This commit is contained in:
Endre Sara 2024-05-30 17:27:26 -03:00 committed by GitHub
commit 715fec25fd
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
103 changed files with 20556 additions and 17224 deletions

View File

@ -1,4 +1,4 @@
local k = import 'ksonnet/ksonnet.beta.4/k.libsonnet';
local k = import 'ksonnet-lib/ksonnet.beta.4/k.libsonnet';
local utils = import 'utils.libsonnet';
local vars = import 'vars.jsonnet';
@ -17,7 +17,7 @@ local vars = import 'vars.jsonnet';
prometheus+:: {
names: 'k8s',
replicas: 1,
namespaces: ['default', 'kube-system', 'monitoring'],
namespaces: ['default', 'kube-system', vars._config.namespace],
},
alertmanager+:: {
@ -60,7 +60,7 @@ local vars = import 'vars.jsonnet';
},
},
plugins: vars.grafana.plugins,
env: vars.grafana.env
env: vars.grafana.env,
},
},
//---------------------------------------

View File

@ -4,10 +4,18 @@
{
"source": {
"git": {
"remote": "https://github.com/coreos/kube-prometheus.git",
"remote": "https://github.com/prometheus-operator/kube-prometheus.git",
"subdir": "jsonnet/kube-prometheus"
}
},
"version": "main"
},
{
"source": {
"git": {
"remote": "https://github.com/ksonnet/ksonnet-lib.git"
}
},
"version": "master"
}
],

View File

@ -8,38 +8,28 @@
"subdir": "grafana"
}
},
"version": "57b4365eacda291b82e0d55ba7eec573a8198dda",
"sum": "92DWADwGjnCfpZaL7Q07C0GZayxBziGla/O03qWea34="
"version": "d039275e4916aceae1c137120882e01d857787ac",
"sum": "515vMn4x4tP8vegL4HLW0nDO5+njGTgnDZB5OOhtsCI="
},
{
"source": {
"git": {
"remote": "https://github.com/coreos/etcd.git",
"subdir": "Documentation/etcd-mixin"
"remote": "https://github.com/etcd-io/etcd.git",
"subdir": "contrib/mixin"
}
},
"version": "d8c8f903eee10b8391abaef7758c38b2cd393c55",
"sum": "pk7mLpdUrHuJKkj2vhD6LGMU7P+oYYooBXAeZyZa398="
"version": "e73f55d4e94666c99558baa2fd4e365aeaca4dc4",
"sum": "IkDHlaE0gvvcPjSNurFT+jQ2aCOAbqHF1WVmXbAgkds="
},
{
"source": {
"git": {
"remote": "https://github.com/coreos/kube-prometheus.git",
"subdir": "jsonnet/kube-prometheus"
"remote": "https://github.com/grafana/grafana.git",
"subdir": "grafana-mixin"
}
},
"version": "17989b42aa10b1c6afa07043cb05bcd5ae492284",
"sum": "2FR289B1LGUf5tTN4PXBj5TjRX7okSFxE8uHkSslzDQ="
},
{
"source": {
"git": {
"remote": "https://github.com/coreos/prometheus-operator.git",
"subdir": "jsonnet/prometheus-operator"
}
},
"version": "e31c69f9b5c6555e0f4a5c1f39d0f03182dd6b41",
"sum": "WggWVWZ+CBEUThQCztSaRELbtqdXf9s3OFzf06HbYNA="
"version": "1120f9e255760a3c104b57871fcb91801e934382",
"sum": "MkjR7zCgq6MUZgjDzop574tFKoTX2OBr7DTwm1K+Ofs="
},
{
"source": {
@ -48,8 +38,18 @@
"subdir": "grafonnet"
}
},
"version": "8fb95bd89990e493a8534205ee636bfcb8db67bd",
"sum": "tDuuSKE9f4Ew2bjBM33Rs6behLEAzkmKkShSt+jpAak="
"version": "30280196507e0fe6fa978a3e0eaca3a62844f817",
"sum": "342u++/7rViR/zj2jeJOjshzglkZ1SY+hFNuyCBFMdc="
},
{
"source": {
"git": {
"remote": "https://github.com/grafana/grafonnet-lib.git",
"subdir": "grafonnet-7.0"
}
},
"version": "30280196507e0fe6fa978a3e0eaca3a62844f817",
"sum": "gCtR9s/4D5fxU9aKXg0Bru+/njZhA0YjLjPiASc61FM="
},
{
"source": {
@ -58,8 +58,8 @@
"subdir": "grafana-builder"
}
},
"version": "881db2241f0c5007c3e831caf34b0c645202b4ab",
"sum": "slxrtftVDiTlQK22ertdfrg4Epnq97gdrLI63ftUfaE="
"version": "d68f9a6e0b1af7c4c4056dc2b43fb8f3bac01f43",
"sum": "tDR6yT2GVfw0wTU12iZH+m01HrbIr6g/xN+/8nzNkU0="
},
{
"source": {
@ -69,8 +69,7 @@
}
},
"version": "0d2f82676817bbf9e4acf6495b2090205f323b9f",
"sum": "h28BXZ7+vczxYJ2sCt8JuR9+yznRtU/iA6DCpQUrtEg=",
"name": "ksonnet"
"sum": "h28BXZ7+vczxYJ2sCt8JuR9+yznRtU/iA6DCpQUrtEg="
},
{
"source": {
@ -79,18 +78,8 @@
"subdir": ""
}
},
"version": "b61c5a34051f8f57284a08fe78ad8a45b430252b",
"sum": "7Hx/5eNm7ubLTsdrpk3b2+e/FLR3XOa4HCukmbRUCAY="
},
{
"source": {
"git": {
"remote": "https://github.com/kubernetes-monitoring/kubernetes-mixin.git",
"subdir": "lib/promgrafonnet"
}
},
"version": "b61c5a34051f8f57284a08fe78ad8a45b430252b",
"sum": "VhgBM39yv0f4bKv8VfGg4FXkg573evGDRalip9ypKbc="
"version": "3c386687c1f8ceb6b79ff887c4a934e9cee1b90a",
"sum": "H8lcnk7gQEUoRi58/xq+JTfd2PcjJUjMQHgxGklUiFY="
},
{
"source": {
@ -99,8 +88,8 @@
"subdir": "jsonnet/kube-state-metrics"
}
},
"version": "d667979ed55ad1c4db44d331b51d646f5b903aa7",
"sum": "cJjGZaLBjcIGrLHZLjRPU9c3KL+ep9rZTb9dbALSKqA="
"version": "71200632a6c97e9b87166dbb27489798a05effe3",
"sum": "4PJ2ROxODsoYO/1Y70+dgLZVjW5zlfzB+TDpxJBHwaI="
},
{
"source": {
@ -109,8 +98,50 @@
"subdir": "jsonnet/kube-state-metrics-mixin"
}
},
"version": "d667979ed55ad1c4db44d331b51d646f5b903aa7",
"sum": "o5avaguRsfFwYFNen00ZEsub1x4i8Z/ZZ2QoEjFMff8="
"version": "71200632a6c97e9b87166dbb27489798a05effe3",
"sum": "u8gaydJoxEjzizQ8jY8xSjYgWooPmxw+wIWdDxifMAk="
},
{
"source": {
"git": {
"remote": "https://github.com/prometheus-operator/kube-prometheus.git",
"subdir": "jsonnet/kube-prometheus"
}
},
"version": "37d00082289c587f5a02a343ba23cfbe167000e2",
"sum": "5onAaPSrjnmgXIAsypnx0W/sIA7iTsHCeCjPrhGxj5A="
},
{
"source": {
"git": {
"remote": "https://github.com/prometheus-operator/prometheus-operator.git",
"subdir": "jsonnet/mixin"
}
},
"version": "df4cbd9526d8ff8e404a903b7ed2532847551d19",
"sum": "GQmaVFJwKMiD/P4n3N2LrAZVcwutriWrP8joclDtBYQ=",
"name": "prometheus-operator-mixin"
},
{
"source": {
"git": {
"remote": "https://github.com/prometheus-operator/prometheus-operator.git",
"subdir": "jsonnet/prometheus-operator"
}
},
"version": "df4cbd9526d8ff8e404a903b7ed2532847551d19",
"sum": "wJ1E8XxYJ0RJrUuDNWLzE7bzo6JrH7P9q1lAu/xi4Ow="
},
{
"source": {
"git": {
"remote": "https://github.com/prometheus/alertmanager.git",
"subdir": "doc/alertmanager-mixin"
}
},
"version": "8afd462a9eaa3979bddf7bd6278bede4bc1f30e2",
"sum": "PsK+V7oETCPKu2gLoPfqY0wwPKH9TzhNj6o2xezjjXc=",
"name": "alertmanager"
},
{
"source": {
@ -119,8 +150,8 @@
"subdir": "docs/node-mixin"
}
},
"version": "08ce3c6dd430deb51798826701a395e460620d60",
"sum": "3jFV2qsc/GZe2GADswTYqxxP2zGOiANTj73W/VNFGqc="
"version": "a3bd2e13052929663dbd7d680fab4a952efb1de6",
"sum": "TwdaTm0Z++diiLyaKAAimmC6hBL7XbrJc0RHhBCpAdU="
},
{
"source": {
@ -129,9 +160,30 @@
"subdir": "documentation/prometheus-mixin"
}
},
"version": "74207c04655e1fd93eea0e9a5d2f31b1cbc4d3d0",
"sum": "lEzhZ8gllSfAO4kmXeTwl4W0anapIeFd5GCaCNuDe18=",
"version": "84c6f0e58444a452a5e2e19d14221409d2b9d790",
"sum": "LRx0tbMnoE1p8KEn+i81j2YsA5Sgt3itE5Y6jBf5eOQ=",
"name": "prometheus"
},
{
"source": {
"git": {
"remote": "https://github.com/pyrra-dev/pyrra.git",
"subdir": "config/crd/bases"
}
},
"version": "2584cefb8e6859eb9ee103df199e232cd0066aab",
"sum": "d1550yhsX4VxdVN7b0gWT0cido/W90P6OGLzLqPwZcs="
},
{
"source": {
"git": {
"remote": "https://github.com/thanos-io/thanos.git",
"subdir": "mixin"
}
},
"version": "3327c510076a77f876ac26e699d5252a61fc529a",
"sum": "Io++1+lp1oQVoQiVRSCXUiGdTIRPV7aL6Ewgs3bShEs=",
"name": "thanos-mixin"
}
],
"legacyImports": false

View File

@ -1,10 +1,10 @@
local utils = import 'utils.libsonnet';
local vars = import 'vars.jsonnet';
local kp = (import 'kube-prometheus/kube-prometheus.libsonnet')
+ (import 'kube-prometheus/kube-prometheus-anti-affinity.libsonnet')
+ (import 'kube-prometheus/kube-prometheus-kops-coredns.libsonnet')
+ (import 'kube-prometheus/kube-prometheus-kubeadm.libsonnet')
local kp = (import 'kube-prometheus/main.libsonnet') + { values+:: { common+: { namespace: vars._config.namespace } } }
+ (import 'kube-prometheus/addons/anti-affinity.libsonnet')
+ (import 'kube-prometheus/platforms/kops-coredns.libsonnet')
+ (import 'kube-prometheus/platforms/kubeadm.libsonnet')
// Additional modules are loaded dynamically from vars.jsonnet
+ utils.join_objects([module.file for module in vars.modules if module.enabled])
// Load K3s customized modules
@ -14,6 +14,7 @@ local kp = (import 'kube-prometheus/kube-prometheus.libsonnet')
// Load image versions last to override default from modules
+ (import 'image_sources_versions.jsonnet');
// Generate core modules
{ ['setup/0namespace-' + name]: kp.kubePrometheus[name] for name in std.objectFields(kp.kubePrometheus) }
// First generate operator resources except the serviceMonitors

View File

@ -2,7 +2,11 @@ apiVersion: monitoring.coreos.com/v1
kind: Alertmanager
metadata:
labels:
alertmanager: main
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: 0.25.0
name: main
namespace: monitoring
spec:
@ -11,22 +15,36 @@ spec:
preferredDuringSchedulingIgnoredDuringExecution:
- podAffinityTerm:
labelSelector:
matchExpressions:
- key: alertmanager
operator: In
values:
- main
matchLabels:
app.kubernetes.io/component: alert-router
app.kubernetes.io/instance: main
app.kubernetes.io/name: alertmanager
app.kubernetes.io/part-of: kube-prometheus
namespaces:
- monitoring
topologyKey: kubernetes.io/hostname
weight: 100
image: prom/alertmanager:v0.21.0
image: quay.io/prometheus/alertmanager:v0.25.0
nodeSelector:
kubernetes.io/os: linux
replicas: 1
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: 0.25.0
replicas: 3
resources:
limits:
cpu: 100m
memory: 100Mi
requests:
cpu: 4m
memory: 100Mi
securityContext:
fsGroup: 2000
runAsNonRoot: true
runAsUser: 1000
serviceAccountName: alertmanager-main
version: v0.21.0
version: 0.25.0

