refactor: integrate CLI's code & CI into main repo (#1343)
This commit is contained in:
dkeven
@@ -0,0 +1,117 @@
|
||||
apiVersion: rbac.authorization.k8s.io/v1
|
||||
kind: ClusterRole
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: exporter
|
||||
app.kubernetes.io/name: kube-state-metrics
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 2.3.0
|
||||
name: kubesphere-kube-state-metrics
|
||||
rules:
|
||||
- apiGroups:
|
||||
- ""
|
||||
resources:
|
||||
- configmaps
|
||||
- secrets
|
||||
- nodes
|
||||
- pods
|
||||
- services
|
||||
- resourcequotas
|
||||
- replicationcontrollers
|
||||
- limitranges
|
||||
- persistentvolumeclaims
|
||||
- persistentvolumes
|
||||
- namespaces
|
||||
- endpoints
|
||||
verbs:
|
||||
- list
|
||||
- watch
|
||||
- apiGroups:
|
||||
- apps
|
||||
resources:
|
||||
- statefulsets
|
||||
- daemonsets
|
||||
- deployments
|
||||
- replicasets
|
||||
verbs:
|
||||
- list
|
||||
- watch
|
||||
- apiGroups:
|
||||
- batch
|
||||
resources:
|
||||
- cronjobs
|
||||
- jobs
|
||||
verbs:
|
||||
- list
|
||||
- watch
|
||||
- apiGroups:
|
||||
- autoscaling
|
||||
resources:
|
||||
- horizontalpodautoscalers
|
||||
verbs:
|
||||
- list
|
||||
- watch
|
||||
- apiGroups:
|
||||
- authentication.k8s.io
|
||||
resources:
|
||||
- tokenreviews
|
||||
verbs:
|
||||
- create
|
||||
- apiGroups:
|
||||
- authorization.k8s.io
|
||||
resources:
|
||||
- subjectaccessreviews
|
||||
verbs:
|
||||
- create
|
||||
- apiGroups:
|
||||
- policy
|
||||
resources:
|
||||
- poddisruptionbudgets
|
||||
verbs:
|
||||
- list
|
||||
- watch
|
||||
- apiGroups:
|
||||
- certificates.k8s.io
|
||||
resources:
|
||||
- certificatesigningrequests
|
||||
verbs:
|
||||
- list
|
||||
- watch
|
||||
- apiGroups:
|
||||
- storage.k8s.io
|
||||
resources:
|
||||
- storageclasses
|
||||
- volumeattachments
|
||||
verbs:
|
||||
- list
|
||||
- watch
|
||||
- apiGroups:
|
||||
- admissionregistration.k8s.io
|
||||
resources:
|
||||
- mutatingwebhookconfigurations
|
||||
- validatingwebhookconfigurations
|
||||
verbs:
|
||||
- list
|
||||
- watch
|
||||
- apiGroups:
|
||||
- networking.k8s.io
|
||||
resources:
|
||||
- networkpolicies
|
||||
- ingresses
|
||||
verbs:
|
||||
- list
|
||||
- watch
|
||||
- apiGroups:
|
||||
- coordination.k8s.io
|
||||
resources:
|
||||
- leases
|
||||
verbs:
|
||||
- list
|
||||
- watch
|
||||
- apiGroups:
|
||||
- iam.kubesphere.io
|
||||
resources:
|
||||
- users
|
||||
verbs:
|
||||
- list
|
||||
- watch
|
||||
@@ -0,0 +1,17 @@
|
||||
apiVersion: rbac.authorization.k8s.io/v1
|
||||
kind: ClusterRoleBinding
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: exporter
|
||||
app.kubernetes.io/name: kube-state-metrics
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 2.3.0
|
||||
name: kubesphere-kube-state-metrics
|
||||
roleRef:
|
||||
apiGroup: rbac.authorization.k8s.io
|
||||
kind: ClusterRole
|
||||
name: kubesphere-kube-state-metrics
|
||||
subjects:
|
||||
- kind: ServiceAccount
|
||||
name: kube-state-metrics
|
||||
namespace: kubesphere-monitoring-system
|
||||
@@ -0,0 +1,108 @@
|
||||
apiVersion: apps/v1
|
||||
kind: Deployment
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: exporter
|
||||
app.kubernetes.io/name: kube-state-metrics
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 2.3.0-ext.1 # todo
|
||||
name: kube-state-metrics
|
||||
namespace: kubesphere-monitoring-system
|
||||
spec:
|
||||
replicas: 1
|
||||
selector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/component: exporter
|
||||
app.kubernetes.io/name: kube-state-metrics
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
strategy: # todo ?
|
||||
rollingUpdate:
|
||||
maxSurge: 25%
|
||||
maxUnavailable: 25%
|
||||
type: RollingUpdate
|
||||
template:
|
||||
metadata:
|
||||
annotations:
|
||||
kubectl.kubernetes.io/default-container: kube-state-metrics
|
||||
labels:
|
||||
app.kubernetes.io/component: exporter
|
||||
app.kubernetes.io/name: kube-state-metrics
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 2.3.0-ext.1 # todo
|
||||
spec:
|
||||
volumes:
|
||||
- name: host-time
|
||||
hostPath:
|
||||
path: /etc/localtime
|
||||
type: ""
|
||||
containers:
|
||||
- args:
|
||||
- --host=127.0.0.1
|
||||
- --port=8081
|
||||
- --telemetry-host=127.0.0.1
|
||||
- --telemetry-port=8082
|
||||
- --metric-denylist=kube_pod_container_status_.*terminated_reason,kube_.+_version,kube_.+_created,kube_deployment_(spec_paused|spec_strategy_rollingupdate_.+),kube_endpoint_(info|address_.+),kube_job_(info|owner|spec_(parallelism|active_deadline_seconds)|status_(active|.+_time)),kube_cronjob_(info|status_.+|spec_.+),kube_namespace_(status_phase),kube_persistentvolume_(info|capacity_.+),kube_persistentvolumeclaim_(resource_.+|access_.+),kube_secret_(type),kube_service_(spec_.+|status_.+),kube_ingress_(info|path|tls),kube_replicaset_(status_.+|spec_.+|owner),kube_poddisruptionbudget_status_.+,kube_replicationcontroller_.+,kube_node_info,kube_(hpa|replicaset|replicationcontroller)_.+_generation
|
||||
- --metric-labels-allowlist=namespaces=[kubesphere.io/workspace,bytetrade.io/ns-owner]
|
||||
image: beclab/kube-state-metrics:v2.3.0-ext.1
|
||||
imagePullPolicy: IfNotPresent
|
||||
name: kube-state-metrics
|
||||
resources:
|
||||
limits:
|
||||
cpu: "1"
|
||||
memory: 8Gi
|
||||
requests:
|
||||
cpu: 100m
|
||||
memory: 150Mi
|
||||
securityContext:
|
||||
runAsUser: 65534
|
||||
volumeMounts:
|
||||
- mountPath: /etc/localtime
|
||||
name: host-time
|
||||
readOnly: 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
|
||||
- --upstream=http://127.0.0.1:8081/
|
||||
image: bitnami/kube-rbac-proxy:0.19.0
|
||||
imagePullPolicy: IfNotPresent
|
||||
name: kube-rbac-proxy-main
|
||||
ports:
|
||||
- containerPort: 8443
|
||||
name: https-main
|
||||
resources:
|
||||
limits:
|
||||
cpu: "1"
|
||||
memory: 100Mi
|
||||
requests:
|
||||
cpu: 10m
|
||||
memory: 20Mi
|
||||
securityContext:
|
||||
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
|
||||
- --upstream=http://127.0.0.1:8082/
|
||||
image: bitnami/kube-rbac-proxy:0.19.0
|
||||
imagePullPolicy: IfNotPresent
|
||||
name: kube-rbac-proxy-self
|
||||
ports:
|
||||
- containerPort: 9443
|
||||
name: https-self
|
||||
resources:
|
||||
limits:
|
||||
cpu: "1"
|
||||
memory: 100Mi
|
||||
requests:
|
||||
cpu: 10m
|
||||
memory: 20Mi
|
||||
securityContext:
|
||||
runAsGroup: 65532
|
||||
runAsNonRoot: true
|
||||
runAsUser: 65532
|
||||
nodeSelector:
|
||||
kubernetes.io/os: linux
|
||||
serviceAccountName: kube-state-metrics
|
||||
@@ -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: 2.3.0
|
||||
prometheus: k8s
|
||||
role: alert-rules
|
||||
name: kube-state-metrics-rules
|
||||
namespace: kubesphere-monitoring-system
|
||||
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
|
||||
@@ -0,0 +1,23 @@
|
||||
apiVersion: v1
|
||||
kind: Service
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: exporter
|
||||
app.kubernetes.io/name: kube-state-metrics
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 2.3.0
|
||||
name: kube-state-metrics
|
||||
namespace: kubesphere-monitoring-system
|
||||
spec:
|
||||
clusterIP: None
|
||||
ports:
|
||||
- name: https-main
|
||||
port: 8443
|
||||
targetPort: https-main
|
||||
- name: https-self
|
||||
port: 9443
|
||||
targetPort: https-self
|
||||
selector:
|
||||
app.kubernetes.io/component: exporter
|
||||
app.kubernetes.io/name: kube-state-metrics
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
@@ -0,0 +1,10 @@
|
||||
apiVersion: v1
|
||||
kind: ServiceAccount
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: exporter
|
||||
app.kubernetes.io/name: kube-state-metrics
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 2.3.0
|
||||
name: kube-state-metrics
|
||||
namespace: kubesphere-monitoring-system
|
||||
@@ -0,0 +1,49 @@
|
||||
apiVersion: monitoring.coreos.com/v1
|
||||
kind: ServiceMonitor
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: exporter
|
||||
app.kubernetes.io/name: kube-state-metrics
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/vendor: kubesphere
|
||||
app.kubernetes.io/version: 2.3.0
|
||||
name: kube-state-metrics
|
||||
namespace: kubesphere-monitoring-system
|
||||
spec:
|
||||
endpoints:
|
||||
- bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token
|
||||
honorLabels: true
|
||||
interval: 1m
|
||||
metricRelabelings:
|
||||
- action: replace
|
||||
regex: (.*)
|
||||
replacement: $1
|
||||
sourceLabels:
|
||||
- label_kubesphere_io_workspace
|
||||
targetLabel: workspace
|
||||
- action: replace
|
||||
regex: (.*)
|
||||
replacement: $1
|
||||
sourceLabels:
|
||||
- label_bytetrade_io_ns_owner
|
||||
targetLabel: user
|
||||
port: https-main
|
||||
relabelings:
|
||||
- action: labeldrop
|
||||
regex: (pod|service|endpoint|namespace)
|
||||
scheme: https
|
||||
scrapeTimeout: 30s
|
||||
tlsConfig:
|
||||
insecureSkipVerify: true
|
||||
- bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token
|
||||
interval: 1m
|
||||
port: https-self
|
||||
scheme: https
|
||||
tlsConfig:
|
||||
insecureSkipVerify: true
|
||||
jobLabel: app.kubernetes.io/name
|
||||
selector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/component: exporter
|
||||
app.kubernetes.io/name: kube-state-metrics
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,15 @@
|
||||
apiVersion: v1
|
||||
kind: Service
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/name: kube-controller-manager
|
||||
name: kube-controller-manager-svc
|
||||
namespace: kube-system
|
||||
spec:
|
||||
clusterIP: None
|
||||
ports:
|
||||
- name: https-metrics
|
||||
port: 10257
|
||||
targetPort: 10257
|
||||
selector:
|
||||
component: kube-controller-manager
|
||||
@@ -0,0 +1,15 @@
|
||||
apiVersion: v1
|
||||
kind: Service
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/name: kube-scheduler
