
|
||||
required:
|
||||
- key
|
||||
type: object
|
||||
x-kubernetes-map-type: atomic
|
||||
type: object
|
||||
caFile:
|
||||
description: Path to the CA cert in the Prometheus container
|
||||
to use for the targets.
|
||||
type: string
|
||||
cert:
|
||||
description: Client certificate to present when doing
|
||||
client-authentication.
|
||||
properties:
|
||||
configMap:
|
||||
description: ConfigMap containing data to use for
|
||||
the targets.
|
||||
properties:
|
||||
key:
|
||||
description: The key to select.
|
||||
type: string
|
||||
name:
|
||||
description: 'Name of the referent. More info:
|
||||
https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
|
||||
TODO: Add other useful fields. apiVersion, kind,
|
||||
uid?'
|
||||
type: string
|
||||
optional:
|
||||
description: Specify whether the ConfigMap or
|
||||
its key must be defined
|
||||
type: boolean
|
||||
required:
|
||||
- key
|
||||
type: object
|
||||
x-kubernetes-map-type: atomic
|
||||
secret:
|
||||
description: Secret containing data to use for the
|
||||
targets.
|
||||
properties:
|
||||
key:
|
||||
description: The key of the secret to select from. Must
|
||||
be a valid secret key.
|
||||
type: string
|
||||
name:
|
||||
description: 'Name of the referent. More info:
|
||||
https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
|
||||
TODO: Add other useful fields. apiVersion, kind,
|
||||
uid?'
|
||||
type: string
|
||||
optional:
|
||||
description: Specify whether the Secret or its
|
||||
key must be defined
|
||||
type: boolean
|
||||
required:
|
||||
- key
|
||||
type: object
|
||||
x-kubernetes-map-type: atomic
|
||||
type: object
|
||||
certFile:
|
||||
description: Path to the client cert file in the Prometheus
|
||||
container for the targets.
|
||||
type: string
|
||||
insecureSkipVerify:
|
||||
description: Disable target certificate validation.
|
||||
type: boolean
|
||||
keyFile:
|
||||
description: Path to the client key file in the Prometheus
|
||||
container for the targets.
|
||||
type: string
|
||||
keySecret:
|
||||
description: Secret containing the client key file for
|
||||
the targets.
|
||||
properties:
|
||||
key:
|
||||
description: The key of the secret to select from. Must
|
||||
be a valid secret key.
|
||||
type: string
|
||||
name:
|
||||
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
|
||||
TODO: Add other useful fields. apiVersion, kind,
|
||||
uid?'
|
||||
type: string
|
||||
optional:
|
||||
description: Specify whether the Secret or its key
|
||||
must be defined
|
||||
type: boolean
|
||||
required:
|
||||
- key
|
||||
type: object
|
||||
x-kubernetes-map-type: atomic
|
||||
serverName:
|
||||
description: Used to verify the hostname for the targets.
|
||||
type: string
|
||||
type: object
|
||||
type: object
|
||||
type: array
|
||||
jobLabel:
|
||||
description: "JobLabel selects the label from the associated Kubernetes\
|
||||
\ service which will be used as the `job` label for all metrics.\
|
||||
\ \n For example: If in `ServiceMonitor.spec.jobLabel: foo` and\
|
||||
\ in `Service.metadata.labels.foo: bar`, then the `job=\"bar\"\
|
||||
` label is added to all metrics. \n If the value of this field\
|
||||
\ is empty or if the label doesn't exist for the given Service,\
|
||||
\ the `job` label of the metrics defaults to the name of the Kubernetes\
|
||||
\ Service."
|
||||
type: string
|
||||
labelLimit:
|
||||
description: Per-scrape limit on number of labels that will be accepted
|
||||
for a sample. Only valid in Prometheus versions 2.27.0 and newer.
|
||||
format: int64
|
||||
type: integer
|
||||
labelNameLengthLimit:
|
||||
description: Per-scrape limit on length of labels name that will
|
||||
be accepted for a sample. Only valid in Prometheus versions 2.27.0
|
||||
and newer.
|
||||
format: int64
|
||||
type: integer
|
||||
labelValueLengthLimit:
|
||||
description: Per-scrape limit on length of labels value that will
|
||||
be accepted for a sample. Only valid in Prometheus versions 2.27.0
|
||||
and newer.
|
||||
format: int64
|
||||
type: integer
|
||||
namespaceSelector:
|
||||
description: Selector to select which namespaces the Kubernetes
|
||||
Endpoints objects are discovered from.
|
||||
properties:
|
||||
any:
|
||||
description: Boolean describing whether all namespaces are selected
|
||||
in contrast to a list restricting them.
|
||||
type: boolean
|
||||
matchNames:
|
||||
description: List of namespace names to select from.
|
||||
items:
|
||||
type: string
|
||||
type: array
|
||||
type: object
|
||||
podTargetLabels:
|
||||
description: PodTargetLabels transfers labels on the Kubernetes
|
||||
`Pod` onto the created metrics.
|
||||
items:
|
||||
type: string
|
||||
type: array
|
||||
sampleLimit:
|
||||
description: SampleLimit defines per-scrape limit on number of scraped
|
||||
samples that will be accepted.
|
||||
format: int64
|
||||
type: integer
|
||||
selector:
|
||||
description: Selector to select Endpoints objects.
|
||||
properties:
|
||||
matchExpressions:
|
||||
description: matchExpressions is a list of label selector requirements.
|
||||
The requirements are ANDed.
|
||||
items:
|
||||
description: A label selector requirement is a selector that
|
||||
contains values, a key, and an operator that relates the
|
||||
key and values.
|
||||
properties:
|
||||
key:
|
||||
description: key is the label key that the selector applies
|
||||
to.
|
||||
type: string
|
||||
operator:
|
||||
description: operator represents a key's relationship
|
||||
to a set of values. Valid operators are In, NotIn, Exists
|
||||
and DoesNotExist.
|
||||
type: string
|
||||
values:
|
||||
description: values is an array of string values. If the
|
||||
operator is In or NotIn, the values array must be non-empty.
|
||||
If the operator is Exists or DoesNotExist, the values
|
||||
array must be empty. This array is replaced during a
|
||||
strategic merge patch.
|
||||
items:
|
||||
type: string
|
||||
type: array
|
||||
required:
|
||||
- key
|
||||
- operator
|
||||
type: object
|
||||
type: array
|
||||
matchLabels:
|
||||
additionalProperties:
|
||||
type: string
|
||||
description: matchLabels is a map of {key,value} pairs. A single
|
||||
{key,value} in the matchLabels map is equivalent to an element
|
||||
of matchExpressions, whose key field is "key", the operator
|
||||
is "In", and the values array contains only "value". The requirements
|
||||
are ANDed.
|
||||
type: object
|
||||
type: object
|
||||
x-kubernetes-map-type: atomic
|
||||
targetLabels:
|
||||
description: TargetLabels transfers labels from the Kubernetes `Service`
|
||||
onto the created metrics.
|
||||
items:
|
||||
type: string
|
||||
type: array
|
||||
targetLimit:
|
||||
description: TargetLimit defines a limit on the number of scraped
|
||||
targets that will be accepted.
|
||||
format: int64
|
||||
type: integer
|
||||
required:
|
||||
- endpoints
|
||||
- selector
|
||||
type: object
|
||||
required:
|
||||
- spec
|
||||
type: object
|
||||
served: true
|
||||
storage: true
|
||||
File diff suppressed because it is too large
Load Diff
|
|
@ -0,0 +1,38 @@
|
|||
apiVersion: monitoring.coreos.com/v1
|
||||
kind: Alertmanager
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: alert-router
|
||||
app.kubernetes.io/instance: main
|
||||
app.kubernetes.io/name: alertmanager
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 0.26.0
|
||||
name: main
|
||||
namespace: monitoring
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
spec:
|
||||
image: quay.io/prometheus/alertmanager:v0.26.0
|
||||
nodeSelector:
|
||||
kubernetes.io/os: linux
|
||||
podMetadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: alert-router
|
||||
app.kubernetes.io/instance: main
|
||||
app.kubernetes.io/name: alertmanager
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 0.26.0
|
||||
replicas: 3
|
||||
resources:
|
||||
limits:
|
||||
cpu: 100m
|
||||
memory: 100Mi
|
||||
requests:
|
||||
cpu: 4m
|
||||
memory: 100Mi
|
||||
securityContext:
|
||||
fsGroup: 2000
|
||||
runAsNonRoot: true
|
||||
runAsUser: 1000
|
||||
serviceAccountName: alertmanager-main
|
||||
version: 0.26.0
|
||||
|
|
@ -0,0 +1,44 @@
|
|||
apiVersion: networking.k8s.io/v1
|
||||
kind: NetworkPolicy
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: alert-router
|
||||
app.kubernetes.io/instance: main
|
||||
app.kubernetes.io/name: alertmanager
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 0.26.0
|
||||
name: alertmanager-main
|
||||
namespace: monitoring
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
spec:
|
||||
egress:
|
||||
- {}
|
||||
ingress:
|
||||
- from:
|
||||
- podSelector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/name: prometheus
|
||||
ports:
|
||||
- port: 9093
|
||||
protocol: TCP
|
||||
- port: 8080
|
||||
protocol: TCP
|
||||
- from:
|
||||
- podSelector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/name: alertmanager
|
||||
ports:
|
||||
- port: 9094
|
||||
protocol: TCP
|
||||
- port: 9094
|
||||
protocol: UDP
|
||||
podSelector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/component: alert-router
|
||||
app.kubernetes.io/instance: main
|
||||
app.kubernetes.io/name: alertmanager
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
policyTypes:
|
||||
- Egress
|
||||
- Ingress
|
||||
|
|
@ -0,0 +1,21 @@
|
|||
apiVersion: policy/v1
|
||||
kind: PodDisruptionBudget
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: alert-router
|
||||
app.kubernetes.io/instance: main
|
||||
app.kubernetes.io/name: alertmanager
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 0.26.0
|
||||
name: alertmanager-main
|
||||
namespace: monitoring
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
spec:
|
||||
maxUnavailable: 1
|
||||
selector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/component: alert-router
|
||||
app.kubernetes.io/instance: main
|
||||
app.kubernetes.io/name: alertmanager
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
|
|
@ -0,0 +1,140 @@
|
|||
apiVersion: monitoring.coreos.com/v1
|
||||
kind: PrometheusRule
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: alert-router
|
||||
app.kubernetes.io/instance: main
|
||||
app.kubernetes.io/name: alertmanager
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 0.26.0
|
||||
prometheus: k8s
|
||||
role: alert-rules
|
||||
name: alertmanager-main-rules
|
||||
namespace: monitoring
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
spec:
|
||||
groups:
|
||||
- name: alertmanager.rules
|
||||
rules:
|
||||
- alert: AlertmanagerFailedReload
|
||||
annotations:
|
||||
description: Configuration has failed to load for {{ $labels.namespace
|
||||
}}/{{ $labels.pod}}.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/alertmanager/alertmanagerfailedreload
|
||||
summary: Reloading an Alertmanager configuration has failed.
|
||||
expr: '# Without max_over_time, failed scrapes could create false negatives,
|
||||
see
|
||||
|
||||
# https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0
|
||||
for details.
|
||||
|
||||
max_over_time(alertmanager_config_last_reload_successful{job="alertmanager-main",namespace="monitoring"}[5m])
|
||||
== 0
|
||||
|
||||
'
|
||||
for: 10m
|
||||
labels:
|
||||
severity: critical
|
||||
- alert: AlertmanagerMembersInconsistent
|
||||
annotations:
|
||||
description: Alertmanager {{ $labels.namespace }}/{{ $labels.pod}} has
|
||||
only found {{ $value }} members of the {{$labels.job}} cluster.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/alertmanager/alertmanagermembersinconsistent
|
||||
summary: A member of an Alertmanager cluster has not found all other cluster
|
||||
members.
|
||||
expr: "# Without max_over_time, failed scrapes could create false negatives,\
|
||||
\ see\n# https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0\
|
||||
\ for details.\n max_over_time(alertmanager_cluster_members{job=\"alertmanager-main\"\
|
||||
,namespace=\"monitoring\"}[5m])\n< on (namespace,service) group_left\n\
|
||||
\ count by (namespace,service) (max_over_time(alertmanager_cluster_members{job=\"\
|
||||
alertmanager-main\",namespace=\"monitoring\"}[5m]))\n"
|
||||
for: 15m
|
||||
labels:
|
||||
severity: critical
|
||||
- alert: AlertmanagerFailedToSendAlerts
|
||||
annotations:
|
||||
description: Alertmanager {{ $labels.namespace }}/{{ $labels.pod}} failed
|
||||
to send {{ $value | humanizePercentage }} of notifications to {{ $labels.integration
|
||||
}}.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/alertmanager/alertmanagerfailedtosendalerts
|
||||
summary: An Alertmanager instance failed to send notifications.
|
||||
expr: "(\n rate(alertmanager_notifications_failed_total{job=\"alertmanager-main\"\
|
||||
,namespace=\"monitoring\"}[5m])\n/\n rate(alertmanager_notifications_total{job=\"\
|
||||
alertmanager-main\",namespace=\"monitoring\"}[5m])\n)\n> 0.01\n"
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
- alert: AlertmanagerClusterFailedToSendAlerts
|
||||
annotations:
|
||||
description: The minimum notification failure rate to {{ $labels.integration
|
||||
}} sent from any instance in the {{$labels.job}} cluster is {{ $value
|
||||
| humanizePercentage }}.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/alertmanager/alertmanagerclusterfailedtosendalerts
|
||||
summary: All Alertmanager instances in a cluster failed to send notifications
|
||||
to a critical integration.
|
||||
expr: "min by (namespace,service, integration) (\n rate(alertmanager_notifications_failed_total{job=\"\
|
||||
alertmanager-main\",namespace=\"monitoring\", integration=~`.*`}[5m])\n\
|
||||
/\n rate(alertmanager_notifications_total{job=\"alertmanager-main\",namespace=\"\
|
||||
monitoring\", integration=~`.*`}[5m])\n)\n> 0.01\n"
|
||||
for: 5m
|
||||
labels:
|
||||
severity: critical
|
||||
- alert: AlertmanagerClusterFailedToSendAlerts
|
||||
annotations:
|
||||
description: The minimum notification failure rate to {{ $labels.integration
|
||||
}} sent from any instance in the {{$labels.job}} cluster is {{ $value
|
||||
| humanizePercentage }}.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/alertmanager/alertmanagerclusterfailedtosendalerts
|
||||
summary: All Alertmanager instances in a cluster failed to send notifications
|
||||
to a non-critical integration.
|
||||
expr: "min by (namespace,service, integration) (\n rate(alertmanager_notifications_failed_total{job=\"\
|
||||
alertmanager-main\",namespace=\"monitoring\", integration!~`.*`}[5m])\n\
|
||||
/\n rate(alertmanager_notifications_total{job=\"alertmanager-main\",namespace=\"\
|
||||
monitoring\", integration!~`.*`}[5m])\n)\n> 0.01\n"
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
- alert: AlertmanagerConfigInconsistent
|
||||
annotations:
|
||||
description: Alertmanager instances within the {{$labels.job}} cluster
|
||||
have different configurations.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/alertmanager/alertmanagerconfiginconsistent
|
||||
summary: Alertmanager instances within the same cluster have different
|
||||
configurations.
|
||||
expr: "count by (namespace,service) (\n count_values by (namespace,service)\
|
||||
\ (\"config_hash\", alertmanager_config_hash{job=\"alertmanager-main\"\
|
||||
,namespace=\"monitoring\"})\n)\n!= 1\n"
|
||||
for: 20m
|
||||
labels:
|
||||
severity: critical
|
||||
- alert: AlertmanagerClusterDown
|
||||
annotations:
|
||||
description: '{{ $value | humanizePercentage }} of Alertmanager instances
|
||||
within the {{$labels.job}} cluster have been up for less than half of
|
||||
the last 5m.'
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/alertmanager/alertmanagerclusterdown
|
||||
summary: Half or more of the Alertmanager instances within the same cluster
|
||||
are down.
|
||||
expr: "(\n count by (namespace,service) (\n avg_over_time(up{job=\"\
|
||||
alertmanager-main\",namespace=\"monitoring\"}[5m]) < 0.5\n )\n/\n count\
|
||||
\ by (namespace,service) (\n up{job=\"alertmanager-main\",namespace=\"\
|
||||
monitoring\"}\n )\n)\n>= 0.5\n"
|
||||
for: 5m
|
||||
labels:
|
||||
severity: critical
|
||||
- alert: AlertmanagerClusterCrashlooping
|
||||
annotations:
|
||||
description: '{{ $value | humanizePercentage }} of Alertmanager instances
|
||||
within the {{$labels.job}} cluster have restarted at least 5 times in
|
||||
the last 10m.'
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/alertmanager/alertmanagerclustercrashlooping
|
||||
summary: Half or more of the Alertmanager instances within the same cluster
|
||||
are crashlooping.