View File

@ -0,0 +1,42 @@
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: 0.25.0
name: alertmanager-main
namespace: monitoring
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

View File

@ -0,0 +1,19 @@
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: 0.25.0
name: alertmanager-main
namespace: monitoring
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

View File

@ -0,0 +1,139 @@
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: 0.25.0
prometheus: k8s
role: alert-rules
name: alertmanager-main-rules
namespace: monitoring
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
# https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.
max_over_time(alertmanager_cluster_members{job="alertmanager-main",namespace="monitoring"}[5m])
< on (namespace,service) group_left
count by (namespace,service) (max_over_time(alertmanager_cluster_members{job="alertmanager-main",namespace="monitoring"}[5m]))
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: |
(
rate(alertmanager_notifications_failed_total{job="alertmanager-main",namespace="monitoring"}[5m])
/
rate(alertmanager_notifications_total{job="alertmanager-main",namespace="monitoring"}[5m])
)
> 0.01
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) (
rate(alertmanager_notifications_failed_total{job="alertmanager-main",namespace="monitoring", integration=~`.*`}[5m])
/
rate(alertmanager_notifications_total{job="alertmanager-main",namespace="monitoring", integration=~`.*`}[5m])
)
> 0.01
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 {{ $value | humanizePercentage }}.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/alertmanager/alertmanagerclusterfailedtosendalerts
summary: All Alertmanager instances in a cluster failed to send notifications to a non-critical integration.
expr: |
min by (namespace,service, integration) (
rate(alertmanager_notifications_failed_total{job="alertmanager-main",namespace="monitoring", integration!~`.*`}[5m])
/
rate(alertmanager_notifications_total{job="alertmanager-main",namespace="monitoring", integration!~`.*`}[5m])
)
> 0.01
for: 5m
labels:
severity: warning
- alert: AlertmanagerConfigInconsistent
annotations:
description: Alertmanager instances within the {{$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) (
count_values by (namespace,service) ("config_hash", alertmanager_config_hash{job="alertmanager-main",namespace="monitoring"})
)
!= 1
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: |
(
count by (namespace,service) (
avg_over_time(up{job="alertmanager-main",namespace="monitoring"}[5m]) < 0.5
)
/
count by (namespace,service) (
up{job="alertmanager-main",namespace="monitoring"}
)
)
>= 0.5
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: |
(
count by (namespace,service) (
changes(process_start_time_seconds{job="alertmanager-main",namespace="monitoring"}[10m]) > 4
)
/
count by (namespace,service) (
up{job="alertmanager-main",namespace="monitoring"}
)
)
>= 0.5
for: 5m
labels:
severity: critical

View File

@ -1,7 +1,12 @@
apiVersion: v1
data: {}
kind: Secret
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: 0.25.0
name: alertmanager-main
namespace: monitoring
stringData:
@ -12,21 +17,28 @@ stringData:
- "equal":
- "namespace"
- "alertname"
"source_match":
"severity": "critical"
"target_match_re":
"severity": "warning|info"
"source_matchers":
- "severity = critical"
"target_matchers":
- "severity =~ warning|info"
- "equal":
- "namespace"
- "alertname"
"source_match":
"severity": "warning"
"target_match_re":
"severity": "info"
"source_matchers":
- "severity = warning"
"target_matchers":
- "severity = info"
- "equal":
- "namespace"
"source_matchers":
- "alertname = InfoInhibitor"
"target_matchers":
- "severity = info"
"receivers":
- "name": "Default"
- "name": "Watchdog"
- "name": "Critical"
- "name": "null"
"route":
"group_by":
- "namespace"
@ -35,10 +47,13 @@ stringData:
"receiver": "Default"
"repeat_interval": "12h"
"routes":
- "match":
"alertname": "Watchdog"
- "matchers":
- "alertname = Watchdog"
"receiver": "Watchdog"
- "match":
"severity": "critical"
- "matchers":
- "alertname = InfoInhibitor"
"receiver": "null"
- "matchers":
- "severity = critical"
"receiver": "Critical"
type: Opaque

View File

@ -2,7 +2,11 @@ apiVersion: v1
kind: Service
metadata:
labels:
alertmanager: main
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: 0.25.0
name: alertmanager-main
namespace: monitoring
spec:
@ -10,7 +14,12 @@ spec:
- name: web
port: 9093
targetPort: web
- name: reloader-web
port: 8080
targetPort: reloader-web
selector:
alertmanager: main
app: alertmanager
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

View File

@ -1,5 +1,12 @@
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: 0.25.0
name: alertmanager-main
namespace: monitoring

View File

@ -2,13 +2,22 @@ apiVersion: monitoring.coreos.com/v1
kind: ServiceMonitor
metadata:
labels:
k8s-app: alertmanager
name: alertmanager
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: 0.25.0
name: alertmanager-main
namespace: monitoring
spec:
endpoints:
- interval: 30s
port: web
- interval: 30s
port: reloader-web
selector:
matchLabels:
alertmanager: main
app.kubernetes.io/component: alert-router
app.kubernetes.io/instance: main
app.kubernetes.io/name: alertmanager
app.kubernetes.io/part-of: kube-prometheus

View File

@ -1,8 +1,15 @@
apiVersion: v1
data:
grafana.ini: W2F1dGguYW5vbnltb3VzXQplbmFibGVkID0gZmFsc2UKW2F1dGguYmFzaWNdCmVuYWJsZWQgPSBmYWxzZQpbc2Vzc2lvbl0KcHJvdmlkZXIgPSBtZW1vcnkKW3NtdHBdCmVuYWJsZWQgPSB0cnVlCmZyb21fYWRkcmVzcyA9IG15ZW1haWxAZ21haWwuY29tCmZyb21fbmFtZSA9IEdyYWZhbmEgQWxlcnQKaG9zdCA9IHNtdHAtc2VydmVyLm1vbml0b3Jpbmcuc3ZjOjI1CnBhc3N3b3JkID0gCnNraXBfdmVyaWZ5ID0gdHJ1ZQp1c2VyID0gCg==
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: 9.3.2
name: grafana-config
namespace: monitoring
stringData:
grafana.ini: |
[date_formats]
default_timezone = UTC
type: Opaque

View File

@ -1,8 +1,27 @@
apiVersion: v1
data:
datasources.yaml: ewogICAgImFwaVZlcnNpb24iOiAxLAogICAgImRhdGFzb3VyY2VzIjogWwogICAgICAgIHsKICAgICAgICAgICAgImFjY2VzcyI6ICJwcm94eSIsCiAgICAgICAgICAgICJlZGl0YWJsZSI6IGZhbHNlLAogICAgICAgICAgICAibmFtZSI6ICJwcm9tZXRoZXVzIiwKICAgICAgICAgICAgIm9yZ0lkIjogMSwKICAgICAgICAgICAgInR5cGUiOiAicHJvbWV0aGV1cyIsCiAgICAgICAgICAgICJ1cmwiOiAiaHR0cDovL3Byb21ldGhldXMtazhzLm1vbml0b3Jpbmcuc3ZjOjkwOTAiLAogICAgICAgICAgICAidmVyc2lvbiI6IDEKICAgICAgICB9CiAgICBdCn0=
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: 9.3.2
name: grafana-datasources
namespace: monitoring
stringData:
datasources.yaml: |-
{
"apiVersion": 1,
"datasources": [
{
"access": "proxy",
"editable": false,
"name": "prometheus",
"orgId": 1,
"type": "prometheus",
"url": "http://prometheus-k8s.monitoring.svc:9090",
"version": 1
}
]
}
type: Opaque

File diff suppressed because it is too large Load Diff

View File

@ -6,6 +6,7 @@ data:
"providers": [
{
"folder": "Default",
"folderUid": "",
"name": "0",
"options": {
"path": "/grafana-dashboard-definitions/0"
@ -17,5 +18,10 @@ data:
}
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: 9.3.2
name: grafana-dashboards
namespace: monitoring

View File

@ -2,22 +2,35 @@ apiVersion: apps/v1
kind: Deployment
metadata:
labels:
app: grafana
app.kubernetes.io/component: grafana
app.kubernetes.io/name: grafana
app.kubernetes.io/part-of: kube-prometheus
app.kubernetes.io/version: 9.3.2
name: grafana
namespace: monitoring
spec:
replicas: 1
selector:
matchLabels:
app: grafana
app.kubernetes.io/component: grafana
app.kubernetes.io/name: grafana
app.kubernetes.io/part-of: kube-prometheus
template:
metadata:
annotations:
checksum/grafana-config: adbde4cde1aa3ca57c408943af53e6f7
checksum/grafana-dashboardproviders: d8fb24844314114bed088b83042b1bdb
checksum/grafana-datasources: 0800bab7ea1e2d8ad5c09586d089e033
labels:
app: grafana
app.kubernetes.io/component: grafana
app.kubernetes.io/name: grafana
app.kubernetes.io/part-of: kube-prometheus
app.kubernetes.io/version: 9.3.2
spec:
automountServiceAccountToken: false
containers:
- env: []
image: grafana/grafana:7.0.3
image: grafana/grafana:9.3.2
name: grafana
ports:
- containerPort: 3000
@ -33,6 +46,12 @@ spec:
requests:
cpu: 100m
memory: 100Mi
securityContext:
allowPrivilegeEscalation: false
capabilities:
drop:
- ALL
readOnlyRootFilesystem: true
volumeMounts:
- mountPath: /var/lib/grafana
name: grafana-storage
@ -43,6 +62,12 @@ spec:
- 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
@ -52,8 +77,8 @@ spec:
- mountPath: /grafana-dashboard-definitions/0/controller-manager
name: grafana-dashboard-controller-manager
readOnly: false
- mountPath: /grafana-dashboard-definitions/0/coredns-dashboard
name: grafana-dashboard-coredns-dashboard
- 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
@ -76,9 +101,6 @@ spec:
- mountPath: /grafana-dashboard-definitions/0/kubelet
name: grafana-dashboard-kubelet
readOnly: false
- mountPath: /grafana-dashboard-definitions/0/kubernetes-cluster-dashboard
name: grafana-dashboard-kubernetes-cluster-dashboard
readOnly: false
- mountPath: /grafana-dashboard-definitions/0/namespace-by-pod
name: grafana-dashboard-namespace-by-pod
readOnly: false
@ -91,6 +113,9 @@ spec:
- 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
@ -100,9 +125,6 @@ spec:
- mountPath: /grafana-dashboard-definitions/0/pod-total
name: grafana-dashboard-pod-total
readOnly: false
- mountPath: /grafana-dashboard-definitions/0/prometheus-dashboard
name: grafana-dashboard-prometheus-dashboard
readOnly: false
- mountPath: /grafana-dashboard-definitions/0/prometheus-remote-write
name: grafana-dashboard-prometheus-remote-write
readOnly: false
@ -115,9 +137,6 @@ spec:
- mountPath: /grafana-dashboard-definitions/0/scheduler
name: grafana-dashboard-scheduler
readOnly: false
- mountPath: /grafana-dashboard-definitions/0/statefulset
name: grafana-dashboard-statefulset
readOnly: false
- mountPath: /grafana-dashboard-definitions/0/workload-total
name: grafana-dashboard-workload-total
readOnly: false
@ -125,8 +144,9 @@ spec:
name: grafana-config
readOnly: false
nodeSelector:
beta.kubernetes.io/os: linux
kubernetes.io/os: linux
securityContext:
fsGroup: 65534
runAsNonRoot: true
runAsUser: 65534
serviceAccountName: grafana
@ -139,6 +159,12 @@ spec:
- 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
@ -149,8 +175,8 @@ spec:
name: grafana-dashboard-controller-manager
name: grafana-dashboard-controller-manager
- configMap:
name: grafana-dashboard-coredns-dashboard
name: grafana-dashboard-coredns-dashboard
name: grafana-dashboard-grafana-overview
name: grafana-dashboard-grafana-overview
- configMap:
name: grafana-dashboard-k8s-resources-cluster
name: grafana-dashboard-k8s-resources-cluster
@ -172,9 +198,6 @@ spec:
- configMap:
name: grafana-dashboard-kubelet
name: grafana-dashboard-kubelet
- configMap:
name: grafana-dashboard-kubernetes-cluster-dashboard
name: grafana-dashboard-kubernetes-cluster-dashboard
- configMap:
name: grafana-dashboard-namespace-by-pod
name: grafana-dashboard-namespace-by-pod
@ -187,6 +210,9 @@ spec:
- 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
@ -196,9 +222,6 @@ spec:
- configMap:
name: grafana-dashboard-pod-total
name: grafana-dashboard-pod-total
- configMap:
name: grafana-dashboard-prometheus-dashboard
name: grafana-dashboard-prometheus-dashboard
- configMap:
name: grafana-dashboard-prometheus-remote-write
name: grafana-dashboard-prometheus-remote-write
@ -211,9 +234,6 @@ spec:
- configMap:
name: grafana-dashboard-scheduler
name: grafana-dashboard-scheduler
- configMap:
name: grafana-dashboard-statefulset
name: grafana-dashboard-statefulset
- configMap:
name: grafana-dashboard-workload-total
name: grafana-dashboard-workload-total