|
||||
name: kube-scheduler-svc
|
||||
namespace: kube-system
|
||||
spec:
|
||||
clusterIP: None
|
||||
ports:
|
||||
- name: https-metrics
|
||||
port: 10259
|
||||
targetPort: 10259
|
||||
selector:
|
||||
component: kube-scheduler
|
||||
@@ -0,0 +1,76 @@
|
||||
apiVersion: monitoring.coreos.com/v1
|
||||
kind: ServiceMonitor
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/name: apiserver
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/vendor: kubesphere
|
||||
name: kube-apiserver
|
||||
namespace: kubesphere-monitoring-system
|
||||
spec:
|
||||
endpoints:
|
||||
- bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token
|
||||
interval: 1m
|
||||
metricRelabelings:
|
||||
- action: drop
|
||||
regex: kubelet_(pod_worker_latency_microseconds|pod_start_latency_microseconds|cgroup_manager_latency_microseconds|pod_worker_start_latency_microseconds|pleg_relist_latency_microseconds|pleg_relist_interval_microseconds|runtime_operations|runtime_operations_latency_microseconds|runtime_operations_errors|eviction_stats_age_microseconds|device_plugin_registration_count|device_plugin_alloc_latency_microseconds|network_plugin_operations_latency_microseconds)
|
||||
sourceLabels:
|
||||
- __name__
|
||||
- action: drop
|
||||
regex: scheduler_(e2e_scheduling_latency_microseconds|scheduling_algorithm_predicate_evaluation|scheduling_algorithm_priority_evaluation|scheduling_algorithm_preemption_evaluation|scheduling_algorithm_latency_microseconds|binding_latency_microseconds|scheduling_latency_seconds)
|
||||
sourceLabels:
|
||||
- __name__
|
||||
- action: drop
|
||||
regex: apiserver_(request_count|request_latencies|request_latencies_summary|dropped_requests|storage_data_key_generation_latencies_microseconds|storage_transformation_failures_total|storage_transformation_latencies_microseconds|proxy_tunnel_sync_latency_secs|longrunning_gauge|registered_watchers)
|
||||
sourceLabels:
|
||||
- __name__
|
||||
- action: drop
|
||||
regex: kubelet_docker_(operations|operations_latency_microseconds|operations_errors|operations_timeout)
|
||||
sourceLabels:
|
||||
- __name__
|
||||
- action: drop
|
||||
regex: reflector_(items_per_list|items_per_watch|list_duration_seconds|lists_total|short_watches_total|watch_duration_seconds|watches_total)
|
||||
sourceLabels:
|
||||
- __name__
|
||||
- action: drop
|
||||
regex: etcd_(helper_cache_hit_count|helper_cache_miss_count|helper_cache_entry_count|object_counts|request_cache_get_latencies_summary|request_cache_add_latencies_summary|request_latencies_summary)
|
||||
sourceLabels:
|
||||
- __name__
|
||||
- action: drop
|
||||
regex: transformation_(transformation_latencies_microseconds|failures_total)
|
||||
sourceLabels:
|
||||
- __name__
|
||||
- action: drop
|
||||
regex: (admission_quota_controller_adds|admission_quota_controller_depth|admission_quota_controller_longest_running_processor_microseconds|admission_quota_controller_queue_latency|admission_quota_controller_unfinished_work_seconds|admission_quota_controller_work_duration|APIServiceOpenAPIAggregationControllerQueue1_adds|APIServiceOpenAPIAggregationControllerQueue1_depth|APIServiceOpenAPIAggregationControllerQueue1_longest_running_processor_microseconds|APIServiceOpenAPIAggregationControllerQueue1_queue_latency|APIServiceOpenAPIAggregationControllerQueue1_retries|APIServiceOpenAPIAggregationControllerQueue1_unfinished_work_seconds|APIServiceOpenAPIAggregationControllerQueue1_work_duration|APIServiceRegistrationController_adds|APIServiceRegistrationController_depth|APIServiceRegistrationController_longest_running_processor_microseconds|APIServiceRegistrationController_queue_latency|APIServiceRegistrationController_retries|APIServiceRegistrationController_unfinished_work_seconds|APIServiceRegistrationController_work_duration|autoregister_adds|autoregister_depth|autoregister_longest_running_processor_microseconds|autoregister_queue_latency|autoregister_retries|autoregister_unfinished_work_seconds|autoregister_work_duration|AvailableConditionController_adds|AvailableConditionController_depth|AvailableConditionController_longest_running_processor_microseconds|AvailableConditionController_queue_latency|AvailableConditionController_retries|AvailableConditionController_unfinished_work_seconds|AvailableConditionController_work_duration|crd_autoregistration_controller_adds|crd_autoregistration_controller_depth|crd_autoregistration_controller_longest_running_processor_microseconds|crd_autoregistration_controller_queue_latency|crd_autoregistration_controller_retries|crd_autoregistration_controller_unfinished_work_seconds|crd_autoregistration_controller_work_duration|crdEstablishing_adds|crdEstablishing_depth|crdEstablishing_longest_running_processor_microseconds|crdEstablishing_queue_latency|crdEstablishing_retries|crdEstablishing_unfinished_work_seconds|crdEstablishing_work_duration|crd_finalizer_adds|crd_finalizer_depth|crd_finalizer_longest_running_processor_microseconds|crd_finalizer_queue_latency|crd_finalizer_retries|crd_finalizer_unfinished_work_seconds|crd_finalizer_work_duration|crd_naming_condition_controller_adds|crd_naming_condition_controller_depth|crd_naming_condition_controller_longest_running_processor_microseconds|crd_naming_condition_controller_queue_latency|crd_naming_condition_controller_retries|crd_naming_condition_controller_unfinished_work_seconds|crd_naming_condition_controller_work_duration|crd_openapi_controller_adds|crd_openapi_controller_depth|crd_openapi_controller_longest_running_processor_microseconds|crd_openapi_controller_queue_latency|crd_openapi_controller_retries|crd_openapi_controller_unfinished_work_seconds|crd_openapi_controller_work_duration|DiscoveryController_adds|DiscoveryController_depth|DiscoveryController_longest_running_processor_microseconds|DiscoveryController_queue_latency|DiscoveryController_retries|DiscoveryController_unfinished_work_seconds|DiscoveryController_work_duration|kubeproxy_sync_proxy_rules_latency_microseconds|non_structural_schema_condition_controller_adds|non_structural_schema_condition_controller_depth|non_structural_schema_condition_controller_longest_running_processor_microseconds|non_structural_schema_condition_controller_queue_latency|non_structural_schema_condition_controller_retries|non_structural_schema_condition_controller_unfinished_work_seconds|non_structural_schema_condition_controller_work_duration|rest_client_request_latency_seconds|storage_operation_errors_total|storage_operation_status_count)
|
||||
sourceLabels:
|
||||
- __name__
|
||||
- action: drop
|
||||
regex: etcd_(debugging|disk|server).*
|
||||
sourceLabels:
|
||||
- __name__
|
||||
- action: drop
|
||||
regex: apiserver_admission_controller_admission_latencies_seconds_.*
|
||||
sourceLabels:
|
||||
- __name__
|
||||
- action: drop
|
||||
regex: apiserver_admission_step_admission_latencies_seconds_.*
|
||||
sourceLabels:
|
||||
- __name__
|
||||
- action: drop
|
||||
regex: apiserver_request_duration_seconds_bucket;(0.15|0.25|0.3|0.35|0.4|0.45|0.6|0.7|0.8|0.9|1.25|1.5|1.75|2.5|3|3.5|4.5|6|7|8|9|15|25|30|50)
|
||||
sourceLabels:
|
||||
- __name__
|
||||
- le
|
||||
port: https
|
||||
scheme: https
|
||||
tlsConfig:
|
||||
caFile: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
|
||||
serverName: kubernetes
|
||||
jobLabel: component
|
||||
namespaceSelector:
|
||||
matchNames:
|
||||
- default
|
||||
selector:
|
||||
matchLabels:
|
||||
component: apiserver
|
||||
provider: kubernetes
|
||||
@@ -0,0 +1,26 @@
|
||||
apiVersion: monitoring.coreos.com/v1
|
||||
kind: ServiceMonitor
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/name: coredns
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/vendor: kubesphere
|
||||
name: coredns
|
||||
namespace: kubesphere-monitoring-system
|
||||
spec:
|
||||
endpoints:
|
||||
- bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token
|
||||
interval: 1m
|
||||
metricRelabelings:
|
||||
- action: drop
|
||||
regex: coredns_cache_misses_total
|
||||
sourceLabels:
|
||||
- __name__
|
||||
port: metrics
|
||||
jobLabel: app.kubernetes.io/name
|
||||
namespaceSelector:
|
||||
matchNames:
|
||||
- kube-system
|
||||
selector:
|
||||
matchLabels:
|
||||
k8s-app: kube-dns
|
||||
@@ -0,0 +1,29 @@
|
||||
apiVersion: monitoring.coreos.com/v1
|
||||
kind: ServiceMonitor
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/name: kube-controller-manager
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/vendor: kubesphere
|
||||
name: kube-controller-manager
|
||||
namespace: kubesphere-monitoring-system
|
||||
spec:
|
||||
endpoints:
|
||||
- bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token
|
||||
interval: 1m
|
||||
metricRelabelings:
|
||||
- action: keep
|
||||
regex: up
|
||||
sourceLabels:
|
||||
- __name__
|
||||
port: https-metrics
|
||||
scheme: https
|
||||
tlsConfig:
|
||||
insecureSkipVerify: true
|
||||
jobLabel: app.kubernetes.io/name
|
||||
namespaceSelector:
|
||||
matchNames:
|
||||
- kube-system
|
||||
selector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/name: kube-controller-manager
|
||||
@@ -0,0 +1,29 @@
|
||||
apiVersion: monitoring.coreos.com/v1
|
||||
kind: ServiceMonitor
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/name: kube-scheduler
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/vendor: kubesphere
|
||||
name: kube-scheduler
|
||||
namespace: kubesphere-monitoring-system
|
||||
spec:
|
||||
endpoints:
|
||||
- bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token
|
||||
interval: 1m
|
||||
metricRelabelings:
|
||||
- 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__
|
||||
port: https-metrics
|
||||
scheme: https
|
||||
tlsConfig:
|
||||
insecureSkipVerify: true
|
||||
jobLabel: app.kubernetes.io/name
|
||||
namespaceSelector:
|
||||
matchNames:
|
||||
- kube-system
|
||||