|
||||
expr: "(\n count by (namespace,service) (\n changes(process_start_time_seconds{job=\"\
|
||||
alertmanager-main\",namespace=\"monitoring\"}[10m]) > 4\n )\n/\n count\
|
||||
\ by (namespace,service) (\n up{job=\"alertmanager-main\",namespace=\"\
|
||||
monitoring\"}\n )\n)\n>= 0.5\n"
|
||||
for: 5m
|
||||
labels:
|
||||
severity: critical
|
||||
|
|
@ -0,0 +1,27 @@
|
|||
apiVersion: v1
|
||||
kind: Service
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: alert-router
|
||||
app.kubernetes.io/instance: main
|
||||
app.kubernetes.io/name: alertmanager
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 0.26.0
|
||||
name: alertmanager-main
|
||||
namespace: monitoring
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
spec:
|
||||
ports:
|
||||
- name: web
|
||||
port: 9093
|
||||
targetPort: web
|
||||
- name: reloader-web
|
||||
port: 8080
|
||||
targetPort: reloader-web
|
||||
selector:
|
||||
app.kubernetes.io/component: alert-router
|
||||
app.kubernetes.io/instance: main
|
||||
app.kubernetes.io/name: alertmanager
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
sessionAffinity: ClientIP
|
||||
|
|
@ -0,0 +1,14 @@
|
|||
apiVersion: v1
|
||||
automountServiceAccountToken: false
|
||||
kind: ServiceAccount
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: alert-router
|
||||
app.kubernetes.io/instance: main
|
||||
app.kubernetes.io/name: alertmanager
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 0.26.0
|
||||
name: alertmanager-main
|
||||
namespace: monitoring
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
|
|
@ -0,0 +1,25 @@
|
|||
apiVersion: monitoring.coreos.com/v1
|
||||
kind: ServiceMonitor
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: alert-router
|
||||
app.kubernetes.io/instance: main
|
||||
app.kubernetes.io/name: alertmanager
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 0.26.0
|
||||
name: alertmanager-main
|
||||
namespace: monitoring
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
spec:
|
||||
endpoints:
|
||||
- interval: 30s
|
||||
port: web
|
||||
- interval: 30s
|
||||
port: reloader-web
|
||||
selector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/component: alert-router
|
||||
app.kubernetes.io/instance: main
|
||||
app.kubernetes.io/name: alertmanager
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
|
|
@ -0,0 +1,19 @@
|
|||
apiVersion: rbac.authorization.k8s.io/v1
|
||||
kind: ClusterRole
|
||||
metadata:
|
||||
name: blackbox-exporter
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
rules:
|
||||
- apiGroups:
|
||||
- authentication.k8s.io
|
||||
resources:
|
||||
- tokenreviews
|
||||
verbs:
|
||||
- create
|
||||
- apiGroups:
|
||||
- authorization.k8s.io
|
||||
resources:
|
||||
- subjectaccessreviews
|
||||
verbs:
|
||||
- create
|
||||
|
|
@ -0,0 +1,19 @@
|
|||
apiVersion: rbac.authorization.k8s.io/v1
|
||||
kind: ClusterRoleBinding
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: exporter
|
||||
app.kubernetes.io/name: blackbox-exporter
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 0.24.0
|
||||
name: blackbox-exporter
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
roleRef:
|
||||
apiGroup: rbac.authorization.k8s.io
|
||||
kind: ClusterRole
|
||||
name: blackbox-exporter
|
||||
subjects:
|
||||
- kind: ServiceAccount
|
||||
name: blackbox-exporter
|
||||
namespace: monitoring
|
||||
|
|
@ -0,0 +1,27 @@
|
|||
apiVersion: v1
|
||||
data:
|
||||
config.yml: "\"modules\":\n \"http_2xx\":\n \"http\":\n \"preferred_ip_protocol\"\
|
||||
: \"ip4\"\n \"prober\": \"http\"\n \"http_post_2xx\":\n \"http\":\n \
|
||||
\ \"method\": \"POST\"\n \"preferred_ip_protocol\": \"ip4\"\n \"prober\"\
|
||||
: \"http\"\n \"irc_banner\":\n \"prober\": \"tcp\"\n \"tcp\":\n \"\
|
||||
preferred_ip_protocol\": \"ip4\"\n \"query_response\":\n - \"send\"\
|
||||
: \"NICK prober\"\n - \"send\": \"USER prober prober prober :prober\"\n \
|
||||
\ - \"expect\": \"PING :([^ ]+)\"\n \"send\": \"PONG ${1}\"\n \
|
||||
\ - \"expect\": \"^:[^ ]+ 001\"\n \"pop3s_banner\":\n \"prober\": \"tcp\"\n\
|
||||
\ \"tcp\":\n \"preferred_ip_protocol\": \"ip4\"\n \"query_response\"\
|
||||
:\n - \"expect\": \"^+OK\"\n \"tls\": true\n \"tls_config\":\n\
|
||||
\ \"insecure_skip_verify\": false\n \"ssh_banner\":\n \"prober\": \"\
|
||||
tcp\"\n \"tcp\":\n \"preferred_ip_protocol\": \"ip4\"\n \"query_response\"\
|
||||
:\n - \"expect\": \"^SSH-2.0-\"\n \"tcp_connect\":\n \"prober\": \"tcp\"\
|
||||
\n \"tcp\":\n \"preferred_ip_protocol\": \"ip4\""
|
||||
kind: ConfigMap
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: exporter
|
||||
app.kubernetes.io/name: blackbox-exporter
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 0.24.0
|
||||
name: blackbox-exporter-configuration
|
||||
namespace: monitoring
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
|
|
@ -0,0 +1,116 @@
|
|||
apiVersion: apps/v1
|
||||
kind: Deployment
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: exporter
|
||||
app.kubernetes.io/name: blackbox-exporter
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 0.24.0
|
||||
name: blackbox-exporter
|
||||
namespace: monitoring
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
spec:
|
||||
replicas: 1
|
||||
selector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/component: exporter
|
||||
app.kubernetes.io/name: blackbox-exporter
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
template:
|
||||
metadata:
|
||||
annotations:
|
||||
kubectl.kubernetes.io/default-container: blackbox-exporter
|
||||
labels:
|
||||
app.kubernetes.io/component: exporter
|
||||
app.kubernetes.io/name: blackbox-exporter
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 0.24.0
|
||||
spec:
|
||||
automountServiceAccountToken: true
|
||||
containers:
|
||||
- args:
|
||||
- --config.file=/etc/blackbox_exporter/config.yml
|
||||
- --web.listen-address=:19115
|
||||
image: quay.io/prometheus/blackbox-exporter:v0.24.0
|
||||
name: blackbox-exporter
|
||||
ports:
|
||||
- containerPort: 19115
|
||||
name: http
|
||||
resources:
|
||||
limits:
|
||||
cpu: 20m
|
||||
memory: 40Mi
|
||||
requests:
|
||||
cpu: 10m
|
||||
memory: 20Mi
|
||||
securityContext:
|
||||
allowPrivilegeEscalation: false
|
||||
capabilities:
|
||||
drop:
|
||||
- ALL
|
||||
readOnlyRootFilesystem: true
|
||||
runAsNonRoot: true
|
||||
runAsUser: 65534
|
||||
volumeMounts:
|
||||
- mountPath: /etc/blackbox_exporter/
|
||||
name: config
|
||||
readOnly: true
|
||||
- args:
|
||||
- --webhook-url=http://localhost:19115/-/reload
|
||||
- --volume-dir=/etc/blackbox_exporter/
|
||||
image: jimmidyson/configmap-reload:v0.5.0
|
||||
name: module-configmap-reloader
|
||||
resources:
|
||||
limits:
|
||||
cpu: 20m
|
||||
memory: 40Mi
|
||||
requests:
|
||||
cpu: 10m
|
||||
memory: 20Mi
|
||||
securityContext:
|
||||
allowPrivilegeEscalation: false
|
||||
capabilities:
|
||||
drop:
|
||||
- ALL
|
||||
readOnlyRootFilesystem: true
|
||||
runAsNonRoot: true
|
||||
runAsUser: 65534
|
||||
terminationMessagePath: /dev/termination-log
|
||||
terminationMessagePolicy: FallbackToLogsOnError
|
||||
volumeMounts:
|
||||
- mountPath: /etc/blackbox_exporter/
|
||||
name: config
|
||||
readOnly: true
|
||||
- args:
|
||||
- --secure-listen-address=:9115
|
||||
- --tls-cipher-suites=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256,TLS_ECDHE_ECDSA_WITH_AES_128_GCM_SHA256,TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384,TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384,TLS_ECDHE_RSA_WITH_CHACHA20_POLY1305,TLS_ECDHE_ECDSA_WITH_CHACHA20_POLY1305
|
||||
- --upstream=http://127.0.0.1:19115/
|
||||
image: quay.io/brancz/kube-rbac-proxy:v0.14.2
|
||||
name: kube-rbac-proxy
|
||||
ports:
|
||||
- containerPort: 9115
|
||||
name: https
|
||||
resources:
|
||||
limits:
|
||||
cpu: 20m
|
||||
memory: 40Mi
|
||||
requests:
|
||||
cpu: 10m
|
||||
memory: 20Mi
|
||||
securityContext:
|
||||
allowPrivilegeEscalation: false
|
||||
capabilities:
|
||||
drop:
|
||||
- ALL
|
||||
readOnlyRootFilesystem: true
|
||||
runAsGroup: 65532
|
||||
runAsNonRoot: true
|
||||
runAsUser: 65532
|
||||
nodeSelector:
|
||||
kubernetes.io/os: linux
|
||||
serviceAccountName: blackbox-exporter
|
||||
volumes:
|
||||
- configMap:
|
||||
name: blackbox-exporter-configuration
|
||||
name: config
|
||||
|
|
@ -0,0 +1,33 @@
|
|||
apiVersion: networking.k8s.io/v1
|
||||
kind: NetworkPolicy
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: exporter
|
||||
app.kubernetes.io/name: blackbox-exporter
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 0.24.0
|
||||
name: blackbox-exporter
|
||||
namespace: monitoring
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
spec:
|
||||
egress:
|
||||
- {}
|
||||
ingress:
|
||||
- from:
|
||||
- podSelector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/name: prometheus
|
||||
ports:
|
||||
- port: 9115
|
||||
protocol: TCP
|
||||
- port: 19115
|
||||
protocol: TCP
|
||||
podSelector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/component: exporter
|
||||
app.kubernetes.io/name: blackbox-exporter
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
policyTypes:
|
||||
- Egress
|
||||
- Ingress
|
||||
|
|
@ -0,0 +1,24 @@
|
|||
apiVersion: v1
|
||||
kind: Service
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: exporter
|
||||
app.kubernetes.io/name: blackbox-exporter
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 0.24.0
|
||||
name: blackbox-exporter
|
||||
namespace: monitoring
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
spec:
|
||||
ports:
|
||||
- name: https
|
||||
port: 9115
|
||||
targetPort: https
|
||||
- name: probe
|
||||
port: 19115
|
||||
targetPort: http
|
||||
selector:
|
||||
app.kubernetes.io/component: exporter
|
||||
app.kubernetes.io/name: blackbox-exporter
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
|
|
@ -0,0 +1,13 @@
|
|||
apiVersion: v1
|
||||
automountServiceAccountToken: false
|
||||
kind: ServiceAccount
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: exporter
|
||||
app.kubernetes.io/name: blackbox-exporter
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 0.24.0
|
||||
name: blackbox-exporter
|
||||
namespace: monitoring
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
|
|
@ -0,0 +1,26 @@
|
|||
apiVersion: monitoring.coreos.com/v1
|
||||
kind: ServiceMonitor
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: exporter
|
||||
app.kubernetes.io/name: blackbox-exporter
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 0.24.0
|
||||
name: blackbox-exporter
|
||||
namespace: monitoring
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
spec:
|
||||
endpoints:
|
||||
- bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token
|
||||
interval: 30s
|
||||
path: /metrics
|
||||
port: https
|
||||
scheme: https
|
||||
tlsConfig:
|
||||
insecureSkipVerify: true
|
||||
selector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/component: exporter
|
||||
app.kubernetes.io/name: blackbox-exporter
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
|
|
@ -0,0 +1,19 @@
|
|||
apiVersion: v1
|
||||
kind: Secret
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: grafana
|
||||
app.kubernetes.io/name: grafana
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 9.5.3
|
||||
name: grafana-config
|
||||
namespace: monitoring
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
stringData:
|
||||
grafana.ini: '[date_formats]
|
||||
|
||||
default_timezone = UTC
|
||||
|
||||
'
|
||||
type: Opaque
|
||||
|
|
@ -0,0 +1,19 @@
|
|||
apiVersion: v1
|
||||
kind: Secret
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: grafana
|
||||
app.kubernetes.io/name: grafana
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 9.5.3
|
||||
name: grafana-datasources
|
||||
namespace: monitoring
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
stringData:
|
||||
datasources.yaml: "{\n \"apiVersion\": 1,\n \"datasources\": [\n {\n\
|
||||
\ \"access\": \"proxy\",\n \"editable\": false,\n \
|
||||
\ \"name\": \"prometheus\",\n \"orgId\": 1,\n \"type\"\
|
||||
: \"prometheus\",\n \"url\": \"http://prometheus-k8s.monitoring.svc:9090\"\
|
||||
,\n \"version\": 1\n }\n ]\n}"
|
||||
type: Opaque
|
||||
File diff suppressed because it is too large
Load Diff
|
|
@ -0,0 +1,18 @@
|
|||
apiVersion: v1
|
||||
data:
|
||||
dashboards.yaml: "{\n \"apiVersion\": 1,\n \"providers\": [\n {\n \
|
||||
\ \"folder\": \"Default\",\n \"folderUid\": \"\",\n \
|
||||
\ \"name\": \"0\",\n \"options\": {\n \"path\"\
|
||||
: \"/grafana-dashboard-definitions/0\"\n },\n \"orgId\"\
|
||||
: 1,\n \"type\": \"file\"\n }\n ]\n}"
|
||||
kind: ConfigMap
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: grafana
|
||||
app.kubernetes.io/name: grafana
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 9.5.3
|
||||
name: grafana-dashboards
|
||||
namespace: monitoring
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
|
|
@ -0,0 +1,252 @@
|
|||
apiVersion: apps/v1
|
||||
kind: Deployment
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: grafana
|
||||
app.kubernetes.io/name: grafana
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 9.5.3
|
||||
name: grafana
|
||||
namespace: monitoring
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
spec:
|
||||
replicas: 1
|
||||
selector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/component: grafana
|
||||
app.kubernetes.io/name: grafana
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
template:
|
||||
metadata:
|
||||
annotations:
|
||||
checksum/grafana-config: 5c598ba58d9b65011bdbb3864138399a
|
||||
checksum/grafana-dashboardproviders: c9c1743868aa1c3dab60d2c402e2dcf0
|
||||
checksum/grafana-datasources: 5ef0e6acaa5b4e8603740fbad440717d
|
||||
labels:
|
||||
app.kubernetes.io/component: grafana
|
||||
app.kubernetes.io/name: grafana
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 9.5.3
|
||||
spec:
|
||||
automountServiceAccountToken: false
|
||||
containers:
|
||||
- env: []
|
||||
image: grafana/grafana:9.5.3
|
||||
name: grafana
|
||||
ports:
|
||||
- containerPort: 3000
|
||||
name: http
|
||||
readinessProbe:
|
||||
httpGet:
|
||||
path: /api/health
|
||||
port: http
|
||||
resources:
|
||||
limits:
|
||||
cpu: 200m
|
||||
memory: 200Mi
|
||||
requests:
|
||||
cpu: 100m
|
||||
memory: 100Mi
|
||||
securityContext:
|
||||
allowPrivilegeEscalation: false
|
||||
capabilities:
|
||||
drop:
|
||||
- ALL
|
||||
readOnlyRootFilesystem: true
|
||||
seccompProfile:
|
||||
type: RuntimeDefault
|
||||
volumeMounts:
|
||||
- mountPath: /var/lib/grafana
|
||||
name: grafana-storage
|
||||
readOnly: false
|
||||
- mountPath: /etc/grafana/provisioning/datasources
|
||||
name: grafana-datasources
|
||||
readOnly: false
|
||||
- mountPath: /etc/grafana/provisioning/dashboards
|
||||
name: grafana-dashboards
|
||||
readOnly: false
|
||||
- mountPath: /tmp
|
||||
name: tmp-plugins
|
||||
readOnly: false
|
||||
- mountPath: /grafana-dashboard-definitions/0/alertmanager-overview
|
||||
name: grafana-dashboard-alertmanager-overview
|
||||
readOnly: false
|
||||
- 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
|
||||
- mountPath: /grafana-dashboard-definitions/0/grafana-overview
|
||||
name: grafana-dashboard-grafana-overview
|
||||
readOnly: false
|
||||
- mountPath: /grafana-dashboard-definitions/0/k8s-resources-cluster
|
||||
name: grafana-dashboard-k8s-resources-cluster
|
||||
readOnly: false
|
||||
- mountPath: /grafana-dashboard-definitions/0/k8s-resources-multicluster
|
||||
name: grafana-dashboard-k8s-resources-multicluster
|
||||
readOnly: false
|
||||
- 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
|
||||
- mountPath: /grafana-dashboard-definitions/0/k8s-resources-workload
|
||||
name: grafana-dashboard-k8s-resources-workload
|
||||
readOnly: false
|
||||
- mountPath: /grafana-dashboard-definitions/0/k8s-resources-workloads-namespace
|
||||
name: grafana-dashboard-k8s-resources-workloads-namespace
|
||||
readOnly: false
|
||||
- mountPath: /grafana-dashboard-definitions/0/kubelet
|
||||
name: grafana-dashboard-kubelet
|
||||
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
|
||||
- mountPath: /grafana-dashboard-definitions/0/node-rsrc-use
|
||||
name: grafana-dashboard-node-rsrc-use
|
||||
readOnly: false
|
||||
- mountPath: /grafana-dashboard-definitions/0/nodes-darwin
|
||||
name: grafana-dashboard-nodes-darwin
|
||||
readOnly: false
|
||||
- mountPath: /grafana-dashboard-definitions/0/nodes
|
||||
name: grafana-dashboard-nodes
|
||||
readOnly: false
|
||||
- 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/prometheus-remote-write
|
||||
name: grafana-dashboard-prometheus-remote-write
|
||||
readOnly: false
|
||||
- mountPath: /grafana-dashboard-definitions/0/prometheus
|
||||
name: grafana-dashboard-prometheus
|
||||
readOnly: false
|
||||
- mountPath: /grafana-dashboard-definitions/0/proxy
|
||||
name: grafana-dashboard-proxy
|
||||
readOnly: false
|
||||
- mountPath: /grafana-dashboard-definitions/0/scheduler
|
||||
name: grafana-dashboard-scheduler
|
||||
readOnly: false
|
||||
- mountPath: /grafana-dashboard-definitions/0/workload-total
|
||||
name: grafana-dashboard-workload-total
|
||||
readOnly: false
|
||||
- mountPath: /etc/grafana
|
||||
name: grafana-config
|
||||
readOnly: false
|
||||
nodeSelector:
|
||||
kubernetes.io/os: linux
|
||||
securityContext:
|
||||
fsGroup: 65534
|
||||
runAsNonRoot: true
|
||||
runAsUser: 65534
|
||||
serviceAccountName: grafana
|
||||
volumes:
|
||||
- emptyDir: {}
|
||||
name: grafana-storage
|
||||
- name: grafana-datasources
|
||||
secret:
|
||||
secretName: grafana-datasources
|
||||
- configMap:
|
||||
name: grafana-dashboards
|
||||
name: grafana-dashboards
|
||||
- emptyDir:
|
||||
medium: Memory
|
||||
name: tmp-plugins
|
||||
- configMap:
|
||||
name: grafana-dashboard-alertmanager-overview
|
||||
name: grafana-dashboard-alertmanager-overview
|
||||
- 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
|
||||
- configMap:
|
||||
name: grafana-dashboard-grafana-overview
|
||||
name: grafana-dashboard-grafana-overview
|
||||
- configMap:
|
||||
name: grafana-dashboard-k8s-resources-cluster
|
||||
name: grafana-dashboard-k8s-resources-cluster
|
||||
- configMap:
|
||||
name: grafana-dashboard-k8s-resources-multicluster
|
||||
name: grafana-dashboard-k8s-resources-multicluster
|
||||
- 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
|
||||
- configMap:
|
||||
name: grafana-dashboard-k8s-resources-workload
|
||||
name: grafana-dashboard-k8s-resources-workload
|
||||
- configMap:
|
||||
name: grafana-dashboard-k8s-resources-workloads-namespace
|
||||
name: grafana-dashboard-k8s-resources-workloads-namespace
|
||||
- configMap:
|
||||
name: grafana-dashboard-kubelet
|
||||
name: grafana-dashboard-kubelet
|
||||
- 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
|
||||
- configMap:
|
||||
name: grafana-dashboard-node-rsrc-use
|
||||
name: grafana-dashboard-node-rsrc-use
|
||||
- configMap:
|
||||
name: grafana-dashboard-nodes-darwin
|
||||
name: grafana-dashboard-nodes-darwin
|
||||
- configMap:
|
||||
name: grafana-dashboard-nodes
|
||||
name: grafana-dashboard-nodes
|
||||
- configMap:
|
||||
name: grafana-dashboard-persistentvolumesusage
|
||||
name: grafana-dashboard-persistentvolumesusage
|
||||
- configMap:
|
||||
name: grafana-dashboard-pod-total
|
||||
name: grafana-dashboard-pod-total
|
||||
- configMap:
|
||||
name: grafana-dashboard-prometheus-remote-write
|
||||
name: grafana-dashboard-prometheus-remote-write
|
||||
- configMap:
|
||||
name: grafana-dashboard-prometheus
|
||||
name: grafana-dashboard-prometheus
|
||||
- configMap:
|
||||
name: grafana-dashboard-proxy
|
||||
name: grafana-dashboard-proxy
|
||||
- configMap:
|
||||
name: grafana-dashboard-scheduler
|
||||
name: grafana-dashboard-scheduler
|
||||
- configMap:
|
||||
name: grafana-dashboard-workload-total
|
||||
name: grafana-dashboard-workload-total
|
||||
- name: grafana-config
|
||||
secret:
|
||||
secretName: grafana-config
|
||||
|
|
@ -0,0 +1,31 @@
|
|||
apiVersion: networking.k8s.io/v1
|
||||
kind: NetworkPolicy
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: grafana
|
||||
app.kubernetes.io/name: grafana
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 9.5.3
|
||||
name: grafana
|
||||
namespace: monitoring
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
spec:
|
||||
egress:
|
||||
- {}
|
||||
ingress:
|
||||
- from:
|
||||
- podSelector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/name: prometheus
|
||||
ports:
|
||||
- port: 3000
|
||||
protocol: TCP
|
||||
podSelector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/component: grafana
|
||||
app.kubernetes.io/name: grafana
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
policyTypes:
|
||||
- Egress
|
||||
- Ingress
|
||||
|
|
@ -0,0 +1,42 @@
|
|||
apiVersion: monitoring.coreos.com/v1
|
||||
kind: PrometheusRule
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: grafana
|
||||
app.kubernetes.io/name: grafana
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 9.5.3
|
||||
prometheus: k8s
|
||||
role: alert-rules
|
||||
name: grafana-rules
|
||||
namespace: monitoring
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
spec:
|
||||
groups:
|
||||
- name: GrafanaAlerts
|
||||
rules:
|
||||
- alert: GrafanaRequestsFailing
|
||||
annotations:
|
||||
message: '{{ $labels.namespace }}/{{ $labels.job }}/{{ $labels.handler
|
||||
}} is experiencing {{ $value | humanize }}% errors'
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/grafana/grafanarequestsfailing
|
||||
expr: '100 * sum without (status_code) (namespace_job_handler_statuscode:grafana_http_request_duration_seconds_count:rate5m{handler!~"/api/datasources/proxy/:id.*|/api/ds/query|/api/tsdb/query",
|
||||
status_code=~"5.."})
|
||||
|
||||
/
|
||||
|
||||
sum without (status_code) (namespace_job_handler_statuscode:grafana_http_request_duration_seconds_count:rate5m{handler!~"/api/datasources/proxy/:id.*|/api/ds/query|/api/tsdb/query"})
|
||||
|
||||
> 50
|
||||
|
||||
'
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
- name: grafana_rules
|
||||
rules:
|
||||
- expr: 'sum by (namespace, job, handler, status_code) (rate(grafana_http_request_duration_seconds_count[5m]))
|
||||
|
||||
'
|
||||
record: namespace_job_handler_statuscode:grafana_http_request_duration_seconds_count:rate5m
|
||||
|
|
@ -0,0 +1,21 @@
|
|||
apiVersion: v1
|
||||
kind: Service
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: grafana
|
||||
app.kubernetes.io/name: grafana
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 9.5.3
|
||||
name: grafana
|
||||
namespace: monitoring
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
spec:
|
||||
ports:
|
||||
- name: http
|
||||
port: 3000
|
||||
targetPort: http
|
||||
selector:
|
||||
app.kubernetes.io/component: grafana
|
||||
app.kubernetes.io/name: grafana
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
|
|
@ -0,0 +1,13 @@
|
|||
apiVersion: v1
|
||||
automountServiceAccountToken: false
|
||||
kind: ServiceAccount
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: grafana
|
||||
app.kubernetes.io/name: grafana
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 9.5.3
|
||||
name: grafana
|
||||
namespace: monitoring
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
|
|
@ -0,0 +1,19 @@
|
|||
apiVersion: monitoring.coreos.com/v1
|
||||
kind: ServiceMonitor
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: grafana
|
||||
app.kubernetes.io/name: grafana
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 9.5.3
|
||||
name: grafana
|
||||
namespace: monitoring
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
spec:
|
||||
endpoints:
|
||||
- interval: 15s
|
||||
port: http
|
||||
selector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/name: grafana
|
||||
|
|
@ -0,0 +1,117 @@
|
|||
apiVersion: monitoring.coreos.com/v1
|
||||
kind: PrometheusRule
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: exporter
|
||||
app.kubernetes.io/name: kube-prometheus
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
prometheus: k8s
|
||||
role: alert-rules
|
||||
name: kube-prometheus-rules
|
||||
namespace: monitoring
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
spec:
|
||||
groups:
|
||||
- name: general.rules
|
||||
rules:
|
||||
- alert: TargetDown
|
||||
annotations:
|
||||
description: '{{ printf "%.4g" $value }}% of the {{ $labels.job }}/{{
|
||||
$labels.service }} targets in {{ $labels.namespace }} namespace are
|
||||
down.'