View File

@ -0,0 +1,29 @@
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: 9.3.2
name: grafana
namespace: monitoring
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

View File

@ -0,0 +1,33 @@
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: 9.3.2
prometheus: k8s
role: alert-rules
name: grafana-rules
namespace: monitoring
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 * 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.."}
/ ignoring (status_code)
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

View File

@ -2,7 +2,10 @@ apiVersion: v1
kind: Service
metadata:
labels:
app: grafana
app.kubernetes.io/component: grafana
app.kubernetes.io/name: grafana
app.kubernetes.io/part-of: kube-prometheus
app.kubernetes.io/version: 9.3.2
name: grafana
namespace: monitoring
spec:
@ -11,4 +14,6 @@ spec:
port: 3000
targetPort: http
selector:
app: grafana
app.kubernetes.io/component: grafana
app.kubernetes.io/name: grafana
app.kubernetes.io/part-of: kube-prometheus

View File

@ -1,5 +1,11 @@
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: 9.3.2
name: grafana
namespace: monitoring

View File

@ -1,6 +1,11 @@
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: 9.3.2
name: grafana
namespace: monitoring
spec:
@ -9,4 +14,4 @@ spec:
port: http
selector:
matchLabels:
app: grafana
app.kubernetes.io/name: grafana

View File

@ -2,8 +2,10 @@ 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/version: 1.9.6
app.kubernetes.io/part-of: kube-prometheus
app.kubernetes.io/version: 2.7.0
name: kube-state-metrics
rules:
- apiGroups:
@ -14,6 +16,7 @@ rules:
- nodes
- pods
- services
- serviceaccounts
- resourcequotas
- replicationcontrollers
- limitranges
@ -24,16 +27,6 @@ rules:
verbs:
- list
- watch
- apiGroups:
- extensions
resources:
- daemonsets
- deployments
- replicasets
- ingresses
verbs:
- list
- watch
- apiGroups:
- apps
resources:
@ -85,6 +78,13 @@ rules:
verbs:
- list
- watch
- apiGroups:
- discovery.k8s.io
resources:
- endpointslices
verbs:
- list
- watch
- apiGroups:
- storage.k8s.io
resources:
@ -105,6 +105,8 @@ rules:
- networking.k8s.io
resources:
- networkpolicies
- ingressclasses
- ingresses
verbs:
- list
- watch
@ -115,3 +117,13 @@ rules:
verbs:
- list
- watch
- apiGroups:
- rbac.authorization.k8s.io
resources:
- clusterrolebindings
- clusterroles
- rolebindings
- roles
verbs:
- list
- watch

View File

@ -2,8 +2,10 @@ 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/version: 1.9.6
app.kubernetes.io/part-of: kube-prometheus
app.kubernetes.io/version: 2.7.0
name: kube-state-metrics
roleRef:
apiGroup: rbac.authorization.k8s.io

View File

@ -2,55 +2,104 @@ apiVersion: apps/v1
kind: Deployment
metadata:
labels:
app.kubernetes.io/component: exporter
app.kubernetes.io/name: kube-state-metrics
app.kubernetes.io/version: 1.9.6
app.kubernetes.io/part-of: kube-prometheus
app.kubernetes.io/version: 2.7.0
name: kube-state-metrics
namespace: monitoring
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/version: 1.9.6
app.kubernetes.io/part-of: kube-prometheus
app.kubernetes.io/version: 2.7.0
spec:
automountServiceAccountToken: true
containers:
- args:
- --host=127.0.0.1
- --port=8081
- --telemetry-host=127.0.0.1
- --telemetry-port=8082
image: carlosedp/kube-state-metrics:v1.9.6
image: registry.k8s.io/kube-state-metrics/kube-state-metrics:v2.7.0
name: kube-state-metrics
resources:
limits:
cpu: 100m
memory: 250Mi
requests:
cpu: 10m
memory: 190Mi
securityContext:
allowPrivilegeEscalation: false
capabilities:
drop:
- ALL
readOnlyRootFilesystem: true
runAsUser: 65534
- args:
- --logtostderr
- --secure-listen-address=:8443
- --tls-cipher-suites=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256,TLS_ECDHE_ECDSA_WITH_AES_128_GCM_SHA256,TLS_RSA_WITH_AES_128_CBC_SHA256,TLS_ECDHE_ECDSA_WITH_AES_128_CBC_SHA256,TLS_ECDHE_RSA_WITH_AES_128_CBC_SHA256
- --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: carlosedp/kube-rbac-proxy:v0.5.0
image: quay.io/brancz/kube-rbac-proxy:v0.14.0
name: kube-rbac-proxy-main
ports:
- containerPort: 8443
name: https-main
resources:
limits:
cpu: 40m
memory: 40Mi
requests:
cpu: 20m
memory: 20Mi
securityContext:
runAsUser: 65534
allowPrivilegeEscalation: false
capabilities:
drop:
- ALL
readOnlyRootFilesystem: true
runAsGroup: 65532
runAsNonRoot: true
runAsUser: 65532
- args:
- --logtostderr
- --secure-listen-address=:9443
- --tls-cipher-suites=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256,TLS_ECDHE_ECDSA_WITH_AES_128_GCM_SHA256,TLS_RSA_WITH_AES_128_CBC_SHA256,TLS_ECDHE_ECDSA_WITH_AES_128_CBC_SHA256,TLS_ECDHE_RSA_WITH_AES_128_CBC_SHA256
- --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: carlosedp/kube-rbac-proxy:v0.5.0
image: quay.io/brancz/kube-rbac-proxy:v0.14.0
name: kube-rbac-proxy-self
ports:
- containerPort: 9443
name: https-self
resources:
limits:
cpu: 20m
memory: 40Mi
requests:
cpu: 10m
memory: 20Mi
securityContext:
runAsUser: 65534
allowPrivilegeEscalation: false
capabilities:
drop:
- ALL
readOnlyRootFilesystem: true
runAsGroup: 65532
runAsNonRoot: true
runAsUser: 65532
nodeSelector:
kubernetes.io/os: linux
serviceAccountName: kube-state-metrics

View File

@ -0,0 +1,31 @@
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: 2.7.0
name: kube-state-metrics
namespace: monitoring
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

View File

@ -0,0 +1,65 @@
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: 2.7.0
prometheus: k8s
role: alert-rules
name: kube-state-metrics-rules
namespace: monitoring
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]))
/
sum(rate(kube_state_metrics_list_total{job="kube-state-metrics"}[5m])))
> 0.01
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]))
/
sum(rate(kube_state_metrics_watch_total{job="kube-state-metrics"}[5m])))
> 0.01
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"}) != 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"}) - 1
-
sum( 2 ^ max by (shard_ordinal) (kube_state_metrics_shard_ordinal{job="kube-state-metrics"}) )
!= 0
for: 15m
labels:
severity: critical

View File

@ -2,8 +2,10 @@ apiVersion: v1
kind: Service
metadata:
labels:
app.kubernetes.io/component: exporter
app.kubernetes.io/name: kube-state-metrics
app.kubernetes.io/version: 1.9.6
app.kubernetes.io/part-of: kube-prometheus
app.kubernetes.io/version: 2.7.0
name: kube-state-metrics
namespace: monitoring
spec:
@ -16,4 +18,6 @@ spec:
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

View File

@ -1,8 +1,11 @@
apiVersion: v1
automountServiceAccountToken: false
kind: ServiceAccount
metadata:
labels:
app.kubernetes.io/component: exporter
app.kubernetes.io/name: kube-state-metrics
app.kubernetes.io/version: 1.9.6
app.kubernetes.io/part-of: kube-prometheus
app.kubernetes.io/version: 2.7.0
name: kube-state-metrics
namespace: monitoring

View File

@ -2,8 +2,10 @@ apiVersion: monitoring.coreos.com/v1
kind: ServiceMonitor
metadata:
labels:
app.kubernetes.io/component: exporter
app.kubernetes.io/name: kube-state-metrics
app.kubernetes.io/version: 1.9.6
app.kubernetes.io/part-of: kube-prometheus
app.kubernetes.io/version: 2.7.0
name: kube-state-metrics
namespace: monitoring
spec:
@ -11,6 +13,11 @@ spec:
- 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
@ -28,4 +35,6 @@ spec:
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

View File

@ -1,7 +1,13 @@
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: 1.5.0
name: node-exporter
namespace: monitoring
rules:
- apiGroups:
- authentication.k8s.io

View File

@ -1,7 +1,13 @@
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: 1.5.0
name: node-exporter
namespace: monitoring
roleRef:
apiGroup: rbac.authorization.k8s.io
kind: ClusterRole

View File

@ -2,30 +2,41 @@ apiVersion: apps/v1
kind: DaemonSet
metadata:
labels:
app.kubernetes.io/component: exporter
app.kubernetes.io/name: node-exporter
app.kubernetes.io/version: v0.18.1
app.kubernetes.io/part-of: kube-prometheus
app.kubernetes.io/version: 1.5.0
name: node-exporter
namespace: monitoring
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/version: v0.18.1
app.kubernetes.io/part-of: kube-prometheus
app.kubernetes.io/version: 1.5.0
spec:
automountServiceAccountToken: true
containers:
- args:
- --web.listen-address=127.0.0.1:9100
- --path.procfs=/host/proc
- --path.sysfs=/host/sys
- --path.rootfs=/host/root
- --path.udev.data=/host/root/run/udev/data
- --no-collector.wifi
- --no-collector.hwmon
- --collector.filesystem.ignored-mount-points=^/(dev|proc|sys|var/lib/docker/.+|var/lib/kubelet/pods/.+)($|/)
image: prom/node-exporter:v0.18.1
- --collector.filesystem.mount-points-exclude=^/(dev|proc|sys|run/k3s/containerd/.+|var/lib/docker/.+|var/lib/kubelet/pods/.+)($|/)
- --collector.netclass.ignored-devices=^(veth.*|[a-f0-9]{15})$
- --collector.netdev.device-exclude=^(veth.*|[a-f0-9]{15})$
image: quay.io/prometheus/node-exporter:v1.5.0
name: node-exporter
resources:
limits:
@ -34,13 +45,19 @@ spec:
requests:
cpu: 102m
memory: 180Mi
securityContext:
allowPrivilegeEscalation: false
capabilities:
add:
- SYS_TIME
drop:
- ALL
readOnlyRootFilesystem: true
volumeMounts:
- mountPath: /host/proc
name: proc
readOnly: false
- mountPath: /host/sys
mountPropagation: HostToContainer
name: sys
readOnly: false
readOnly: true
- mountPath: /host/root
mountPropagation: HostToContainer
name: root
@ -48,14 +65,14 @@ spec:
- args:
- --logtostderr
- --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_RSA_WITH_AES_128_CBC_SHA256,TLS_ECDHE_ECDSA_WITH_AES_128_CBC_SHA256,TLS_ECDHE_RSA_WITH_AES_128_CBC_SHA256
- --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: carlosedp/kube-rbac-proxy:v0.5.0
image: quay.io/brancz/kube-rbac-proxy:v0.14.0
name: kube-rbac-proxy
ports:
- containerPort: 9100
@ -68,10 +85,20 @@ spec:
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
@ -79,12 +106,13 @@ spec:
tolerations:
- operator: Exists
volumes:
- hostPath:
path: /proc
name: proc
- hostPath:
path: /sys
name: sys
- hostPath:
path: /
name: root
updateStrategy:
rollingUpdate:
maxUnavailable: 10%
type: RollingUpdate

View File

@ -0,0 +1,29 @@
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: 1.5.0
name: node-exporter
namespace: monitoring
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

