Kube-Prometheus监控指标

0.环境准备

Kubernetes-v1.17.4部署kube-prometheus-v0.5.0
离线搭建Kubernetes-v1.17.4集群及kube-prometheus监控

1.monitoring/alertmanager/0 (3/3 up)

manifests/alertmanager-serviceMonitor.yaml

apiVersion: monitoring.coreos.com/v1
kind: ServiceMonitor
metadata:
  labels:
    k8s-app: alertmanager
  name: alertmanager
  namespace: monitoring
spec:
  endpoints:
  - interval: 30s
    port: web
  selector:
    matchLabels:
      alertmanager: main

2.monitoring/coredns/0 (2/2 up)

manifests/prometheus-serviceMonitorCoreDNS.yaml

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

3.monitoring/grafana/0 (1/1 up)

manifests/grafana-serviceMonitor.yaml

apiVersion: monitoring.coreos.com/v1
kind: ServiceMonitor
metadata:
  name: grafana
  namespace: monitoring
spec:
  endpoints:
  - interval: 15s
    port: http
  selector:
    matchLabels:
      app: grafana

4.monitoring/kube-apiserver/0 (1/1 up)

4.1 manifests/prometheus-serviceMonitorApiserver.yaml

apiVersion: monitoring.coreos.com/v1
kind: ServiceMonitor
metadata:
  labels:
    k8s-app: apiserver
  name: kube-apiserver
  namespace: monitoring
spec:
  endpoints:
  - bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token
    interval: 30s
    metricRelabelings:
    - action: drop
      regex: kubelet_(pod_worker_latency_microseconds|pod_start_latency_microseconds|cgroup_manager_latency_microseconds|pod_worker_start_latency_microseconds|pleg_relist_latency_microseconds|pleg_relist_interval_microseconds|runtime_operations|runtime_operations_latency_microseconds|runtime_operations_errors|eviction_stats_age_microseconds|device_plugin_registration_count|device_plugin_alloc_latency_microseconds|network_plugin_operations_latency_microseconds)
      sourceLabels:
      - __name__
    - action: drop
      regex: scheduler_(e2e_scheduling_latency_microseconds|scheduling_algorithm_predicate_evaluation|scheduling_algorithm_priority_evaluation|scheduling_algorithm_preemption_evaluation|scheduling_algorithm_latency_microseconds|binding_latency_microseconds|scheduling_latency_seconds)
      sourceLabels:
      - __name__
    - action: drop
      regex: apiserver_(request_count|request_latencies|request_latencies_summary|dropped_requests|storage_data_key_generation_latencies_microseconds|storage_transformation_failures_total|storage_transformation_latencies_microseconds|proxy_tunnel_sync_latency_secs)
      sourceLabels:
      - __name__
    - action: drop
      regex: kubelet_docker_(operations|operations_latency_microseconds|operations_errors|operations_timeout)
      sourceLabels:
      - __name__
    - action: drop
      regex: reflector_(items_per_list|items_per_watch|list_duration_seconds|lists_total|short_watches_total|watch_duration_seconds|watches_total)
      sourceLabels:
      - __name__
    - action: drop
      regex: etcd_(helper_cache_hit_count|helper_cache_miss_count|helper_cache_entry_count|request_cache_get_latencies_summary|request_cache_add_latencies_summary|request_latencies_summary)
      sourceLabels:
      - __name__
    - action: drop
      regex: transformation_(transformation_latencies_microseconds|failures_total)
      sourceLabels:
      - __name__
    - action: drop
      regex: (admission_quota_controller_adds|crd_autoregistration_controller_work_duration|APIServiceOpenAPIAggregationControllerQueue1_adds|AvailableConditionController_retries|crd_openapi_controller_unfinished_work_seconds|APIServiceRegistrationController_retries|admission_quota_controller_longest_running_processor_microseconds|crdEstablishing_longest_running_processor_microseconds|crdEstablishing_unfinished_work_seconds|crd_openapi_controller_adds|crd_autoregistration_controller_retries|crd_finalizer_queue_latency|AvailableConditionController_work_duration|non_structural_schema_condition_controller_depth|crd_autoregistration_controller_unfinished_work_seconds|AvailableConditionController_adds|DiscoveryController_longest_running_processor_microseconds|autoregister_queue_latency|crd_autoregistration_controller_adds|non_structural_schema_condition_controller_work_duration|APIServiceRegistrationController_adds|crd_finalizer_work_duration|crd_naming_condition_controller_unfinished_work_seconds|crd_openapi_controller_longest_running_processor_microseconds|DiscoveryController_adds|crd_autoregistration