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/general/targetdown
|
||||
summary: One or more targets are unreachable.
|
||||
expr: 100 * (count(up == 0) BY (cluster, job, namespace, service) / count(up)
|
||||
BY (cluster, job, namespace, service)) > 10
|
||||
for: 10m
|
||||
labels:
|
||||
severity: warning
|
||||
- alert: Watchdog
|
||||
annotations:
|
||||
description: 'This is an alert meant to ensure that the entire alerting
|
||||
pipeline is functional.
|
||||
|
||||
This alert is always firing, therefore it should always be firing in
|
||||
Alertmanager
|
||||
|
||||
and always fire against a receiver. There are integrations with various
|
||||
notification
|
||||
|
||||
mechanisms that send a notification when this alert is not firing. For
|
||||
example the
|
||||
|
||||
"DeadMansSnitch" integration in PagerDuty.
|
||||
|
||||
'
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/general/watchdog
|
||||
summary: An alert that should always be firing to certify that Alertmanager
|
||||
is working properly.
|
||||
expr: vector(1)
|
||||
labels:
|
||||
severity: none
|
||||
- alert: InfoInhibitor
|
||||
annotations:
|
||||
description: 'This is an alert that is used to inhibit info alerts.
|
||||
|
||||
By themselves, the info-level alerts are sometimes very noisy, but they
|
||||
are relevant when combined with
|
||||
|
||||
other alerts.
|
||||
|
||||
This alert fires whenever there''s a severity="info" alert, and stops
|
||||
firing when another alert with a
|
||||
|
||||
severity of ''warning'' or ''critical'' starts firing on the same namespace.
|
||||
|
||||
This alert should be routed to a null receiver and configured to inhibit
|
||||
alerts with severity="info".
|
||||
|
||||
'
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/general/infoinhibitor
|
||||
summary: Info-level alert inhibition.
|
||||
expr: ALERTS{severity = "info"} == 1 unless on(namespace) ALERTS{alertname
|
||||
!= "InfoInhibitor", severity =~ "warning|critical", alertstate="firing"}
|
||||
== 1
|
||||
labels:
|
||||
severity: none
|
||||
- name: node-network
|
||||
rules:
|
||||
- alert: NodeNetworkInterfaceFlapping
|
||||
annotations:
|
||||
description: Network interface "{{ $labels.device }}" changing its up
|
||||
status often on node-exporter {{ $labels.namespace }}/{{ $labels.pod
|
||||
}}
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/general/nodenetworkinterfaceflapping
|
||||
summary: Network interface is often changing its status
|
||||
expr: 'changes(node_network_up{job="node-exporter",device!~"veth.+"}[2m])
|
||||
> 2
|
||||
|
||||
'
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
- name: kube-prometheus-node-recording.rules
|
||||
rules:
|
||||
- expr: sum(rate(node_cpu_seconds_total{mode!="idle",mode!="iowait",mode!="steal"}[3m]))
|
||||
BY (instance)
|
||||
record: instance:node_cpu:rate:sum
|
||||
- expr: sum(rate(node_network_receive_bytes_total[3m])) BY (instance)
|
||||
record: instance:node_network_receive_bytes:rate:sum
|
||||
- expr: sum(rate(node_network_transmit_bytes_total[3m])) BY (instance)
|
||||
record: instance:node_network_transmit_bytes:rate:sum
|
||||
- expr: sum(rate(node_cpu_seconds_total{mode!="idle",mode!="iowait",mode!="steal"}[5m]))
|
||||
WITHOUT (cpu, mode) / ON(instance) GROUP_LEFT() count(sum(node_cpu_seconds_total)
|
||||
BY (instance, cpu)) BY (instance)
|
||||
record: instance:node_cpu:ratio
|
||||
- expr: sum(rate(node_cpu_seconds_total{mode!="idle",mode!="iowait",mode!="steal"}[5m]))
|
||||
record: cluster:node_cpu:sum_rate5m
|
||||
- expr: cluster:node_cpu:sum_rate5m / count(sum(node_cpu_seconds_total) BY
|
||||
(instance, cpu))
|
||||
record: cluster:node_cpu:ratio
|
||||
- name: kube-prometheus-general.rules
|
||||
rules:
|
||||
- expr: count without(instance, pod, node) (up == 1)
|
||||
record: count:up1
|
||||
- expr: count without(instance, pod, node) (up == 0)
|
||||
record: count:up0
|
||||
|
|
@ -0,0 +1,131 @@
|
|||
apiVersion: rbac.authorization.k8s.io/v1
|
||||
kind: ClusterRole
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: exporter
|
||||
app.kubernetes.io/name: kube-state-metrics
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 2.9.2
|
||||
name: kube-state-metrics
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
rules:
|
||||
- apiGroups:
|
||||
- ''
|
||||
resources:
|
||||
- configmaps
|
||||
- secrets
|
||||
- nodes
|
||||
- pods
|
||||
- services
|
||||
- serviceaccounts
|
||||
- resourcequotas
|
||||
- replicationcontrollers
|
||||
- limitranges
|
||||
- persistentvolumeclaims
|
||||
- persistentvolumes
|
||||
- namespaces
|
||||
- endpoints
|
||||
verbs:
|
||||
- list
|
||||
- watch
|
||||
- apiGroups:
|
||||
- apps
|
||||
resources:
|
||||
- statefulsets
|
||||
- daemonsets
|
||||
- deployments
|
||||
- replicasets
|
||||
verbs:
|
||||
- list
|
||||
- watch
|
||||
- apiGroups:
|
||||
- batch
|
||||
resources:
|
||||
- cronjobs
|
||||
- jobs
|
||||
verbs:
|
||||
- list
|
||||
- watch
|
||||
- apiGroups:
|
||||
- autoscaling
|
||||
resources:
|
||||
- horizontalpodautoscalers
|
||||
verbs:
|
||||
- list
|
||||
- watch
|
||||
- apiGroups:
|
||||
- authentication.k8s.io
|
||||
resources:
|
||||
- tokenreviews
|
||||
verbs:
|
||||
- create
|
||||
- apiGroups:
|
||||
- authorization.k8s.io
|
||||
resources:
|
||||
- subjectaccessreviews
|
||||
verbs:
|
||||
- create
|
||||
- apiGroups:
|
||||
- policy
|
||||
resources:
|
||||
- poddisruptionbudgets
|
||||
verbs:
|
||||
- list
|
||||
- watch
|
||||
- apiGroups:
|
||||
- certificates.k8s.io
|
||||
resources:
|
||||
- certificatesigningrequests
|
||||
verbs:
|
||||
- list
|
||||
- watch
|
||||
- apiGroups:
|
||||
- discovery.k8s.io
|
||||
resources:
|
||||
- endpointslices
|
||||
verbs:
|
||||
- list
|
||||
- watch
|
||||
- apiGroups:
|
||||
- storage.k8s.io
|
||||
resources:
|
||||
- storageclasses
|
||||
- volumeattachments
|
||||
verbs:
|
||||
- list
|
||||
- watch
|
||||
- apiGroups:
|
||||
- admissionregistration.k8s.io
|
||||
resources:
|
||||
- mutatingwebhookconfigurations
|
||||
- validatingwebhookconfigurations
|
||||
verbs:
|
||||
- list
|
||||
- watch
|
||||
- apiGroups:
|
||||
- networking.k8s.io
|
||||
resources:
|
||||
- networkpolicies
|
||||
- ingressclasses
|
||||
- ingresses
|
||||
verbs:
|
||||
- list
|
||||
- watch
|
||||
- apiGroups:
|
||||
- coordination.k8s.io
|
||||
resources:
|
||||
- leases
|
||||
verbs:
|
||||
- list
|
||||
- watch
|
||||
- apiGroups:
|
||||
- rbac.authorization.k8s.io
|
||||
resources:
|
||||
- clusterrolebindings
|
||||
- clusterroles
|
||||
- rolebindings
|
||||
- roles
|
||||
verbs:
|
||||
- list
|
||||
- watch
|
||||
|
|
@ -0,0 +1,19 @@
|
|||
apiVersion: rbac.authorization.k8s.io/v1
|
||||
kind: ClusterRoleBinding
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: exporter
|
||||
app.kubernetes.io/name: kube-state-metrics
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 2.9.2
|
||||
name: kube-state-metrics
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
roleRef:
|
||||
apiGroup: rbac.authorization.k8s.io
|
||||
kind: ClusterRole
|
||||
name: kube-state-metrics
|
||||
subjects:
|
||||
- kind: ServiceAccount
|
||||
name: kube-state-metrics
|
||||
namespace: monitoring
|
||||
|
|
@ -0,0 +1,108 @@
|
|||
apiVersion: apps/v1
|
||||
kind: Deployment
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: exporter
|
||||
app.kubernetes.io/name: kube-state-metrics
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 2.9.2
|
||||
name: kube-state-metrics
|
||||
namespace: monitoring
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
spec:
|
||||
replicas: 1
|
||||
selector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/component: exporter
|
||||
app.kubernetes.io/name: kube-state-metrics
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
template:
|
||||
metadata:
|
||||
annotations:
|
||||
kubectl.kubernetes.io/default-container: kube-state-metrics
|
||||
labels:
|
||||
app.kubernetes.io/component: exporter
|
||||
app.kubernetes.io/name: kube-state-metrics
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 2.9.2
|
||||
spec:
|
||||
automountServiceAccountToken: true
|
||||
containers:
|
||||
- args:
|
||||
- --host=127.0.0.1
|
||||
- --port=8081
|
||||
- --telemetry-host=127.0.0.1
|
||||
- --telemetry-port=8082
|
||||
image: registry.k8s.io/kube-state-metrics/kube-state-metrics:v2.9.2
|
||||
name: kube-state-metrics
|
||||
resources:
|
||||
limits:
|
||||
cpu: 100m
|
||||
memory: 250Mi
|
||||
requests:
|
||||
cpu: 10m
|
||||
memory: 190Mi
|
||||
securityContext:
|
||||
allowPrivilegeEscalation: false
|
||||
capabilities:
|
||||
drop:
|
||||
- ALL
|
||||
readOnlyRootFilesystem: true
|
||||
runAsNonRoot: true
|
||||
runAsUser: 65534
|
||||
seccompProfile:
|
||||
type: RuntimeDefault
|
||||
- args:
|
||||
- --secure-listen-address=:8443
|
||||
- --tls-cipher-suites=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256,TLS_ECDHE_ECDSA_WITH_AES_128_GCM_SHA256,TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384,TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384,TLS_ECDHE_RSA_WITH_CHACHA20_POLY1305,TLS_ECDHE_ECDSA_WITH_CHACHA20_POLY1305
|
||||
- --upstream=http://127.0.0.1:8081/
|
||||
image: quay.io/brancz/kube-rbac-proxy:v0.14.2
|
||||
name: kube-rbac-proxy-main
|
||||
ports:
|
||||
- containerPort: 8443
|
||||
name: https-main
|
||||
resources:
|
||||
limits:
|
||||
cpu: 40m
|
||||
memory: 40Mi
|
||||
requests:
|
||||
cpu: 20m
|
||||
memory: 20Mi
|
||||
securityContext:
|
||||
allowPrivilegeEscalation: false
|
||||
capabilities:
|
||||
drop:
|
||||
- ALL
|
||||
readOnlyRootFilesystem: true
|
||||
runAsGroup: 65532
|
||||
runAsNonRoot: true
|
||||
runAsUser: 65532
|
||||
- args:
|
||||
- --secure-listen-address=:9443
|
||||
- --tls-cipher-suites=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256,TLS_ECDHE_ECDSA_WITH_AES_128_GCM_SHA256,TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384,TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384,TLS_ECDHE_RSA_WITH_CHACHA20_POLY1305,TLS_ECDHE_ECDSA_WITH_CHACHA20_POLY1305
|
||||
- --upstream=http://127.0.0.1:8082/
|
||||
image: quay.io/brancz/kube-rbac-proxy:v0.14.2
|
||||
name: kube-rbac-proxy-self
|
||||
ports:
|
||||
- containerPort: 9443
|
||||
name: https-self
|
||||
resources:
|
||||
limits:
|
||||
cpu: 20m
|
||||
memory: 40Mi
|
||||
requests:
|
||||
cpu: 10m
|
||||
memory: 20Mi
|
||||
securityContext:
|
||||
allowPrivilegeEscalation: false
|
||||
capabilities:
|
||||
drop:
|
||||
- ALL
|
||||
readOnlyRootFilesystem: true
|
||||
runAsGroup: 65532
|
||||
runAsNonRoot: true
|
||||
runAsUser: 65532
|
||||
nodeSelector:
|
||||
kubernetes.io/os: linux
|
||||
serviceAccountName: kube-state-metrics
|
||||
|
|
@ -0,0 +1,33 @@
|
|||
apiVersion: networking.k8s.io/v1
|
||||
kind: NetworkPolicy
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: exporter
|
||||
app.kubernetes.io/name: kube-state-metrics
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 2.9.2
|
||||
name: kube-state-metrics
|
||||
namespace: monitoring
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
spec:
|
||||
egress:
|
||||
- {}
|
||||
ingress:
|
||||
- from:
|
||||
- podSelector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/name: prometheus
|
||||
ports:
|
||||
- port: 8443
|
||||
protocol: TCP
|
||||
- port: 9443
|
||||
protocol: TCP
|
||||
podSelector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/component: exporter
|
||||
app.kubernetes.io/name: kube-state-metrics
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
policyTypes:
|
||||
- Egress
|
||||
- Ingress
|
||||
|
|
@ -0,0 +1,70 @@
|
|||
apiVersion: monitoring.coreos.com/v1
|
||||
kind: PrometheusRule
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: exporter
|
||||
app.kubernetes.io/name: kube-state-metrics
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 2.9.2
|
||||
prometheus: k8s
|
||||
role: alert-rules
|
||||
name: kube-state-metrics-rules
|
||||
namespace: monitoring
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
spec:
|
||||
groups:
|
||||
- name: kube-state-metrics
|
||||
rules:
|
||||
- alert: KubeStateMetricsListErrors
|
||||
annotations:
|
||||
description: kube-state-metrics is experiencing errors at an elevated
|
||||
rate in list operations. This is likely causing it to not be able to
|
||||
expose metrics about Kubernetes objects correctly or at all.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kube-state-metrics/kubestatemetricslisterrors
|
||||
summary: kube-state-metrics is experiencing errors in list operations.
|
||||
expr: "(sum(rate(kube_state_metrics_list_total{job=\"kube-state-metrics\"\
|
||||
,result=\"error\"}[5m])) by (cluster)\n /\nsum(rate(kube_state_metrics_list_total{job=\"\
|
||||
kube-state-metrics\"}[5m])) by (cluster))\n> 0.01\n"
|
||||
for: 15m
|
||||
labels:
|
||||
severity: critical
|
||||
- alert: KubeStateMetricsWatchErrors
|
||||
annotations:
|
||||
description: kube-state-metrics is experiencing errors at an elevated
|
||||
rate in watch operations. This is likely causing it to not be able to
|
||||
expose metrics about Kubernetes objects correctly or at all.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kube-state-metrics/kubestatemetricswatcherrors
|
||||
summary: kube-state-metrics is experiencing errors in watch operations.
|
||||
expr: "(sum(rate(kube_state_metrics_watch_total{job=\"kube-state-metrics\"\
|
||||
,result=\"error\"}[5m])) by (cluster)\n /\nsum(rate(kube_state_metrics_watch_total{job=\"\
|
||||
kube-state-metrics\"}[5m])) by (cluster))\n> 0.01\n"
|
||||
for: 15m
|
||||
labels:
|
||||
severity: critical
|
||||
- alert: KubeStateMetricsShardingMismatch
|
||||
annotations:
|
||||
description: kube-state-metrics pods are running with different --total-shards
|
||||
configuration, some Kubernetes objects may be exposed multiple times
|
||||
or not exposed at all.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kube-state-metrics/kubestatemetricsshardingmismatch
|
||||
summary: kube-state-metrics sharding is misconfigured.
|
||||
expr: 'stdvar (kube_state_metrics_total_shards{job="kube-state-metrics"})
|
||||
by (cluster) != 0
|
||||
|
||||
'
|
||||
for: 15m
|
||||
labels:
|
||||
severity: critical
|
||||
- alert: KubeStateMetricsShardsMissing
|
||||
annotations:
|
||||
description: kube-state-metrics shards are missing, some Kubernetes objects
|
||||
are not being exposed.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kube-state-metrics/kubestatemetricsshardsmissing
|
||||
summary: kube-state-metrics shards are missing.
|
||||
expr: "2^max(kube_state_metrics_total_shards{job=\"kube-state-metrics\"\
|
||||
}) by (cluster) - 1\n -\nsum( 2 ^ max by (cluster, shard_ordinal) (kube_state_metrics_shard_ordinal{job=\"\
|
||||
kube-state-metrics\"}) ) by (cluster)\n!= 0\n"
|
||||
for: 15m
|
||||
labels:
|
||||
severity: critical
|
||||
|
|
@ -0,0 +1,25 @@
|
|||
apiVersion: v1
|
||||
kind: Service
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: exporter
|
||||
app.kubernetes.io/name: kube-state-metrics
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 2.9.2
|
||||
name: kube-state-metrics
|
||||
namespace: monitoring
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
spec:
|
||||
clusterIP: None
|
||||
ports:
|
||||
- name: https-main
|
||||
port: 8443
|
||||
targetPort: https-main
|
||||
- name: https-self
|
||||
port: 9443
|
||||
targetPort: https-self
|
||||
selector:
|
||||
app.kubernetes.io/component: exporter
|
||||
app.kubernetes.io/name: kube-state-metrics
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
|
|
@ -0,0 +1,13 @@
|
|||
apiVersion: v1
|
||||
automountServiceAccountToken: false
|
||||
kind: ServiceAccount
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: exporter
|
||||
app.kubernetes.io/name: kube-state-metrics
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 2.9.2
|
||||
name: kube-state-metrics
|
||||
namespace: monitoring
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
|
|
@ -0,0 +1,42 @@
|
|||
apiVersion: monitoring.coreos.com/v1
|
||||
kind: ServiceMonitor
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: exporter
|
||||
app.kubernetes.io/name: kube-state-metrics
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 2.9.2
|
||||
name: kube-state-metrics
|
||||
namespace: monitoring
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
spec:
|
||||
endpoints:
|
||||
- bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token
|
||||
honorLabels: true
|
||||
interval: 30s
|
||||
metricRelabelings:
|
||||
- action: drop
|
||||
regex: kube_endpoint_address_not_ready|kube_endpoint_address_available
|
||||
sourceLabels:
|
||||
- __name__
|
||||
port: https-main
|
||||
relabelings:
|
||||
- action: labeldrop
|
||||
regex: (pod|service|endpoint|namespace)
|
||||
scheme: https
|
||||
scrapeTimeout: 30s
|
||||
tlsConfig:
|
||||
insecureSkipVerify: true
|
||||
- bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token
|
||||
interval: 30s
|
||||
port: https-self
|
||||
scheme: https
|
||||
tlsConfig:
|
||||
insecureSkipVerify: true
|
||||
jobLabel: app.kubernetes.io/name
|
||||
selector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/component: exporter
|
||||
app.kubernetes.io/name: kube-state-metrics
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
File diff suppressed because it is too large
Load Diff
|
|
@ -0,0 +1,77 @@
|
|||
apiVersion: monitoring.coreos.com/v1
|
||||
kind: ServiceMonitor
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/name: apiserver
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
name: kube-apiserver
|
||||
namespace: monitoring
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
spec:
|
||||
endpoints:
|
||||
- bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token
|
||||
interval: 30s
|
||||
metricRelabelings:
|
||||
- action: drop
|
||||
regex: kubelet_(pod_worker_latency_microseconds|pod_start_latency_microseconds|cgroup_manager_latency_microseconds|pod_worker_start_latency_microseconds|pleg_relist_latency_microseconds|pleg_relist_interval_microseconds|runtime_operations|runtime_operations_latency_microseconds|runtime_operations_errors|eviction_stats_age_microseconds|device_plugin_registration_count|device_plugin_alloc_latency_microseconds|network_plugin_operations_latency_microseconds)
|
||||
sourceLabels:
|
||||
- __name__
|
||||
- action: drop
|
||||
regex: scheduler_(e2e_scheduling_latency_microseconds|scheduling_algorithm_predicate_evaluation|scheduling_algorithm_priority_evaluation|scheduling_algorithm_preemption_evaluation|scheduling_algorithm_latency_microseconds|binding_latency_microseconds|scheduling_latency_seconds)
|
||||
sourceLabels:
|
||||
- __name__
|
||||
- action: drop
|
||||
regex: apiserver_(request_count|request_latencies|request_latencies_summary|dropped_requests|storage_data_key_generation_latencies_microseconds|storage_transformation_failures_total|storage_transformation_latencies_microseconds|proxy_tunnel_sync_latency_secs|longrunning_gauge|registered_watchers|storage_db_total_size_in_bytes)
|
||||
sourceLabels:
|
||||
- __name__
|
||||
- action: drop
|
||||
regex: kubelet_docker_(operations|operations_latency_microseconds|operations_errors|operations_timeout)
|
||||
sourceLabels:
|
||||
- __name__
|
||||
- action: drop
|
||||
regex: reflector_(items_per_list|items_per_watch|list_duration_seconds|lists_total|short_watches_total|watch_duration_seconds|watches_total)
|
||||
sourceLabels:
|
||||
- __name__
|
||||
- action: drop
|
||||
regex: etcd_(helper_cache_hit_count|helper_cache_miss_count|helper_cache_entry_count|object_counts|request_cache_get_latencies_summary|request_cache_add_latencies_summary|request_latencies_summary)
|
||||
sourceLabels:
|
||||
- __name__
|
||||
- action: drop
|
||||
regex: transformation_(transformation_latencies_microseconds|failures_total)
|
||||
sourceLabels:
|
||||
- __name__
|
||||
- action: drop
|
||||
regex: (admission_quota_controller_adds|admission_quota_controller_depth|admission_quota_controller_longest_running_processor_microseconds|admission_quota_controller_queue_latency|admission_quota_controller_unfinished_work_seconds|admission_quota_controller_work_duration|APIServiceOpenAPIAggregationControllerQueue1_adds|APIServiceOpenAPIAggregationControllerQueue1_depth|APIServiceOpenAPIAggregationControllerQueue1_longest_running_processor_microseconds|APIServiceOpenAPIAggregationControllerQueue1_queue_latency|APIServiceOpenAPIAggregationControllerQueue1_retries|APIServiceOpenAPIAggregationControllerQueue1_unfinished_work_seconds|APIServiceOpenAPIAggregationControllerQueue1_work_duration|APIServiceRegistrationController_adds|APIServiceRegistrationController_depth|APIServiceRegistrationController_longest_running_processor_microseconds|APIServiceRegistrationController_queue_latency|APIServiceRegistrationController_retries|APIServiceRegistrationController_unfinished_work_seconds|APIServiceRegistrationController_work_duration|autoregister_adds|autoregister_depth|autoregister_longest_running_processor_microseconds|autoregister_queue_latency|autoregister_retries|autoregister_unfinished_work_seconds|autoregister_work_duration|AvailableConditionController_adds|AvailableConditionController_depth|AvailableConditionController_longest_running_processor_microseconds|AvailableConditionController_queue_latency|AvailableConditionController_retries|AvailableConditionController_unfinished_work_seconds|AvailableConditionController_work_duration|crd_autoregistration_controller_adds|crd_autoregistration_controller_depth|crd_autoregistration_controller_longest_running_processor_microseconds|crd_autoregistration_controller_queue_latency|crd_autoregistration_controller_retries|crd_autoregistration_controller_unfinished_work_seconds|crd_autoregistration_controller_work_duration|crdEstablishing_adds|crdEstablishing_depth|crdEstablishing_longest_running_processor_microseconds|crdEstablishing_queue_latency|crdEstablishing_retries|crdEstablishing_unfinished_work_seconds|crdEstablishing_work_duration|crd_finalizer_adds|crd_finalizer_depth|crd_finalizer_longest_running_processor_microseconds|crd_finalizer_queue_latency|crd_finalizer_retries|crd_finalizer_unfinished_work_seconds|crd_finalizer_work_duration|crd_naming_condition_controller_adds|crd_naming_condition_controller_depth|crd_naming_condition_controller_longest_running_processor_microseconds|crd_naming_condition_controller_queue_latency|crd_naming_condition_controller_retries|crd_naming_condition_controller_unfinished_work_seconds|crd_naming_condition_controller_work_duration|crd_openapi_controller_adds|crd_openapi_controller_depth|crd_openapi_controller_longest_running_processor_microseconds|crd_openapi_controller_queue_latency|crd_openapi_controller_retries|crd_openapi_controller_unfinished_work_seconds|crd_openapi_controller_work_duration|DiscoveryController_adds|DiscoveryController_depth|DiscoveryController_longest_running_processor_microseconds|DiscoveryController_queue_latency|DiscoveryController_retries|DiscoveryController_unfinished_work_seconds|DiscoveryController_work_duration|kubeproxy_sync_proxy_rules_latency_microseconds|non_structural_schema_condition_controller_adds|non_structural_schema_condition_controller_depth|non_structural_schema_condition_controller_longest_running_processor_microseconds|non_structural_schema_condition_controller_queue_latency|non_structural_schema_condition_controller_retries|non_structural_schema_condition_controller_unfinished_work_seconds|non_structural_schema_condition_controller_work_duration|rest_client_request_latency_seconds|storage_operation_errors_total|storage_operation_status_count)
|
||||
sourceLabels:
|
||||
- __name__
|
||||
- action: drop
|
||||
regex: etcd_(debugging|disk|server).*
|
||||
sourceLabels:
|
||||
- __name__
|
||||
- action: drop
|
||||
regex: apiserver_admission_controller_admission_latencies_seconds_.*