selector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/name: kube-scheduler
|
||||
@@ -0,0 +1,55 @@
|
||||
apiVersion: monitoring.coreos.com/v1
|
||||
kind: ServiceMonitor
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/name: kubelet
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/vendor: kubesphere
|
||||
name: kubelet
|
||||
namespace: kubesphere-monitoring-system
|
||||
spec:
|
||||
endpoints:
|
||||
- bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token
|
||||
honorLabels: true
|
||||
interval: 1m
|
||||
metricRelabelings:
|
||||
- action: keep
|
||||
regex: kubelet_node_name|kubelet_running_container_count|kubelet_running_pod_count|kubelet_volume_stats.*|kubelet_pleg_relist_duration_seconds_.+
|
||||
sourceLabels:
|
||||
- __name__
|
||||
port: https-metrics
|
||||
relabelings:
|
||||
- sourceLabels:
|
||||
- __metrics_path__
|
||||
targetLabel: metrics_path
|
||||
- action: labeldrop
|
||||
regex: (service|endpoint)
|
||||
scheme: https
|
||||
tlsConfig:
|
||||
insecureSkipVerify: true
|
||||
- bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token
|
||||
honorLabels: true
|
||||
interval: 1m
|
||||
metricRelabelings:
|
||||
- action: keep
|
||||
regex: container_cpu_usage_seconds_total|container_memory_usage_bytes|container_memory_cache|container_network_.+_bytes_total|container_memory_working_set_bytes|container_cpu_cfs_.*periods_total|container_processes.*|container_threads.*
|
||||
sourceLabels:
|
||||
- __name__
|
||||
path: /metrics/cadvisor
|
||||
port: https-metrics
|
||||
relabelings:
|
||||
- sourceLabels:
|
||||
- __metrics_path__
|
||||
targetLabel: metrics_path
|
||||
- action: labeldrop
|
||||
regex: (service|endpoint)
|
||||
scheme: https
|
||||
tlsConfig:
|
||||
insecureSkipVerify: true
|
||||
jobLabel: app.kubernetes.io/name
|
||||
namespaceSelector:
|
||||
matchNames:
|
||||
- kube-system
|
||||
selector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/name: kubelet
|
||||
@@ -0,0 +1,23 @@
|
||||
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: 1.3.1
|
||||
name: kubesphere-node-exporter
|
||||
namespace: kubesphere-monitoring-system
|
||||
rules:
|
||||
- apiGroups:
|
||||
- authentication.k8s.io
|
||||
resources:
|
||||
- tokenreviews
|
||||
verbs:
|
||||
- create
|
||||
- apiGroups:
|
||||
- authorization.k8s.io
|
||||
resources:
|
||||
- subjectaccessreviews
|
||||
verbs:
|
||||
- create
|
||||
@@ -0,0 +1,18 @@
|
||||
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: 1.3.1
|
||||
name: kubesphere-node-exporter
|
||||
namespace: kubesphere-monitoring-system
|
||||
roleRef:
|
||||
apiGroup: rbac.authorization.k8s.io
|
||||
kind: ClusterRole
|
||||
name: kubesphere-node-exporter
|
||||
subjects:
|
||||
- kind: ServiceAccount
|
||||
name: node-exporter
|
||||
namespace: kubesphere-monitoring-system
|
||||
@@ -0,0 +1,114 @@
|
||||
apiVersion: apps/v1
|
||||
kind: DaemonSet
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: exporter
|
||||
app.kubernetes.io/name: node-exporter
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 1.3.1
|
||||
name: node-exporter
|
||||
namespace: kubesphere-monitoring-system
|
||||
spec:
|
||||
selector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/component: exporter
|
||||
app.kubernetes.io/name: node-exporter
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
template:
|
||||
metadata:
|
||||
annotations:
|
||||
kubectl.kubernetes.io/default-container: node-exporter
|
||||
labels:
|
||||
app.kubernetes.io/component: exporter
|
||||
app.kubernetes.io/name: node-exporter
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 1.3.1
|
||||
spec:
|
||||
affinity:
|
||||
nodeAffinity:
|
||||
requiredDuringSchedulingIgnoredDuringExecution:
|
||||
nodeSelectorTerms:
|
||||
- matchExpressions:
|
||||
- key: node-role.kubernetes.io/edge
|
||||
operator: DoesNotExist
|
||||
containers:
|
||||
- args:
|
||||
- --web.listen-address=127.0.0.1:9100
|
||||
- --path.sysfs=/host/sys
|
||||
- --path.rootfs=/host/root
|
||||
- --no-collector.wifi
|
||||
- --collector.cpu.info
|
||||
- --collector.network_route
|
||||
- --collector.netdev.address-info
|
||||
- --collector.filesystem.ignored-mount-points=^/(dev|proc|sys|var/lib/docker/.+)($|/)
|
||||
- --collector.filesystem.ignored-fs-types=^(autofs|binfmt_misc|cgroup|configfs|debugfs|devpts|devtmpfs|fusectl|hugetlbfs|mqueue|overlay|proc|procfs|pstore|rpc_pipefs|securityfs|sysfs|tracefs)$
|
||||
image: beclab/node-exporter:0.0.1
|
||||
name: node-exporter
|
||||
securityContext:
|
||||
privileged: true
|
||||
runAsUser: 0
|
||||
resources:
|
||||
limits:
|
||||
cpu: "1"
|
||||
memory: 500Mi
|
||||
requests:
|
||||
cpu: 102m
|
||||
memory: 180Mi
|
||||
volumeMounts:
|
||||
- mountPath: /host/proc
|
||||
name: proc
|
||||
readOnly: true
|
||||
- mountPath: /host/sys
|
||||
name: sys
|
||||
readOnly: true
|
||||
- mountPath: /host/root
|
||||
mountPropagation: HostToContainer
|
||||
name: root
|
||||
readOnly: true
|
||||
- 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
|
||||
- --upstream=http://127.0.0.1:9100/
|
||||
env:
|
||||
- name: IP
|
||||
valueFrom:
|
||||
fieldRef:
|
||||
fieldPath: status.podIP
|
||||
image: bitnami/kube-rbac-proxy:0.19.0
|
||||
imagePullPolicy: IfNotPresent
|
||||
name: kube-rbac-proxy
|
||||
ports:
|
||||
- containerPort: 9100
|
||||
hostPort: 9100
|
||||
name: https
|
||||
resources:
|
||||
limits:
|
||||
cpu: "1"
|
||||
memory: 100Mi
|
||||
requests:
|
||||
cpu: 10m
|
||||
memory: 20Mi
|
||||
securityContext:
|
||||
runAsGroup: 65532
|
||||
runAsNonRoot: true
|
||||
runAsUser: 65532
|
||||
hostNetwork: true
|
||||
hostPID: true
|
||||
nodeSelector:
|
||||
kubernetes.io/os: linux
|
||||
securityContext:
|
||||
runAsUser: 65534
|
||||
serviceAccountName: node-exporter
|
||||
tolerations:
|
||||
- operator: Exists
|
||||
volumes:
|
||||
- hostPath:
|
||||
path: /proc
|
||||
name: proc
|
||||
- hostPath:
|
||||
path: /sys
|
||||
name: sys
|
||||
- hostPath:
|
||||
path: /
|
||||
name: root
|
||||
@@ -0,0 +1,173 @@
|
||||
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: 1.3.1
|
||||
prometheus: k8s
|
||||
role: alert-rules
|
||||
name: node-exporter-rules
|
||||
namespace: kubesphere-monitoring-system
|
||||
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.
|
||||
summary: Filesystem is predicted to run out of space within the next 24 hours.
|
||||
expr: |
|
||||
(
|
||||
node_filesystem_avail_bytes{job="node-exporter",fstype!=""} / node_filesystem_size_bytes{job="node-exporter",fstype!=""} * 100 < 20
|
||||
and
|
||||
predict_linear(node_filesystem_avail_bytes{job="node-exporter",fstype!=""}[6h], 24*60*60) < 0
|
||||
and
|
||||
node_filesystem_readonly{job="node-exporter",fstype!=""} == 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.
|
||||
summary: Filesystem is predicted to run out of space within the next 4 hours.
|
||||
expr: |
|
||||
(
|
||||
node_filesystem_avail_bytes{job="node-exporter",fstype!=""} / node_filesystem_size_bytes{job="node-exporter",fstype!=""} * 100 < 15
|
||||
and
|
||||
predict_linear(node_filesystem_avail_bytes{job="node-exporter",fstype!=""}[6h], 4*60*60) < 0
|
||||
and
|
||||
node_filesystem_readonly{job="node-exporter",fstype!=""} == 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.
|
||||
summary: Filesystem has less than 5% space left.
|
||||
expr: |
|
||||
(
|
||||
node_filesystem_avail_bytes{job="node-exporter",fstype!=""} / node_filesystem_size_bytes{job="node-exporter",fstype!=""} * 100 < 5
|
||||
and
|
||||
node_filesystem_readonly{job="node-exporter",fstype!=""} == 0
|
||||
)
|
||||
for: 1h
|
||||
labels:
|
||||
severity: warning
|
||||
- alert: NodeFilesystemAlmostOutOfSpace
|
||||
annotations:
|
||||
description: Filesystem on {{ $labels.device }} at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available space left.
|
||||
summary: Filesystem has less than 3% space left.
|
||||
expr: |
|
||||
(
|
||||
node_filesystem_avail_bytes{job="node-exporter",fstype!=""} / node_filesystem_size_bytes{job="node-exporter",fstype!=""} * 100 < 3
|
||||
and
|
||||
node_filesystem_readonly{job="node-exporter",fstype!=""} == 0
|
||||
)
|
||||
for: 1h
|
||||
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.
|
||||
summary: Filesystem is predicted to run out of inodes within the next 24 hours.
|
||||
expr: |
|
||||
(
|
||||
node_filesystem_files_free{job="node-exporter",fstype!=""} / node_filesystem_files{job="node-exporter",fstype!=""} * 100 < 40
|
||||
and
|
||||
predict_linear(node_filesystem_files_free{job="node-exporter",fstype!=""}[6h], 24*60*60) < 0
|
||||
and
|
||||
node_filesystem_readonly{job="node-exporter",fstype!=""} == 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.
|
||||
summary: Filesystem is predicted to run out of inodes within the next 4 hours.
|
||||
expr: |
|
||||
(
|
||||
node_filesystem_files_free{job="node-exporter",fstype!=""} / node_filesystem_files{job="node-exporter",fstype!=""} * 100 < 20
|
||||
and
|
||||
predict_linear(node_filesystem_files_free{job="node-exporter",fstype!=""}[6h], 4*60*60) < 0
|
||||
and
|
||||
node_filesystem_readonly{job="node-exporter",fstype!=""} == 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.
|
||||
summary: Filesystem has less than 5% inodes left.
|
||||
expr: |
|
||||
(
|
||||
node_filesystem_files_free{job="node-exporter",fstype!=""} / node_filesystem_files{job="node-exporter",fstype!=""} * 100 < 5
|
||||
and
|
||||
node_filesystem_readonly{job="node-exporter",fstype!=""} == 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.
|
||||
summary: Filesystem has less than 3% inodes left.
|
||||
expr: |
|
||||
(
|
||||
node_filesystem_files_free{job="node-exporter",fstype!=""} / node_filesystem_files{job="node-exporter",fstype!=""} * 100 < 3
|
||||
and
|
||||
node_filesystem_readonly{job="node-exporter",fstype!=""} == 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.'