View File

@ -0,0 +1,316 @@
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: 1.5.0
prometheus: k8s
role: alert-rules
name: node-exporter-rules
namespace: monitoring
spec:
groups:
- name: node-exporter
rules:
- alert: NodeFilesystemSpaceFillingUp
annotations:
description: Filesystem on {{ $labels.device }} 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: |
(
node_filesystem_avail_bytes{job="node-exporter",fstype!="",mountpoint!=""} / node_filesystem_size_bytes{job="node-exporter",fstype!="",mountpoint!=""} * 100 < 15
and
predict_linear(node_filesystem_avail_bytes{job="node-exporter",fstype!="",mountpoint!=""}[6h], 24*60*60) < 0
and
node_filesystem_readonly{job="node-exporter",fstype!="",mountpoint!=""} == 0
)
for: 1h
labels:
severity: warning
- alert: NodeFilesystemSpaceFillingUp
annotations:
description: Filesystem on {{ $labels.device }} at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available space left and is filling up fast.
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: |
(
node_filesystem_avail_bytes{job="node-exporter",fstype!="",mountpoint!=""} / node_filesystem_size_bytes{job="node-exporter",fstype!="",mountpoint!=""} * 100 < 10
and
predict_linear(node_filesystem_avail_bytes{job="node-exporter",fstype!="",mountpoint!=""}[6h], 4*60*60) < 0
and
node_filesystem_readonly{job="node-exporter",fstype!="",mountpoint!=""} == 0
)
for: 1h
labels:
severity: critical
- alert: NodeFilesystemAlmostOutOfSpace
annotations:
description: Filesystem on {{ $labels.device }} 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: |
(
node_filesystem_avail_bytes{job="node-exporter",fstype!="",mountpoint!=""} / node_filesystem_size_bytes{job="node-exporter",fstype!="",mountpoint!=""} * 100 < 5
and
node_filesystem_readonly{job="node-exporter",fstype!="",mountpoint!=""} == 0
)
for: 30m
labels:
severity: warning
- alert: NodeFilesystemAlmostOutOfSpace
annotations:
description: Filesystem on {{ $labels.device }} 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: |
(
node_filesystem_avail_bytes{job="node-exporter",fstype!="",mountpoint!=""} / node_filesystem_size_bytes{job="node-exporter",fstype!="",mountpoint!=""} * 100 < 3
and
node_filesystem_readonly{job="node-exporter",fstype!="",mountpoint!=""} == 0
)
for: 30m
labels:
severity: critical
- alert: NodeFilesystemFilesFillingUp
annotations:
description: Filesystem on {{ $labels.device }} at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available inodes left and is filling up.
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: |
(
node_filesystem_files_free{job="node-exporter",fstype!="",mountpoint!=""} / node_filesystem_files{job="node-exporter",fstype!="",mountpoint!=""} * 100 < 40
and
predict_linear(node_filesystem_files_free{job="node-exporter",fstype!="",mountpoint!=""}[6h], 24*60*60) < 0
and
node_filesystem_readonly{job="node-exporter",fstype!="",mountpoint!=""} == 0
)
for: 1h
labels:
severity: warning
- alert: NodeFilesystemFilesFillingUp
annotations:
description: Filesystem on {{ $labels.device }} at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available inodes left and is filling up fast.
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: |
(
node_filesystem_files_free{job="node-exporter",fstype!="",mountpoint!=""} / node_filesystem_files{job="node-exporter",fstype!="",mountpoint!=""} * 100 < 20
and
predict_linear(node_filesystem_files_free{job="node-exporter",fstype!="",mountpoint!=""}[6h], 4*60*60) < 0
and
node_filesystem_readonly{job="node-exporter",fstype!="",mountpoint!=""} == 0
)
for: 1h
labels:
severity: critical
- alert: NodeFilesystemAlmostOutOfFiles
annotations:
description: Filesystem on {{ $labels.device }} 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: |
(
node_filesystem_files_free{job="node-exporter",fstype!="",mountpoint!=""} / node_filesystem_files{job="node-exporter",fstype!="",mountpoint!=""} * 100 < 5
and
node_filesystem_readonly{job="node-exporter",fstype!="",mountpoint!=""} == 0
)
for: 1h
labels:
severity: warning
- alert: NodeFilesystemAlmostOutOfFiles
annotations:
description: Filesystem on {{ $labels.device }} 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: |
(
node_filesystem_files_free{job="node-exporter",fstype!="",mountpoint!=""} / node_filesystem_files{job="node-exporter",fstype!="",mountpoint!=""} * 100 < 3
and
node_filesystem_readonly{job="node-exporter",fstype!="",mountpoint!=""} == 0
)
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[2m]) / rate(node_network_receive_packets_total[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[2m]) / rate(node_network_transmit_packets_total[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 / node_nf_conntrack_entries_limit) > 0.75
labels:
severity: warning
- alert: NodeTextFileCollectorScrapeError
annotations:
description: Node Exporter text file collector 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 on {{ $labels.instance }} is out of sync by more than 300s. Ensure NTP is configured correctly on this host.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodeclockskewdetected
summary: Clock skew detected.
expr: |
(
node_timex_offset_seconds{job="node-exporter"} > 0.05
and
deriv(node_timex_offset_seconds{job="node-exporter"}[5m]) >= 0
)
or
(
node_timex_offset_seconds{job="node-exporter"} < -0.05
and
deriv(node_timex_offset_seconds{job="node-exporter"}[5m]) <= 0
)
for: 10m
labels:
severity: warning
- alert: NodeClockNotSynchronising
annotations:
description: Clock on {{ $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 }}' on {{ $labels.instance }} is in degraded state due to one or more disks failures. Number of spare drives is insufficient to fix issue automatically.
runbook_url: https://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 on {{ $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: |
(
node_filefd_allocated{job="node-exporter"} * 100 / node_filefd_maximum{job="node-exporter"} > 70
)
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: |
(
node_filefd_allocated{job="node-exporter"} * 100 / node_filefd_maximum{job="node-exporter"} > 90
)
for: 15m
labels:
severity: critical
- name: node-exporter.rules
rules:
- expr: |
count without (cpu, mode) (
node_cpu_seconds_total{job="node-exporter",mode="idle"}
)
record: instance:node_num_cpu:sum
- expr: |
1 - avg without (cpu) (
sum without (mode) (rate(node_cpu_seconds_total{job="node-exporter", mode=~"idle|iowait|steal"}[5m]))
)
record: instance:node_cpu_utilisation:rate5m
- expr: |
(
node_load1{job="node-exporter"}
/
instance:node_num_cpu:sum{job="node-exporter"}
)
record: instance:node_load1_per_cpu:ratio
- expr: |
1 - (
(
node_memory_MemAvailable_bytes{job="node-exporter"}
or
(
node_memory_Buffers_bytes{job="node-exporter"}
+
node_memory_Cached_bytes{job="node-exporter"}
+
node_memory_MemFree_bytes{job="node-exporter"}
+
node_memory_Slab_bytes{job="node-exporter"}
)
)
/
node_memory_MemTotal_bytes{job="node-exporter"}
)
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) (
rate(node_network_receive_bytes_total{job="node-exporter", device!="lo"}[5m])
)
record: instance:node_network_receive_bytes_excluding_lo:rate5m
- expr: |
sum without (device) (
rate(node_network_transmit_bytes_total{job="node-exporter", device!="lo"}[5m])
)
record: instance:node_network_transmit_bytes_excluding_lo:rate5m
- expr: |
sum without (device) (
rate(node_network_receive_drop_total{job="node-exporter", device!="lo"}[5m])
)
record: instance:node_network_receive_drop_excluding_lo:rate5m
- expr: |
sum without (device) (
rate(node_network_transmit_drop_total{job="node-exporter", device!="lo"}[5m])
)
record: instance:node_network_transmit_drop_excluding_lo:rate5m

View File

@ -2,8 +2,10 @@ apiVersion: v1
kind: Service
metadata:
labels:
app.kubernetes.io/component: exporter
app.kubernetes.io/name: node-exporter
app.kubernetes.io/version: v0.18.1
app.kubernetes.io/part-of: kube-prometheus
app.kubernetes.io/version: 1.5.0
name: node-exporter
namespace: monitoring
spec:
@ -13,4 +15,6 @@ spec:
port: 9100
targetPort: https
selector:
app.kubernetes.io/component: exporter
app.kubernetes.io/name: node-exporter
app.kubernetes.io/part-of: kube-prometheus

View File

@ -1,5 +1,11 @@
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: 1.5.0
name: node-exporter
namespace: monitoring

View File

@ -2,8 +2,10 @@ apiVersion: monitoring.coreos.com/v1
kind: ServiceMonitor
metadata:
labels:
app.kubernetes.io/component: exporter
app.kubernetes.io/name: node-exporter
app.kubernetes.io/version: v0.18.1
app.kubernetes.io/part-of: kube-prometheus
app.kubernetes.io/version: 1.5.0
name: node-exporter
namespace: monitoring
spec:
@ -24,4 +26,6 @@ spec:
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

View File

@ -1,6 +1,11 @@
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: 0.10.0
name: v1beta1.metrics.k8s.io
spec:
group: metrics.k8s.io

View File

@ -1,7 +1,13 @@
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: 0.10.0
name: prometheus-adapter
namespace: monitoring
rules:
- apiGroups:
- ""

View File

@ -2,10 +2,15 @@ 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: 0.10.0
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
namespace: monitoring
rules:
- apiGroups:
- metrics.k8s.io

View File

@ -1,7 +1,13 @@
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: 0.10.0
name: prometheus-adapter
namespace: monitoring
roleRef:
apiGroup: rbac.authorization.k8s.io
kind: ClusterRole

View File

@ -1,7 +1,13 @@
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: 0.10.0
name: resource-metrics:system:auth-delegator
namespace: monitoring
roleRef:
apiGroup: rbac.authorization.k8s.io
kind: ClusterRole

View File

@ -1,7 +1,13 @@
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: 0.10.0
name: resource-metrics-server-resources
namespace: monitoring
rules:
- apiGroups:
- metrics.k8s.io

View File

@ -4,8 +4,26 @@ data:
"resourceRules":
"cpu":
"containerLabel": "container"
"containerQuery": "sum(irate(container_cpu_usage_seconds_total{<<.LabelMatchers>>,container!=\"POD\",container!=\"\",pod!=\"\"}[5m])) by (<<.GroupBy>>)"
"nodeQuery": "sum(1 - irate(node_cpu_seconds_total{mode=\"idle\"}[5m]) * on(namespace, pod) group_left(node) node_namespace_pod:kube_pod_info:{<<.LabelMatchers>>}) by (<<.GroupBy>>)"
"containerQuery": |
sum by (<<.GroupBy>>) (
irate (
container_cpu_usage_seconds_total{<<.LabelMatchers>>,container!="",pod!=""}[120s]
)
)
"nodeQuery": |
sum by (<<.GroupBy>>) (
1 - irate(
node_cpu_seconds_total{mode="idle"}[60s]
)
* on(namespace, pod) group_left(node) (
node_namespace_pod:kube_pod_info:{<<.LabelMatchers>>}
)
)
or sum by (<<.GroupBy>>) (
1 - irate(
windows_cpu_time_total{mode="idle", job="windows-exporter",<<.LabelMatchers>>}[4m]
)
)
"resources":
"overrides":
"namespace":
@ -16,8 +34,21 @@ data:
"resource": "pod"
"memory":
"containerLabel": "container"
"containerQuery": "sum(container_memory_working_set_bytes{<<.LabelMatchers>>,container!=\"POD\",container!=\"\",pod!=\"\"}) by (<<.GroupBy>>)"
"nodeQuery": "sum(node_memory_MemTotal_bytes{job=\"node-exporter\",<<.LabelMatchers>>} - node_memory_MemAvailable_bytes{job=\"node-exporter\",<<.LabelMatchers>>}) by (<<.GroupBy>>)"
"containerQuery": |
sum by (<<.GroupBy>>) (
container_memory_working_set_bytes{<<.LabelMatchers>>,container!="",pod!=""}
)
"nodeQuery": |
sum by (<<.GroupBy>>) (
node_memory_MemTotal_bytes{job="node-exporter",<<.LabelMatchers>>}
-
node_memory_MemAvailable_bytes{job="node-exporter",<<.LabelMatchers>>}
)
or sum by (<<.GroupBy>>) (
windows_cs_physical_memory_bytes{job="windows-exporter",<<.LabelMatchers>>}
-
windows_memory_available_bytes{job="windows-exporter",<<.LabelMatchers>>}
)
"resources":
"overrides":
"instance":
@ -29,5 +60,10 @@ data:
"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: 0.10.0
name: adapter-config
namespace: monitoring