|
||||
sourceLabels:
|
||||
- __name__
|
||||
- action: drop
|
||||
regex: apiserver_admission_step_admission_latencies_seconds_.*
|
||||
sourceLabels:
|
||||
- __name__
|
||||
- action: drop
|
||||
regex: apiserver_request_duration_seconds_bucket;(0.15|0.25|0.3|0.35|0.4|0.45|0.6|0.7|0.8|0.9|1.25|1.5|1.75|2.5|3|3.5|4.5|6|7|8|9|15|25|30|50)
|
||||
sourceLabels:
|
||||
- __name__
|
||||
- le
|
||||
port: https
|
||||
scheme: https
|
||||
tlsConfig:
|
||||
caFile: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
|
||||
serverName: kubernetes
|
||||
jobLabel: component
|
||||
namespaceSelector:
|
||||
matchNames:
|
||||
- default
|
||||
selector:
|
||||
matchLabels:
|
||||
component: apiserver
|
||||
provider: kubernetes
|
||||
|
|
@ -0,0 +1,27 @@
|
|||
apiVersion: monitoring.coreos.com/v1
|
||||
kind: ServiceMonitor
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/name: coredns
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
name: coredns
|
||||
namespace: monitoring
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
spec:
|
||||
endpoints:
|
||||
- bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token
|
||||
interval: 15s
|
||||
metricRelabelings:
|
||||
- action: drop
|
||||
regex: coredns_cache_misses_total
|
||||
sourceLabels:
|
||||
- __name__
|
||||
port: metrics
|
||||
jobLabel: app.kubernetes.io/name
|
||||
namespaceSelector:
|
||||
matchNames:
|
||||
- kube-system
|
||||
selector:
|
||||
matchLabels:
|
||||
k8s-app: kube-dns
|
||||
|
|
@ -0,0 +1,62 @@
|
|||
apiVersion: monitoring.coreos.com/v1
|
||||
kind: ServiceMonitor
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/name: kube-controller-manager
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
name: kube-controller-manager
|
||||
namespace: monitoring
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
spec:
|
||||
endpoints:
|
||||
- bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token
|
||||
interval: 30s
|
||||
metricRelabelings:
|
||||
- action: drop
|
||||
regex: kubelet_(pod_worker_latency_microseconds|pod_start_latency_microseconds|cgroup_manager_latency_microseconds|pod_worker_start_latency_microseconds|pleg_relist_latency_microseconds|pleg_relist_interval_microseconds|runtime_operations|runtime_operations_latency_microseconds|runtime_operations_errors|eviction_stats_age_microseconds|device_plugin_registration_count|device_plugin_alloc_latency_microseconds|network_plugin_operations_latency_microseconds)
|
||||
sourceLabels:
|
||||
- __name__
|
||||
- action: drop
|
||||
regex: scheduler_(e2e_scheduling_latency_microseconds|scheduling_algorithm_predicate_evaluation|scheduling_algorithm_priority_evaluation|scheduling_algorithm_preemption_evaluation|scheduling_algorithm_latency_microseconds|binding_latency_microseconds|scheduling_latency_seconds)
|
||||
sourceLabels:
|
||||
- __name__
|
||||
- action: drop
|
||||
regex: apiserver_(request_count|request_latencies|request_latencies_summary|dropped_requests|storage_data_key_generation_latencies_microseconds|storage_transformation_failures_total|storage_transformation_latencies_microseconds|proxy_tunnel_sync_latency_secs|longrunning_gauge|registered_watchers|storage_db_total_size_in_bytes)
|
||||
sourceLabels:
|
||||
- __name__
|
||||
- action: drop
|
||||
regex: kubelet_docker_(operations|operations_latency_microseconds|operations_errors|operations_timeout)
|
||||
sourceLabels:
|
||||
- __name__
|
||||
- action: drop
|
||||
regex: reflector_(items_per_list|items_per_watch|list_duration_seconds|lists_total|short_watches_total|watch_duration_seconds|watches_total)
|
||||
sourceLabels:
|
||||
- __name__
|
||||
- action: drop
|
||||
regex: etcd_(helper_cache_hit_count|helper_cache_miss_count|helper_cache_entry_count|object_counts|request_cache_get_latencies_summary|request_cache_add_latencies_summary|request_latencies_summary)
|
||||
sourceLabels:
|
||||
- __name__
|
||||
- action: drop
|
||||
regex: transformation_(transformation_latencies_microseconds|failures_total)
|
||||
sourceLabels:
|
||||
- __name__
|
||||
- action: drop
|
||||
regex: (admission_quota_controller_adds|admission_quota_controller_depth|admission_quota_controller_longest_running_processor_microseconds|admission_quota_controller_queue_latency|admission_quota_controller_unfinished_work_seconds|admission_quota_controller_work_duration|APIServiceOpenAPIAggregationControllerQueue1_adds|APIServiceOpenAPIAggregationControllerQueue1_depth|APIServiceOpenAPIAggregationControllerQueue1_longest_running_processor_microseconds|APIServiceOpenAPIAggregationControllerQueue1_queue_latency|APIServiceOpenAPIAggregationControllerQueue1_retries|APIServiceOpenAPIAggregationControllerQueue1_unfinished_work_seconds|APIServiceOpenAPIAggregationControllerQueue1_work_duration|APIServiceRegistrationController_adds|APIServiceRegistrationController_depth|APIServiceRegistrationController_longest_running_processor_microseconds|APIServiceRegistrationController_queue_latency|APIServiceRegistrationController_retries|APIServiceRegistrationController_unfinished_work_seconds|APIServiceRegistrationController_work_duration|autoregister_adds|autoregister_depth|autoregister_longest_running_processor_microseconds|autoregister_queue_latency|autoregister_retries|autoregister_unfinished_work_seconds|autoregister_work_duration|AvailableConditionController_adds|AvailableConditionController_depth|AvailableConditionController_longest_running_processor_microseconds|AvailableConditionController_queue_latency|AvailableConditionController_retries|AvailableConditionController_unfinished_work_seconds|AvailableConditionController_work_duration|crd_autoregistration_controller_adds|crd_autoregistration_controller_depth|crd_autoregistration_controller_longest_running_processor_microseconds|crd_autoregistration_controller_queue_latency|crd_autoregistration_controller_retries|crd_autoregistration_controller_unfinished_work_seconds|crd_autoregistration_controller_work_duration|crdEstablishing_adds|crdEstablishing_depth|crdEstablishing_longest_running_processor_microseconds|crdEstablishing_queue_latency|crdEstablishing_retries|crdEstablishing_unfinished_work_seconds|crdEstablishing_work_duration|crd_finalizer_adds|crd_finalizer_depth|crd_finalizer_longest_running_processor_microseconds|crd_finalizer_queue_latency|crd_finalizer_retries|crd_finalizer_unfinished_work_seconds|crd_finalizer_work_duration|crd_naming_condition_controller_adds|crd_naming_condition_controller_depth|crd_naming_condition_controller_longest_running_processor_microseconds|crd_naming_condition_controller_queue_latency|crd_naming_condition_controller_retries|crd_naming_condition_controller_unfinished_work_seconds|crd_naming_condition_controller_work_duration|crd_openapi_controller_adds|crd_openapi_controller_depth|crd_openapi_controller_longest_running_processor_microseconds|crd_openapi_controller_queue_latency|crd_openapi_controller_retries|crd_openapi_controller_unfinished_work_seconds|crd_openapi_controller_work_duration|DiscoveryController_adds|DiscoveryController_depth|DiscoveryController_longest_running_processor_microseconds|DiscoveryController_queue_latency|DiscoveryController_retries|DiscoveryController_unfinished_work_seconds|DiscoveryController_work_duration|kubeproxy_sync_proxy_rules_latency_microseconds|non_structural_schema_condition_controller_adds|non_structural_schema_condition_controller_depth|non_structural_schema_condition_controller_longest_running_processor_microseconds|non_structural_schema_condition_controller_queue_latency|non_structural_schema_condition_controller_retries|non_structural_schema_condition_controller_unfinished_work_seconds|non_structural_schema_condition_controller_work_duration|rest_client_request_latency_seconds|storage_operation_errors_total|storage_operation_status_count)
|
||||
sourceLabels:
|
||||
- __name__
|
||||
- action: drop
|
||||
regex: etcd_(debugging|disk|request|server).*
|
||||
sourceLabels:
|
||||
- __name__
|
||||
port: https-metrics
|
||||
scheme: https
|
||||
tlsConfig:
|
||||
insecureSkipVerify: true
|
||||
jobLabel: app.kubernetes.io/name
|
||||
namespaceSelector:
|
||||
matchNames:
|
||||
- kube-system
|
||||
selector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/name: kube-controller-manager
|
||||
|
|
@ -0,0 +1,25 @@
|
|||
apiVersion: monitoring.coreos.com/v1
|
||||
kind: ServiceMonitor
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/name: kube-scheduler
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
name: kube-scheduler
|
||||
namespace: monitoring
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
spec:
|
||||
endpoints:
|
||||
- bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token
|
||||
interval: 30s
|
||||
port: https-metrics
|
||||
scheme: https
|
||||
tlsConfig:
|
||||
insecureSkipVerify: true
|
||||
jobLabel: app.kubernetes.io/name
|
||||
namespaceSelector:
|
||||
matchNames:
|
||||
- kube-system
|
||||
selector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/name: kube-scheduler
|
||||
|
|
@ -0,0 +1,107 @@
|
|||
apiVersion: monitoring.coreos.com/v1
|
||||
kind: ServiceMonitor
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/name: kubelet
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
name: kubelet
|
||||
namespace: monitoring
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
spec:
|
||||
endpoints:
|
||||
- bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token
|
||||
honorLabels: true
|
||||
interval: 30s
|
||||
metricRelabelings:
|
||||
- action: drop
|
||||
regex: kubelet_(pod_worker_latency_microseconds|pod_start_latency_microseconds|cgroup_manager_latency_microseconds|pod_worker_start_latency_microseconds|pleg_relist_latency_microseconds|pleg_relist_interval_microseconds|runtime_operations|runtime_operations_latency_microseconds|runtime_operations_errors|eviction_stats_age_microseconds|device_plugin_registration_count|device_plugin_alloc_latency_microseconds|network_plugin_operations_latency_microseconds)
|
||||
sourceLabels:
|
||||
- __name__
|
||||
- action: drop
|
||||
regex: scheduler_(e2e_scheduling_latency_microseconds|scheduling_algorithm_predicate_evaluation|scheduling_algorithm_priority_evaluation|scheduling_algorithm_preemption_evaluation|scheduling_algorithm_latency_microseconds|binding_latency_microseconds|scheduling_latency_seconds)
|
||||
sourceLabels:
|
||||
- __name__
|
||||
- action: drop
|
||||
regex: apiserver_(request_count|request_latencies|request_latencies_summary|dropped_requests|storage_data_key_generation_latencies_microseconds|storage_transformation_failures_total|storage_transformation_latencies_microseconds|proxy_tunnel_sync_latency_secs|longrunning_gauge|registered_watchers|storage_db_total_size_in_bytes)
|
||||
sourceLabels:
|
||||
- __name__
|
||||
- action: drop
|
||||
regex: kubelet_docker_(operations|operations_latency_microseconds|operations_errors|operations_timeout)
|
||||
sourceLabels:
|
||||
- __name__
|
||||
- action: drop
|
||||
regex: reflector_(items_per_list|items_per_watch|list_duration_seconds|lists_total|short_watches_total|watch_duration_seconds|watches_total)
|
||||
sourceLabels:
|
||||
- __name__
|
||||
- action: drop
|
||||
regex: etcd_(helper_cache_hit_count|helper_cache_miss_count|helper_cache_entry_count|object_counts|request_cache_get_latencies_summary|request_cache_add_latencies_summary|request_latencies_summary)
|
||||
sourceLabels:
|
||||
- __name__
|
||||
- action: drop
|
||||
regex: transformation_(transformation_latencies_microseconds|failures_total)
|
||||
sourceLabels:
|
||||
- __name__
|
||||
- action: drop
|
||||
regex: (admission_quota_controller_adds|admission_quota_controller_depth|admission_quota_controller_longest_running_processor_microseconds|admission_quota_controller_queue_latency|admission_quota_controller_unfinished_work_seconds|admission_quota_controller_work_duration|APIServiceOpenAPIAggregationControllerQueue1_adds|APIServiceOpenAPIAggregationControllerQueue1_depth|APIServiceOpenAPIAggregationControllerQueue1_longest_running_processor_microseconds|APIServiceOpenAPIAggregationControllerQueue1_queue_latency|APIServiceOpenAPIAggregationControllerQueue1_retries|APIServiceOpenAPIAggregationControllerQueue1_unfinished_work_seconds|APIServiceOpenAPIAggregationControllerQueue1_work_duration|APIServiceRegistrationController_adds|APIServiceRegistrationController_depth|APIServiceRegistrationController_longest_running_processor_microseconds|APIServiceRegistrationController_queue_latency|APIServiceRegistrationController_retries|APIServiceRegistrationController_unfinished_work_seconds|APIServiceRegistrationController_work_duration|autoregister_adds|autoregister_depth|autoregister_longest_running_processor_microseconds|autoregister_queue_latency|autoregister_retries|autoregister_unfinished_work_seconds|autoregister_work_duration|AvailableConditionController_adds|AvailableConditionController_depth|AvailableConditionController_longest_running_processor_microseconds|AvailableConditionController_queue_latency|AvailableConditionController_retries|AvailableConditionController_unfinished_work_seconds|AvailableConditionController_work_duration|crd_autoregistration_controller_adds|crd_autoregistration_controller_depth|crd_autoregistration_controller_longest_running_processor_microseconds|crd_autoregistration_controller_queue_latency|crd_autoregistration_controller_retries|crd_autoregistration_controller_unfinished_work_seconds|crd_autoregistration_controller_work_duration|crdEstablishing_adds|crdEstablishing_depth|crdEstablishing_longest_running_processor_microseconds|crdEstablishing_queue_latency|crdEstablishing_retries|crdEstablishing_unfinished_work_seconds|crdEstablishing_work_duration|crd_finalizer_adds|crd_finalizer_depth|crd_finalizer_longest_running_processor_microseconds|crd_finalizer_queue_latency|crd_finalizer_retries|crd_finalizer_unfinished_work_seconds|crd_finalizer_work_duration|crd_naming_condition_controller_adds|crd_naming_condition_controller_depth|crd_naming_condition_controller_longest_running_processor_microseconds|crd_naming_condition_controller_queue_latency|crd_naming_condition_controller_retries|crd_naming_condition_controller_unfinished_work_seconds|crd_naming_condition_controller_work_duration|crd_openapi_controller_adds|crd_openapi_controller_depth|crd_openapi_controller_longest_running_processor_microseconds|crd_openapi_controller_queue_latency|crd_openapi_controller_retries|crd_openapi_controller_unfinished_work_seconds|crd_openapi_controller_work_duration|DiscoveryController_adds|DiscoveryController_depth|DiscoveryController_longest_running_processor_microseconds|DiscoveryController_queue_latency|DiscoveryController_retries|DiscoveryController_unfinished_work_seconds|DiscoveryController_work_duration|kubeproxy_sync_proxy_rules_latency_microseconds|non_structural_schema_condition_controller_adds|non_structural_schema_condition_controller_depth|non_structural_schema_condition_controller_longest_running_processor_microseconds|non_structural_schema_condition_controller_queue_latency|non_structural_schema_condition_controller_retries|non_structural_schema_condition_controller_unfinished_work_seconds|non_structural_schema_condition_controller_work_duration|rest_client_request_latency_seconds|storage_operation_errors_total|storage_operation_status_count)
|
||||
sourceLabels:
|
||||
- __name__
|
||||
port: https-metrics
|
||||
relabelings:
|
||||
- action: replace
|
||||
sourceLabels:
|
||||
- __metrics_path__
|
||||
targetLabel: metrics_path
|
||||
scheme: https
|
||||
tlsConfig:
|
||||
insecureSkipVerify: true
|
||||
- bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token
|
||||
honorLabels: true
|
||||
honorTimestamps: false
|
||||
interval: 30s
|
||||
metricRelabelings:
|
||||
- action: drop
|
||||
regex: container_(network_tcp_usage_total|network_udp_usage_total|tasks_state|cpu_load_average_10s)
|
||||
sourceLabels:
|
||||
- __name__
|
||||
- action: drop
|
||||
regex: (container_spec_.*|container_file_descriptors|container_sockets|container_threads_max|container_threads|container_start_time_seconds|container_last_seen);;
|
||||
sourceLabels:
|
||||
- __name__
|
||||
- pod
|
||||
- namespace
|
||||
- action: drop
|
||||
regex: (container_blkio_device_usage_total);.+
|
||||
sourceLabels:
|
||||
- __name__
|
||||
- container
|
||||
path: /metrics/cadvisor
|
||||
port: https-metrics
|
||||
relabelings:
|
||||
- action: replace
|
||||
sourceLabels:
|
||||
- __metrics_path__
|
||||
targetLabel: metrics_path
|
||||
scheme: https
|
||||
tlsConfig:
|
||||
insecureSkipVerify: true
|
||||
- bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token
|
||||
honorLabels: true
|
||||
interval: 30s
|
||||
path: /metrics/probes
|
||||
port: https-metrics
|
||||
relabelings:
|
||||
- action: replace
|
||||
sourceLabels:
|
||||
- __metrics_path__
|
||||
targetLabel: metrics_path
|
||||
scheme: https
|
||||
tlsConfig:
|
||||
insecureSkipVerify: true
|
||||
jobLabel: app.kubernetes.io/name
|
||||
namespaceSelector:
|
||||
matchNames:
|
||||
- kube-system
|
||||
selector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/name: kubelet
|
||||
|
|
@ -0,0 +1,6 @@
|
|||
apiVersion: v1
|
||||
kind: Namespace
|
||||
metadata:
|
||||
name: monitoring
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '0'
|
||||
|
|
@ -0,0 +1,24 @@
|
|||
apiVersion: rbac.authorization.k8s.io/v1
|
||||
kind: ClusterRole
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: exporter
|
||||
app.kubernetes.io/name: node-exporter
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 1.6.1
|
||||
name: node-exporter
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
rules:
|
||||
- apiGroups:
|
||||
- authentication.k8s.io
|
||||
resources:
|
||||
- tokenreviews
|
||||
verbs:
|
||||
- create
|
||||
- apiGroups:
|
||||
- authorization.k8s.io
|
||||
resources:
|
||||
- subjectaccessreviews
|
||||
verbs:
|
||||
- create
|
||||
|
|
@ -0,0 +1,19 @@
|
|||
apiVersion: rbac.authorization.k8s.io/v1
|
||||
kind: ClusterRoleBinding
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: exporter
|
||||
app.kubernetes.io/name: node-exporter
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 1.6.1
|
||||
name: node-exporter
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
roleRef:
|
||||
apiGroup: rbac.authorization.k8s.io
|
||||
kind: ClusterRole
|
||||
name: node-exporter
|
||||
subjects:
|
||||
- kind: ServiceAccount
|
||||
name: node-exporter
|
||||
namespace: monitoring
|
||||
|
|
@ -0,0 +1,120 @@
|
|||
apiVersion: apps/v1
|
||||
kind: DaemonSet
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: exporter
|
||||
app.kubernetes.io/name: node-exporter
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 1.6.1
|
||||
name: node-exporter
|
||||
namespace: monitoring
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
spec:
|
||||
selector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/component: exporter
|
||||
app.kubernetes.io/name: node-exporter
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
template:
|
||||
metadata:
|
||||
annotations:
|
||||
kubectl.kubernetes.io/default-container: node-exporter
|
||||
labels:
|
||||
app.kubernetes.io/component: exporter
|
||||
app.kubernetes.io/name: node-exporter
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 1.6.1
|
||||
spec:
|
||||
automountServiceAccountToken: true
|
||||
containers:
|
||||
- args:
|
||||
- --web.listen-address=127.0.0.1:9100
|
||||
- --path.sysfs=/host/sys
|
||||
- --path.rootfs=/host/root
|
||||
- --path.udev.data=/host/root/run/udev/data
|
||||
- --no-collector.wifi
|
||||
- --no-collector.hwmon
|
||||
- --no-collector.btrfs
|
||||
- --collector.filesystem.mount-points-exclude=^/(dev|proc|sys|run/k3s/containerd/.+|var/lib/docker/.+|var/lib/kubelet/pods/.+)($|/)
|
||||
- --collector.netclass.ignored-devices=^(veth.*|[a-f0-9]{15})$
|
||||
- --collector.netdev.device-exclude=^(veth.*|[a-f0-9]{15})$
|
||||
image: quay.io/prometheus/node-exporter:v1.6.1
|
||||
name: node-exporter
|
||||
resources:
|
||||
limits:
|
||||
cpu: 250m
|
||||
memory: 180Mi
|
||||
requests:
|
||||
cpu: 102m
|
||||
memory: 180Mi
|
||||
securityContext:
|
||||
allowPrivilegeEscalation: false
|
||||
capabilities:
|
||||
add:
|
||||
- SYS_TIME
|
||||
drop:
|
||||
- ALL
|
||||
readOnlyRootFilesystem: true
|
||||
volumeMounts:
|
||||
- mountPath: /host/sys
|
||||
mountPropagation: HostToContainer
|
||||
name: sys
|
||||
readOnly: true
|
||||
- mountPath: /host/root
|
||||
mountPropagation: HostToContainer
|
||||
name: root
|
||||
readOnly: true
|
||||
- args:
|
||||
- --secure-listen-address=[$(IP)]:9100
|
||||
- --tls-cipher-suites=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256,TLS_ECDHE_ECDSA_WITH_AES_128_GCM_SHA256,TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384,TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384,TLS_ECDHE_RSA_WITH_CHACHA20_POLY1305,TLS_ECDHE_ECDSA_WITH_CHACHA20_POLY1305
|
||||
- --upstream=http://127.0.0.1:9100/
|
||||
env:
|
||||
- name: IP
|
||||
valueFrom:
|
||||
fieldRef:
|
||||
fieldPath: status.podIP
|
||||
image: quay.io/brancz/kube-rbac-proxy:v0.14.2
|
||||
name: kube-rbac-proxy
|
||||
ports:
|
||||
- containerPort: 9100
|
||||
hostPort: 9100
|
||||
name: https
|
||||
resources:
|
||||
limits:
|
||||
cpu: 20m
|
||||
memory: 40Mi
|
||||
requests:
|
||||
cpu: 10m
|
||||
memory: 20Mi
|
||||
securityContext:
|
||||
allowPrivilegeEscalation: false
|
||||
capabilities:
|
||||
drop:
|
||||
- ALL
|
||||
readOnlyRootFilesystem: true
|
||||
runAsGroup: 65532
|
||||
runAsNonRoot: true
|
||||
runAsUser: 65532
|
||||
hostNetwork: true
|
||||
hostPID: true
|
||||
nodeSelector:
|
||||
kubernetes.io/os: linux
|
||||
priorityClassName: system-cluster-critical
|
||||
securityContext:
|
||||
runAsNonRoot: true
|
||||
runAsUser: 65534
|
||||
serviceAccountName: node-exporter
|
||||
tolerations:
|
||||
- operator: Exists
|
||||
volumes:
|
||||
- hostPath:
|
||||
path: /sys
|
||||
name: sys
|
||||
- hostPath:
|
||||
path: /
|
||||
name: root
|
||||
updateStrategy:
|
||||
rollingUpdate:
|
||||
maxUnavailable: 10%
|
||||
type: RollingUpdate
|
||||
|
|
@ -0,0 +1,31 @@
|
|||
apiVersion: networking.k8s.io/v1
|
||||
kind: NetworkPolicy
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: exporter
|
||||
app.kubernetes.io/name: node-exporter
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 1.6.1
|
||||
name: node-exporter
|
||||
namespace: monitoring
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
spec:
|
||||
egress:
|
||||
- {}
|
||||
ingress:
|
||||
- from:
|
||||
- podSelector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/name: prometheus
|
||||
ports:
|
||||
- port: 9100
|
||||
protocol: TCP
|
||||
podSelector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/component: exporter
|
||||
app.kubernetes.io/name: node-exporter
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
policyTypes:
|
||||
- Egress
|
||||
- Ingress
|
||||
|
|
@ -0,0 +1,429 @@
|
|||
apiVersion: monitoring.coreos.com/v1
|
||||
kind: PrometheusRule
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: exporter
|
||||
app.kubernetes.io/name: node-exporter
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 1.6.1
|
||||
prometheus: k8s
|
||||
role: alert-rules
|
||||
name: node-exporter-rules
|
||||
namespace: monitoring
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
spec:
|
||||
groups:
|
||||
- name: node-exporter
|
||||
rules:
|
||||
- alert: NodeFilesystemSpaceFillingUp
|
||||
annotations:
|
||||
description: Filesystem on {{ $labels.device }}, mounted on {{ $labels.mountpoint
|
||||
}}, at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available
|
||||
space left and is filling up.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodefilesystemspacefillingup
|
||||
summary: Filesystem is predicted to run out of space within the next 24
|
||||
hours.