|
||||
summary: Network interface is reporting many receive errors.
|
||||
expr: |
|
||||
increase(node_network_receive_errs_total[2m]) > 10
|
||||
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.'
|
||||
summary: Network interface is reporting many transmit errors.
|
||||
expr: |
|
||||
increase(node_network_transmit_errs_total[2m]) > 10
|
||||
for: 1h
|
||||
labels:
|
||||
severity: warning
|
||||
- alert: NodeHighNumberConntrackEntriesUsed
|
||||
annotations:
|
||||
description: '{{ $value | humanizePercentage }} of conntrack entries are used.'
|
||||
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: NodeClockSkewDetected
|
||||
annotations:
|
||||
message: Clock on {{ $labels.instance }} is out of sync by more than 300s. Ensure NTP is configured correctly on this host.
|
||||
summary: Clock skew detected.
|
||||
expr: |
|
||||
(
|
||||
node_timex_offset_seconds > 0.05
|
||||
and
|
||||
deriv(node_timex_offset_seconds[5m]) >= 0
|
||||
)
|
||||
or
|
||||
(
|
||||
node_timex_offset_seconds < -0.05
|
||||
and
|
||||
deriv(node_timex_offset_seconds[5m]) <= 0
|
||||
)
|
||||
for: 10m
|
||||
labels:
|
||||
severity: warning
|
||||
@@ -0,0 +1,20 @@
|
||||
apiVersion: v1
|
||||
kind: Service
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: exporter
|
||||
app.kubernetes.io/name: node-exporter
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 1.3.1
|
||||
name: node-exporter
|
||||
namespace: kubesphere-monitoring-system
|
||||
spec:
|
||||
clusterIP: None
|
||||
ports:
|
||||
- name: https
|
||||
port: 9100
|
||||
targetPort: https
|
||||
selector:
|
||||
app.kubernetes.io/component: exporter
|
||||
app.kubernetes.io/name: node-exporter
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
@@ -0,0 +1,10 @@
|
||||
apiVersion: v1
|
||||
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: 1.3.1
|
||||
name: node-exporter
|
||||
namespace: kubesphere-monitoring-system
|
||||
@@ -0,0 +1,39 @@
|
||||
apiVersion: monitoring.coreos.com/v1
|
||||
kind: ServiceMonitor
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: exporter
|
||||
app.kubernetes.io/name: node-exporter
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/vendor: kubesphere
|
||||
app.kubernetes.io/version: 1.3.1
|
||||
name: node-exporter
|
||||
namespace: kubesphere-monitoring-system
|
||||
spec:
|
||||
endpoints:
|
||||
- bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token
|
||||
interval: 1m
|
||||
metricRelabelings:
|
||||
- action: keep
|
||||
regex: node_(uname|network|disk|cpu)_info|node_cpu_.+|node_hwmon_temp_celsius|node_hwmon_chip_names|node_network_route_info|node_network_address_info|node_memory_Mem.+_bytes|node_memory_SReclaimable_bytes|node_memory_Cached_bytes|node_memory_Buffers_bytes|node_network_(.+_bytes_total|up)|node_network_.+_errs_total|node_nf_conntrack_entries.*|node_disk_.+_completed_total|node_disk_.+_bytes_total|node_disk_smartctl_info|node_disk_power_on_hours|node_disk_temp_celsius|node_filesystem_files|node_filesystem_files_free|node_filesystem_avail_bytes|node_filesystem_size_bytes|node_filesystem_free_bytes|node_filesystem_readonly|node_load.+|node_timex_offset_seconds
|
||||
sourceLabels:
|
||||
- __name__
|
||||
port: https
|
||||
relabelings:
|
||||
- action: replace
|
||||
regex: (.*)
|
||||
replacement: $1
|
||||
sourceLabels:
|
||||
- __meta_kubernetes_pod_node_name
|
||||
targetLabel: instance
|
||||
- action: labeldrop
|
||||
regex: (service|endpoint)
|
||||
scheme: https
|
||||
tlsConfig:
|
||||
insecureSkipVerify: true
|
||||
jobLabel: app.kubernetes.io/name
|
||||
selector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/component: exporter
|
||||
app.kubernetes.io/name: node-exporter
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,460 @@
|
||||
apiVersion: apiextensions.k8s.io/v1
|
||||
kind: CustomResourceDefinition
|
||||
metadata:
|
||||
annotations:
|
||||
controller-gen.kubebuilder.io/version: v0.6.2
|
||||
creationTimestamp: null
|
||||
name: podmonitors.monitoring.coreos.com
|
||||
spec:
|
||||
group: monitoring.coreos.com
|
||||
names:
|
||||
categories:
|
||||
- prometheus-operator
|
||||
kind: PodMonitor
|
||||
listKind: PodMonitorList
|
||||
plural: podmonitors
|
||||
singular: podmonitor
|
||||
scope: Namespaced
|
||||
versions:
|
||||
- name: v1
|
||||
schema:
|
||||
openAPIV3Schema:
|
||||
description: PodMonitor defines monitoring for a set of pods.
|
||||
properties:
|
||||
apiVersion:
|
||||
description: 'APIVersion defines the versioned schema of this representation of an object. Servers should convert recognized schemas to the latest internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources'
|
||||
type: string
|
||||
kind:
|
||||
description: 'Kind is a string value representing the REST resource this object represents. Servers may infer this from the endpoint the client submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds'
|
||||
type: string
|
||||
metadata:
|
||||
type: object
|
||||
spec:
|
||||
description: Specification of desired Pod selection for target discovery by Prometheus.
|
||||
properties:
|
||||
jobLabel:
|
||||
description: The label to use to retrieve the job name from.
|
||||
type: string
|
||||
labelLimit:
|
||||
description: Per-scrape limit on number of labels that will be accepted for a sample. Only valid in Prometheus versions 2.27.0 and newer.
|
||||
format: int64
|
||||
type: integer
|
||||
labelNameLengthLimit:
|
||||
description: Per-scrape limit on length of labels name that will be accepted for a sample. Only valid in Prometheus versions 2.27.0 and newer.
|
||||
format: int64
|
||||
type: integer
|
||||
labelValueLengthLimit:
|
||||
description: Per-scrape limit on length of labels value that will be accepted for a sample. Only valid in Prometheus versions 2.27.0 and newer.
|
||||
format: int64
|
||||
type: integer
|
||||
namespaceSelector:
|
||||
description: Selector to select which namespaces the Endpoints objects are discovered from.
|
||||
properties:
|
||||
any:
|
||||
description: Boolean describing whether all namespaces are selected in contrast to a list restricting them.
|
||||
type: boolean
|
||||
matchNames:
|
||||
description: List of namespace names.
|
||||
items:
|
||||
type: string
|
||||
type: array
|
||||
type: object
|
||||
podMetricsEndpoints:
|
||||
description: A list of endpoints allowed as part of this PodMonitor.
|
||||
items:
|
||||
description: PodMetricsEndpoint defines a scrapeable endpoint of a Kubernetes Pod serving Prometheus metrics.
|
||||
properties:
|
||||
authorization:
|
||||
description: Authorization section for this endpoint
|
||||
properties:
|
||||
credentials:
|
||||
description: 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
|
||||
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
|
||||
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
|
||||
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
|
||||
honorLabels:
|
||||
description: HonorLabels chooses the metric's labels on collisions with target labels.
|
||||
type: boolean
|
||||
honorTimestamps:
|
||||
description: HonorTimestamps controls whether Prometheus respects the timestamps present in scraped data.
|
||||
type: boolean
|
||||
interval:
|
||||
description: Interval at which metrics should be scraped
|
||||
type: string
|
||||
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:
|
||||
description: Action to perform based on regex matching. Default is 'replace'
|
||||
type: string
|
||||
modulus:
|
||||
description: Modulus to take of the hash of the source label values.
|
||||
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:
|
||||
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
|
||||
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
|
||||
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
|
||||
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
|
||||
endpointParams:
|
||||
additionalProperties:
|
||||
type: string
|
||||
description: Parameters to append to the token URL
|
||||
type: object
|
||||
scopes:
|
||||
description: OAuth2 scopes used for the token request
|
||||
items:
|
||||
type: string
|
||||
type: array
|
||||
tokenUrl:
|
||||
description: The URL to fetch the token from
|
||||
minLength: 1
|
||||
type: string
|
||||
required:
|
||||
- clientId
|
||||
- clientSecret
|
||||
- tokenUrl
|
||||
type: object
|
||||
params:
|
||||
additionalProperties:
|
||||
items:
|
||||
type: string
|
||||
type: array
|
||||
description: Optional HTTP URL parameters
|
||||
type: object
|
||||
path:
|
||||
description: HTTP path to scrape for metrics.
|
||||
type: string
|
||||
port:
|
||||
description: Name of the pod port this endpoint refers to. Mutually exclusive with targetPort.
|
||||
type: string
|
||||
proxyUrl:
|
||||
description: ProxyURL eg http://proxyserver:2195 Directs scrapes to proxy through this endpoint.
|
||||
type: string
|
||||
relabelings:
|
||||
description: 'RelabelConfigs to apply to samples before scraping. Prometheus Operator automatically adds relabelings for a few standard Kubernetes fields and replaces original scrape job name with __tmp_prometheus_job_name. 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'
|
||||
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:
|
||||
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
|
||||
scheme:
|
||||
description: HTTP scheme to use for scraping.
|
||||
type: string
|
||||
scrapeTimeout:
|
||||
description: Timeout after which the scrape is ended
|
||||
type: string
|
||||
targetPort:
|
||||
anyOf:
|
||||
- type: integer
|
||||
- type: string
|
||||
description: 'Deprecated: Use ''port'' instead.'
|
||||
x-kubernetes-int-or-string: true
|
||||
tlsConfig:
|
||||
description: TLS configuration to use when scraping the endpoint.
|
||||
properties:
|
||||
ca:
|
||||
description: Struct containing the CA cert to use for the targets.
|
||||
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
|
||||
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
|
||||
type: object
|
||||
cert:
|
||||
description: Struct containing the client cert file for the targets.
|
||||
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
|
||||
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
|
||||
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
|
||||
serverName:
|
||||
description: Used to verify the hostname for the targets.
|
||||
type: string
|
||||
type: object
|
||||
type: object
|
||||
type: array
|
||||
podTargetLabels:
|
||||
description: PodTargetLabels transfers labels on the Kubernetes Pod onto the target.
|
||||
items:
|
||||
type: string
|
||||
type: array
|
||||
sampleLimit:
|
||||
description: SampleLimit defines per-scrape limit on number of scraped samples that will be accepted.
|
||||
format: int64
|
||||
type: integer
|
||||
selector:
|
||||
description: Selector to select Pod objects.
|
||||
properties:
|
||||
matchExpressions:
|
||||
description: matchExpressions is a list of label selector requirements. The requirements are ANDed.
|
||||
items:
|
||||
description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values.
|
||||
properties:
|
||||
key:
|
||||
description: key is the label key that the selector applies to.
|
||||
type: string
|
||||
operator:
|
||||
description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist.
|
||||
type: string
|
||||
values:
|
||||
description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch.