View File

@ -1,22 +1,46 @@
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: 0.10.0
name: prometheus-adapter
namespace: monitoring
spec:
replicas: 1
replicas: 2
selector:
matchLabels:
name: prometheus-adapter
app.kubernetes.io/component: metrics-adapter
app.kubernetes.io/name: prometheus-adapter
app.kubernetes.io/part-of: kube-prometheus
strategy:
rollingUpdate:
maxSurge: 1
maxUnavailable: 0
maxUnavailable: 1
template:
metadata:
labels:
name: prometheus-adapter
app.kubernetes.io/component: metrics-adapter
app.kubernetes.io/name: prometheus-adapter
app.kubernetes.io/part-of: kube-prometheus
app.kubernetes.io/version: 0.10.0
spec:
affinity:
podAntiAffinity:
preferredDuringSchedulingIgnoredDuringExecution:
- podAffinityTerm:
labelSelector:
matchLabels:
app.kubernetes.io/component: metrics-adapter
app.kubernetes.io/name: prometheus-adapter
app.kubernetes.io/part-of: kube-prometheus
namespaces:
- monitoring
topologyKey: kubernetes.io/hostname
weight: 100
automountServiceAccountToken: true
containers:
- args:
- --cert-dir=/var/run/serving-cert
@ -25,10 +49,41 @@ spec:
- --metrics-relist-interval=1m
- --prometheus-url=http://prometheus-k8s.monitoring.svc:9090/
- --secure-port=6443
image: directxman12/k8s-prometheus-adapter:v0.7.0
- --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:v0.10.0
livenessProbe:
failureThreshold: 5
httpGet:
path: /livez
port: https
scheme: HTTPS
initialDelaySeconds: 30
periodSeconds: 5
name: prometheus-adapter
ports:
- containerPort: 6443
name: https
readinessProbe:
failureThreshold: 5
httpGet:
path: /readyz
port: https
scheme: HTTPS
initialDelaySeconds: 30
periodSeconds: 5
resources:
limits:
cpu: 250m
memory: 180Mi
requests:
cpu: 102m
memory: 180Mi
securityContext:
allowPrivilegeEscalation: false
capabilities:
drop:
- ALL
readOnlyRootFilesystem: true
volumeMounts:
- mountPath: /tmp
name: tmpfs

View File

@ -0,0 +1,23 @@
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: 0.10.0
name: prometheus-adapter
namespace: monitoring
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

View File

@ -0,0 +1,17 @@
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: 0.10.0
name: prometheus-adapter
namespace: monitoring
spec:
minAvailable: 1
selector:
matchLabels:
app.kubernetes.io/component: metrics-adapter
app.kubernetes.io/name: prometheus-adapter
app.kubernetes.io/part-of: kube-prometheus

View File

@ -1,6 +1,11 @@
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: 0.10.0
name: resource-metrics-auth-reader
namespace: kube-system
roleRef:

View File

@ -2,7 +2,10 @@ apiVersion: v1
kind: Service
metadata:
labels:
name: prometheus-adapter
app.kubernetes.io/component: metrics-adapter
app.kubernetes.io/name: prometheus-adapter
app.kubernetes.io/part-of: kube-prometheus
app.kubernetes.io/version: 0.10.0
name: prometheus-adapter
namespace: monitoring
spec:
@ -11,4 +14,6 @@ spec:
port: 443
targetPort: 6443
selector:
name: prometheus-adapter
app.kubernetes.io/component: metrics-adapter
app.kubernetes.io/name: prometheus-adapter
app.kubernetes.io/part-of: kube-prometheus

View File

@ -1,5 +1,11 @@
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: 0.10.0
name: prometheus-adapter
namespace: monitoring

View File

@ -0,0 +1,28 @@
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: 0.10.0
name: prometheus-adapter
namespace: monitoring
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

View File

@ -1,6 +1,12 @@
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: 2.41.0
name: prometheus-k8s
rules:
- apiGroups:

View File

@ -1,6 +1,12 @@
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: 2.41.0
name: prometheus-k8s
roleRef:
apiGroup: rbac.authorization.k8s.io

View File

@ -1,15 +0,0 @@
apiVersion: v1
kind: Service
metadata:
labels:
k8s-app: kube-controller-manager
name: kube-controller-manager-prometheus-discovery
namespace: kube-system
spec:
clusterIP: None
ports:
- name: http-metrics
port: 10252
targetPort: 10252
selector:
component: kube-controller-manager

View File

@ -1,15 +0,0 @@
apiVersion: v1
kind: Service
metadata:
labels:
k8s-app: kube-dns
name: kube-dns-prometheus-discovery
namespace: kube-system
spec:
clusterIP: None
ports:
- name: metrics
port: 9153
targetPort: 9153
selector:
k8s-app: kube-dns

View File

@ -1,15 +0,0 @@
apiVersion: v1
kind: Service
metadata:
labels:
k8s-app: kube-scheduler
name: kube-scheduler-prometheus-discovery
namespace: kube-system
spec:
clusterIP: None
ports:
- name: http-metrics
port: 10251
targetPort: 10251
selector:
component: kube-scheduler

View File

@ -0,0 +1,40 @@
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: 2.41.0
name: prometheus-k8s
namespace: monitoring
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: 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

View File

@ -4,7 +4,8 @@ metadata:
labels:
app.kubernetes.io/component: controller
app.kubernetes.io/name: prometheus-operator
app.kubernetes.io/version: v0.40.0
app.kubernetes.io/part-of: kube-prometheus
app.kubernetes.io/version: 0.61.1
name: prometheus-operator
namespace: monitoring
spec:
@ -19,4 +20,5 @@ spec:
matchLabels:
app.kubernetes.io/component: controller
app.kubernetes.io/name: prometheus-operator
app.kubernetes.io/version: v0.40.0
app.kubernetes.io/part-of: kube-prometheus
app.kubernetes.io/version: 0.61.1

View File

@ -0,0 +1,19 @@
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: 2.41.0
name: prometheus-k8s
namespace: monitoring
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

View File

@ -2,7 +2,11 @@ apiVersion: monitoring.coreos.com/v1
kind: Prometheus
metadata:
labels:
prometheus: k8s
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: 2.41.0
name: k8s
namespace: monitoring
spec:
@ -11,35 +15,45 @@ spec:
preferredDuringSchedulingIgnoredDuringExecution:
- podAffinityTerm:
labelSelector:
matchExpressions:
- key: prometheus
operator: In
values:
- k8s
matchLabels:
app.kubernetes.io/component: prometheus
app.kubernetes.io/instance: k8s
app.kubernetes.io/name: prometheus
app.kubernetes.io/part-of: kube-prometheus
namespaces:
- monitoring
topologyKey: kubernetes.io/hostname
weight: 100
alerting:
alertmanagers:
- name: alertmanager-main
- apiVersion: v2
name: alertmanager-main
namespace: monitoring
port: web
enableFeatures: []
externalLabels: {}
externalUrl: http://prometheus.192.168.1.15.nip.io
image: prom/prometheus:v2.19.1
image: quay.io/prometheus/prometheus:v2.41.0
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: 2.41.0
podMonitorNamespaceSelector: {}
podMonitorSelector: {}
probeNamespaceSelector: {}
probeSelector: {}
replicas: 1
resources:
requests:
memory: 400Mi
retention: 15d
ruleSelector:
matchLabels:
prometheus: k8s
role: alert-rules
ruleNamespaceSelector: {}
ruleSelector: {}
scrapeInterval: 30s
scrapeTimeout: 30s
securityContext:
@ -49,4 +63,4 @@ spec:
serviceAccountName: prometheus-k8s
serviceMonitorNamespaceSelector: {}
serviceMonitorSelector: {}
version: v2.19.1
version: 2.41.0

View File

@ -0,0 +1,280 @@
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: 2.41.0
prometheus: k8s
role: alert-rules
name: prometheus-k8s-prometheus-rules
namespace: monitoring
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: 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
# https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.
(
predict_linear(prometheus_notifications_queue_length{job="prometheus-k8s",namespace="monitoring"}[5m], 60 * 30)
>
min_over_time(prometheus_notifications_queue_capacity{job="prometheus-k8s",namespace="monitoring"}[5m])
)
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: |
(
rate(prometheus_notifications_errors_total{job="prometheus-k8s",namespace="monitoring"}[5m])
/
rate(prometheus_notifications_sent_total{job="prometheus-k8s",namespace="monitoring"}[5m])
)
* 100
> 1
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: |
(
rate(prometheus_tsdb_head_samples_appended_total{job="prometheus-k8s",namespace="monitoring"}[5m]) <= 0
and
(
sum without(scrape_job) (prometheus_target_metadata_cache_entries{job="prometheus-k8s",namespace="monitoring"}) > 0
or
sum without(rule_group) (prometheus_rule_group_rules{job="prometheus-k8s",namespace="monitoring"}) > 0
)
)
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}}:{{ $labels.url }}
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusremotestoragefailures
summary: Prometheus fails to send samples to remote storage.
expr: |
(
(rate(prometheus_remote_storage_failed_samples_total{job="prometheus-k8s",namespace="monitoring"}[5m]) or rate(prometheus_remote_storage_samples_failed_total{job="prometheus-k8s",namespace="monitoring"}[5m]))
/
(
(rate(prometheus_remote_storage_failed_samples_total{job="prometheus-k8s",namespace="monitoring"}[5m]) or rate(prometheus_remote_storage_samples_failed_total{job="prometheus-k8s",namespace="monitoring"}[5m]))
+
(rate(prometheus_remote_storage_succeeded_samples_total{job="prometheus-k8s",namespace="monitoring"}[5m]) or rate(prometheus_remote_storage_samples_total{job="prometheus-k8s",namespace="monitoring"}[5m]))
)
)
* 100
> 1
for: 15m
labels:
severity: critical
- alert: PrometheusRemoteWriteBehind
annotations:
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} remote write is {{ printf "%.1f" $value }}s behind for {{ $labels.remote_name}}:{{ $labels.url }}.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusremotewritebehind
summary: Prometheus remote write is behind.
expr: |
# Without max_over_time, failed scrapes could create false negatives, see
# https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.
(
max_over_time(prometheus_remote_storage_highest_timestamp_in_seconds{job="prometheus-k8s",namespace="monitoring"}[5m])
- ignoring(remote_name, url) group_right
max_over_time(prometheus_remote_storage_queue_highest_sent_timestamp_seconds{job="prometheus-k8s",namespace="monitoring"}[5m])
)
> 120
for: 15m
labels:
severity: critical
- alert: PrometheusRemoteWriteDesiredShards
annotations:
description: Prometheus {{$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"}` $labels.instance | query | first | value }}.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusremotewritedesiredshards
summary: Prometheus remote write desired shards calculation wants to run more than configured max shards.
expr: |
# Without max_over_time, failed scrapes could create false negatives, see
# https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.
(
max_over_time(prometheus_remote_storage_shards_desired{job="prometheus-k8s",namespace="monitoring"}[5m])
>
max_over_time(prometheus_remote_storage_shards_max{job="prometheus-k8s",namespace="monitoring"}[5m])
)
for: 15m
labels:
severity: warning
- alert: PrometheusRuleFailures
annotations:
description: Prometheus {{$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) (
rate(prometheus_notifications_errors_total{job="prometheus-k8s",namespace="monitoring",alertmanager!~``}[5m])
/
rate(prometheus_notifications_sent_total{job="prometheus-k8s",namespace="monitoring",alertmanager!~``}[5m])
)
* 100
> 3
for: 15m
labels:
severity: critical

View File

@ -1,6 +1,12 @@
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: 2.41.0
name: prometheus-k8s-config
namespace: monitoring
roleRef:

View File

@ -3,6 +3,12 @@ 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: 2.41.0
name: prometheus-k8s
namespace: default
roleRef:
@ -16,6 +22,12 @@ 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: 2.41.0
name: prometheus-k8s
namespace: kube-system
roleRef:
@ -29,6 +41,12 @@ 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: 2.41.0
name: prometheus-k8s
namespace: monitoring
roleRef:

View File

@ -1,6 +1,12 @@
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: 2.41.0
name: prometheus-k8s-config
namespace: monitoring
rules:

View File

@ -3,6 +3,12 @@ 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: 2.41.0
name: prometheus-k8s
namespace: default
rules:
@ -16,9 +22,31 @@ items:
- 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: 2.41.0
name: prometheus-k8s
namespace: kube-system
rules:
@ -32,9 +60,31 @@ items:
- 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: 2.41.0
name: prometheus-k8s
namespace: monitoring
rules:
@ -48,4 +98,20 @@ items:
- get
- list
- watch
- apiGroups:
- extensions
resources:
- ingresses
verbs:
- get
- list
- watch
- apiGroups:
- networking.k8s.io
resources:
- ingresses
verbs:
- get
- list
- watch
kind: RoleList

File diff suppressed because it is too large Load Diff

View File

@ -2,7 +2,11 @@ apiVersion: v1
kind: Service
metadata:
labels:
prometheus: k8s
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: 2.41.0
name: prometheus-k8s
namespace: monitoring
spec:
@ -10,7 +14,12 @@ spec:
- name: web
port: 9090
targetPort: web
- name: reloader-web
port: 8080
targetPort: reloader-web
selector:
app: prometheus
prometheus: k8s
app.kubernetes.io/component: prometheus
app.kubernetes.io/instance: k8s
app.kubernetes.io/name: prometheus
app.kubernetes.io/part-of: kube-prometheus
sessionAffinity: ClientIP