|
||||
expr: "(\n node_filesystem_avail_bytes{job=\"node-exporter\",fstype!=\"\
|
||||
\",mountpoint!=\"\"} / node_filesystem_size_bytes{job=\"node-exporter\"\
|
||||
,fstype!=\"\",mountpoint!=\"\"} * 100 < 15\nand\n predict_linear(node_filesystem_avail_bytes{job=\"\
|
||||
node-exporter\",fstype!=\"\",mountpoint!=\"\"}[6h], 24*60*60) < 0\nand\n\
|
||||
\ node_filesystem_readonly{job=\"node-exporter\",fstype!=\"\",mountpoint!=\"\
|
||||
\"} == 0\n)\n"
|
||||
for: 1h
|
||||
labels:
|
||||
severity: warning
|
||||
- alert: NodeFilesystemSpaceFillingUp
|
||||
annotations:
|
||||
description: Filesystem on {{ $labels.device }}, mounted on {{ $labels.mountpoint
|
||||
}}, at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available
|
||||
space left and is filling up fast.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodefilesystemspacefillingup
|
||||
summary: Filesystem is predicted to run out of space within the next 4
|
||||
hours.
|
||||
expr: "(\n node_filesystem_avail_bytes{job=\"node-exporter\",fstype!=\"\
|
||||
\",mountpoint!=\"\"} / node_filesystem_size_bytes{job=\"node-exporter\"\
|
||||
,fstype!=\"\",mountpoint!=\"\"} * 100 < 10\nand\n predict_linear(node_filesystem_avail_bytes{job=\"\
|
||||
node-exporter\",fstype!=\"\",mountpoint!=\"\"}[6h], 4*60*60) < 0\nand\n\
|
||||
\ node_filesystem_readonly{job=\"node-exporter\",fstype!=\"\",mountpoint!=\"\
|
||||
\"} == 0\n)\n"
|
||||
for: 1h
|
||||
labels:
|
||||
severity: critical
|
||||
- alert: NodeFilesystemAlmostOutOfSpace
|
||||
annotations:
|
||||
description: Filesystem on {{ $labels.device }}, mounted on {{ $labels.mountpoint
|
||||
}}, at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available
|
||||
space left.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodefilesystemalmostoutofspace
|
||||
summary: Filesystem has less than 5% space left.
|
||||
expr: "(\n node_filesystem_avail_bytes{job=\"node-exporter\",fstype!=\"\
|
||||
\",mountpoint!=\"\"} / node_filesystem_size_bytes{job=\"node-exporter\"\
|
||||
,fstype!=\"\",mountpoint!=\"\"} * 100 < 5\nand\n node_filesystem_readonly{job=\"\
|
||||
node-exporter\",fstype!=\"\",mountpoint!=\"\"} == 0\n)\n"
|
||||
for: 30m
|
||||
labels:
|
||||
severity: warning
|
||||
- alert: NodeFilesystemAlmostOutOfSpace
|
||||
annotations:
|
||||
description: Filesystem on {{ $labels.device }}, mounted on {{ $labels.mountpoint
|
||||
}}, at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available
|
||||
space left.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodefilesystemalmostoutofspace
|
||||
summary: Filesystem has less than 3% space left.
|
||||
expr: "(\n node_filesystem_avail_bytes{job=\"node-exporter\",fstype!=\"\
|
||||
\",mountpoint!=\"\"} / node_filesystem_size_bytes{job=\"node-exporter\"\
|
||||
,fstype!=\"\",mountpoint!=\"\"} * 100 < 3\nand\n node_filesystem_readonly{job=\"\
|
||||
node-exporter\",fstype!=\"\",mountpoint!=\"\"} == 0\n)\n"
|
||||
for: 30m
|
||||
labels:
|
||||
severity: critical
|
||||
- alert: NodeFilesystemFilesFillingUp
|
||||
annotations:
|
||||
description: Filesystem on {{ $labels.device }}, mounted on {{ $labels.mountpoint
|
||||
}}, at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available
|
||||
inodes left and is filling up.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodefilesystemfilesfillingup
|
||||
summary: Filesystem is predicted to run out of inodes within the next
|
||||
24 hours.
|
||||
expr: "(\n node_filesystem_files_free{job=\"node-exporter\",fstype!=\"\"\
|
||||
,mountpoint!=\"\"} / node_filesystem_files{job=\"node-exporter\",fstype!=\"\
|
||||
\",mountpoint!=\"\"} * 100 < 40\nand\n predict_linear(node_filesystem_files_free{job=\"\
|
||||
node-exporter\",fstype!=\"\",mountpoint!=\"\"}[6h], 24*60*60) < 0\nand\n\
|
||||
\ node_filesystem_readonly{job=\"node-exporter\",fstype!=\"\",mountpoint!=\"\
|
||||
\"} == 0\n)\n"
|
||||
for: 1h
|
||||
labels:
|
||||
severity: warning
|
||||
- alert: NodeFilesystemFilesFillingUp
|
||||
annotations:
|
||||
description: Filesystem on {{ $labels.device }}, mounted on {{ $labels.mountpoint
|
||||
}}, at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available
|
||||
inodes left and is filling up fast.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodefilesystemfilesfillingup
|
||||
summary: Filesystem is predicted to run out of inodes within the next
|
||||
4 hours.
|
||||
expr: "(\n node_filesystem_files_free{job=\"node-exporter\",fstype!=\"\"\
|
||||
,mountpoint!=\"\"} / node_filesystem_files{job=\"node-exporter\",fstype!=\"\
|
||||
\",mountpoint!=\"\"} * 100 < 20\nand\n predict_linear(node_filesystem_files_free{job=\"\
|
||||
node-exporter\",fstype!=\"\",mountpoint!=\"\"}[6h], 4*60*60) < 0\nand\n\
|
||||
\ node_filesystem_readonly{job=\"node-exporter\",fstype!=\"\",mountpoint!=\"\
|
||||
\"} == 0\n)\n"
|
||||
for: 1h
|
||||
labels:
|
||||
severity: critical
|
||||
- alert: NodeFilesystemAlmostOutOfFiles
|
||||
annotations:
|
||||
description: Filesystem on {{ $labels.device }}, mounted on {{ $labels.mountpoint
|
||||
}}, at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available
|
||||
inodes left.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodefilesystemalmostoutoffiles
|
||||
summary: Filesystem has less than 5% inodes left.
|
||||
expr: "(\n node_filesystem_files_free{job=\"node-exporter\",fstype!=\"\"\
|
||||
,mountpoint!=\"\"} / node_filesystem_files{job=\"node-exporter\",fstype!=\"\
|
||||
\",mountpoint!=\"\"} * 100 < 5\nand\n node_filesystem_readonly{job=\"\
|
||||
node-exporter\",fstype!=\"\",mountpoint!=\"\"} == 0\n)\n"
|
||||
for: 1h
|
||||
labels:
|
||||
severity: warning
|
||||
- alert: NodeFilesystemAlmostOutOfFiles
|
||||
annotations:
|
||||
description: Filesystem on {{ $labels.device }}, mounted on {{ $labels.mountpoint
|
||||
}}, at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available
|
||||
inodes left.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodefilesystemalmostoutoffiles
|
||||
summary: Filesystem has less than 3% inodes left.
|
||||
expr: "(\n node_filesystem_files_free{job=\"node-exporter\",fstype!=\"\"\
|
||||
,mountpoint!=\"\"} / node_filesystem_files{job=\"node-exporter\",fstype!=\"\
|
||||
\",mountpoint!=\"\"} * 100 < 3\nand\n node_filesystem_readonly{job=\"\
|
||||
node-exporter\",fstype!=\"\",mountpoint!=\"\"} == 0\n)\n"
|
||||
for: 1h
|
||||
labels:
|
||||
severity: critical
|
||||
- alert: NodeNetworkReceiveErrs
|
||||
annotations:
|
||||
description: '{{ $labels.instance }} interface {{ $labels.device }} has
|
||||
encountered {{ printf "%.0f" $value }} receive errors in the last two
|
||||
minutes.'
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodenetworkreceiveerrs
|
||||
summary: Network interface is reporting many receive errors.
|
||||
expr: 'rate(node_network_receive_errs_total{job="node-exporter"}[2m]) /
|
||||
rate(node_network_receive_packets_total{job="node-exporter"}[2m]) > 0.01
|
||||
|
||||
'
|
||||
for: 1h
|
||||
labels:
|
||||
severity: warning
|
||||
- alert: NodeNetworkTransmitErrs
|
||||
annotations:
|
||||
description: '{{ $labels.instance }} interface {{ $labels.device }} has
|
||||
encountered {{ printf "%.0f" $value }} transmit errors in the last two
|
||||
minutes.'
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodenetworktransmiterrs
|
||||
summary: Network interface is reporting many transmit errors.
|
||||
expr: 'rate(node_network_transmit_errs_total{job="node-exporter"}[2m]) /
|
||||
rate(node_network_transmit_packets_total{job="node-exporter"}[2m]) > 0.01
|
||||
|
||||
'
|
||||
for: 1h
|
||||
labels:
|
||||
severity: warning
|
||||
- alert: NodeHighNumberConntrackEntriesUsed
|
||||
annotations:
|
||||
description: '{{ $value | humanizePercentage }} of conntrack entries are
|
||||
used.'
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodehighnumberconntrackentriesused
|
||||
summary: Number of conntrack are getting close to the limit.
|
||||
expr: '(node_nf_conntrack_entries{job="node-exporter"} / node_nf_conntrack_entries_limit)
|
||||
> 0.75
|
||||
|
||||
'
|
||||
labels:
|
||||
severity: warning
|
||||
- alert: NodeTextFileCollectorScrapeError
|
||||
annotations:
|
||||
description: Node Exporter text file collector on {{ $labels.instance
|
||||
}} failed to scrape.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodetextfilecollectorscrapeerror
|
||||
summary: Node Exporter text file collector failed to scrape.
|
||||
expr: 'node_textfile_scrape_error{job="node-exporter"} == 1
|
||||
|
||||
'
|
||||
labels:
|
||||
severity: warning
|
||||
- alert: NodeClockSkewDetected
|
||||
annotations:
|
||||
description: Clock at {{ $labels.instance }} is out of sync by more than
|
||||
0.05s. Ensure NTP is configured correctly on this host.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodeclockskewdetected
|
||||
summary: Clock skew detected.
|
||||
expr: "(\n node_timex_offset_seconds{job=\"node-exporter\"} > 0.05\nand\n\
|
||||
\ deriv(node_timex_offset_seconds{job=\"node-exporter\"}[5m]) >= 0\n\
|
||||
)\nor\n(\n node_timex_offset_seconds{job=\"node-exporter\"} < -0.05\n\
|
||||
and\n deriv(node_timex_offset_seconds{job=\"node-exporter\"}[5m]) <=\
|
||||
\ 0\n)\n"
|
||||
for: 10m
|
||||
labels:
|
||||
severity: warning
|
||||
- alert: NodeClockNotSynchronising
|
||||
annotations:
|
||||
description: Clock at {{ $labels.instance }} is not synchronising. Ensure
|
||||
NTP is configured on this host.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodeclocknotsynchronising
|
||||
summary: Clock not synchronising.
|
||||
expr: 'min_over_time(node_timex_sync_status{job="node-exporter"}[5m]) ==
|
||||
0
|
||||
|
||||
and
|
||||
|
||||
node_timex_maxerror_seconds{job="node-exporter"} >= 16
|
||||
|
||||
'
|
||||
for: 10m
|
||||
labels:
|
||||
severity: warning
|
||||
- alert: NodeRAIDDegraded
|
||||
annotations:
|
||||
description: RAID array '{{ $labels.device }}' at {{ $labels.instance
|
||||
}} is in degraded state due to one or more disks failures. Number of
|
||||
spare drives is insufficient to fix issue automatically.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/noderaiddegraded
|
||||
summary: RAID Array is degraded.
|
||||
expr: 'node_md_disks_required{job="node-exporter",device=~"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)"}
|
||||
- ignoring (state) (node_md_disks{state="active",job="node-exporter",device=~"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)"})
|
||||
> 0
|
||||
|
||||
'
|
||||
for: 15m
|
||||
labels:
|
||||
severity: critical
|
||||
- alert: NodeRAIDDiskFailure
|
||||
annotations:
|
||||
description: At least one device in RAID array at {{ $labels.instance
|
||||
}} failed. Array '{{ $labels.device }}' needs attention and possibly
|
||||
a disk swap.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/noderaiddiskfailure
|
||||
summary: Failed device in RAID array.
|
||||
expr: 'node_md_disks{state="failed",job="node-exporter",device=~"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)"}
|
||||
> 0
|
||||
|
||||
'
|
||||
labels:
|
||||
severity: warning
|
||||
- alert: NodeFileDescriptorLimit
|
||||
annotations:
|
||||
description: File descriptors limit at {{ $labels.instance }} is currently
|
||||
at {{ printf "%.2f" $value }}%.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodefiledescriptorlimit
|
||||
summary: Kernel is predicted to exhaust file descriptors limit soon.
|
||||
expr: "(\n node_filefd_allocated{job=\"node-exporter\"} * 100 / node_filefd_maximum{job=\"\
|
||||
node-exporter\"} > 70\n)\n"
|
||||
for: 15m
|
||||
labels:
|
||||
severity: warning
|
||||
- alert: NodeFileDescriptorLimit
|
||||
annotations:
|
||||
description: File descriptors limit at {{ $labels.instance }} is currently
|
||||
at {{ printf "%.2f" $value }}%.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodefiledescriptorlimit
|
||||
summary: Kernel is predicted to exhaust file descriptors limit soon.
|
||||
expr: "(\n node_filefd_allocated{job=\"node-exporter\"} * 100 / node_filefd_maximum{job=\"\
|
||||
node-exporter\"} > 90\n)\n"
|
||||
for: 15m
|
||||
labels:
|
||||
severity: critical
|
||||
- alert: NodeCPUHighUsage
|
||||
annotations:
|
||||
description: 'CPU usage at {{ $labels.instance }} has been above 90% for
|
||||
the last 15 minutes, is currently at {{ printf "%.2f" $value }}%.
|
||||
|
||||
'
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodecpuhighusage
|
||||
summary: High CPU usage.
|
||||
expr: 'sum without(mode) (avg without (cpu) (rate(node_cpu_seconds_total{job="node-exporter",
|
||||
mode!="idle"}[2m]))) * 100 > 90
|
||||
|
||||
'
|
||||
for: 15m
|
||||
labels:
|
||||
severity: info
|
||||
- alert: NodeSystemSaturation
|
||||
annotations:
|
||||
description: 'System load per core at {{ $labels.instance }} has been
|
||||
above 2 for the last 15 minutes, is currently at {{ printf "%.2f" $value
|
||||
}}.
|
||||
|
||||
This might indicate this instance resources saturation and can cause
|
||||
it becoming unresponsive.
|
||||
|
||||
'
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodesystemsaturation
|
||||
summary: System saturated, load per core is very high.
|
||||
expr: 'node_load1{job="node-exporter"}
|
||||
|
||||
/ count without (cpu, mode) (node_cpu_seconds_total{job="node-exporter",
|
||||
mode="idle"}) > 2
|
||||
|
||||
'
|
||||
for: 15m
|
||||
labels:
|
||||
severity: warning
|
||||
- alert: NodeMemoryMajorPagesFaults
|
||||
annotations:
|
||||
description: 'Memory major pages are occurring at very high rate at {{
|
||||
$labels.instance }}, 500 major page faults per second for the last 15
|
||||
minutes, is currently at {{ printf "%.2f" $value }}.
|
||||
|
||||
Please check that there is enough memory available at this instance.
|
||||
|
||||
'
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodememorymajorpagesfaults
|
||||
summary: Memory major page faults are occurring at very high rate.
|
||||
expr: 'rate(node_vmstat_pgmajfault{job="node-exporter"}[5m]) > 500
|
||||
|
||||
'
|
||||
for: 15m
|
||||
labels:
|
||||
severity: warning
|
||||
- alert: NodeMemoryHighUtilization
|
||||
annotations:
|
||||
description: 'Memory is filling up at {{ $labels.instance }}, has been
|
||||
above 90% for the last 15 minutes, is currently at {{ printf "%.2f"
|
||||
$value }}%.
|
||||
|
||||
'
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodememoryhighutilization
|
||||
summary: Host is running out of memory.
|
||||
expr: '100 - (node_memory_MemAvailable_bytes{job="node-exporter"} / node_memory_MemTotal_bytes{job="node-exporter"}
|
||||
* 100) > 90
|
||||
|
||||
'
|
||||
for: 15m
|
||||
labels:
|
||||
severity: warning
|
||||
- alert: NodeDiskIOSaturation
|
||||
annotations:
|
||||
description: 'Disk IO queue (aqu-sq) is high on {{ $labels.device }} at
|
||||
{{ $labels.instance }}, has been above 10 for the last 15 minutes, is
|
||||
currently at {{ printf "%.2f" $value }}.
|
||||
|
||||
This symptom might indicate disk saturation.
|
||||
|
||||
'
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodediskiosaturation
|
||||
summary: Disk IO queue is high.
|
||||
expr: 'rate(node_disk_io_time_weighted_seconds_total{job="node-exporter",
|
||||
device=~"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)"}[5m])
|
||||
> 10
|
||||
|
||||
'
|
||||
for: 30m
|
||||
labels:
|
||||
severity: warning
|
||||
- alert: NodeSystemdServiceFailed
|
||||
annotations:
|
||||
description: Systemd service {{ $labels.name }} has entered failed state
|
||||
at {{ $labels.instance }}
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodesystemdservicefailed
|
||||
summary: Systemd service has entered failed state.