_controller_longest_running_processor_microseconds|autoregister_unfinished_work_seconds|crd_naming_condition_controller_queue_latency|crd_naming_condition_controller_retries|non_structural_schema_condition_controller_queue_latency|crd_naming_condition_controller_depth|AvailableConditionController_longest_running_processor_microseconds|crdEstablishing_depth|crd_finalizer_longest_running_processor_microseconds|crd_naming_condition_controller_adds|APIServiceOpenAPIAggregationControllerQueue1_longest_running_processor_microseconds|DiscoveryController_queue_latency|DiscoveryController_unfinished_work_seconds|crd_openapi_controller_depth|APIServiceOpenAPIAggregationControllerQueue1_queue_latency|APIServiceOpenAPIAggregationControllerQueue1_unfinished_work_seconds|DiscoveryController_work_duration|autoregister_adds|crd_autoregistration_controller_queue_latency|crd_finalizer_retries|AvailableConditionController_unfinished_work_seconds|autoregister_longest_running_processor_microseconds|non_structural_schema_condition_controller_unfinished_work_seconds|APIServiceOpenAPIAggregationControllerQueue1_depth|AvailableConditionController_depth|DiscoveryController_retries|admission_quota_controller_depth|crdEstablishing_adds|APIServiceOpenAPIAggregationControllerQueue1_retries|crdEstablishing_queue_latency|non_structural_schema_condition_controller_longest_running_processor_microseconds|autoregister_work_duration|crd_openapi_controller_retries|APIServiceRegistrationController_work_duration|crdEstablishing_work_duration|crd_finalizer_adds|crd_finalizer_depth|crd_openapi_controller_queue_latency|APIServiceOpenAPIAggregationControllerQueue1_work_duration|APIServiceRegistrationController_queue_latency|crd_autoregistration_controller_depth|AvailableConditionController_queue_latency|admission_quota_controller_queue_latency|crd_naming_condition_controller_work_duration|crd_openapi_controller_work_duration|DiscoveryController_depth|crd_naming_condition_controller_longest_running_processor_microseconds|APIServiceRegistrationController_depth|APIServiceRegistrationController_longest_running_processor_microseconds|crd_finalizer_unfinished_work_seconds|crdEstablishing_retries|admission_quota_controller_unfinished_work_seconds|non_structural_schema_condition_controller_adds|APIServiceRegistrationController_unfinished_work_seconds|admission_quota_controller_work_duration|autoregister_depth|autoregister_retries|kubeproxy_sync_proxy_rules_latency_microseconds|rest_client_request_latency_seconds|non_structural_schema_condition_controller_retries)
      sourceLabels:
      - __name__
    - action: drop
      regex: etcd_(debugging|disk|request|server).*
      sourceLabels:
      - __name__
    - action: drop
      regex: apiserver_admission_controller_admission_latencies_seconds_.*
      sourceLabels:
      - __name__
    - action: drop
      regex: apiserver_admission_step_admission_latencies_seconds_.*
      sourceLabels:
      - __name__
    - action: drop
      regex: apiserver_request_duration_seconds_bucket;(0.15|0.25|0.3|0.35|0.4|0.45|0.6|0.7|0.8|0.9|1.25|1.5|1.75|2.5|3|3.5|4.5|6|7|8|9|15|25|30|50)
      sourceLabels:
      - __name__
      - le
    port: https
    scheme: https
    tlsConfig:
      caFile: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
      serverName: kubernetes
  jobLabel: component
  namespaceSelector:
    matchNames:
    - default
  selector:
    matchLabels:
      component: apiserver
      provider: kubernetes

4.2 Grafana - Default/Kubernetes/API server

5.monitoring/kube-controller-manager/0 (1/1 up)

5.1 manifests/prometheus-kubeControllerManagerService.yaml

apiVersion: v1
kind: Service
metadata:
  namespace: kube-system
  name: kube-controller-manager
  labels:
    k8s-app: kube-controller-manager
spec:
  selector:
    component: kube-controller-manager
  type: ClusterIP
  clusterIP: None
  ports:
  - name: http-metrics
    port: 10252
    targetPort: 10252
    protocol: TCP
---
apiVersion: v1
kind: Endpoints
metadata:
  labels:
    k8s-app: kube-controller-manager
  name: kube-controller-manager
  namespace: kube-system
subsets:
- addresses:
  - ip: 10.180.249.245
  ports:
  - name: http-metrics
    port: 10252
    protocol: TCP

5.2 Grafana - Default/Kubernetes/Controller Manager

6.monitoring/kube-scheduler/0 (1/1 up)