View File

@ -1,5 +1,12 @@
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: 2.41.0
name: prometheus-k8s
namespace: monitoring

View File

@ -2,13 +2,22 @@ apiVersion: monitoring.coreos.com/v1
kind: ServiceMonitor
metadata:
labels:
k8s-app: prometheus
name: prometheus
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: 2.41.0
name: prometheus-k8s
namespace: monitoring
spec:
endpoints:
- interval: 30s
port: web
- interval: 30s
port: reloader-web
selector:
matchLabels:
prometheus: k8s
app.kubernetes.io/component: prometheus
app.kubernetes.io/instance: k8s
app.kubernetes.io/name: prometheus
app.kubernetes.io/part-of: kube-prometheus

View File

@ -1,74 +0,0 @@
apiVersion: monitoring.coreos.com/v1
kind: ServiceMonitor
metadata:
labels:
k8s-app: apiserver
name: kube-apiserver
namespace: monitoring
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)
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|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|crd_autoregistration_controller_work_duration|APIServiceOpenAPIAggregationControllerQueue1_adds|AvailableConditionController_retries|crd_openapi_controller_unfinished_work_seconds|APIServiceRegistrationController_retries|admission_quota_controller_longest_running_processor_microseconds|crdEstablishing_longest_running_processor_microseconds|crdEstablishing_unfinished_work_seconds|crd_openapi_controller_adds|crd_autoregistration_controller_retries|crd_finalizer_queue_latency|AvailableConditionController_work_duration|non_structural_schema_condition_controller_depth|crd_autoregistration_controller_unfinished_work_seconds|AvailableConditionController_adds|DiscoveryController_longest_running_processor_microseconds|autoregister_queue_latency|crd_autoregistration_controller_adds|non_structural_schema_condition_controller_work_duration|APIServiceRegistrationController_adds|crd_finalizer_work_duration|crd_naming_condition_controller_unfinished_work_seconds|crd_openapi_controller_longest_running_processor_microseconds|DiscoveryController_adds|crd_autoregistration_controller_longest_running_processor_microseconds|autoregister_unfinished_work_seconds|crd_naming_condition_controller_queue_latency|crd_naming_condition_controller_retries|non_structural_schema_condition_controller_queue_latency|crd_naming_condition_controller_depth|AvailableConditionController_longest_running_processor_microseconds|crdEstablishing_depth|crd_finalizer_longest_running_processor_microseconds|crd_naming_condition_controller_adds|APIServiceOpenAPIAggregationControllerQueue1_longest_running_processor_microseconds|DiscoveryController_queue_latency|DiscoveryController_unfinished_work_seconds|crd_openapi_controller_depth|APIServiceOpenAPIAggregationControllerQueue1_queue_latency|APIServiceOpenAPIAggregationControllerQueue1_unfinished_work_seconds|DiscoveryController_work_duration|autoregister_adds|crd_autoregistration_controller_queue_latency|crd_finalizer_retries|AvailableConditionController_unfinished_work_seconds|autoregister_longest_running_processor_microseconds|non_structural_schema_condition_controller_unfinished_work_seconds|APIServiceOpenAPIAggregationControllerQueue1_depth|AvailableConditionController_depth|DiscoveryController_retries|admission_quota_controller_depth|crdEstablishing_adds|APIServiceOpenAPIAggregationControllerQueue1_retries|crdEstablishing_queue_latency|non_structural_schema_condition_controller_longest_running_processor_microseconds|autoregister_work_duration|crd_openapi_controller_retries|APIServiceRegistrationController_work_duration|crdEstablishing_work_duration|crd_finalizer_adds|crd_finalizer_depth|crd_openapi_controller_queue_latency|APIServiceOpenAPIAggregationControllerQueue1_work_duration|APIServiceRegistrationController_queue_latency|crd_autoregistration_controller_depth|AvailableConditionController_queue_latency|admission_quota_controller_queue_latency|crd_naming_condition_controller_work_duration|crd_openapi_controller_work_duration|DiscoveryController_depth|crd_naming_condition_controller_longest_running_processor_microseconds|APIServiceRegistrationController_depth|APIServiceRegistrationController_longest_running_processor_microseconds|crd_finalizer_unfinished_work_seconds|crdEstablishing_retries|admission_quota_controller_unfinished_work_seconds|non_structural_schema_condition_controller_adds|APIServiceRegistrationController_unfinished_work_seconds|admission_quota_controller_work_duration|autoregister_depth|autoregister_retries|kubeproxy_sync_proxy_rules_latency_microseconds|rest_client_request_latency_seconds|non_structural_schema_condition_controller_retries)
sourceLabels:
- __name__
- action: drop
regex: etcd_(debugging|disk|request|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

View File

@ -1,19 +0,0 @@
apiVersion: monitoring.coreos.com/v1
kind: ServiceMonitor
metadata:
labels:
k8s-app: coredns
name: coredns
namespace: monitoring
spec:
endpoints:
- bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token
interval: 15s
port: metrics
jobLabel: k8s-app
namespaceSelector:
matchNames:
- kube-system
selector:
matchLabels:
k8s-app: kube-dns

View File

@ -1,55 +0,0 @@
apiVersion: monitoring.coreos.com/v1
kind: ServiceMonitor
metadata:
labels:
k8s-app: kube-controller-manager
name: kube-controller-manager
namespace: monitoring
spec:
endpoints:
- 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)
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|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|crd_autoregistration_controller_work_duration|APIServiceOpenAPIAggregationControllerQueue1_adds|AvailableConditionController_retries|crd_openapi_controller_unfinished_work_seconds|APIServiceRegistrationController_retries|admission_quota_controller_longest_running_processor_microseconds|crdEstablishing_longest_running_processor_microseconds|crdEstablishing_unfinished_work_seconds|crd_openapi_controller_adds|crd_autoregistration_controller_retries|crd_finalizer_queue_latency|AvailableConditionController_work_duration|non_structural_schema_condition_controller_depth|crd_autoregistration_controller_unfinished_work_seconds|AvailableConditionController_adds|DiscoveryController_longest_running_processor_microseconds|autoregister_queue_latency|crd_autoregistration_controller_adds|non_structural_schema_condition_controller_work_duration|APIServiceRegistrationController_adds|crd_finalizer_work_duration|crd_naming_condition_controller_unfinished_work_seconds|crd_openapi_controller_longest_running_processor_microseconds|DiscoveryController_adds|crd_autoregistration_controller_longest_running_processor_microseconds|autoregister_unfinished_work_seconds|crd_naming_condition_controller_queue_latency|crd_naming_condition_controller_retries|non_structural_schema_condition_controller_queue_latency|crd_naming_condition_controller_depth|AvailableConditionController_longest_running_processor_microseconds|crdEstablishing_depth|crd_finalizer_longest_running_processor_microseconds|crd_naming_condition_controller_adds|APIServiceOpenAPIAggregationControllerQueue1_longest_running_processor_microseconds|DiscoveryController_queue_latency|DiscoveryController_unfinished_work_seconds|crd_openapi_controller_depth|APIServiceOpenAPIAggregationControllerQueue1_queue_latency|APIServiceOpenAPIAggregationControllerQueue1_unfinished_work_seconds|DiscoveryController_work_duration|autoregister_adds|crd_autoregistration_controller_queue_latency|crd_finalizer_retries|AvailableConditionController_unfinished_work_seconds|autoregister_longest_running_processor_microseconds|non_structural_schema_condition_controller_unfinished_work_seconds|APIServiceOpenAPIAggregationControllerQueue1_depth|AvailableConditionController_depth|DiscoveryController_retries|admission_quota_controller_depth|crdEstablishing_adds|APIServiceOpenAPIAggregationControllerQueue1_retries|crdEstablishing_queue_latency|non_structural_schema_condition_controller_longest_running_processor_microseconds|autoregister_work_duration|crd_openapi_controller_retries|APIServiceRegistrationController_work_duration|crdEstablishing_work_duration|crd_finalizer_adds|crd_finalizer_depth|crd_openapi_controller_queue_latency|APIServiceOpenAPIAggregationControllerQueue1_work_duration|APIServiceRegistrationController_queue_latency|crd_autoregistration_controller_depth|AvailableConditionController_queue_latency|admission_quota_controller_queue_latency|crd_naming_condition_controller_work_duration|crd_openapi_controller_work_duration|DiscoveryController_depth|crd_naming_condition_controller_longest_running_processor_microseconds|APIServiceRegistrationController_depth|APIServiceRegistrationController_longest_running_processor_microseconds|crd_finalizer_unfinished_work_seconds|crdEstablishing_retries|admission_quota_controller_unfinished_work_seconds|non_structural_schema_condition_controller_adds|APIServiceRegistrationController_unfinished_work_seconds|admission_quota_controller_work_duration|autoregister_depth|autoregister_retries|kubeproxy_sync_proxy_rules_latency_microseconds|rest_client_request_latency_seconds|non_structural_schema_condition_controller_retries)
sourceLabels:
- __name__
- action: drop
regex: etcd_(debugging|disk|request|server).*
sourceLabels:
- __name__
port: http-metrics
jobLabel: k8s-app
namespaceSelector:
matchNames:
- kube-system
selector:
matchLabels:
k8s-app: kube-controller-manager

View File

@ -1,18 +0,0 @@
apiVersion: monitoring.coreos.com/v1
kind: ServiceMonitor
metadata:
labels:
k8s-app: kube-scheduler
name: kube-scheduler
namespace: monitoring
spec:
endpoints:
- interval: 30s
port: http-metrics
jobLabel: k8s-app
namespaceSelector:
matchNames:
- kube-system
selector:
matchLabels:
k8s-app: kube-scheduler

View File

@ -1,77 +0,0 @@
apiVersion: monitoring.coreos.com/v1
kind: ServiceMonitor
metadata:
labels:
k8s-app: kubelet
name: kubelet
namespace: monitoring
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)
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|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|crd_autoregistration_controller_work_duration|APIServiceOpenAPIAggregationControllerQueue1_adds|AvailableConditionController_retries|crd_openapi_controller_unfinished_work_seconds|APIServiceRegistrationController_retries|admission_quota_controller_longest_running_processor_microseconds|crdEstablishing_longest_running_processor_microseconds|crdEstablishing_unfinished_work_seconds|crd_openapi_controller_adds|crd_autoregistration_controller_retries|crd_finalizer_queue_latency|AvailableConditionController_work_duration|non_structural_schema_condition_controller_depth|crd_autoregistration_controller_unfinished_work_seconds|AvailableConditionController_adds|DiscoveryController_longest_running_processor_microseconds|autoregister_queue_latency|crd_autoregistration_controller_adds|non_structural_schema_condition_controller_work_duration|APIServiceRegistrationController_adds|crd_finalizer_work_duration|crd_naming_condition_controller_unfinished_work_seconds|crd_openapi_controller_longest_running_processor_microseconds|DiscoveryController_adds|crd_autoregistration_controller_longest_running_processor_microseconds|autoregister_unfinished_work_seconds|crd_naming_condition_controller_queue_latency|crd_naming_condition_controller_retries|non_structural_schema_condition_controller_queue_latency|crd_naming_condition_controller_depth|AvailableConditionController_longest_running_processor_microseconds|crdEstablishing_depth|crd_finalizer_longest_running_processor_microseconds|crd_naming_condition_controller_adds|APIServiceOpenAPIAggregationControllerQueue1_longest_running_processor_microseconds|DiscoveryController_queue_latency|DiscoveryController_unfinished_work_seconds|crd_openapi_controller_depth|APIServiceOpenAPIAggregationControllerQueue1_queue_latency|APIServiceOpenAPIAggregationControllerQueue1_unfinished_work_seconds|DiscoveryController_work_duration|autoregister_adds|crd_autoregistration_controller_queue_latency|crd_finalizer_retries|AvailableConditionController_unfinished_work_seconds|autoregister_longest_running_processor_microseconds|non_structural_schema_condition_controller_unfinished_work_seconds|APIServiceOpenAPIAggregationControllerQueue1_depth|AvailableConditionController_depth|DiscoveryController_retries|admission_quota_controller_depth|crdEstablishing_adds|APIServiceOpenAPIAggregationControllerQueue1_retries|crdEstablishing_queue_latency|non_structural_schema_condition_controller_longest_running_processor_microseconds|autoregister_work_duration|crd_openapi_controller_retries|APIServiceRegistrationController_work_duration|crdEstablishing_work_duration|crd_finalizer_adds|crd_finalizer_depth|crd_openapi_controller_queue_latency|APIServiceOpenAPIAggregationControllerQueue1_work_duration|APIServiceRegistrationController_queue_latency|crd_autoregistration_controller_depth|AvailableConditionController_queue_latency|admission_quota_controller_queue_latency|crd_naming_condition_controller_work_duration|crd_openapi_controller_work_duration|DiscoveryController_depth|crd_naming_condition_controller_longest_running_processor_microseconds|APIServiceRegistrationController_depth|APIServiceRegistrationController_longest_running_processor_microseconds|crd_finalizer_unfinished_work_seconds|crdEstablishing_retries|admission_quota_controller_unfinished_work_seconds|non_structural_schema_condition_controller_adds|APIServiceRegistrationController_unfinished_work_seconds|admission_quota_controller_work_duration|autoregister_depth|autoregister_retries|kubeproxy_sync_proxy_rules_latency_microseconds|rest_client_request_latency_seconds|non_structural_schema_condition_controller_retries)
sourceLabels:
- __name__
port: https-metrics
relabelings:
- sourceLabels:
- __metrics_path__
targetLabel: metrics_path
scheme: https
tlsConfig:
insecureSkipVerify: true
- bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token
honorLabels: true
interval: 30s
metricRelabelings:
- action: drop
regex: container_(network_tcp_usage_total|network_udp_usage_total|tasks_state|cpu_load_average_10s)
sourceLabels:
- __name__
path: /metrics/cadvisor
port: https-metrics
relabelings:
- sourceLabels:
- __metrics_path__
targetLabel: metrics_path
scheme: https
tlsConfig:
insecureSkipVerify: true
jobLabel: k8s-app
namespaceSelector:
matchNames:
- kube-system
selector:
matchLabels:
k8s-app: kubelet