|
||||
expr: 'node_systemd_unit_state{job="node-exporter", state="failed"} == 1
|
||||
|
||||
'
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
- alert: NodeBondingDegraded
|
||||
annotations:
|
||||
description: Bonding interface {{ $labels.master }} on {{ $labels.instance
|
||||
}} is in degraded state due to one or more slave failures.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodebondingdegraded
|
||||
summary: Bonding interface is degraded
|
||||
expr: '(node_bonding_slaves - node_bonding_active) != 0
|
||||
|
||||
'
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
- name: node-exporter.rules
|
||||
rules:
|
||||
- expr: "count without (cpu, mode) (\n node_cpu_seconds_total{job=\"node-exporter\"\
|
||||
,mode=\"idle\"}\n)\n"
|
||||
record: instance:node_num_cpu:sum
|
||||
- expr: "1 - avg without (cpu) (\n sum without (mode) (rate(node_cpu_seconds_total{job=\"\
|
||||
node-exporter\", mode=~\"idle|iowait|steal\"}[5m]))\n)\n"
|
||||
record: instance:node_cpu_utilisation:rate5m
|
||||
- expr: "(\n node_load1{job=\"node-exporter\"}\n/\n instance:node_num_cpu:sum{job=\"\
|
||||
node-exporter\"}\n)\n"
|
||||
record: instance:node_load1_per_cpu:ratio
|
||||
- expr: "1 - (\n (\n node_memory_MemAvailable_bytes{job=\"node-exporter\"\
|
||||
}\n or\n (\n node_memory_Buffers_bytes{job=\"node-exporter\"\
|
||||
}\n +\n node_memory_Cached_bytes{job=\"node-exporter\"}\n \
|
||||
\ +\n node_memory_MemFree_bytes{job=\"node-exporter\"}\n \
|
||||
\ +\n node_memory_Slab_bytes{job=\"node-exporter\"}\n )\n )\n\
|
||||
/\n node_memory_MemTotal_bytes{job=\"node-exporter\"}\n)\n"
|
||||
record: instance:node_memory_utilisation:ratio
|
||||
- expr: 'rate(node_vmstat_pgmajfault{job="node-exporter"}[5m])
|
||||
|
||||
'
|
||||
record: instance:node_vmstat_pgmajfault:rate5m
|
||||
- expr: 'rate(node_disk_io_time_seconds_total{job="node-exporter", device=~"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)"}[5m])
|
||||
|
||||
'
|
||||
record: instance_device:node_disk_io_time_seconds:rate5m
|
||||
- expr: 'rate(node_disk_io_time_weighted_seconds_total{job="node-exporter",
|
||||
device=~"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)"}[5m])
|
||||
|
||||
'
|
||||
record: instance_device:node_disk_io_time_weighted_seconds:rate5m
|
||||
- expr: "sum without (device) (\n rate(node_network_receive_bytes_total{job=\"\
|
||||
node-exporter\", device!=\"lo\"}[5m])\n)\n"
|
||||
record: instance:node_network_receive_bytes_excluding_lo:rate5m
|
||||
- expr: "sum without (device) (\n rate(node_network_transmit_bytes_total{job=\"\
|
||||
node-exporter\", device!=\"lo\"}[5m])\n)\n"
|
||||
record: instance:node_network_transmit_bytes_excluding_lo:rate5m
|
||||
- expr: "sum without (device) (\n rate(node_network_receive_drop_total{job=\"\
|
||||
node-exporter\", device!=\"lo\"}[5m])\n)\n"
|
||||
record: instance:node_network_receive_drop_excluding_lo:rate5m
|
||||
- expr: "sum without (device) (\n rate(node_network_transmit_drop_total{job=\"\
|
||||
node-exporter\", device!=\"lo\"}[5m])\n)\n"
|
||||
record: instance:node_network_transmit_drop_excluding_lo:rate5m
|
||||
|
|
@ -0,0 +1,22 @@
|
|||
apiVersion: v1
|
||||
kind: Service
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: exporter
|
||||
app.kubernetes.io/name: node-exporter
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 1.6.1
|
||||
name: node-exporter
|
||||
namespace: monitoring
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
spec:
|
||||
clusterIP: None
|
||||
ports:
|
||||
- name: https
|
||||
port: 9100
|
||||
targetPort: https
|
||||
selector:
|
||||
app.kubernetes.io/component: exporter
|
||||
app.kubernetes.io/name: node-exporter
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
|
|
@ -0,0 +1,13 @@
|
|||
apiVersion: v1
|
||||
automountServiceAccountToken: false
|
||||
kind: ServiceAccount
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: exporter
|
||||
app.kubernetes.io/name: node-exporter
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 1.6.1
|
||||
name: node-exporter
|
||||
namespace: monitoring
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
|
|
@ -0,0 +1,33 @@
|
|||
apiVersion: monitoring.coreos.com/v1
|
||||
kind: ServiceMonitor
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: exporter
|
||||
app.kubernetes.io/name: node-exporter
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 1.6.1
|
||||
name: node-exporter
|
||||
namespace: monitoring
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
spec:
|
||||
endpoints:
|
||||
- bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token
|
||||
interval: 15s
|
||||
port: https
|
||||
relabelings:
|
||||
- action: replace
|
||||
regex: (.*)
|
||||
replacement: $1
|
||||
sourceLabels:
|
||||
- __meta_kubernetes_pod_node_name
|
||||
targetLabel: instance
|
||||
scheme: https
|
||||
tlsConfig:
|
||||
insecureSkipVerify: true
|
||||
jobLabel: app.kubernetes.io/name
|
||||
selector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/component: exporter
|
||||
app.kubernetes.io/name: node-exporter
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
|
|
@ -0,0 +1,23 @@
|
|||
apiVersion: rbac.authorization.k8s.io/v1
|
||||
kind: ClusterRole
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: prometheus
|
||||
app.kubernetes.io/instance: k8s
|
||||
app.kubernetes.io/name: prometheus
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 2.46.0
|
||||
name: prometheus-k8s
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
rules:
|
||||
- apiGroups:
|
||||
- ''
|
||||
resources:
|
||||
- nodes/metrics
|
||||
verbs:
|
||||
- get
|
||||
- nonResourceURLs:
|
||||
- /metrics
|
||||
verbs:
|
||||
- get
|
||||
|
|
@ -0,0 +1,20 @@
|
|||
apiVersion: rbac.authorization.k8s.io/v1
|
||||
kind: ClusterRoleBinding
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: prometheus
|
||||
app.kubernetes.io/instance: k8s
|
||||
app.kubernetes.io/name: prometheus
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 2.46.0
|
||||
name: prometheus-k8s
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
roleRef:
|
||||
apiGroup: rbac.authorization.k8s.io
|
||||
kind: ClusterRole
|
||||
name: prometheus-k8s
|
||||
subjects:
|
||||
- kind: ServiceAccount
|
||||
name: prometheus-k8s
|
||||
namespace: monitoring
|
||||
|
|
@ -0,0 +1,49 @@
|
|||
apiVersion: networking.k8s.io/v1
|
||||
kind: NetworkPolicy
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: prometheus
|
||||
app.kubernetes.io/instance: k8s
|
||||
app.kubernetes.io/name: prometheus
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 2.46.0
|
||||
name: prometheus-k8s
|
||||
namespace: monitoring
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
spec:
|
||||
egress:
|
||||
- {}
|
||||
ingress:
|
||||
- from:
|
||||
- podSelector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/name: prometheus
|
||||
ports:
|
||||
- port: 9090
|
||||
protocol: TCP
|
||||
- port: 8080
|
||||
protocol: TCP
|
||||
- from:
|
||||
- podSelector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/name: prometheus-adapter
|
||||
ports:
|
||||
- port: 9090
|
||||
protocol: TCP
|
||||
- from:
|
||||
- podSelector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/name: grafana
|
||||
ports:
|
||||
- port: 9090
|
||||
protocol: TCP
|
||||
podSelector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/component: prometheus
|
||||
app.kubernetes.io/instance: k8s
|
||||
app.kubernetes.io/name: prometheus
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
policyTypes:
|
||||
- Egress
|
||||
- Ingress
|
||||
|
|
@ -0,0 +1,21 @@
|
|||
apiVersion: policy/v1
|
||||
kind: PodDisruptionBudget
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: prometheus
|
||||
app.kubernetes.io/instance: k8s
|
||||
app.kubernetes.io/name: prometheus
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 2.46.0
|
||||
name: prometheus-k8s
|
||||
namespace: monitoring
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
spec:
|
||||
minAvailable: 1
|
||||
selector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/component: prometheus
|
||||
app.kubernetes.io/instance: k8s
|
||||
app.kubernetes.io/name: prometheus
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
|
|
@ -0,0 +1,50 @@
|
|||
apiVersion: monitoring.coreos.com/v1
|
||||
kind: Prometheus
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: prometheus
|
||||
app.kubernetes.io/instance: k8s
|
||||
app.kubernetes.io/name: prometheus
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 2.46.0
|
||||
name: k8s
|
||||
namespace: monitoring
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
spec:
|
||||
alerting:
|
||||
alertmanagers:
|
||||
- apiVersion: v2
|
||||
name: alertmanager-main
|
||||
namespace: monitoring
|
||||
port: web
|
||||
enableFeatures: []
|
||||
externalLabels: {}
|
||||
image: quay.io/prometheus/prometheus:v2.46.0
|
||||
nodeSelector:
|
||||
kubernetes.io/os: linux
|
||||
podMetadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: prometheus
|
||||
app.kubernetes.io/instance: k8s
|
||||
app.kubernetes.io/name: prometheus
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 2.46.0
|
||||
podMonitorNamespaceSelector: {}
|
||||
podMonitorSelector: {}
|
||||
probeNamespaceSelector: {}
|
||||
probeSelector: {}
|
||||
replicas: 2
|
||||
resources:
|
||||
requests:
|
||||
memory: 400Mi
|
||||
ruleNamespaceSelector: {}
|
||||
ruleSelector: {}
|
||||
securityContext:
|
||||
fsGroup: 2000
|
||||
runAsNonRoot: true
|
||||
runAsUser: 1000
|
||||
serviceAccountName: prometheus-k8s
|
||||
serviceMonitorNamespaceSelector: {}
|
||||
serviceMonitorSelector: {}
|
||||
version: 2.46.0
|
||||
|
|
@ -0,0 +1,348 @@
|
|||
apiVersion: monitoring.coreos.com/v1
|
||||
kind: PrometheusRule
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: prometheus
|
||||
app.kubernetes.io/instance: k8s
|
||||
app.kubernetes.io/name: prometheus
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 2.46.0
|
||||
prometheus: k8s
|
||||
role: alert-rules
|
||||
name: prometheus-k8s-prometheus-rules
|
||||
namespace: monitoring
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
spec:
|
||||
groups:
|
||||
- name: prometheus
|
||||
rules:
|
||||
- alert: PrometheusBadConfig
|
||||
annotations:
|
||||
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has failed
|
||||
to reload its configuration.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusbadconfig
|
||||
summary: Failed Prometheus configuration reload.
|
||||
expr: '# Without max_over_time, failed scrapes could create false negatives,
|
||||
see
|
||||
|
||||
# https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0
|
||||
for details.
|
||||
|
||||
max_over_time(prometheus_config_last_reload_successful{job="prometheus-k8s",namespace="monitoring"}[5m])
|
||||
== 0
|
||||
|
||||
'
|
||||
for: 10m
|
||||
labels:
|
||||
severity: critical
|
||||
- alert: PrometheusSDRefreshFailure
|
||||
annotations:
|
||||
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has failed
|
||||
to refresh SD with mechanism {{$labels.mechanism}}.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheussdrefreshfailure
|
||||
summary: Failed Prometheus SD refresh.
|
||||
expr: 'increase(prometheus_sd_refresh_failures_total{job="prometheus-k8s",namespace="monitoring"}[10m])
|
||||
> 0
|
||||
|
||||
'
|
||||
for: 20m
|
||||
labels:
|
||||
severity: warning
|
||||
- alert: PrometheusNotificationQueueRunningFull
|
||||
annotations:
|
||||
description: Alert notification queue of Prometheus {{$labels.namespace}}/{{$labels.pod}}
|
||||
is running full.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusnotificationqueuerunningfull
|
||||
summary: Prometheus alert notification queue predicted to run full in
|
||||
less than 30m.
|
||||
expr: "# Without min_over_time, failed scrapes could create false negatives,\
|
||||
\ see\n# https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0\
|
||||
\ for details.\n(\n predict_linear(prometheus_notifications_queue_length{job=\"\
|
||||
prometheus-k8s\",namespace=\"monitoring\"}[5m], 60 * 30)\n>\n min_over_time(prometheus_notifications_queue_capacity{job=\"\
|
||||
prometheus-k8s\",namespace=\"monitoring\"}[5m])\n)\n"
|
||||
for: 15m
|
||||
labels:
|
||||
severity: warning
|
||||
- alert: PrometheusErrorSendingAlertsToSomeAlertmanagers
|
||||
annotations:
|
||||
description: '{{ printf "%.1f" $value }}% errors while sending alerts
|
||||
from Prometheus {{$labels.namespace}}/{{$labels.pod}} to Alertmanager
|
||||
{{$labels.alertmanager}}.'
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheuserrorsendingalertstosomealertmanagers
|
||||
summary: Prometheus has encountered more than 1% errors sending alerts
|
||||
to a specific Alertmanager.
|
||||
expr: "(\n rate(prometheus_notifications_errors_total{job=\"prometheus-k8s\"\
|
||||
,namespace=\"monitoring\"}[5m])\n/\n rate(prometheus_notifications_sent_total{job=\"\
|
||||
prometheus-k8s\",namespace=\"monitoring\"}[5m])\n)\n* 100\n> 1\n"
|
||||
for: 15m
|
||||
labels:
|
||||
severity: warning
|
||||
- alert: PrometheusNotConnectedToAlertmanagers
|
||||
annotations:
|
||||
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} is not connected
|
||||
to any Alertmanagers.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusnotconnectedtoalertmanagers
|
||||
summary: Prometheus is not connected to any Alertmanagers.
|
||||
expr: '# Without max_over_time, failed scrapes could create false negatives,
|
||||
see
|
||||
|
||||
# https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0
|
||||
for details.
|
||||
|
||||
max_over_time(prometheus_notifications_alertmanagers_discovered{job="prometheus-k8s",namespace="monitoring"}[5m])
|
||||
< 1
|
||||
|
||||
'
|
||||
for: 10m
|
||||
labels:
|
||||
severity: warning
|
||||
- alert: PrometheusTSDBReloadsFailing
|
||||
annotations:
|
||||
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has detected
|
||||
{{$value | humanize}} reload failures over the last 3h.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheustsdbreloadsfailing
|
||||
summary: Prometheus has issues reloading blocks from disk.
|
||||
expr: 'increase(prometheus_tsdb_reloads_failures_total{job="prometheus-k8s",namespace="monitoring"}[3h])
|
||||
> 0
|
||||
|
||||
'
|
||||
for: 4h
|
||||
labels:
|
||||
severity: warning
|
||||
- alert: PrometheusTSDBCompactionsFailing
|
||||
annotations:
|
||||
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has detected
|
||||
{{$value | humanize}} compaction failures over the last 3h.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheustsdbcompactionsfailing
|
||||
summary: Prometheus has issues compacting blocks.
|
||||
expr: 'increase(prometheus_tsdb_compactions_failed_total{job="prometheus-k8s",namespace="monitoring"}[3h])
|
||||
> 0
|
||||
|
||||
'
|
||||
for: 4h
|
||||
labels:
|
||||
severity: warning
|
||||
- alert: PrometheusNotIngestingSamples
|
||||
annotations:
|
||||
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} is not ingesting
|
||||
samples.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusnotingestingsamples
|
||||
summary: Prometheus is not ingesting samples.
|
||||
expr: "(\n rate(prometheus_tsdb_head_samples_appended_total{job=\"prometheus-k8s\"\
|
||||
,namespace=\"monitoring\"}[5m]) <= 0\nand\n (\n sum without(scrape_job)\
|
||||
\ (prometheus_target_metadata_cache_entries{job=\"prometheus-k8s\",namespace=\"\
|
||||
monitoring\"}) > 0\n or\n sum without(rule_group) (prometheus_rule_group_rules{job=\"\
|
||||
prometheus-k8s\",namespace=\"monitoring\"}) > 0\n )\n)\n"
|
||||
for: 10m
|
||||
labels:
|
||||
severity: warning
|
||||
- alert: PrometheusDuplicateTimestamps
|
||||
annotations:
|
||||
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} is dropping
|
||||
{{ printf "%.4g" $value }} samples/s with different values but duplicated
|
||||
timestamp.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusduplicatetimestamps
|
||||
summary: Prometheus is dropping samples with duplicate timestamps.
|
||||
expr: 'rate(prometheus_target_scrapes_sample_duplicate_timestamp_total{job="prometheus-k8s",namespace="monitoring"}[5m])
|
||||
> 0
|
||||
|
||||
'
|
||||
for: 10m
|
||||
labels:
|
||||
severity: warning
|
||||
- alert: PrometheusOutOfOrderTimestamps
|
||||
annotations:
|
||||
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} is dropping
|
||||
{{ printf "%.4g" $value }} samples/s with timestamps arriving out of
|
||||
order.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusoutofordertimestamps
|
||||
summary: Prometheus drops samples with out-of-order timestamps.
|
||||
expr: 'rate(prometheus_target_scrapes_sample_out_of_order_total{job="prometheus-k8s",namespace="monitoring"}[5m])
|
||||
> 0
|
||||
|
||||
'
|
||||
for: 10m
|
||||
labels:
|
||||
severity: warning
|
||||
- alert: PrometheusRemoteStorageFailures
|
||||
annotations:
|
||||
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} failed to
|
||||
send {{ printf "%.1f" $value }}% of the samples to {{ $labels.remote_name}}:{{
|
||||
$labels.url }}
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusremotestoragefailures
|
||||
summary: Prometheus fails to send samples to remote storage.
|
||||
expr: "(\n (rate(prometheus_remote_storage_failed_samples_total{job=\"\
|
||||
prometheus-k8s\",namespace=\"monitoring\"}[5m]) or rate(prometheus_remote_storage_samples_failed_total{job=\"\
|
||||
prometheus-k8s\",namespace=\"monitoring\"}[5m]))\n/\n (\n (rate(prometheus_remote_storage_failed_samples_total{job=\"\
|
||||
prometheus-k8s\",namespace=\"monitoring\"}[5m]) or rate(prometheus_remote_storage_samples_failed_total{job=\"\
|
||||
prometheus-k8s\",namespace=\"monitoring\"}[5m]))\n +\n (rate(prometheus_remote_storage_succeeded_samples_total{job=\"\
|
||||
prometheus-k8s\",namespace=\"monitoring\"}[5m]) or rate(prometheus_remote_storage_samples_total{job=\"\
|
||||
prometheus-k8s\",namespace=\"monitoring\"}[5m]))\n )\n)\n* 100\n> 1\n"
|
||||
for: 15m
|
||||
labels:
|
||||
severity: critical
|
||||
- alert: PrometheusRemoteWriteBehind
|
||||
annotations:
|
||||
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} remote write
|
||||
is {{ printf "%.1f" $value }}s behind for {{ $labels.remote_name}}:{{
|
||||
$labels.url }}.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusremotewritebehind
|
||||
summary: Prometheus remote write is behind.
|
||||
expr: "# Without max_over_time, failed scrapes could create false negatives,\
|
||||
\ see\n# https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0\
|
||||
\ for details.\n(\n max_over_time(prometheus_remote_storage_highest_timestamp_in_seconds{job=\"\
|
||||
prometheus-k8s\",namespace=\"monitoring\"}[5m])\n- ignoring(remote_name,\
|
||||
\ url) group_right\n max_over_time(prometheus_remote_storage_queue_highest_sent_timestamp_seconds{job=\"\
|
||||
prometheus-k8s\",namespace=\"monitoring\"}[5m])\n)\n> 120\n"
|
||||
for: 15m
|
||||
labels:
|
||||
severity: critical
|
||||
- alert: PrometheusRemoteWriteDesiredShards
|
||||
annotations:
|
||||
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} remote write
|
||||
desired shards calculation wants to run {{ $value }} shards for queue
|
||||
{{ $labels.remote_name}}:{{ $labels.url }}, which is more than the max
|
||||
of {{ printf `prometheus_remote_storage_shards_max{instance="%s",job="prometheus-k8s",namespace="monitoring"}`
|
||||
$labels.instance | query | first | value }}.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusremotewritedesiredshards
|
||||
summary: Prometheus remote write desired shards calculation wants to run
|
||||
more than configured max shards.
|
||||
expr: "# Without max_over_time, failed scrapes could create false negatives,\
|
||||
\ see\n# https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0\
|
||||
\ for details.\n(\n max_over_time(prometheus_remote_storage_shards_desired{job=\"\
|
||||
prometheus-k8s\",namespace=\"monitoring\"}[5m])\n>\n max_over_time(prometheus_remote_storage_shards_max{job=\"\
|
||||
prometheus-k8s\",namespace=\"monitoring\"}[5m])\n)\n"
|
||||
for: 15m
|
||||
labels:
|
||||
severity: warning
|
||||
- alert: PrometheusRuleFailures
|
||||
annotations:
|
||||
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has failed
|
||||
to evaluate {{ printf "%.0f" $value }} rules in the last 5m.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusrulefailures
|
||||
summary: Prometheus is failing rule evaluations.
|
||||
expr: 'increase(prometheus_rule_evaluation_failures_total{job="prometheus-k8s",namespace="monitoring"}[5m])
|
||||
> 0
|
||||
|
||||
'
|
||||
for: 15m
|
||||
labels:
|
||||
severity: critical
|
||||
- alert: PrometheusMissingRuleEvaluations
|
||||
annotations:
|
||||
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has missed
|
||||
{{ printf "%.0f" $value }} rule group evaluations in the last 5m.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusmissingruleevaluations
|
||||
summary: Prometheus is missing rule evaluations due to slow rule group
|
||||
evaluation.
|
||||
expr: 'increase(prometheus_rule_group_iterations_missed_total{job="prometheus-k8s",namespace="monitoring"}[5m])
|
||||
> 0
|
||||
|
||||
'
|
||||
for: 15m
|
||||
labels:
|
||||
severity: warning
|
||||
- alert: PrometheusTargetLimitHit
|
||||
annotations:
|
||||
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has dropped
|
||||
{{ printf "%.0f" $value }} targets because the number of targets exceeded
|
||||
the configured target_limit.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheustargetlimithit
|
||||
summary: Prometheus has dropped targets because some scrape configs have
|
||||
exceeded the targets limit.
|
||||
expr: 'increase(prometheus_target_scrape_pool_exceeded_target_limit_total{job="prometheus-k8s",namespace="monitoring"}[5m])
|
||||
> 0
|
||||
|
||||
'
|
||||
for: 15m
|
||||
labels:
|
||||
severity: warning
|
||||
- alert: PrometheusLabelLimitHit
|
||||
annotations:
|
||||
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has dropped
|
||||
{{ printf "%.0f" $value }} targets because some samples exceeded the
|
||||
configured label_limit, label_name_length_limit or label_value_length_limit.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheuslabellimithit
|
||||
summary: Prometheus has dropped targets because some scrape configs have
|
||||
exceeded the labels limit.
|
||||
expr: 'increase(prometheus_target_scrape_pool_exceeded_label_limits_total{job="prometheus-k8s",namespace="monitoring"}[5m])
|
||||
> 0
|
||||
|
||||
'
|
||||
for: 15m
|
||||
labels:
|
||||
severity: warning
|
||||
- alert: PrometheusScrapeBodySizeLimitHit
|
||||
annotations:
|
||||
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has failed
|
||||
{{ printf "%.0f" $value }} scrapes in the last 5m because some targets
|
||||
exceeded the configured body_size_limit.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusscrapebodysizelimithit
|
||||
summary: Prometheus has dropped some targets that exceeded body size limit.
|
||||
expr: 'increase(prometheus_target_scrapes_exceeded_body_size_limit_total{job="prometheus-k8s",namespace="monitoring"}[5m])
|
||||
> 0
|
||||
|
||||
'
|
||||
for: 15m
|
||||
labels:
|
||||
severity: warning
|
||||
- alert: PrometheusScrapeSampleLimitHit
|
||||
annotations:
|
||||
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has failed
|
||||
{{ printf "%.0f" $value }} scrapes in the last 5m because some targets
|
||||
exceeded the configured sample_limit.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusscrapesamplelimithit
|
||||
summary: Prometheus has failed scrapes that have exceeded the configured
|
||||
sample limit.
|
||||
expr: 'increase(prometheus_target_scrapes_exceeded_sample_limit_total{job="prometheus-k8s",namespace="monitoring"}[5m])
|
||||
> 0
|
||||
|
||||
'
|
||||
for: 15m
|
||||
labels:
|
||||
severity: warning
|
||||
- alert: PrometheusTargetSyncFailure
|
||||
annotations:
|
||||
description: '{{ printf "%.0f" $value }} targets in Prometheus {{$labels.namespace}}/{{$labels.pod}}
|
||||
have failed to sync because invalid configuration was supplied.'