|
||||
items:
|
||||
type: string
|
||||
type: array
|
||||
required:
|
||||
- key
|
||||
- operator
|
||||
type: object
|
||||
type: array
|
||||
matchLabels:
|
||||
additionalProperties:
|
||||
type: string
|
||||
description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed.
|
||||
type: object
|
||||
type: object
|
||||
targetLimit:
|
||||
description: TargetLimit defines a limit on the number of scraped targets that will be accepted.
|
||||
format: int64
|
||||
type: integer
|
||||
required:
|
||||
- podMetricsEndpoints
|
||||
- selector
|
||||
type: object
|
||||
required:
|
||||
- spec
|
||||
type: object
|
||||
served: true
|
||||
storage: true
|
||||
status:
|
||||
acceptedNames:
|
||||
kind: ""
|
||||
plural: ""
|
||||
conditions: []
|
||||
storedVersions: []
|
||||
@@ -0,0 +1,488 @@
|
||||
apiVersion: apiextensions.k8s.io/v1
|
||||
kind: CustomResourceDefinition
|
||||
metadata:
|
||||
annotations:
|
||||
controller-gen.kubebuilder.io/version: v0.6.2
|
||||
creationTimestamp: null
|
||||
name: probes.monitoring.coreos.com
|
||||
spec:
|
||||
group: monitoring.coreos.com
|
||||
names:
|
||||
categories:
|
||||
- prometheus-operator
|
||||
kind: Probe
|
||||
listKind: ProbeList
|
||||
plural: probes
|
||||
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
|
||||
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
|
||||
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
|
||||
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
|
||||
interval:
|
||||
description: Interval at which targets are probed using the configured prober. If not specified Prometheus' global scrape interval is used.
|
||||
type: string
|
||||
jobName:
|
||||
description: The job name assigned to scraped metrics by default.
|
||||
type: string
|
||||
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:
|
||||
description: Action to perform based on regex matching. Default is 'replace'
|
||||
type: string
|
||||
modulus:
|
||||
description: Modulus to take of the hash of the source label values.
|
||||
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:
|
||||
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
|
||||
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
|
||||
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
|
||||
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:
|
||||
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.
|
||||
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 and/or dynamically discovered targets to be probed using the prober.
|
||||
properties:
|
||||
ingress:
|
||||
description: Ingress defines the set of dynamically discovered ingress objects which hosts are considered for probing.
|
||||
properties:
|
||||
namespaceSelector:
|
||||
description: Select Ingress objects by namespace.
|
||||
properties:
|
||||
any:
|
||||
description: Boolean describing whether all namespaces are selected in contrast to a list restricting them.
|
||||
type: boolean
|
||||
matchNames:
|
||||
description: List of namespace names.
|
||||
items:
|
||||
type: string
|
||||
type: array
|
||||
type: object
|
||||
relabelingConfigs:
|
||||
description: 'RelabelConfigs to apply to samples before ingestion. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#relabel_config'
|
||||
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'
|
||||
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:
|
||||
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: Select Ingress objects by labels.
|
||||
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
|
||||
type: object
|
||||
staticConfig:
|
||||
description: 'StaticConfig defines static targets which are considers for probing. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#static_config.'
|
||||
properties:
|
||||
labels:
|
||||
additionalProperties:
|
||||
type: string
|
||||
description: Labels assigned to all metrics scraped from the targets.
|
||||
type: object
|
||||
relabelingConfigs:
|
||||
description: 'RelabelConfigs to apply to samples before ingestion. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#relabel_config'
|
||||
items:
|
||||
description: 'RelabelConfig allows dynamic rewriting of the label set, being applied to samples before ingestion. It defines `<metric_relabel_configs>`-section of Prometheus configuration. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#metric_relabel_configs'
|
||||
properties:
|
||||
action:
|
||||
description: Action to perform based on regex matching. Default is 'replace'
|
||||
type: string
|
||||
modulus:
|
||||
description: Modulus to take of the hash of the source label values.
|
||||
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:
|
||||
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: Targets is a list of URLs to probe using the configured prober.
|
||||
items:
|
||||
type: string
|
||||
type: array
|
||||
type: object
|
||||
type: object
|
||||
tlsConfig:
|
||||
description: TLS configuration to use when scraping the endpoint.
|
||||
properties:
|
||||
ca:
|
||||
description: Struct containing the CA cert to use for the targets.
|
||||
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
|
||||
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
|
||||
type: object
|
||||
cert:
|
||||
description: Struct containing the client cert file for the targets.
|
||||
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
|
||||
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
|
||||
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
|
||||
serverName:
|
||||
description: Used to verify the hostname for the targets.
|
||||
type: string
|
||||
type: object
|
||||
type: object
|
||||
required:
|
||||
- spec
|
||||
type: object
|
||||
served: true
|
||||
storage: true
|
||||
status:
|
||||
acceptedNames:
|
||||
kind: ""
|
||||
plural: ""
|
||||
conditions: []
|
||||
storedVersions: []
|
||||
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,89 @@
|
||||
apiVersion: apiextensions.k8s.io/v1
|
||||
kind: CustomResourceDefinition
|
||||
metadata:
|
||||
annotations:
|
||||
controller-gen.kubebuilder.io/version: v0.6.2
|
||||
creationTimestamp: null
|
||||
name: prometheusrules.monitoring.coreos.com
|
||||
spec:
|
||||
group: monitoring.coreos.com
|
||||
names:
|
||||
categories:
|
||||
- prometheus-operator
|
||||
kind: PrometheusRule
|
||||
listKind: PrometheusRuleList
|
||||
plural: prometheusrules
|
||||
singular: prometheusrule
|
||||
scope: Namespaced
|
||||
versions:
|
||||
- name: v1
|
||||
schema:
|
||||
openAPIV3Schema:
|
||||
description: PrometheusRule defines recording and alerting rules for a Prometheus instance
|
||||
properties:
|
||||
apiVersion:
|
||||
description: 'APIVersion defines the versioned schema of this representation of an object. Servers should convert recognized schemas to the latest internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources'
|
||||
type: string
|
||||
kind:
|
||||
description: 'Kind is a string value representing the REST resource this object represents. Servers may infer this from the endpoint the client submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds'
|
||||
type: string
|
||||
metadata:
|
||||
type: object
|
||||
spec:
|
||||
description: Specification of desired alerting rule definitions for Prometheus.
|
||||
properties:
|
||||
groups:
|
||||
description: Content of Prometheus rule file
|
||||
items:
|
||||
description: 'RuleGroup is a list of sequentially evaluated recording and alerting rules. 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/main/docs/components/rule.md#partial-response'
|
||||
properties:
|
||||
interval:
|
||||
type: string
|
||||
name:
|
||||
type: string
|
||||
partial_response_strategy:
|
||||
type: string
|
||||
rules:
|
||||
items:
|
||||
description: 'Rule describes an alerting or recording rule See Prometheus documentation: [alerting](https://www.prometheus.io/docs/prometheus/latest/configuration/alerting_rules/) or [recording](https://www.prometheus.io/docs/prometheus/latest/configuration/recording_rules/#recording-rules) rule'
|
||||
properties:
|
||||
alert:
|
||||
type: string
|
||||
annotations:
|
||||
additionalProperties:
|
||||
type: string
|
||||
type: object
|
||||
expr:
|
||||
anyOf:
|
||||
- type: integer
|
||||
- type: string
|
||||
x-kubernetes-int-or-string: true
|
||||
for:
|
||||
type: string
|
||||
labels:
|
||||
additionalProperties:
|
||||
type: string
|
||||
type: object
|
||||
record:
|
||||
type: string
|
||||
required:
|
||||
- expr
|
||||
type: object
|
||||
type: array
|
||||
required:
|
||||
- name
|
||||
- rules
|
||||
type: object
|
||||
type: array
|
||||
type: object
|
||||
required:
|
||||
- spec
|
||||
type: object
|
||||
served: true
|
||||
storage: true
|
||||
status:
|
||||
acceptedNames:
|
||||
kind: ""
|
||||
plural: ""
|
||||
conditions: []
|
||||
storedVersions: []
|
||||
@@ -0,0 +1,477 @@
|
||||
apiVersion: apiextensions.k8s.io/v1
|
||||
kind: CustomResourceDefinition
|
||||
metadata:
|
||||
annotations:
|
||||
controller-gen.kubebuilder.io/version: v0.6.2
|
||||
creationTimestamp: null
|
||||
name: servicemonitors.monitoring.coreos.com
|
||||
spec:
|
||||
group: monitoring.coreos.com
|
||||
names:
|
||||
categories:
|
||||
- prometheus-operator
|
||||
kind: ServiceMonitor
|
||||
listKind: ServiceMonitorList
|
||||
plural: servicemonitors
|
||||
singular: servicemonitor
|
||||
scope: Namespaced
|
||||
versions:
|
||||
- name: v1
|
||||
schema:
|
||||
openAPIV3Schema:
|
||||
description: ServiceMonitor defines monitoring for a set of services.
|
||||
properties:
|
||||
apiVersion:
|
||||
description: 'APIVersion defines the versioned schema of this representation of an object. Servers should convert recognized schemas to the latest internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources'
|
||||
type: string
|
||||
kind:
|
||||
description: 'Kind is a string value representing the REST resource this object represents. Servers may infer this from the endpoint the client submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds'
|
||||
type: string
|
||||
metadata:
|
||||
type: object
|
||||
spec:
|
||||
description: Specification of desired Service selection for target discovery by Prometheus.
|
||||
properties:
|
||||
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
|
||||
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:
|
||||
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
|
||||
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
|
||||
type: object
|
||||
bearerTokenFile:
|
||||
description: File to read bearer token for scraping targets.
|
||||
type: string
|
||||
bearerTokenSecret:
|
||||
description: Secret to mount to read bearer token for scraping targets. The secret needs to be in the same namespace as the service monitor and accessible by the Prometheus Operator.
|
||||
properties:
|
||||
key:
|
||||
description: The key of the secret to select from. Must be a valid secret key.
|
||||
type: string
|
||||
name:
|
||||
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?'
|
||||
type: string
|
||||
optional:
|
||||
description: Specify whether the Secret or its key must be defined
|
||||
type: boolean
|
||||
required:
|
||||
- key
|
||||
type: object
|
||||
honorLabels:
|
||||
description: HonorLabels chooses the metric's labels on collisions with target labels.
|
||||
type: boolean
|
||||
honorTimestamps:
|
||||
description: HonorTimestamps controls whether Prometheus respects the timestamps present in scraped data.
|
||||
type: boolean
|
||||
interval:
|
||||
description: Interval at which metrics should be scraped
|
||||
type: string
|
||||
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:
|
||||
description: Action to perform based on regex matching. Default is 'replace'
|
||||
type: string
|
||||
modulus:
|
||||
description: Modulus to take of the hash of the source label values.
|
||||
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:
|
||||
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
|
||||
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
|
||||
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
|
||||
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
|
||||
endpointParams:
|
||||
additionalProperties:
|
||||
type: string
|
||||
description: Parameters to append to the token URL
|
||||
type: object
|
||||
scopes:
|
||||
description: OAuth2 scopes used for the token request
|
||||
items:
|
||||
type: string
|
||||
type: array
|
||||
tokenUrl:
|
||||
description: The URL to fetch the token from
|
||||
minLength: 1
|
||||
type: string
|
||||
required:
|
||||
- clientId
|
||||
- clientSecret
|
||||
- tokenUrl
|
||||
type: object
|
||||
params:
|
||||
additionalProperties:
|
||||
items:
|
||||
type: string
|
||||
type: array
|
||||
description: Optional HTTP URL parameters
|
||||
type: object
|
||||
path:
|
||||
description: HTTP path to scrape for metrics.