6.1 manifests/prometheus-kubeSchedulerService.yaml

kind: Service
metadata:
  namespace: kube-system
  name: kube-scheduler
  labels:
    k8s-app: kube-scheduler
spec:
  type: ClusterIP
  clusterIP: None
  ports:
  - name: port
    port: 10251
    protocol: TCP
---
apiVersion: v1
kind: Endpoints
metadata:
  labels:
    k8s-app: kube-scheduler
  name: kube-scheduler
  namespace: kube-system
subsets:
- addresses:
  - ip: 10.180.249.245
  ports:
  - name: http-metrics
    port: 10251
    protocol: TCP

6.2 Grafana - Default/Kubernetes/Scheduler

7.monitoring/kube-state-metrics/0 (1/1 up)

manifests/kube-state-metrics-serviceMonitor.yaml

apiVersion: monitoring.coreos.com/v1
kind: ServiceMonitor
metadata:
  labels:
    app.kubernetes.io/name: kube-state-metrics
    app.kubernetes.io/version: 1.9.5
  name: kube-state-metrics
  namespace: monitoring
spec:
  endpoints:
  - bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token
    honorLabels: true
    interval: 30s
    port: https-main
    relabelings:
    - action: labeldrop
      regex: (pod|service|endpoint|namespace)
    scheme: https
    scrapeTimeout: 30s
    tlsConfig:
      insecureSkipVerify: true
  - bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token
    interval: 30s
    port: https-self
    scheme: https
    tlsConfig:
      insecureSkipVerify: true
  jobLabel: app.kubernetes.io/name
  selector:
    matchLabels:
      app.kubernetes.io/name: kube-state-metrics

8.monitoring/kubelet/0 (3/3 up)