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheustargetsyncfailure
|
||||
summary: Prometheus has failed to sync targets.
|
||||
expr: 'increase(prometheus_target_sync_failed_total{job="prometheus-k8s",namespace="monitoring"}[30m])
|
||||
> 0
|
||||
|
||||
'
|
||||
for: 5m
|
||||
labels:
|
||||
severity: critical
|
||||
- alert: PrometheusHighQueryLoad
|
||||
annotations:
|
||||
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} query API
|
||||
has less than 20% available capacity in its query engine for the last
|
||||
15 minutes.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheushighqueryload
|
||||
summary: Prometheus is reaching its maximum capacity serving concurrent
|
||||
requests.
|
||||
expr: 'avg_over_time(prometheus_engine_queries{job="prometheus-k8s",namespace="monitoring"}[5m])
|
||||
/ max_over_time(prometheus_engine_queries_concurrent_max{job="prometheus-k8s",namespace="monitoring"}[5m])
|
||||
> 0.8
|
||||
|
||||
'
|
||||
for: 15m
|
||||
labels:
|
||||
severity: warning
|
||||
- alert: PrometheusErrorSendingAlertsToAnyAlertmanager
|
||||
annotations:
|
||||
description: '{{ printf "%.1f" $value }}% minimum errors while sending
|
||||
alerts from Prometheus {{$labels.namespace}}/{{$labels.pod}} to any
|
||||
Alertmanager.'
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheuserrorsendingalertstoanyalertmanager
|
||||
summary: Prometheus encounters more than 3% errors sending alerts to any
|
||||
Alertmanager.
|
||||
expr: "min without (alertmanager) (\n rate(prometheus_notifications_errors_total{job=\"\
|
||||
prometheus-k8s\",namespace=\"monitoring\",alertmanager!~``}[5m])\n/\n\
|
||||
\ rate(prometheus_notifications_sent_total{job=\"prometheus-k8s\",namespace=\"\
|
||||
monitoring\",alertmanager!~``}[5m])\n)\n* 100\n> 3\n"
|
||||
for: 15m
|
||||
labels:
|
||||
severity: critical
|
||||
|
|
@ -0,0 +1,21 @@
|
|||
apiVersion: rbac.authorization.k8s.io/v1
|
||||
kind: RoleBinding
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: prometheus
|
||||
app.kubernetes.io/instance: k8s
|
||||
app.kubernetes.io/name: prometheus
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 2.46.0
|
||||
name: prometheus-k8s-config
|
||||
namespace: monitoring
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
roleRef:
|
||||
apiGroup: rbac.authorization.k8s.io
|
||||
kind: Role
|
||||
name: prometheus-k8s-config
|
||||
subjects:
|
||||
- kind: ServiceAccount
|
||||
name: prometheus-k8s
|
||||
namespace: monitoring
|
||||
|
|
@ -0,0 +1,63 @@
|
|||
apiVersion: rbac.authorization.k8s.io/v1
|
||||
items:
|
||||
- apiVersion: rbac.authorization.k8s.io/v1
|
||||
kind: RoleBinding
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: prometheus
|
||||
app.kubernetes.io/instance: k8s
|
||||
app.kubernetes.io/name: prometheus
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 2.46.0
|
||||
name: prometheus-k8s
|
||||
namespace: default
|
||||
roleRef:
|
||||
apiGroup: rbac.authorization.k8s.io
|
||||
kind: Role
|
||||
name: prometheus-k8s
|
||||
subjects:
|
||||
- kind: ServiceAccount
|
||||
name: prometheus-k8s
|
||||
namespace: monitoring
|
||||
- apiVersion: rbac.authorization.k8s.io/v1
|
||||
kind: RoleBinding
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: prometheus
|
||||
app.kubernetes.io/instance: k8s
|
||||
app.kubernetes.io/name: prometheus
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 2.46.0
|
||||
name: prometheus-k8s
|
||||
namespace: kube-system
|
||||
roleRef:
|
||||
apiGroup: rbac.authorization.k8s.io
|
||||
kind: Role
|
||||
name: prometheus-k8s
|
||||
subjects:
|
||||
- kind: ServiceAccount
|
||||
name: prometheus-k8s
|
||||
namespace: monitoring
|
||||
- apiVersion: rbac.authorization.k8s.io/v1
|
||||
kind: RoleBinding
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: prometheus
|
||||
app.kubernetes.io/instance: k8s
|
||||
app.kubernetes.io/name: prometheus
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 2.46.0
|
||||
name: prometheus-k8s
|
||||
namespace: monitoring
|
||||
roleRef:
|
||||
apiGroup: rbac.authorization.k8s.io
|
||||
kind: Role
|
||||
name: prometheus-k8s
|
||||
subjects:
|
||||
- kind: ServiceAccount
|
||||
name: prometheus-k8s
|
||||
namespace: monitoring
|
||||
kind: RoleBindingList
|
||||
metadata:
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
|
|
@ -0,0 +1,20 @@
|
|||
apiVersion: rbac.authorization.k8s.io/v1
|
||||
kind: Role
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: prometheus
|
||||
app.kubernetes.io/instance: k8s
|
||||
app.kubernetes.io/name: prometheus
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 2.46.0
|
||||
name: prometheus-k8s-config
|
||||
namespace: monitoring
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
rules:
|
||||
- apiGroups:
|
||||
- ''
|
||||
resources:
|
||||
- configmaps
|
||||
verbs:
|
||||
- get
|
||||
|
|
@ -0,0 +1,120 @@
|
|||
apiVersion: rbac.authorization.k8s.io/v1
|
||||
items:
|
||||
- apiVersion: rbac.authorization.k8s.io/v1
|
||||
kind: Role
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: prometheus
|
||||
app.kubernetes.io/instance: k8s
|
||||
app.kubernetes.io/name: prometheus
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 2.46.0
|
||||
name: prometheus-k8s
|
||||
namespace: default
|
||||
rules:
|
||||
- apiGroups:
|
||||
- ''
|
||||
resources:
|
||||
- services
|
||||
- endpoints
|
||||
- pods
|
||||
verbs:
|
||||
- get
|
||||
- list
|
||||
- watch
|
||||
- apiGroups:
|
||||
- extensions
|
||||
resources:
|
||||
- ingresses
|
||||
verbs:
|
||||
- get
|
||||
- list
|
||||
- watch
|
||||
- apiGroups:
|
||||
- networking.k8s.io
|
||||
resources:
|
||||
- ingresses
|
||||
verbs:
|
||||
- get
|
||||
- list
|
||||
- watch
|
||||
- apiVersion: rbac.authorization.k8s.io/v1
|
||||
kind: Role
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: prometheus
|
||||
app.kubernetes.io/instance: k8s
|
||||
app.kubernetes.io/name: prometheus
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 2.46.0
|
||||
name: prometheus-k8s
|
||||
namespace: kube-system
|
||||
rules:
|
||||
- apiGroups:
|
||||
- ''
|
||||
resources:
|
||||
- services
|
||||
- endpoints
|
||||
- pods
|
||||
verbs:
|
||||
- get
|
||||
- list
|
||||
- watch
|
||||
- apiGroups:
|
||||
- extensions
|
||||
resources:
|
||||
- ingresses
|
||||
verbs:
|
||||
- get
|
||||
- list
|
||||
- watch
|
||||
- apiGroups:
|
||||
- networking.k8s.io
|
||||
resources:
|
||||
- ingresses
|
||||
verbs:
|
||||
- get
|
||||
- list
|
||||
- watch
|
||||
- apiVersion: rbac.authorization.k8s.io/v1
|
||||
kind: Role
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: prometheus
|
||||
app.kubernetes.io/instance: k8s
|
||||
app.kubernetes.io/name: prometheus
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 2.46.0
|
||||
name: prometheus-k8s
|
||||
namespace: monitoring
|
||||
rules:
|
||||
- apiGroups:
|
||||
- ''
|
||||
resources:
|
||||
- services
|
||||
- endpoints
|
||||
- pods
|
||||
verbs:
|
||||
- get
|
||||
- list
|
||||
- watch
|
||||
- apiGroups:
|
||||
- extensions
|
||||
resources:
|
||||
- ingresses
|
||||
verbs:
|
||||
- get
|
||||
- list
|
||||
- watch
|
||||
- apiGroups:
|
||||
- networking.k8s.io
|
||||
resources:
|
||||
- ingresses
|
||||
verbs:
|
||||
- get
|
||||
- list
|
||||
- watch
|
||||
kind: RoleList
|
||||
metadata:
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
|
|
@ -0,0 +1,27 @@
|
|||
apiVersion: v1
|
||||
kind: Service
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: prometheus
|
||||
app.kubernetes.io/instance: k8s
|
||||
app.kubernetes.io/name: prometheus
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 2.46.0
|
||||
name: prometheus-k8s
|
||||
namespace: monitoring
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
spec:
|
||||
ports:
|
||||
- name: web
|
||||
port: 9090
|
||||
targetPort: web
|
||||
- name: reloader-web
|
||||
port: 8080
|
||||
targetPort: reloader-web
|
||||
selector:
|
||||
app.kubernetes.io/component: prometheus
|
||||
app.kubernetes.io/instance: k8s
|
||||
app.kubernetes.io/name: prometheus
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
sessionAffinity: ClientIP
|
||||
|
|
@ -0,0 +1,14 @@
|
|||
apiVersion: v1
|
||||
automountServiceAccountToken: true
|
||||
kind: ServiceAccount
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: prometheus
|
||||
app.kubernetes.io/instance: k8s
|
||||
app.kubernetes.io/name: prometheus
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 2.46.0
|
||||
name: prometheus-k8s
|
||||
namespace: monitoring
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
|
|
@ -0,0 +1,25 @@
|
|||
apiVersion: monitoring.coreos.com/v1
|
||||
kind: ServiceMonitor
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: prometheus
|
||||
app.kubernetes.io/instance: k8s
|
||||
app.kubernetes.io/name: prometheus
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 2.46.0
|
||||
name: prometheus-k8s
|
||||
namespace: monitoring
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
spec:
|
||||
endpoints:
|
||||
- interval: 30s
|
||||
port: web
|
||||
- interval: 30s
|
||||
port: reloader-web
|
||||
selector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/component: prometheus
|
||||
app.kubernetes.io/instance: k8s
|
||||
app.kubernetes.io/name: prometheus
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
|
|
@ -0,0 +1,20 @@
|
|||
apiVersion: apiregistration.k8s.io/v1
|
||||
kind: APIService
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: metrics-adapter
|
||||
app.kubernetes.io/name: prometheus-adapter
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 0.11.1
|
||||
name: v1beta1.metrics.k8s.io
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
spec:
|
||||
group: metrics.k8s.io
|
||||
groupPriorityMinimum: 100
|
||||
insecureSkipTLSVerify: true
|
||||
service:
|
||||
name: prometheus-adapter
|
||||
namespace: monitoring
|
||||
version: v1beta1
|
||||
versionPriority: 100
|
||||
|
|
@ -0,0 +1,23 @@
|
|||
apiVersion: rbac.authorization.k8s.io/v1
|
||||
kind: ClusterRole
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: metrics-adapter
|
||||
app.kubernetes.io/name: prometheus-adapter
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 0.11.1
|
||||
name: prometheus-adapter
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
rules:
|
||||
- apiGroups:
|
||||
- ''
|
||||
resources:
|
||||
- nodes
|
||||
- namespaces
|
||||
- pods
|
||||
- services
|
||||
verbs:
|
||||
- get
|
||||
- list
|
||||
- watch
|
||||
|
|
@ -0,0 +1,24 @@
|
|||
apiVersion: rbac.authorization.k8s.io/v1
|
||||
kind: ClusterRole
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: metrics-adapter
|
||||
app.kubernetes.io/name: prometheus-adapter
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 0.11.1
|
||||
rbac.authorization.k8s.io/aggregate-to-admin: 'true'
|
||||
rbac.authorization.k8s.io/aggregate-to-edit: 'true'
|
||||
rbac.authorization.k8s.io/aggregate-to-view: 'true'
|
||||
name: system:aggregated-metrics-reader
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
rules:
|
||||
- apiGroups:
|
||||
- metrics.k8s.io
|
||||
resources:
|
||||
- pods
|
||||
- nodes
|
||||
verbs:
|
||||
- get
|
||||
- list
|
||||
- watch
|
||||
|
|
@ -0,0 +1,19 @@
|
|||
apiVersion: rbac.authorization.k8s.io/v1
|
||||
kind: ClusterRoleBinding
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: metrics-adapter
|
||||
app.kubernetes.io/name: prometheus-adapter
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 0.11.1
|
||||
name: prometheus-adapter
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
roleRef:
|
||||
apiGroup: rbac.authorization.k8s.io
|
||||
kind: ClusterRole
|
||||
name: prometheus-adapter
|
||||
subjects:
|
||||
- kind: ServiceAccount
|
||||
name: prometheus-adapter
|
||||
namespace: monitoring
|
||||
|
|
@ -0,0 +1,19 @@
|
|||
apiVersion: rbac.authorization.k8s.io/v1
|
||||
kind: ClusterRoleBinding
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: metrics-adapter
|
||||
app.kubernetes.io/name: prometheus-adapter
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 0.11.1
|
||||
name: resource-metrics:system:auth-delegator
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
roleRef:
|
||||
apiGroup: rbac.authorization.k8s.io
|
||||
kind: ClusterRole
|
||||
name: system:auth-delegator
|
||||
subjects:
|
||||
- kind: ServiceAccount
|
||||
name: prometheus-adapter
|
||||
namespace: monitoring
|
||||
|
|
@ -0,0 +1,18 @@
|
|||
apiVersion: rbac.authorization.k8s.io/v1
|
||||
kind: ClusterRole
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: metrics-adapter
|
||||
app.kubernetes.io/name: prometheus-adapter
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 0.11.1
|
||||
name: resource-metrics-server-resources
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
rules:
|
||||
- apiGroups:
|
||||
- metrics.k8s.io
|
||||
resources:
|
||||
- '*'
|
||||
verbs:
|
||||
- '*'
|
||||
|
|
@ -0,0 +1,35 @@
|
|||
apiVersion: v1
|
||||
data:
|
||||
config.yaml: "\"resourceRules\":\n \"cpu\":\n \"containerLabel\": \"container\"\
|
||||
\n \"containerQuery\": |\n sum by (<<.GroupBy>>) (\n irate (\n\
|
||||
\ container_cpu_usage_seconds_total{<<.LabelMatchers>>,container!=\"\
|
||||
\",pod!=\"\"}[120s]\n )\n )\n \"nodeQuery\": |\n sum by (<<.GroupBy>>)\
|
||||
\ (\n 1 - irate(\n node_cpu_seconds_total{mode=\"idle\"}[60s]\n\
|
||||
\ )\n * on(namespace, pod) group_left(node) (\n node_namespace_pod:kube_pod_info:{<<.LabelMatchers>>}\n\
|
||||
\ )\n )\n or sum by (<<.GroupBy>>) (\n 1 - irate(\n \
|
||||
\ windows_cpu_time_total{mode=\"idle\", job=\"windows-exporter\",<<.LabelMatchers>>}[4m]\n\
|
||||
\ )\n )\n \"resources\":\n \"overrides\":\n \"namespace\"\
|
||||
:\n \"resource\": \"namespace\"\n \"node\":\n \"resource\"\
|
||||
: \"node\"\n \"pod\":\n \"resource\": \"pod\"\n \"memory\":\n\
|
||||
\ \"containerLabel\": \"container\"\n \"containerQuery\": |\n sum by\
|
||||
\ (<<.GroupBy>>) (\n container_memory_working_set_bytes{<<.LabelMatchers>>,container!=\"\
|
||||
\",pod!=\"\"}\n )\n \"nodeQuery\": |\n sum by (<<.GroupBy>>) (\n\
|
||||
\ node_memory_MemTotal_bytes{job=\"node-exporter\",<<.LabelMatchers>>}\n\
|
||||
\ -\n node_memory_MemAvailable_bytes{job=\"node-exporter\",<<.LabelMatchers>>}\n\
|
||||
\ )\n or sum by (<<.GroupBy>>) (\n windows_cs_physical_memory_bytes{job=\"\
|
||||
windows-exporter\",<<.LabelMatchers>>}\n -\n windows_memory_available_bytes{job=\"\
|
||||
windows-exporter\",<<.LabelMatchers>>}\n )\n \"resources\":\n \"\
|
||||
overrides\":\n \"instance\":\n \"resource\": \"node\"\n \
|
||||
\ \"namespace\":\n \"resource\": \"namespace\"\n \"pod\":\n \
|
||||
\ \"resource\": \"pod\"\n \"window\": \"5m\""
|
||||
kind: ConfigMap
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: metrics-adapter
|
||||
app.kubernetes.io/name: prometheus-adapter
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 0.11.1
|
||||
name: adapter-config
|
||||
namespace: monitoring
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
|
|
@ -0,0 +1,102 @@
|
|||
apiVersion: apps/v1
|
||||
kind: Deployment
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: metrics-adapter
|
||||
app.kubernetes.io/name: prometheus-adapter
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 0.11.1
|
||||
name: prometheus-adapter
|
||||
namespace: monitoring
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
spec:
|
||||
replicas: 2
|
||||
selector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/component: metrics-adapter
|
||||
app.kubernetes.io/name: prometheus-adapter
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
strategy:
|
||||
rollingUpdate:
|
||||
maxSurge: 1
|
||||
maxUnavailable: 1
|
||||
template:
|
||||
metadata:
|
||||
annotations:
|
||||
checksum.config/md5: 3b1ebf7df0232d1675896f67b66373db
|
||||
labels:
|
||||
app.kubernetes.io/component: metrics-adapter
|
||||
app.kubernetes.io/name: prometheus-adapter
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 0.11.1
|
||||
spec:
|
||||
automountServiceAccountToken: true
|
||||
containers:
|
||||
- args:
|
||||
- --cert-dir=/var/run/serving-cert
|
||||
- --config=/etc/adapter/config.yaml
|
||||
- --metrics-relist-interval=1m
|
||||
- --prometheus-url=http://prometheus-k8s.monitoring.svc:9090/
|
||||
- --secure-port=6443
|
||||
- --tls-cipher-suites=TLS_ECDHE_RSA_WITH_CHACHA20_POLY1305,TLS_ECDHE_ECDSA_WITH_CHACHA20_POLY1305,TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256,TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384,TLS_ECDHE_ECDSA_WITH_AES_128_GCM_SHA256,TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384,TLS_ECDHE_RSA_WITH_AES_128_CBC_SHA,TLS_ECDHE_ECDSA_WITH_AES_128_CBC_SHA256,TLS_ECDHE_ECDSA_WITH_AES_128_CBC_SHA,TLS_ECDHE_RSA_WITH_AES_256_CBC_SHA,TLS_ECDHE_ECDSA_WITH_AES_256_CBC_SHA,TLS_RSA_WITH_AES_128_GCM_SHA256,TLS_RSA_WITH_AES_256_GCM_SHA384,TLS_RSA_WITH_AES_128_CBC_SHA,TLS_RSA_WITH_AES_256_CBC_SHA
|
||||
image: registry.k8s.io/prometheus-adapter/prometheus-adapter:v0.11.1
|
||||
livenessProbe:
|
||||
failureThreshold: 5
|
||||
httpGet:
|
||||
path: /livez
|
||||
port: https
|
||||
scheme: HTTPS
|
||||
periodSeconds: 5
|
||||
name: prometheus-adapter
|
||||
ports:
|
||||
- containerPort: 6443
|
||||
name: https
|
||||
readinessProbe:
|
||||
failureThreshold: 5
|
||||
httpGet:
|
||||
path: /readyz
|
||||
port: https
|
||||
scheme: HTTPS
|
||||
periodSeconds: 5
|
||||
resources:
|
||||
limits:
|
||||
cpu: 250m
|
||||
memory: 180Mi
|
||||
requests:
|
||||
cpu: 102m
|
||||
memory: 180Mi
|
||||
securityContext:
|
||||
allowPrivilegeEscalation: false
|
||||
capabilities:
|
||||
drop:
|
||||
- ALL
|
||||
readOnlyRootFilesystem: true
|
||||
startupProbe:
|
||||
failureThreshold: 18
|
||||
httpGet:
|
||||
path: /livez
|
||||
port: https
|
||||
scheme: HTTPS
|
||||
periodSeconds: 10
|
||||
volumeMounts:
|
||||
- mountPath: /tmp
|
||||
name: tmpfs
|
||||
readOnly: false
|
||||
- mountPath: /var/run/serving-cert
|
||||
name: volume-serving-cert
|
||||
readOnly: false
|
||||
- mountPath: /etc/adapter
|
||||
name: config
|
||||
readOnly: false
|
||||
nodeSelector:
|
||||
kubernetes.io/os: linux
|
||||
serviceAccountName: prometheus-adapter
|
||||
volumes:
|
||||
- emptyDir: {}
|
||||
name: tmpfs
|
||||
- emptyDir: {}
|
||||
name: volume-serving-cert
|
||||
- configMap:
|
||||
name: adapter-config
|
||||
name: config
|
||||
|
|
@ -0,0 +1,25 @@
|
|||
apiVersion: networking.k8s.io/v1
|
||||
kind: NetworkPolicy
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: metrics-adapter
|
||||
app.kubernetes.io/name: prometheus-adapter
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 0.11.1
|
||||
name: prometheus-adapter
|
||||
namespace: monitoring
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
spec:
|
||||
egress:
|
||||
- {}
|
||||
ingress:
|
||||
- {}
|
||||
podSelector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/component: metrics-adapter
|
||||
app.kubernetes.io/name: prometheus-adapter
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
policyTypes:
|
||||
- Egress
|
||||
- Ingress
|
||||
|
|
@ -0,0 +1,19 @@
|
|||
apiVersion: policy/v1
|
||||
kind: PodDisruptionBudget
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: metrics-adapter