View File

@ -0,0 +1,83 @@
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
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 (job, namespace, service) / count(up) BY (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

View File

@ -2,15 +2,19 @@ apiVersion: apiextensions.k8s.io/v1
kind: CustomResourceDefinition
metadata:
annotations:
controller-gen.kubebuilder.io/version: v0.2.4
controller-gen.kubebuilder.io/version: v0.9.2
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:
@ -30,9 +34,28 @@ spec:
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:
@ -40,7 +63,7 @@ spec:
description: Boolean describing whether all namespaces are selected in contrast to a list restricting them.
type: boolean
matchNames:
description: List of namespace names.
description: List of namespace names to select from.
items:
type: string
type: array
@ -50,6 +73,90 @@ spec:
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: The secret's key that contains the credentials of the request
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: Set the authentication type. Defaults to Bearer, Basic will cause an error
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
@ -57,7 +164,8 @@ spec:
description: HonorTimestamps controls whether Prometheus respects the timestamps present in scraped data.
type: boolean
interval:
description: Interval at which metrics should be scraped
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.
@ -65,7 +173,27 @@ spec:
description: 'RelabelConfig allows dynamic rewriting of the label set, being applied to samples before ingestion. It defines `<metric_relabel_configs>`-section of Prometheus configuration. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#metric_relabel_configs'
properties:
action:
description: Action to perform based on regex matching. Default is 'replace'
default: replace
description: Action to perform based on regex matching. Default is 'replace'. uppercase and lowercase actions require Prometheus >= 2.36.
enum:
- replace
- Replace
- keep
- Keep
- drop
- Drop
- hashmod
- HashMod
- labelmap
- LabelMap
- labeldrop
- LabelDrop
- labelkeep
- LabelKeep
- lowercase
- Lowercase
- uppercase
- Uppercase
type: string
modulus:
description: Modulus to take of the hash of the source label values.
@ -83,6 +211,8 @@ spec:
sourceLabels:
description: The source labels select values from existing labels. Their content is concatenated using the configured separator and matched against the configured regular expression for the replace, keep, and drop actions.
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:
@ -90,6 +220,80 @@ spec:
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:
@ -98,7 +302,7 @@ spec:
description: Optional HTTP URL parameters
type: object
path:
description: HTTP path to scrape for metrics.
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.
@ -107,12 +311,32 @@ spec:
description: ProxyURL eg http://proxyserver:2195 Directs scrapes to proxy through this endpoint.
type: string
relabelings:
description: 'RelabelConfigs to apply to samples before ingestion. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#relabel_config'
description: 'RelabelConfigs to apply to samples before 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, being applied to samples before ingestion. It defines `<metric_relabel_configs>`-section of Prometheus configuration. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#metric_relabel_configs'
properties:
action:
description: Action to perform based on regex matching. Default is 'replace'
default: replace
description: Action to perform based on regex matching. Default is 'replace'. uppercase and lowercase actions require Prometheus >= 2.36.
enum:
- replace
- Replace
- keep
- Keep
- drop
- Drop
- hashmod
- HashMod
- labelmap
- LabelMap
- labeldrop
- LabelDrop
- labelkeep
- LabelKeep
- lowercase
- Lowercase
- uppercase
- Uppercase
type: string
modulus:
description: Modulus to take of the hash of the source label values.
@ -130,6 +354,8 @@ spec:
sourceLabels:
description: The source labels select values from existing labels. Their content is concatenated using the configured separator and matched against the configured regular expression for the replace, keep, and drop actions.
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:
@ -141,7 +367,8 @@ spec:
description: HTTP scheme to use for scraping.
type: string
scrapeTimeout:
description: Timeout after which the scrape is ended
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:
@ -149,6 +376,104 @@ spec:
- 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:
@ -190,6 +515,11 @@ spec:
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
@ -199,9 +529,3 @@ spec:
type: object
served: true
storage: true
status:
acceptedNames:
kind: ""
plural: ""
conditions: []
storedVersions: []

View File

@ -0,0 +1,566 @@
apiVersion: apiextensions.k8s.io/v1
kind: CustomResourceDefinition
metadata:
annotations:
controller-gen.kubebuilder.io/version: v0.9.2
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: The secret's key that contains the credentials of the request
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: Set the authentication type. Defaults to Bearer, Basic will cause an error
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, being applied to samples before ingestion. It defines `<metric_relabel_configs>`-section of Prometheus configuration. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#metric_relabel_configs'
properties:
action:
default: replace
description: Action to perform based on regex matching. Default is 'replace'. uppercase and lowercase actions require Prometheus >= 2.36.
enum:
- replace
- Replace
- keep
- Keep
- drop
- Drop
- hashmod
- HashMod
- labelmap
- LabelMap
- labeldrop
- LabelDrop
- labelkeep
- LabelKeep
- lowercase
- Lowercase
- uppercase
- Uppercase
type: string
modulus:
description: Modulus to take of the hash of the source label values.
format: int64
type: integer
regex:
description: Regular expression against which the extracted value is matched. Default is '(.*)'
type: string
replacement:
description: Replacement value against which a regex replace is performed if the regular expression matches. Regex capture groups are available. Default is '$1'
type: string
separator:
description: Separator placed between concatenated source label values. default is ';'.
type: string
sourceLabels:
description: The source labels select values from existing labels. Their content is concatenated using the configured separator and matched against the configured regular expression for the replace, keep, and drop actions.
items:
description: LabelName is a valid Prometheus label name which may only contain ASCII letters, numbers, as well as underscores.
pattern: ^[a-zA-Z_][a-zA-Z0-9_]*$
type: string
type: array
targetLabel:
description: Label to which the resulting value is written in a replace action. It is mandatory for replace actions. 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. Defaults to `http`.
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 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
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, being applied to samples before ingestion. It defines `<metric_relabel_configs>`-section of Prometheus configuration. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#metric_relabel_configs'
properties:
action:
default: replace
description: Action to perform based on regex matching. Default is 'replace'. uppercase and lowercase actions require Prometheus >= 2.36.
enum:
- replace
- Replace
- keep
- Keep
- drop
- Drop
- hashmod
- HashMod
- labelmap
- LabelMap
- labeldrop
- LabelDrop
- labelkeep
- LabelKeep
- lowercase
- Lowercase
- uppercase
- Uppercase
type: string
modulus:
description: Modulus to take of the hash of the source label values.
format: int64
type: integer
regex:
description: Regular expression against which the extracted value is matched. Default is '(.*)'
type: string
replacement:
description: Replacement value against which a regex replace is performed if the regular expression matches. Regex capture groups are available. Default is '$1'
type: string
separator:
description: Separator placed between concatenated source label values. default is ';'.
type: string
sourceLabels:
description: The source labels select values from existing labels. Their content is concatenated using the configured separator and matched against the configured regular expression for the replace, keep, and drop actions.
items:
description: LabelName is a valid Prometheus label name which may only contain ASCII letters, numbers, as well as underscores.
pattern: ^[a-zA-Z_][a-zA-Z0-9_]*$
type: string
type: array
targetLabel:
description: Label to which the resulting value is written in a replace action. It is mandatory for replace actions. 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, being applied to samples before ingestion. It defines `<metric_relabel_configs>`-section of Prometheus configuration. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#metric_relabel_configs'
properties:
action:
default: replace
description: Action to perform based on regex matching. Default is 'replace'. uppercase and lowercase actions require Prometheus >= 2.36.
enum:
- replace
- Replace
- keep
- Keep
- drop
- Drop
- hashmod
- HashMod
- labelmap
- LabelMap
- labeldrop
- LabelDrop
- labelkeep
- LabelKeep
- lowercase
- Lowercase
- uppercase
- Uppercase
type: string
modulus:
description: Modulus to take of the hash of the source label values.
format: int64
type: integer
regex:
description: Regular expression against which the extracted value is matched. Default is '(.*)'
type: string
replacement:
description: Replacement value against which a regex replace is performed if the regular expression matches. Regex capture groups are available. Default is '$1'
type: string
separator:
description: Separator placed between concatenated source label values. default is ';'.
type: string
sourceLabels:
description: The source labels select values from existing labels. Their content is concatenated using the configured separator and matched against the configured regular expression for the replace, keep, and drop actions.
items:
description: LabelName is a valid Prometheus label name which may only contain ASCII letters, numbers, as well as underscores.
pattern: ^[a-zA-Z_][a-zA-Z0-9_]*$
type: string
type: array
targetLabel:
description: Label to which the resulting value is written in a replace action. It is mandatory for replace actions. 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

View File

@ -2,22 +2,26 @@ apiVersion: apiextensions.k8s.io/v1
kind: CustomResourceDefinition
metadata:
annotations:
controller-gen.kubebuilder.io/version: v0.2.4
controller-gen.kubebuilder.io/version: v0.9.2
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 alerting rules for a Prometheus instance
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'
@ -33,36 +37,50 @@ spec:
groups:
description: Content of Prometheus rule file
items:
description: 'RuleGroup is a list of sequentially evaluated recording and alerting rules. Note: PartialResponseStrategy is only used by ThanosRuler and will be ignored by Prometheus instances. Valid values for this field are ''warn'' or ''abort''. More info: https://github.com/thanos-io/thanos/blob/master/docs/components/rule.md#partial-response'
description: RuleGroup is a list of sequentially evaluated recording and alerting rules.
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
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.
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
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
@ -73,15 +91,12 @@ spec:
- rules
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
status:
acceptedNames:
kind: ""
plural: ""
conditions: []
storedVersions: []