|
||||
type: string
|
||||
port:
|
||||
description: Name of the service port this endpoint refers to. Mutually exclusive with targetPort.
|
||||
type: string
|
||||
proxyUrl:
|
||||
description: ProxyURL eg http://proxyserver:2195 Directs scrapes to proxy through this endpoint.
|
||||
type: string
|
||||
relabelings:
|
||||
description: 'RelabelConfigs to apply to samples before scraping. Prometheus Operator automatically adds relabelings for a few standard Kubernetes fields and replaces original scrape job name with __tmp_prometheus_job_name. 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'
|
||||
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:
|
||||
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
|
||||
scheme:
|
||||
description: HTTP scheme to use for scraping.
|
||||
type: string
|
||||
scrapeTimeout:
|
||||
description: Timeout after which the scrape is ended
|
||||
type: string
|
||||
targetPort:
|
||||
anyOf:
|
||||
- type: integer
|
||||
- type: string
|
||||
description: Name or number of the target port of the Pod behind the Service, the port must be specified with container port property. Mutually exclusive with port.
|
||||
x-kubernetes-int-or-string: true
|
||||
tlsConfig:
|
||||
description: TLS configuration to use when scraping the endpoint
|
||||
properties:
|
||||
ca:
|
||||
description: Struct containing the CA cert to use for the targets.
|
||||
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
|
||||
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
|
||||
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.
|
||||
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
|
||||
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
|
||||
type: object
|
||||
certFile:
|
||||
description: Path to the client cert file in the Prometheus container for the targets.
|
||||
type: string
|
||||
insecureSkipVerify:
|
||||
description: Disable target certificate validation.
|
||||
type: boolean
|
||||
keyFile:
|
||||
description: Path to the client key file in the Prometheus container for the targets.
|
||||
type: string
|
||||
keySecret:
|
||||
description: Secret containing the client key file for the targets.
|
||||
properties:
|
||||
key:
|
||||
description: The key of the secret to select from. Must be a valid secret key.
|
||||
type: string
|
||||
name:
|
||||
description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?'
|
||||
type: string
|
||||
optional:
|
||||
description: Specify whether the Secret or its key must be defined
|
||||
type: boolean
|
||||
required:
|
||||
- key
|
||||
type: object
|
||||
serverName:
|
||||
description: Used to verify the hostname for the targets.
|
||||
type: string
|
||||
type: object
|
||||
type: object
|
||||
type: array
|
||||
jobLabel:
|
||||
description: "Chooses the label of the Kubernetes `Endpoints`. Its value will be used for the `job`-label's value of the created metrics. \n Default & fallback value: the name of the respective Kubernetes `Endpoint`."
|
||||
type: string
|
||||
labelLimit:
|
||||
description: Per-scrape limit on number of labels that will be accepted for a sample. Only valid in Prometheus versions 2.27.0 and newer.
|
||||
format: int64
|
||||
type: integer
|
||||
labelNameLengthLimit:
|
||||
description: Per-scrape limit on length of labels name that will be accepted for a sample. Only valid in Prometheus versions 2.27.0 and newer.
|
||||
format: int64
|
||||
type: integer
|
||||
labelValueLengthLimit:
|
||||
description: Per-scrape limit on length of labels value that will be accepted for a sample. Only valid in Prometheus versions 2.27.0 and newer.
|
||||
format: int64
|
||||
type: integer
|
||||
namespaceSelector:
|
||||
description: Selector to select which namespaces the Kubernetes Endpoints objects are discovered from.
|
||||
properties:
|
||||
any:
|
||||
description: Boolean describing whether all namespaces are selected in contrast to a list restricting them.
|
||||
type: boolean
|
||||
matchNames:
|
||||
description: List of namespace names.
|
||||
items:
|
||||
type: string
|
||||
type: array
|
||||
type: object
|
||||
podTargetLabels:
|
||||
description: PodTargetLabels transfers labels on the Kubernetes `Pod` onto the created metrics.
|
||||
items:
|
||||
type: string
|
||||
type: array
|
||||
sampleLimit:
|
||||
description: SampleLimit defines per-scrape limit on number of scraped samples that will be accepted.
|
||||
format: int64
|
||||
type: integer
|
||||
selector:
|
||||
description: Selector to select Endpoints objects.
|
||||
properties:
|
||||
matchExpressions:
|
||||
description: matchExpressions is a list of label selector requirements. The requirements are ANDed.
|
||||
items:
|
||||
description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values.
|
||||
properties:
|
||||
key:
|
||||
description: key is the label key that the selector applies to.
|
||||
type: string
|
||||
operator:
|
||||
description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist.
|
||||
type: string
|
||||
values:
|
||||
description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch.
|
||||
items:
|
||||
type: string
|
||||
type: array
|
||||
required:
|
||||
- key
|
||||
- operator
|
||||
type: object
|
||||
type: array
|
||||
matchLabels:
|
||||
additionalProperties:
|
||||
type: string
|
||||
description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed.
|
||||
type: object
|
||||
type: object
|
||||
targetLabels:
|
||||
description: TargetLabels transfers labels from the Kubernetes `Service` onto the created metrics. All labels set in `selector.matchLabels` are automatically transferred.
|
||||
items:
|
||||
type: string
|
||||
type: array
|
||||
targetLimit:
|
||||
description: TargetLimit defines a limit on the number of scraped targets that will be accepted.
|
||||
format: int64
|
||||
type: integer
|
||||
required:
|
||||
- endpoints
|
||||
- selector
|
||||
type: object
|
||||
required:
|
||||
- spec
|
||||
type: object
|
||||
served: true
|
||||
storage: true
|
||||
status:
|
||||
acceptedNames:
|
||||
kind: ""
|
||||
plural: ""
|
||||
conditions: []
|
||||
storedVersions: []
|
||||
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,92 @@
|
||||
apiVersion: rbac.authorization.k8s.io/v1
|
||||
kind: ClusterRole
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: controller
|
||||
app.kubernetes.io/name: prometheus-operator
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 0.55.1
|
||||
name: kubesphere-prometheus-operator
|
||||
rules:
|
||||
- apiGroups:
|
||||
- monitoring.coreos.com
|
||||
resources:
|
||||
- alertmanagers
|
||||
- alertmanagers/finalizers
|
||||
- alertmanagerconfigs
|
||||
- prometheuses
|
||||
- prometheuses/finalizers
|
||||
- thanosrulers
|
||||
- thanosrulers/finalizers
|
||||
- servicemonitors
|
||||
- podmonitors
|
||||
- probes
|
||||
- prometheusrules
|
||||
verbs:
|
||||
- '*'
|
||||
- apiGroups:
|
||||
- apps
|
||||
resources:
|
||||
- statefulsets
|
||||
verbs:
|
||||
- '*'
|
||||
- apiGroups:
|
||||
- ""
|
||||
resources:
|
||||
- configmaps
|
||||
- secrets
|
||||
verbs:
|
||||
- '*'
|
||||
- apiGroups:
|
||||
- ""
|
||||
resources:
|
||||
- pods
|
||||
verbs:
|
||||
- list
|
||||
- delete
|
||||
- apiGroups:
|
||||
- ""
|
||||
resources:
|
||||
- services
|
||||
- services/finalizers
|
||||
- endpoints
|
||||
verbs:
|
||||
- get
|
||||
- create
|
||||
- update
|
||||
- delete
|
||||
- apiGroups:
|
||||
- ""
|
||||
resources:
|
||||
- nodes
|
||||
verbs:
|
||||
- list
|
||||
- watch
|
||||
- apiGroups:
|
||||
- ""
|
||||
resources:
|
||||
- namespaces
|
||||
verbs:
|
||||
- get
|
||||
- list
|
||||
- watch
|
||||
- apiGroups:
|
||||
- networking.k8s.io
|
||||
resources:
|
||||
- ingresses
|
||||
verbs:
|
||||
- get
|
||||
- list
|
||||
- watch
|
||||
- apiGroups:
|
||||
- authentication.k8s.io
|
||||
resources:
|
||||
- tokenreviews
|
||||
verbs:
|
||||
- create
|
||||
- apiGroups:
|
||||
- authorization.k8s.io
|
||||
resources:
|
||||
- subjectaccessreviews
|
||||
verbs:
|
||||
- create
|
||||
@@ -0,0 +1,17 @@
|
||||
apiVersion: rbac.authorization.k8s.io/v1
|
||||
kind: ClusterRoleBinding
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: controller
|
||||
app.kubernetes.io/name: prometheus-operator
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 0.55.1
|
||||
name: kubesphere-prometheus-operator
|
||||
roleRef:
|
||||
apiGroup: rbac.authorization.k8s.io
|
||||
kind: ClusterRole
|
||||
name: kubesphere-prometheus-operator
|
||||
subjects:
|
||||
- kind: ServiceAccount
|
||||
name: prometheus-operator
|
||||
namespace: kubesphere-monitoring-system
|
||||
@@ -0,0 +1,73 @@
|
||||
apiVersion: apps/v1
|
||||
kind: Deployment
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: controller
|
||||
app.kubernetes.io/name: prometheus-operator
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 0.55.1
|
||||
name: prometheus-operator
|
||||
namespace: kubesphere-monitoring-system
|
||||
spec:
|
||||
replicas: 1
|
||||
selector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/component: controller
|
||||
app.kubernetes.io/name: prometheus-operator
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
template:
|
||||
metadata:
|
||||
annotations:
|
||||
kubectl.kubernetes.io/default-container: prometheus-operator
|
||||
labels:
|
||||
app.kubernetes.io/component: controller
|
||||
app.kubernetes.io/name: prometheus-operator
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 0.55.1
|
||||
spec:
|
||||
containers:
|
||||
- args:
|
||||
- --kubelet-service=kube-system/kubelet
|
||||
- --prometheus-config-reloader=kubesphere/prometheus-config-reloader:v0.55.1
|
||||
image: kubesphere/prometheus-operator:v0.55.1
|
||||
name: prometheus-operator
|
||||
ports:
|
||||
- containerPort: 8080
|
||||
name: http
|
||||
resources:
|
||||
limits:
|
||||
cpu: 200m
|
||||
memory: 200Mi
|
||||
requests:
|
||||
cpu: 100m
|
||||
memory: 100Mi
|
||||
securityContext:
|
||||
allowPrivilegeEscalation: false
|
||||
- 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
|
||||
- --upstream=http://127.0.0.1:8080/
|
||||
image: bitnami/kube-rbac-proxy:0.19.0
|
||||
name: kube-rbac-proxy
|
||||
ports:
|
||||
- containerPort: 8443
|
||||
name: https
|
||||
resources:
|
||||
limits:
|
||||
cpu: "1"
|
||||
memory: 100Mi
|
||||
requests:
|
||||
cpu: 10m
|
||||
memory: 20Mi
|
||||
securityContext:
|
||||
runAsGroup: 65532
|
||||
runAsNonRoot: true
|
||||
runAsUser: 65532
|
||||
nodeSelector:
|
||||
kubernetes.io/os: linux
|
||||
affinity: {}
|
||||
securityContext:
|
||||
runAsNonRoot: true
|
||||
runAsUser: 65534
|
||||
serviceAccountName: prometheus-operator
|
||||
@@ -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: 0.55.1
|
||||
prometheus: k8s
|
||||
role: alert-rules
|
||||
name: prometheus-operator-rules
|
||||
namespace: kubesphere-monitoring-system
|
||||
spec:
|
||||
groups:
|
||||
- name: prometheus-operator
|
||||
rules:
|
||||
- alert: PrometheusOperatorListErrors
|
||||
annotations:
|
||||
description: Errors while performing List operations in controller {{$labels.controller}} in {{$labels.namespace}} namespace.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus-operator/prometheusoperatorlisterrors
|
||||
summary: Errors while performing list operations in controller.