|
||||
app.kubernetes.io/name: prometheus-adapter
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 0.11.1
|
||||
name: prometheus-adapter
|
||||
namespace: monitoring
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
spec:
|
||||
minAvailable: 1
|
||||
selector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/component: metrics-adapter
|
||||
app.kubernetes.io/name: prometheus-adapter
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
|
|
@ -0,0 +1,20 @@
|
|||
apiVersion: rbac.authorization.k8s.io/v1
|
||||
kind: RoleBinding
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: metrics-adapter
|
||||
app.kubernetes.io/name: prometheus-adapter
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 0.11.1
|
||||
name: resource-metrics-auth-reader
|
||||
namespace: kube-system
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
roleRef:
|
||||
apiGroup: rbac.authorization.k8s.io
|
||||
kind: Role
|
||||
name: extension-apiserver-authentication-reader
|
||||
subjects:
|
||||
- kind: ServiceAccount
|
||||
name: prometheus-adapter
|
||||
namespace: monitoring
|
||||
|
|
@ -0,0 +1,21 @@
|
|||
apiVersion: v1
|
||||
kind: Service
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: metrics-adapter
|
||||
app.kubernetes.io/name: prometheus-adapter
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 0.11.1
|
||||
name: prometheus-adapter
|
||||
namespace: monitoring
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
spec:
|
||||
ports:
|
||||
- name: https
|
||||
port: 443
|
||||
targetPort: 6443
|
||||
selector:
|
||||
app.kubernetes.io/component: metrics-adapter
|
||||
app.kubernetes.io/name: prometheus-adapter
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
|
|
@ -0,0 +1,13 @@
|
|||
apiVersion: v1
|
||||
automountServiceAccountToken: false
|
||||
kind: ServiceAccount
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: metrics-adapter
|
||||
app.kubernetes.io/name: prometheus-adapter
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 0.11.1
|
||||
name: prometheus-adapter
|
||||
namespace: monitoring
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
|
|
@ -0,0 +1,30 @@
|
|||
apiVersion: monitoring.coreos.com/v1
|
||||
kind: ServiceMonitor
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: metrics-adapter
|
||||
app.kubernetes.io/name: prometheus-adapter
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 0.11.1
|
||||
name: prometheus-adapter
|
||||
namespace: monitoring
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
spec:
|
||||
endpoints:
|
||||
- bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token
|
||||
interval: 30s
|
||||
metricRelabelings:
|
||||
- action: drop
|
||||
regex: (apiserver_client_certificate_.*|apiserver_envelope_.*|apiserver_flowcontrol_.*|apiserver_storage_.*|apiserver_webhooks_.*|workqueue_.*)
|
||||
sourceLabels:
|
||||
- __name__
|
||||
port: https
|
||||
scheme: https
|
||||
tlsConfig:
|
||||
insecureSkipVerify: true
|
||||
selector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/component: metrics-adapter
|
||||
app.kubernetes.io/name: prometheus-adapter
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
|
|
@ -0,0 +1,101 @@
|
|||
apiVersion: rbac.authorization.k8s.io/v1
|
||||
kind: ClusterRole
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: controller
|
||||
app.kubernetes.io/name: prometheus-operator
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 0.67.1
|
||||
name: prometheus-operator
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
rules:
|
||||
- apiGroups:
|
||||
- monitoring.coreos.com
|
||||
resources:
|
||||
- alertmanagers
|
||||
- alertmanagers/finalizers
|
||||
- alertmanagers/status
|
||||
- alertmanagerconfigs
|
||||
- prometheuses
|
||||
- prometheuses/finalizers
|
||||
- prometheuses/status
|
||||
- prometheusagents
|
||||
- prometheusagents/finalizers
|
||||
- prometheusagents/status
|
||||
- thanosrulers
|
||||
- thanosrulers/finalizers
|
||||
- thanosrulers/status
|
||||
- scrapeconfigs
|
||||
- servicemonitors
|
||||
- podmonitors
|
||||
- probes
|
||||
- prometheusrules
|
||||
verbs:
|
||||
- '*'
|
||||
- apiGroups:
|
||||
- apps
|
||||
resources:
|
||||
- statefulsets
|
||||
verbs:
|
||||
- '*'
|
||||
- apiGroups:
|
||||
- ''
|
||||
resources:
|
||||
- configmaps
|
||||
- secrets
|
||||
verbs:
|
||||
- '*'
|
||||
- apiGroups:
|
||||
- ''
|
||||
resources:
|
||||
- pods
|
||||
verbs:
|
||||
- list
|
||||
- delete
|
||||
- apiGroups:
|
||||
- ''
|
||||
resources:
|
||||
- services
|
||||
- services/finalizers
|
||||
- endpoints
|
||||
verbs:
|
||||
- get
|
||||
- create
|
||||
- update
|
||||
- delete
|
||||
- apiGroups:
|
||||
- ''
|
||||
resources:
|
||||
- nodes
|
||||
verbs:
|
||||
- list
|
||||
- watch
|
||||
- apiGroups:
|
||||
- ''
|
||||
resources:
|
||||
- namespaces
|
||||
verbs:
|
||||
- get
|
||||
- list
|
||||
- watch
|
||||
- apiGroups:
|
||||
- networking.k8s.io
|
||||
resources:
|
||||
- ingresses
|
||||
verbs:
|
||||
- get
|
||||
- list
|
||||
- watch
|
||||
- apiGroups:
|
||||
- authentication.k8s.io
|
||||
resources:
|
||||
- tokenreviews
|
||||
verbs:
|
||||
- create
|
||||
- apiGroups:
|
||||
- authorization.k8s.io
|
||||
resources:
|
||||
- subjectaccessreviews
|
||||
verbs:
|
||||
- create
|
||||
|
|
@ -0,0 +1,19 @@
|
|||
apiVersion: rbac.authorization.k8s.io/v1
|
||||
kind: ClusterRoleBinding
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: controller
|
||||
app.kubernetes.io/name: prometheus-operator
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 0.67.1
|
||||
name: prometheus-operator
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
roleRef:
|
||||
apiGroup: rbac.authorization.k8s.io
|
||||
kind: ClusterRole
|
||||
name: prometheus-operator
|
||||
subjects:
|
||||
- kind: ServiceAccount
|
||||
name: prometheus-operator
|
||||
namespace: monitoring
|
||||
|
|
@ -0,0 +1,85 @@
|
|||
apiVersion: apps/v1
|
||||
kind: Deployment
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: controller
|
||||
app.kubernetes.io/name: prometheus-operator
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 0.67.1
|
||||
name: prometheus-operator
|
||||
namespace: monitoring
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
spec:
|
||||
replicas: 1
|
||||
selector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/component: controller
|
||||
app.kubernetes.io/name: prometheus-operator
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
template:
|
||||
metadata:
|
||||
annotations:
|
||||
kubectl.kubernetes.io/default-container: prometheus-operator
|
||||
labels:
|
||||
app.kubernetes.io/component: controller
|
||||
app.kubernetes.io/name: prometheus-operator
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 0.67.1
|
||||
spec:
|
||||
automountServiceAccountToken: true
|
||||
containers:
|
||||
- args:
|
||||
- --kubelet-service=kube-system/kubelet
|
||||
- --prometheus-config-reloader=quay.io/prometheus-operator/prometheus-config-reloader:v0.67.1
|
||||
image: quay.io/prometheus-operator/prometheus-operator:v0.67.1
|
||||
name: prometheus-operator
|
||||
ports:
|
||||
- containerPort: 8080
|
||||
name: http
|
||||
resources:
|
||||
limits:
|
||||
cpu: 200m
|
||||
memory: 200Mi
|
||||
requests:
|
||||
cpu: 100m
|
||||
memory: 100Mi
|
||||
securityContext:
|
||||
allowPrivilegeEscalation: false
|
||||
capabilities:
|
||||
drop:
|
||||
- ALL
|
||||
readOnlyRootFilesystem: true
|
||||
- args:
|
||||
- --secure-listen-address=:8443
|
||||
- --tls-cipher-suites=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256,TLS_ECDHE_ECDSA_WITH_AES_128_GCM_SHA256,TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384,TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384,TLS_ECDHE_RSA_WITH_CHACHA20_POLY1305,TLS_ECDHE_ECDSA_WITH_CHACHA20_POLY1305
|
||||
- --upstream=http://127.0.0.1:8080/
|
||||
image: quay.io/brancz/kube-rbac-proxy:v0.14.2
|
||||
name: kube-rbac-proxy
|
||||
ports:
|
||||
- containerPort: 8443
|
||||
name: https
|
||||
resources:
|
||||
limits:
|
||||
cpu: 20m
|
||||
memory: 40Mi
|
||||
requests:
|
||||
cpu: 10m
|
||||
memory: 20Mi
|
||||
securityContext:
|
||||
allowPrivilegeEscalation: false
|
||||
capabilities:
|
||||
drop:
|
||||
- ALL
|
||||
readOnlyRootFilesystem: true
|
||||
runAsGroup: 65532
|
||||
runAsNonRoot: true
|
||||
runAsUser: 65532
|
||||
nodeSelector:
|
||||
kubernetes.io/os: linux
|
||||
securityContext:
|
||||
runAsNonRoot: true
|
||||
runAsUser: 65534
|
||||
seccompProfile:
|
||||
type: RuntimeDefault
|
||||
serviceAccountName: prometheus-operator
|
||||
|
|
@ -0,0 +1,31 @@
|
|||
apiVersion: networking.k8s.io/v1
|
||||
kind: NetworkPolicy
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: controller
|
||||
app.kubernetes.io/name: prometheus-operator
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 0.67.1
|
||||
name: prometheus-operator
|
||||
namespace: monitoring
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
spec:
|
||||
egress:
|
||||
- {}
|
||||
ingress:
|
||||
- from:
|
||||
- podSelector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/name: prometheus
|
||||
ports:
|
||||
- port: 8443
|
||||
protocol: TCP
|
||||
podSelector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/component: controller
|
||||
app.kubernetes.io/name: prometheus-operator
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
policyTypes:
|
||||
- Egress
|
||||
- Ingress
|
||||
|
|
@ -0,0 +1,132 @@
|
|||
apiVersion: monitoring.coreos.com/v1
|
||||
kind: PrometheusRule
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: controller
|
||||
app.kubernetes.io/name: prometheus-operator
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 0.67.1
|
||||
prometheus: k8s
|
||||
role: alert-rules
|
||||
name: prometheus-operator-rules
|
||||
namespace: monitoring
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
spec:
|
||||
groups:
|
||||
- name: prometheus-operator
|
||||
rules:
|
||||
- alert: PrometheusOperatorListErrors
|
||||
annotations:
|
||||
description: Errors while performing List operations in controller {{$labels.controller}}
|
||||
in {{$labels.namespace}} namespace.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus-operator/prometheusoperatorlisterrors
|
||||
summary: Errors while performing list operations in controller.
|
||||
expr: '(sum by (cluster,controller,namespace) (rate(prometheus_operator_list_operations_failed_total{job="prometheus-operator",namespace="monitoring"}[10m]))
|
||||
/ sum by (cluster,controller,namespace) (rate(prometheus_operator_list_operations_total{job="prometheus-operator",namespace="monitoring"}[10m])))
|
||||
> 0.4
|
||||
|
||||
'
|
||||
for: 15m
|
||||
labels:
|
||||
severity: warning
|
||||
- alert: PrometheusOperatorWatchErrors
|
||||
annotations:
|
||||
description: Errors while performing watch operations in controller {{$labels.controller}}
|
||||
in {{$labels.namespace}} namespace.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus-operator/prometheusoperatorwatcherrors
|
||||
summary: Errors while performing watch operations in controller.
|
||||
expr: '(sum by (cluster,controller,namespace) (rate(prometheus_operator_watch_operations_failed_total{job="prometheus-operator",namespace="monitoring"}[5m]))
|
||||
/ sum by (cluster,controller,namespace) (rate(prometheus_operator_watch_operations_total{job="prometheus-operator",namespace="monitoring"}[5m])))
|
||||
> 0.4
|
||||
|
||||
'
|
||||
for: 15m
|
||||
labels:
|
||||
severity: warning
|
||||
- alert: PrometheusOperatorSyncFailed
|
||||
annotations:
|
||||
description: Controller {{ $labels.controller }} in {{ $labels.namespace
|
||||
}} namespace fails to reconcile {{ $value }} objects.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus-operator/prometheusoperatorsyncfailed
|
||||
summary: Last controller reconciliation failed
|
||||
expr: 'min_over_time(prometheus_operator_syncs{status="failed",job="prometheus-operator",namespace="monitoring"}[5m])
|
||||
> 0
|
||||
|
||||
'
|
||||
for: 10m
|
||||
labels:
|
||||
severity: warning
|
||||
- alert: PrometheusOperatorReconcileErrors
|
||||
annotations:
|
||||
description: '{{ $value | humanizePercentage }} of reconciling operations
|
||||
failed for {{ $labels.controller }} controller in {{ $labels.namespace
|
||||
}} namespace.'
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus-operator/prometheusoperatorreconcileerrors
|
||||
summary: Errors while reconciling controller.
|
||||
expr: '(sum by (cluster,controller,namespace) (rate(prometheus_operator_reconcile_errors_total{job="prometheus-operator",namespace="monitoring"}[5m])))
|
||||
/ (sum by (cluster,controller,namespace) (rate(prometheus_operator_reconcile_operations_total{job="prometheus-operator",namespace="monitoring"}[5m])))
|
||||
> 0.1
|
||||
|
||||
'
|
||||
for: 10m
|
||||
labels:
|
||||
severity: warning
|
||||
- alert: PrometheusOperatorNodeLookupErrors
|
||||
annotations:
|
||||
description: Errors while reconciling Prometheus in {{ $labels.namespace
|
||||
}} Namespace.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus-operator/prometheusoperatornodelookuperrors
|
||||
summary: Errors while reconciling Prometheus.
|
||||
expr: 'rate(prometheus_operator_node_address_lookup_errors_total{job="prometheus-operator",namespace="monitoring"}[5m])
|
||||
> 0.1
|
||||
|
||||
'
|
||||
for: 10m
|
||||
labels:
|
||||
severity: warning
|
||||
- alert: PrometheusOperatorNotReady
|
||||
annotations:
|
||||
description: Prometheus operator in {{ $labels.namespace }} namespace
|
||||
isn't ready to reconcile {{ $labels.controller }} resources.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus-operator/prometheusoperatornotready
|
||||
summary: Prometheus operator not ready
|
||||
expr: 'min by (cluster,controller,namespace) (max_over_time(prometheus_operator_ready{job="prometheus-operator",namespace="monitoring"}[5m])
|
||||
== 0)
|
||||
|
||||
'
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
- alert: PrometheusOperatorRejectedResources
|
||||
annotations:
|
||||
description: Prometheus operator in {{ $labels.namespace }} namespace
|
||||
rejected {{ printf "%0.0f" $value }} {{ $labels.controller }}/{{ $labels.resource
|
||||
}} resources.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus-operator/prometheusoperatorrejectedresources
|
||||
summary: Resources rejected by Prometheus operator
|
||||
expr: 'min_over_time(prometheus_operator_managed_resources{state="rejected",job="prometheus-operator",namespace="monitoring"}[5m])
|
||||
> 0
|
||||
|
||||
'
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
- name: config-reloaders
|
||||
rules:
|
||||
- alert: ConfigReloaderSidecarErrors
|
||||
annotations:
|
||||
description: 'Errors encountered while the {{$labels.pod}} config-reloader
|
||||
sidecar attempts to sync config in {{$labels.namespace}} namespace.
|
||||
|
||||
As a result, configuration for service running in {{$labels.pod}} may
|
||||
be stale and cannot be updated anymore.'
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus-operator/configreloadersidecarerrors
|
||||
summary: config-reloader sidecar has not had a successful reload for 10m
|
||||
expr: 'max_over_time(reloader_last_reload_successful{namespace=~".+"}[5m])
|
||||
== 0
|
||||
|
||||
'
|
||||
for: 10m
|
||||
labels:
|
||||
severity: warning
|
||||
|
|
@ -0,0 +1,22 @@
|
|||
apiVersion: v1
|
||||
kind: Service
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: controller
|
||||
app.kubernetes.io/name: prometheus-operator
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 0.67.1
|
||||
name: prometheus-operator
|
||||
namespace: monitoring
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
spec:
|
||||
clusterIP: None
|
||||
ports:
|
||||
- name: https
|
||||
port: 8443
|
||||
targetPort: https
|
||||
selector:
|
||||
app.kubernetes.io/component: controller
|
||||
app.kubernetes.io/name: prometheus-operator
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
|
|
@ -0,0 +1,13 @@
|
|||
apiVersion: v1
|
||||
automountServiceAccountToken: false
|
||||
kind: ServiceAccount
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: controller
|
||||
app.kubernetes.io/name: prometheus-operator
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 0.67.1
|
||||
name: prometheus-operator
|
||||
namespace: monitoring
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
|
|
@ -0,0 +1,26 @@
|
|||
apiVersion: monitoring.coreos.com/v1
|
||||
kind: ServiceMonitor
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: controller
|
||||
app.kubernetes.io/name: prometheus-operator
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 0.67.1
|
||||
name: prometheus-operator
|
||||
namespace: monitoring
|
||||
annotations:
|
||||
argocd.argoproj.io/sync-wave: '1'
|
||||
spec:
|
||||
endpoints:
|
||||
- bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token
|
||||
honorLabels: true
|
||||
port: https
|
||||
scheme: https
|
||||
tlsConfig:
|
||||
insecureSkipVerify: true
|
||||
selector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/component: controller
|
||||
app.kubernetes.io/name: prometheus-operator
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 0.67.1
|
||||
|
|
@ -0,0 +1,17 @@
|
|||
apiVersion: argoproj.io/v1alpha1
|
||||
kind: Application
|
||||
metadata:
|
||||
name: kube-prometheus
|
||||
namespace: argocd
|
||||
spec:
|
||||
destination:
|
||||
namespace: monitoring
|
||||
server: https://kubernetes.default.svc
|
||||
project: infra
|
||||
source:
|
||||
path: apps-kustomized/kube-prometheus
|
||||
repoURL: https://git.martyn.berlin/martyn/infra4talos
|
||||
targetRevision: HEAD
|
||||
syncPolicy:
|
||||
automated:
|
||||
selfHeal: true
|
||||
|
|
@ -0,0 +1,39 @@
|
|||
#!/bin/bash
|
||||
|
||||
# the directory of the script
|
||||
DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )"
|
||||
|
||||
# the temp directory used, within $DIR
|
||||
# omit the -p parameter to create a temporal directory in the default location
|
||||
WORK_DIR=`mktemp -d -p "$DIR"`
|
||||
|
||||
# check if tmp dir was created
|
||||
if [[ ! "$WORK_DIR" || ! -d "$WORK_DIR" ]]; then
|
||||
echo "Could not create temp dir"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# deletes the temp directory
|
||||
function cleanup {
|
||||
rm -rf "$WORK_DIR"
|
||||
echo "Deleted temp working directory $WORK_DIR"
|
||||
}
|
||||
|
||||
# register the cleanup function to be called on the EXIT signal
|
||||
trap cleanup EXIT
|
||||
|
||||
# implementation of script starts here
|
||||
KUBE_PROM_VERSION=release-0.13
|
||||
|
||||
cd $WORK_DIR
|
||||
git clone https://github.com/prometheus-operator/kube-prometheus.git
|
||||
cd kube-prometheus
|
||||
git checkout $KUBE_PROM_VERSION
|
||||
rm manifests/alertmanager-secret.yaml
|
||||
for y in manifests/setup/*.yaml; do
|
||||
yq -y '.metadata.annotations += {"argocd.argoproj.io/sync-wave":"0"}' $y > $DIR/apps-kustomized/kube-prometheus/`basename $y`
|
||||
done
|
||||
for y in manifests/*.yaml; do
|
||||
yq -y '.metadata.annotations += {"argocd.argoproj.io/sync-wave":"1"}' $y > $DIR/apps-kustomized/kube-prometheus/`basename $y`
|
||||
done
|
||||
|
||||
Loading…
Reference in New Issue