View File

@ -2,15 +2,19 @@ apiVersion: apiextensions.k8s.io/v1
kind: CustomResourceDefinition
metadata:
annotations:
controller-gen.kubebuilder.io/version: v0.2.4
controller-gen.kubebuilder.io/version: v0.9.2
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:
@ -30,11 +34,41 @@ spec:
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: The secret's key that contains the credentials of the request
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: Set the authentication type. Defaults to Bearer, Basic will cause an error
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:
@ -53,6 +87,7 @@ spec:
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:
@ -68,6 +103,7 @@ spec:
required:
- key
type: object
x-kubernetes-map-type: atomic
type: object
bearerTokenFile:
description: File to read bearer token for scraping targets.
@ -87,6 +123,16 @@ spec:
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
@ -94,7 +140,8 @@ spec:
description: HonorTimestamps controls whether Prometheus respects the timestamps present in scraped data.
type: boolean
interval:
description: Interval at which metrics should be scraped
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.
@ -102,7 +149,27 @@ spec:
description: 'RelabelConfig allows dynamic rewriting of the label set, being applied to samples before ingestion. It defines `<metric_relabel_configs>`-section of Prometheus configuration. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#metric_relabel_configs'
properties:
action:
description: Action to perform based on regex matching. Default is 'replace'
default: replace
description: Action to perform based on regex matching. Default is 'replace'. uppercase and lowercase actions require Prometheus >= 2.36.
enum:
- replace
- Replace
- keep
- Keep
- drop
- Drop
- hashmod
- HashMod
- labelmap
- LabelMap
- labeldrop
- LabelDrop
- labelkeep
- LabelKeep
- lowercase
- Lowercase
- uppercase
- Uppercase
type: string
modulus:
description: Modulus to take of the hash of the source label values.
@ -120,6 +187,8 @@ spec:
sourceLabels:
description: The source labels select values from existing labels. Their content is concatenated using the configured separator and matched against the configured regular expression for the replace, keep, and drop actions.
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:
@ -127,6 +196,80 @@ spec:
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:
@ -135,7 +278,7 @@ spec:
description: Optional HTTP URL parameters
type: object
path:
description: HTTP path to scrape for metrics.
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.
@ -144,12 +287,32 @@ spec:
description: ProxyURL eg http://proxyserver:2195 Directs scrapes to proxy through this endpoint.
type: string
relabelings:
description: 'RelabelConfigs to apply to samples before scraping. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#relabel_config'
description: 'RelabelConfigs to apply to samples before scraping. 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, being applied to samples before ingestion. It defines `<metric_relabel_configs>`-section of Prometheus configuration. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#metric_relabel_configs'
properties:
action:
description: Action to perform based on regex matching. Default is 'replace'
default: replace
description: Action to perform based on regex matching. Default is 'replace'. uppercase and lowercase actions require Prometheus >= 2.36.
enum:
- replace
- Replace
- keep
- Keep
- drop
- Drop
- hashmod
- HashMod
- labelmap
- LabelMap
- labeldrop
- LabelDrop
- labelkeep
- LabelKeep
- lowercase
- Lowercase
- uppercase
- Uppercase
type: string
modulus:
description: Modulus to take of the hash of the source label values.
@ -167,6 +330,8 @@ spec:
sourceLabels:
description: The source labels select values from existing labels. Their content is concatenated using the configured separator and matched against the configured regular expression for the replace, keep, and drop actions.
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:
@ -178,19 +343,20 @@ spec:
description: HTTP scheme to use for scraping.
type: string
scrapeTimeout:
description: Timeout after which the scrape is ended
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 pod port this endpoint refers to. Mutually exclusive with port.
description: Name or number of the target port of the Pod behind the Service, the port must be specified with container port property. Mutually exclusive with port.
x-kubernetes-int-or-string: true
tlsConfig:
description: TLS configuration to use when scraping the endpoint
properties:
ca:
description: Stuct containing the CA cert to use for the targets.
description: Certificate authority used when verifying server certificates.
properties:
configMap:
description: ConfigMap containing data to use for the targets.
@ -207,6 +373,7 @@ spec:
required:
- key
type: object
x-kubernetes-map-type: atomic
secret:
description: Secret containing data to use for the targets.
properties:
@ -222,12 +389,13 @@ spec:
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: Struct containing the client cert file for the targets.
description: Client certificate to present when doing client-authentication.
properties:
configMap:
description: ConfigMap containing data to use for the targets.
@ -244,6 +412,7 @@ spec:
required:
- key
type: object
x-kubernetes-map-type: atomic
secret:
description: Secret containing data to use for the targets.
properties:
@ -259,6 +428,7 @@ spec:
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.
@ -284,6 +454,7 @@ spec:
required:
- key
type: object
x-kubernetes-map-type: atomic
serverName:
description: Used to verify the hostname for the targets.
type: string
@ -291,22 +462,34 @@ spec:
type: object
type: array
jobLabel:
description: The label to use to retrieve the job name from.
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 Endpoints objects are discovered from.
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.
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 target.
description: PodTargetLabels transfers labels on the Kubernetes `Pod` onto the created metrics.
items:
type: string
type: array
@ -344,11 +527,16 @@ spec:
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 on the Kubernetes Service onto the target.
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
@ -358,9 +546,3 @@ spec:
type: object
served: true
storage: true
status:
acceptedNames:
kind: ""
plural: ""
conditions: []
storedVersions: []

View File

@ -4,7 +4,8 @@ metadata:
labels:
app.kubernetes.io/component: controller
app.kubernetes.io/name: prometheus-operator
app.kubernetes.io/version: v0.40.0
app.kubernetes.io/part-of: kube-prometheus
app.kubernetes.io/version: 0.61.1
name: prometheus-operator
rules:
- apiGroups:
@ -12,12 +13,15 @@ rules:
resources:
- alertmanagers
- alertmanagers/finalizers
- alertmanagerconfigs
- prometheuses
- prometheuses/finalizers
- prometheuses/status
- thanosrulers
- thanosrulers/finalizers
- servicemonitors
- podmonitors
- probes
- prometheusrules
verbs:
- '*'
@ -67,6 +71,14 @@ rules:
- get
- list
- watch
- apiGroups:
- networking.k8s.io
resources:
- ingresses
verbs:
- get
- list
- watch
- apiGroups:
- authentication.k8s.io
resources:

View File

@ -4,7 +4,8 @@ metadata:
labels:
app.kubernetes.io/component: controller
app.kubernetes.io/name: prometheus-operator
app.kubernetes.io/version: v0.40.0
app.kubernetes.io/part-of: kube-prometheus
app.kubernetes.io/version: 0.61.1
name: prometheus-operator
roleRef:
apiGroup: rbac.authorization.k8s.io

View File

@ -4,7 +4,8 @@ metadata:
labels:
app.kubernetes.io/component: controller
app.kubernetes.io/name: prometheus-operator
app.kubernetes.io/version: v0.40.0
app.kubernetes.io/part-of: kube-prometheus
app.kubernetes.io/version: 0.61.1
name: prometheus-operator
namespace: monitoring
spec:
@ -13,20 +14,23 @@ spec:
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/version: v0.40.0
app.kubernetes.io/part-of: kube-prometheus
app.kubernetes.io/version: 0.61.1
spec:
automountServiceAccountToken: true
containers:
- args:
- --kubelet-service=kube-system/kubelet
- --logtostderr=true
- --config-reloader-image=carlosedp/configmap-reload:latest
- --prometheus-config-reloader=carlosedp/prometheus-config-reloader:v0.40.0
image: carlosedp/prometheus-operator:v0.40.0
- --prometheus-config-reloader=quay.io/prometheus-operator/prometheus-config-reloader:v0.61.1
image: quay.io/prometheus-operator/prometheus-operator:v0.61.1
name: prometheus-operator
ports:
- containerPort: 8080
@ -40,20 +44,38 @@ spec:
memory: 100Mi
securityContext:
allowPrivilegeEscalation: false
capabilities:
drop:
- ALL
readOnlyRootFilesystem: true
- args:
- --logtostderr
- --secure-listen-address=:8443
- --tls-cipher-suites=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256,TLS_ECDHE_ECDSA_WITH_AES_128_GCM_SHA256,TLS_RSA_WITH_AES_128_CBC_SHA256,TLS_ECDHE_ECDSA_WITH_AES_128_CBC_SHA256,TLS_ECDHE_RSA_WITH_AES_128_CBC_SHA256
- --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: carlosedp/kube-rbac-proxy:v0.5.0
image: quay.io/brancz/kube-rbac-proxy:v0.14.0
name: kube-rbac-proxy
ports:
- containerPort: 8443
name: https
resources:
limits:
cpu: 20m
memory: 40Mi
requests:
cpu: 10m
memory: 20Mi
securityContext:
runAsUser: 65534
allowPrivilegeEscalation: false
capabilities:
drop:
- ALL
readOnlyRootFilesystem: true
runAsGroup: 65532
runAsNonRoot: true
runAsUser: 65532
nodeSelector:
beta.kubernetes.io/os: linux
kubernetes.io/os: linux
securityContext:
runAsNonRoot: true
runAsUser: 65534

View File

@ -0,0 +1,29 @@
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: 0.61.1
name: prometheus-operator
namespace: monitoring
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

View File

@ -0,0 +1,100 @@
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: 0.61.1
prometheus: k8s
role: alert-rules
name: prometheus-operator-rules
namespace: monitoring
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 (controller,namespace) (rate(prometheus_operator_list_operations_failed_total{job="prometheus-operator",namespace="monitoring"}[10m])) / sum by (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 (controller,namespace) (rate(prometheus_operator_watch_operations_failed_total{job="prometheus-operator",namespace="monitoring"}[5m])) / sum by (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 (controller,namespace) (rate(prometheus_operator_reconcile_errors_total{job="prometheus-operator",namespace="monitoring"}[5m]))) / (sum by (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 (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

View File

@ -4,7 +4,8 @@ metadata:
labels:
app.kubernetes.io/component: controller
app.kubernetes.io/name: prometheus-operator
app.kubernetes.io/version: v0.40.0
app.kubernetes.io/part-of: kube-prometheus
app.kubernetes.io/version: 0.61.1
name: prometheus-operator
namespace: monitoring
spec:
@ -16,3 +17,4 @@ spec:
selector:
app.kubernetes.io/component: controller
app.kubernetes.io/name: prometheus-operator
app.kubernetes.io/part-of: kube-prometheus

View File

@ -1,9 +1,11 @@
apiVersion: v1
automountServiceAccountToken: false
kind: ServiceAccount
metadata:
labels:
app.kubernetes.io/component: controller
app.kubernetes.io/name: prometheus-operator
app.kubernetes.io/version: v0.40.0
app.kubernetes.io/part-of: kube-prometheus
app.kubernetes.io/version: 0.61.1
name: prometheus-operator
namespace: monitoring

View File

@ -1,5 +1,5 @@
local utils = import '../utils.libsonnet';
local k = import 'ksonnet/ksonnet.beta.4/k.libsonnet';
local k = import 'ksonnet-lib/ksonnet.beta.4/k.libsonnet';
{
_config+:: {

View File

@ -1,5 +1,5 @@
local utils = import '../utils.libsonnet';
local k = import 'ksonnet/ksonnet.beta.4/k.libsonnet';
local k = import 'ksonnet-lib/ksonnet.beta.4/k.libsonnet';
{
_config+:: {

View File

@ -1,6 +1,6 @@
local utils = import '../utils.libsonnet';
local vars = import '../vars.jsonnet';
local k = import 'ksonnet/ksonnet.beta.4/k.libsonnet';
local k = import 'ksonnet-lib/ksonnet.beta.4/k.libsonnet';
local service = k.core.v1.service;
local servicePort = k.core.v1.service.mixin.spec.portsType;

View File

@ -1,5 +1,5 @@
local utils = import '../utils.libsonnet';
local k = import 'ksonnet/ksonnet.beta.4/k.libsonnet';
local k = import 'ksonnet-lib/ksonnet.beta.4/k.libsonnet';
{
_config+:: {

View File

@ -1,5 +1,5 @@
local utils = import '../utils.libsonnet';
local k = import 'ksonnet/ksonnet.beta.4/k.libsonnet';
local k = import 'ksonnet-lib/ksonnet.beta.4/k.libsonnet';
{
_config+:: {
@ -18,9 +18,9 @@ local k = import 'ksonnet/ksonnet.beta.4/k.libsonnet';
local servicePort = k.core.v1.service.mixin.spec.portsType;
local nginxPort = servicePort.newNamed('prometheus', 10254, 10254);
service.new('ingress-nginx-metrics', {'app.kubernetes.io/name': 'ingress-nginx'}, nginxPort) +
service.new('ingress-nginx-metrics', { 'app.kubernetes.io/name': 'ingress-nginx' }, nginxPort) +
service.mixin.metadata.withNamespace('ingress-nginx') +
service.mixin.metadata.withLabels({'app.kubernetes.io/name': 'ingress-nginx'}) +
service.mixin.metadata.withLabels({ 'app.kubernetes.io/name': 'ingress-nginx' }) +
service.mixin.spec.withClusterIp('None'),
clusterRole:

View File

@ -1,4 +1,4 @@
local k = import 'ksonnet/ksonnet.beta.4/k.libsonnet';
local k = import 'ksonnet-lib/ksonnet.beta.4/k.libsonnet';
{
_config+:: {

View File

@ -1,5 +1,5 @@
local utils = import '../utils.libsonnet';
local k = import 'ksonnet/ksonnet.beta.4/k.libsonnet';
local k = import 'ksonnet-lib/ksonnet.beta.4/k.libsonnet';
{
_config+:: {
@ -7,7 +7,7 @@ local k = import 'ksonnet/ksonnet.beta.4/k.libsonnet';
replicas: 1,
imageRepos+:: {
speedtestExporter: 'ghcr.io/miguelndecarvalho/speedtest-exporter',
speedtestExporter: 'ghcr.io/miguelndecarvalho/speedtest-exporter',
},
// Add custom dashboards

View File

@ -1,5 +1,5 @@
local utils = import '../utils.libsonnet';
local k = import 'ksonnet/ksonnet.beta.4/k.libsonnet';
local k = import 'ksonnet-lib/ksonnet.beta.4/k.libsonnet';
{
_config+:: {

View File

@ -1,5 +1,5 @@
local utils = import '../utils.libsonnet';
local k = import 'ksonnet/ksonnet.beta.4/k.libsonnet';
local k = import 'ksonnet-lib/ksonnet.beta.4/k.libsonnet';
{
_config+:: {

Some files were not shown because too many files have changed in this diff Show More