|
||||
expr: |
|
||||
(sum by (controller,namespace) (rate(prometheus_operator_list_operations_failed_total{job="prometheus-operator",namespace="kubesphere-monitoring-system"}[10m])) / sum by (controller,namespace) (rate(prometheus_operator_list_operations_total{job="prometheus-operator",namespace="kubesphere-monitoring-system"}[10m]))) > 0.4
|
||||
for: 15m
|
||||
labels:
|
||||
severity: warning
|
||||
- alert: PrometheusOperatorWatchErrors
|
||||
annotations:
|
||||
description: Errors while performing watch operations in controller {{$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="kubesphere-monitoring-system"}[10m])) / sum by (controller,namespace) (rate(prometheus_operator_watch_operations_total{job="prometheus-operator",namespace="kubesphere-monitoring-system"}[10m]))) > 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="kubesphere-monitoring-system"}[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="kubesphere-monitoring-system"}[5m]))) / (sum by (controller,namespace) (rate(prometheus_operator_reconcile_operations_total{job="prometheus-operator",namespace="kubesphere-monitoring-system"}[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="kubesphere-monitoring-system"}[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(namespace, controller) (max_over_time(prometheus_operator_ready{job="prometheus-operator",namespace="kubesphere-monitoring-system"}[5m]) == 0)
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
- alert: PrometheusOperatorRejectedResources
|
||||
annotations:
|
||||
description: Prometheus operator in {{ $labels.namespace }} namespace rejected {{ printf "%0.0f" $value }} {{ $labels.controller }}/{{ $labels.resource }} resources.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus-operator/prometheusoperatorrejectedresources
|
||||
summary: Resources rejected by Prometheus operator
|
||||
expr: |
|
||||
min_over_time(prometheus_operator_managed_resources{state="rejected",job="prometheus-operator",namespace="kubesphere-monitoring-system"}[5m]) > 0
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
- name: config-reloaders
|
||||
rules:
|
||||
- alert: ConfigReloaderSidecarErrors
|
||||
annotations:
|
||||
description: |-
|
||||
Errors encountered while the {{$labels.pod}} config-reloader sidecar attempts to sync config in {{$labels.namespace}} namespace.
|
||||
As a result, configuration for service running in {{$labels.pod}} may be stale and cannot be updated anymore.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus-operator/configreloadersidecarerrors
|
||||
summary: config-reloader sidecar has not had a successful reload for 10m
|
||||
expr: |
|
||||
max_over_time(reloader_last_reload_successful{namespace=~".+"}[5m]) == 0
|
||||
for: 10m
|
||||
labels:
|
||||
severity: warning
|
||||
@@ -0,0 +1,20 @@
|
||||
apiVersion: v1
|
||||
kind: Service
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: controller
|
||||
app.kubernetes.io/name: prometheus-operator
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 0.55.1
|
||||
name: prometheus-operator
|
||||
namespace: kubesphere-monitoring-system
|
||||
spec:
|
||||
clusterIP: None
|
||||
ports:
|
||||
- name: https
|
||||
port: 8443
|
||||
targetPort: https
|
||||
selector:
|
||||
app.kubernetes.io/component: controller
|
||||
app.kubernetes.io/name: prometheus-operator
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
@@ -0,0 +1,10 @@
|
||||
apiVersion: v1
|
||||
kind: ServiceAccount
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: controller
|
||||
app.kubernetes.io/name: prometheus-operator
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 0.55.1
|
||||
name: prometheus-operator
|
||||
namespace: kubesphere-monitoring-system
|
||||
@@ -0,0 +1,26 @@
|
||||
apiVersion: monitoring.coreos.com/v1
|
||||
kind: ServiceMonitor
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: controller
|
||||
app.kubernetes.io/name: prometheus-operator
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/vendor: kubesphere
|
||||
app.kubernetes.io/version: 0.55.1
|
||||
name: prometheus-operator
|
||||
namespace: kubesphere-monitoring-system
|
||||
spec:
|
||||
endpoints:
|
||||
- bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token
|
||||
honorLabels: true
|
||||
interval: 1m
|
||||
port: https
|
||||
scheme: https
|
||||
tlsConfig:
|
||||
insecureSkipVerify: true
|
||||
selector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/component: controller
|
||||
app.kubernetes.io/name: prometheus-operator
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 0.55.1
|
||||
@@ -0,0 +1,44 @@
|
||||
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: 2.34.0
|
||||
name: kubesphere-prometheus-k8s
|
||||
namespace: kubesphere-monitoring-system
|
||||
rules:
|
||||
- apiGroups:
|
||||
- ""
|
||||
resources:
|
||||
- nodes/metrics
|
||||
- nodes
|
||||
- services
|
||||
- endpoints
|
||||
- pods
|
||||
verbs:
|
||||
- get
|
||||
- list
|
||||
- watch
|
||||
- apiGroups:
|
||||
- extensions
|
||||
resources:
|
||||
- ingresses
|
||||
verbs:
|
||||
- get
|
||||
- list
|
||||
- watch
|
||||
- apiGroups:
|
||||
- networking.k8s.io
|
||||
resources:
|
||||
- ingresses
|
||||
verbs:
|
||||
- get
|
||||
- list
|
||||
- watch
|
||||
- nonResourceURLs:
|
||||
- /metrics
|
||||
verbs:
|
||||
- get
|
||||
@@ -0,0 +1,19 @@
|
||||
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: 2.34.0
|
||||
name: kubesphere-prometheus-k8s
|
||||
namespace: kubesphere-monitoring-system
|
||||
roleRef:
|
||||
apiGroup: rbac.authorization.k8s.io
|
||||
kind: ClusterRole
|
||||
name: kubesphere-prometheus-k8s
|
||||
subjects:
|
||||
- kind: ServiceAccount
|
||||
name: prometheus-k8s
|
||||
namespace: kubesphere-monitoring-system
|
||||
@@ -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: 2.34.0
|
||||
name: prometheus-k8s
|
||||
namespace: kubesphere-monitoring-system
|
||||
spec:
|
||||
minAvailable: 1
|
||||
selector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/component: prometheus
|
||||
app.kubernetes.io/instance: k8s
|
||||
app.kubernetes.io/name: prometheus
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
@@ -0,0 +1,91 @@
|
||||
apiVersion: monitoring.coreos.com/v1
|
||||
kind: Prometheus
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: prometheus
|
||||
app.kubernetes.io/instance: k8s
|
||||
app.kubernetes.io/name: prometheus
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 2.34.0
|
||||
name: k8s
|
||||
namespace: kubesphere-monitoring-system
|
||||
spec:
|
||||
affinity:
|
||||
nodeAffinity:
|
||||
preferredDuringSchedulingIgnoredDuringExecution:
|
||||
- preference:
|
||||
matchExpressions:
|
||||
- key: node-role.kubernetes.io/monitoring
|
||||
operator: Exists
|
||||
weight: 100
|
||||
podAntiAffinity:
|
||||
preferredDuringSchedulingIgnoredDuringExecution:
|
||||
- podAffinityTerm:
|
||||
labelSelector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/component: prometheus
|
||||
app.kubernetes.io/instance: k8s
|
||||
app.kubernetes.io/name: prometheus
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
namespaces:
|
||||
- kubesphere-monitoring-system
|
||||
topologyKey: kubernetes.io/hostname
|
||||
weight: 100
|
||||
alerting:
|
||||
alertmanagers:
|
||||
- apiVersion: v2
|
||||
name: alertmanager-main
|
||||
namespace: kubesphere-monitoring-system
|
||||
port: web
|
||||
evaluationInterval: 1m
|
||||
externalLabels: {}
|
||||
image: prom/prometheus:v2.34.0
|
||||
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: 2.34.0
|
||||
tolerations:
|
||||
- effect: NoSchedule
|
||||
key: dedicated
|
||||
operator: Equal
|
||||
value: monitoring
|
||||
podMonitorNamespaceSelector: {}
|
||||
podMonitorSelector: {}
|
||||
probeNamespaceSelector: {}
|
||||
probeSelector: {}
|
||||
query:
|
||||
maxConcurrency: 1000
|
||||
replicas: 1 # todo
|
||||
resources:
|
||||
limits:
|
||||
cpu: "1"
|
||||
memory: 4Gi
|
||||
requests:
|
||||
cpu: 200m
|
||||
memory: 400Mi
|
||||
ruleNamespaceSelector: {}
|
||||
ruleSelector:
|
||||
matchLabels:
|
||||
prometheus: k8s
|
||||
role: alert-rules
|
||||
scrapeInterval: 1m
|
||||
securityContext:
|
||||
fsGroup: 0
|
||||
runAsNonRoot: false
|
||||
runAsUser: 0
|
||||
serviceAccountName: prometheus-k8s
|
||||
serviceMonitorNamespaceSelector: {}
|
||||
serviceMonitorSelector: {}
|
||||
retention: 7d
|
||||
storage:
|
||||
volumeClaimTemplate:
|
||||
spec:
|
||||
resources:
|
||||
requests:
|
||||
storage: 20Gi
|
||||
version: 2.34.0
|
||||
@@ -0,0 +1,258 @@
|
||||
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: 2.34.0
|
||||
prometheus: k8s
|
||||
role: alert-rules
|
||||
name: prometheus-k8s-prometheus-rules
|
||||
namespace: kubesphere-monitoring-system
|
||||
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="kubesphere-monitoring-system"}[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="kubesphere-monitoring-system"}[5m], 60 * 30)
|
||||
>
|
||||
min_over_time(prometheus_notifications_queue_capacity{job="prometheus-k8s",namespace="kubesphere-monitoring-system"}[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="kubesphere-monitoring-system"}[5m])
|
||||
/
|
||||
rate(prometheus_notifications_sent_total{job="prometheus-k8s",namespace="kubesphere-monitoring-system"}[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="kubesphere-monitoring-system"}[5m]) < 1
|
||||
for: 10m
|
||||
labels:
|
||||
severity: warning
|
||||
- alert: PrometheusTSDBReloadsFailing
|
||||
annotations:
|
||||
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has detected {{$value | humanize}} reload failures over the last 3h.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheustsdbreloadsfailing
|
||||
summary: Prometheus has issues reloading blocks from disk.
|
||||
expr: |
|
||||
increase(prometheus_tsdb_reloads_failures_total{job="prometheus-k8s",namespace="kubesphere-monitoring-system"}[3h]) > 0
|
||||
for: 4h
|
||||
labels:
|
||||
severity: warning
|
||||
- alert: PrometheusTSDBCompactionsFailing
|
||||
annotations:
|
||||
description: Prometheus {{$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="kubesphere-monitoring-system"}[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="kubesphere-monitoring-system"}[5m]) <= 0
|
||||
and
|
||||
(
|
||||
sum without(scrape_job) (prometheus_target_metadata_cache_entries{job="prometheus-k8s",namespace="kubesphere-monitoring-system"}) > 0
|
||||
or
|
||||
sum without(rule_group) (prometheus_rule_group_rules{job="prometheus-k8s",namespace="kubesphere-monitoring-system"}) > 0
|
||||
)
|
||||
)
|
||||
for: 10m
|
||||
labels:
|
||||
severity: warning
|
||||
- alert: PrometheusDuplicateTimestamps
|
||||
annotations:
|
||||
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} is dropping {{ printf "%.4g" $value }} samples/s with different values but duplicated timestamp.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusduplicatetimestamps
|
||||
summary: Prometheus is dropping samples with duplicate timestamps.
|
||||
expr: |
|
||||
rate(prometheus_target_scrapes_sample_duplicate_timestamp_total{job="prometheus-k8s",namespace="kubesphere-monitoring-system"}[5m]) > 0
|
||||
for: 10m
|
||||
labels:
|
||||
severity: warning
|
||||
- alert: PrometheusOutOfOrderTimestamps
|
||||
annotations:
|
||||
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} is dropping {{ printf "%.4g" $value }} samples/s with timestamps arriving out of order.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusoutofordertimestamps
|
||||
summary: Prometheus drops samples with out-of-order timestamps.
|
||||
expr: |
|
||||
rate(prometheus_target_scrapes_sample_out_of_order_total{job="prometheus-k8s",namespace="kubesphere-monitoring-system"}[5m]) > 0
|
||||
for: 10m
|
||||
labels:
|
||||
severity: warning
|
||||
- alert: PrometheusRemoteStorageFailures
|
||||
annotations:
|
||||
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} failed to send {{ printf "%.1f" $value }}% of the samples to {{ $labels.remote_name}}:{{ $labels.url }}
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusremotestoragefailures
|
||||
summary: Prometheus fails to send samples to remote storage.
|
||||
expr: |
|
||||
(
|
||||
(rate(prometheus_remote_storage_failed_samples_total{job="prometheus-k8s",namespace="kubesphere-monitoring-system"}[5m]) or rate(prometheus_remote_storage_samples_failed_total{job="prometheus-k8s",namespace="kubesphere-monitoring-system"}[5m]))
|
||||
/
|
||||
(
|
||||
(rate(prometheus_remote_storage_failed_samples_total{job="prometheus-k8s",namespace="kubesphere-monitoring-system"}[5m]) or rate(prometheus_remote_storage_samples_failed_total{job="prometheus-k8s",namespace="kubesphere-monitoring-system"}[5m]))
|
||||
+
|
||||
(rate(prometheus_remote_storage_succeeded_samples_total{job="prometheus-k8s",namespace="kubesphere-monitoring-system"}[5m]) or rate(prometheus_remote_storage_samples_total{job="prometheus-k8s",namespace="kubesphere-monitoring-system"}[5m]))
|
||||
)
|
||||
)
|
||||
* 100
|
||||
> 1
|
||||
for: 15m
|
||||
labels:
|
||||
severity: critical
|
||||
- alert: PrometheusRemoteWriteBehind
|
||||
annotations:
|
||||
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} remote write is {{ printf "%.1f" $value }}s behind for {{ $labels.remote_name}}:{{ $labels.url }}.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusremotewritebehind
|
||||
summary: Prometheus remote write is behind.
|
||||
expr: |
|
||||
# Without max_over_time, failed scrapes could create false negatives, see
|
||||
# https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.
|
||||
(
|
||||
max_over_time(prometheus_remote_storage_highest_timestamp_in_seconds{job="prometheus-k8s",namespace="kubesphere-monitoring-system"}[5m])
|
||||
- ignoring(remote_name, url) group_right
|
||||
max_over_time(prometheus_remote_storage_queue_highest_sent_timestamp_seconds{job="prometheus-k8s",namespace="kubesphere-monitoring-system"}[5m])
|
||||
)
|
||||
> 120
|
||||
for: 15m
|
||||
labels:
|
||||
severity: critical
|
||||
- alert: PrometheusRemoteWriteDesiredShards
|
||||
annotations:
|
||||
description: Prometheus {{$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="kubesphere-monitoring-system"}` $labels.instance | query | first | value }}.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusremotewritedesiredshards
|
||||
summary: Prometheus remote write desired shards calculation wants to run more than configured max shards.
|
||||
expr: |
|
||||
# Without max_over_time, failed scrapes could create false negatives, see
|
||||
# https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.
|
||||
(
|
||||
max_over_time(prometheus_remote_storage_shards_desired{job="prometheus-k8s",namespace="kubesphere-monitoring-system"}[5m])
|
||||
>
|
||||
max_over_time(prometheus_remote_storage_shards_max{job="prometheus-k8s",namespace="kubesphere-monitoring-system"}[5m])
|
||||
)
|
||||
for: 15m
|
||||
labels:
|
||||
severity: warning
|
||||
- alert: PrometheusRuleFailures
|
||||
annotations:
|
||||
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has failed to evaluate {{ printf "%.0f" $value }} rules in the last 5m.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusrulefailures
|
||||
summary: Prometheus is failing rule evaluations.
|
||||
expr: |
|
||||
increase(prometheus_rule_evaluation_failures_total{job="prometheus-k8s",namespace="kubesphere-monitoring-system"}[5m]) > 0
|
||||
for: 15m
|
||||
labels:
|
||||
severity: critical
|
||||
- alert: PrometheusMissingRuleEvaluations
|
||||
annotations:
|
||||
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has missed {{ printf "%.0f" $value }} rule group evaluations in the last 5m.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusmissingruleevaluations
|
||||
summary: Prometheus is missing rule evaluations due to slow rule group evaluation.
|
||||
expr: |
|
||||
increase(prometheus_rule_group_iterations_missed_total{job="prometheus-k8s",namespace="kubesphere-monitoring-system"}[5m]) > 0
|
||||
for: 15m
|
||||
labels:
|
||||
severity: warning
|
||||
- alert: PrometheusTargetLimitHit
|
||||
annotations:
|
||||
description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has dropped {{ printf "%.0f" $value }} targets because the number of targets exceeded the configured target_limit.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheustargetlimithit
|
||||
summary: Prometheus has dropped targets because some scrape configs have exceeded the targets limit.
|
||||
expr: |
|
||||
increase(prometheus_target_scrape_pool_exceeded_target_limit_total{job="prometheus-k8s",namespace="kubesphere-monitoring-system"}[5m]) > 0
|
||||
for: 15m
|
||||
labels:
|
||||
severity: warning
|
||||
- alert: PrometheusLabelLimitHit
|
||||
annotations:
|
||||
description: Prometheus {{$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="kubesphere-monitoring-system"}[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="kubesphere-monitoring-system"}[30m]) > 0
|
||||
for: 5m
|
||||
labels:
|
||||
severity: critical
|
||||
- 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="kubesphere-monitoring-system",alertmanager!~``}[5m])
|
||||
/
|
||||
rate(prometheus_notifications_sent_total{job="prometheus-k8s",namespace="kubesphere-monitoring-system",alertmanager!~``}[5m])
|
||||
)
|
||||
* 100
|
||||
> 3
|
||||
for: 15m
|
||||
labels:
|
||||
severity: critical
|
||||
- name: prometheus.rules
|
||||
rules:
|
||||
- expr: |
|
||||
sum(up{job="prometheus-k8s",namespace="kubesphere-monitoring-system"} == 1)
|
||||
record: prometheus:up:sum
|
||||
- expr: |
|
||||
sum(rate(prometheus_tsdb_head_samples_appended_total{job="prometheus-k8s",namespace="kubesphere-monitoring-system"} [5m])) by (job, pod)
|
||||
record: prometheus:prometheus_tsdb_head_samples_appended:sum_rate
|
||||
@@ -0,0 +1,19 @@
|
||||
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: 2.34.0
|
||||
name: prometheus-k8s-config
|
||||
namespace: kubesphere-monitoring-system
|
||||
roleRef:
|
||||
apiGroup: rbac.authorization.k8s.io
|
||||
kind: Role
|
||||
name: prometheus-k8s-config
|
||||
subjects:
|
||||
- kind: ServiceAccount
|
||||
name: prometheus-k8s
|
||||
namespace: kubesphere-monitoring-system
|
||||
@@ -0,0 +1,18 @@
|
||||
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: 2.34.0
|
||||
name: prometheus-k8s-config
|
||||
namespace: kubesphere-monitoring-system
|
||||
rules:
|
||||
- apiGroups:
|
||||
- ""
|
||||
resources:
|
||||
- configmaps
|
||||
verbs:
|
||||
- get
|
||||
@@ -0,0 +1,25 @@
|
||||
apiVersion: v1
|
||||
kind: Service
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: prometheus
|
||||
app.kubernetes.io/instance: k8s
|
||||
app.kubernetes.io/name: prometheus
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/version: 2.34.0
|
||||
name: prometheus-k8s
|
||||
namespace: kubesphere-monitoring-system
|
||||
spec:
|
||||
ports:
|
||||
- name: web
|
||||
port: 9090
|
||||
targetPort: web
|
||||
- name: reloader-web
|
||||
port: 8080
|
||||
targetPort: reloader-web
|
||||
selector:
|
||||
app.kubernetes.io/component: prometheus
|
||||
app.kubernetes.io/instance: k8s
|
||||
app.kubernetes.io/name: prometheus
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
sessionAffinity: ClientIP
|
||||
@@ -0,0 +1,11 @@
|
||||
apiVersion: v1
|
||||
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: 2.34.0
|
||||
name: prometheus-k8s
|
||||
namespace: kubesphere-monitoring-system
|
||||
@@ -0,0 +1,24 @@
|
||||
apiVersion: monitoring.coreos.com/v1
|
||||
kind: ServiceMonitor
|
||||
metadata:
|
||||
labels:
|
||||
app.kubernetes.io/component: prometheus
|
||||
app.kubernetes.io/instance: k8s
|
||||
app.kubernetes.io/name: prometheus
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
app.kubernetes.io/vendor: kubesphere
|
||||
app.kubernetes.io/version: 2.34.0
|
||||
name: prometheus-k8s
|
||||
namespace: kubesphere-monitoring-system
|
||||
spec:
|
||||
endpoints:
|
||||
- interval: 1m
|
||||
port: web
|
||||
- interval: 1m
|
||||
port: reloader-web
|
||||
selector:
|
||||
matchLabels:
|
||||
app.kubernetes.io/component: prometheus
|
||||
app.kubernetes.io/instance: k8s
|
||||
app.kubernetes.io/name: prometheus
|
||||
app.kubernetes.io/part-of: kube-prometheus
|
||||
Reference in New Issue
Block a user