8.1 manifests/prometheus-serviceMonitorKubelet.yaml

apiVersion: monitoring.coreos.com/v1
kind: ServiceMonitor
metadata:
  labels:
    k8s-app: kubelet
  name: kubelet
  namespace: monitoring
spec:
  endpoints:
  - bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token
    honorLabels: true
    interval: 30s
    metricRelabelings:
    - action: drop
      regex: kubelet_(pod_worker_latency_microseconds|pod_start_latency_microseconds|cgroup_manager_latency_microseconds|pod_worker_start_latency_microseconds|pleg_relist_latency_microseconds|pleg_relist_interval_microseconds|runtime_operations|runtime_operations_latency_microseconds|runtime_operations_errors|eviction_stats_age_microseconds|device_plugin_registration_count|device_plugin_alloc_latency_microseconds|network_plugin_operations_latency_microseconds)
      sourceLabels:
      - __name__
    - action: drop
      regex: scheduler_(e2e_scheduling_latency_microseconds|scheduling_algorithm_predicate_evaluation|scheduling_algorithm_priority_evaluation|scheduling_algorithm_preemption_evaluation|scheduling_algorithm_latency_microseconds|binding_latency_microseconds|scheduling_latency_seconds)
      sourceLabels:
      - __name__
    - action: drop
      regex: apiserver_(request_count|request_latencies|request_latencies_summary|dropped_requests|storage_data_key_generation_latencies_microseconds|storage_transformation_failures_total|storage_transformation_latencies_microseconds|proxy_tunnel_sync_latency_secs)
      sourceLabels:
      - __name__
    - action: drop
      regex: kubelet_docker_(operations|operations_latency_microseconds|operations_errors|operations_timeout)
      sourceLabels:
      - __name__
    - action: drop
      regex: reflector_(items_per_list|items_per_watch|list_duration_seconds|lists_total|short_watches_total|watch_duration_seconds|watches_total)
      sourceLabels:
      - __name__
    - action: drop
      regex: etcd_(helper_cache_hit_count|helper_cache_miss_count|helper_cache_entry_count|request_cache_get_latencies_summary|request_cache_add_latencies_summary|request_latencies_summary)
      sourceLabels:
      - __name__
    - action: drop
      regex: transformation_(transformation_latencies_microseconds|failures_total)
      sourceLabels:
      - __name__
    - action: drop
      regex: (admission_quota_controller_adds|crd_autoregistration_controller_work_duration|APIServiceOpenAPIAggregationControllerQueue1_adds|AvailableConditionController_retries|crd_openapi_controller_unfinished_work_seconds|APIServiceRegistrationController_retries|admission_quota_controller_longest_running_processor_microseconds|crdEstablishing_longest_running_processor_microseconds|crdEstablishing_unfinished_work_seconds|crd_openapi_controller_adds|crd_autoregistration_controller_retries|crd_finalizer_queue_latency|AvailableConditionController_work_duration|non_structural_schema_condition_controller_depth|crd_autoregistration_controller_unfinished_work_seconds|AvailableConditionController_adds|DiscoveryController_longest_running_processor_microseconds|autoregister_queue_latency|crd_autoregistration_controller_adds|non_structural_schema_condition_controller_work_duration|APIServiceRegistrationController_adds|crd_finalizer_work_duration|crd_naming_condition_controller_unfinished_work_seconds|crd_openapi_controller_longest_running_processor_microseconds|DiscoveryController_adds|crd_autoregistration_controller_longest_running_processor_microseconds|autoregister_unfinished_work_seconds|crd_naming_condition_controller_queue_latency|crd_naming_condition_controller_retries|non_structural_schema_condition_controller_queue_latency|crd_naming_condition_controller_depth|AvailableConditionController_longest_running_processor_microseconds|crdEstablishing_depth|crd_finalizer_longest_running_processor_microseconds|crd_naming_condition_controller_adds|APIServiceOpenAPIAggregationControllerQueue1_longest_running_processor_microseconds|DiscoveryController_queue_latency|DiscoveryController_unfinished_work_seconds|crd_openapi_controller_depth|APIServiceOpenAPIAggregationControllerQueue1_queue_latency|APIServiceOpenAPIAggregationControllerQueue1_unfinished_work_seconds|DiscoveryController_work_duration|autoregister_adds|crd_autoregistration_controller_queue_latency|crd_finalizer_retries|AvailableConditionController_unfinished_work_seconds|autoregister_longest_running_processor_microseconds|non_structural_schema_condition_controller_unfinished_work_seconds|APIServiceOpenAPIAggregationControllerQueue1_depth|AvailableConditionController_depth|DiscoveryController_retries|admission_quota_controller_depth|crdEstablishing_adds|APIServiceOpenAPIAggregationControllerQueue1_retries|crdEstablishing_queue_latency|non_structural_schema_condition_controller_longest_running_processor_microseconds|autoregister_work_duration|crd_openapi_controller_retries|APIServiceRegistrationController_work_duration|crdEstablishing_work_duration|crd_finalizer_adds|crd_finalizer_depth|crd_openapi_controller_queue_latency|APIServiceOpenAPIAggregationControllerQueue1_work_duration|APIServiceRegistrationController_queue_latency|crd_autoregistration_controller_depth|AvailableConditionController_queue_latency|admission_quota_controller_queue_latency|crd_naming_condition_controller_work_duration|crd_openapi_controller_work_duration|DiscoveryController_depth|crd_naming_condition_controller_longest_running_processor_microseconds|APIServiceRegistrationController_depth|APIServiceRegistrationController_longest_running_processor_microseconds|crd_finalizer_unfinished_work_seconds|crdEstablishing_retries|admission_quota_controller_unfinished_work_seconds|non_structural_schema_condition_controller_adds|APIServiceRegistrationController_unfinished_work_seconds|admission_quota_controller_work_duration|autoregister_depth|autoregister_retries|kubeproxy_sync_proxy_rules_latency_microseconds|rest_client_request_latency_seconds|non_structural_schema_condition_controller_retries)
      sourceLabels:
      - __name__
    port: https-metrics
    relabelings:
    - sourceLabels:
      - __metrics_path__
      targetLabel: metrics_path
    scheme: https
    tlsConfig:
      insecureSkipVerify: true
  - bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token
    honorLabels: true
    interval: 30s
    metricRelabelings:
    - action: drop
      regex: container_(network_tcp_usage_total|network_udp_usage_total|tasks_state|cpu_load_average_10s)
      sourceLabels:
      - __name__
    path: /metrics/cadvisor
    port: https-metrics
    relabelings:
    - sourceLabels:
      - __metrics_path__
      targetLabel: metrics_path
    scheme: https
    tlsConfig:
      insecureSkipVerify: true
  jobLabel: k8s-app
  namespaceSelector:
    matchNames:
    - kube-system
  selector:
    matchLabels:
      k8s-app: kubelet

8.2 Grafana - Default/Kubernetes/Kubelet

9.monitoring/node-exporter/0 (3/3 up)

manifests/node-exporter-serviceMonitor.yaml

apiVersion: monitoring.coreos.com/v1
kind: ServiceMonitor
metadata:
  labels:
    app.kubernetes.io/name: node-exporter
    app.kubernetes.io/version: v0.18.1
  name: node-exporter
  namespace: monitoring
spec:
  endpoints:
  - bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token
    interval: 15s
    port: https
    relabelings:
    - action: replace
      regex: (.*)
      replacement: $1
      sourceLabels:
      - __meta_kubernetes_pod_node_name
      targetLabel: instance
    scheme: https
    tlsConfig:
      insecureSkipVerify: true
  jobLabel: app.kubernetes.io/name
  selector:
    matchLabels:
      app.kubernetes.io/name: node-exporter
      app.kubernetes.io/version: v0.18.1

10.monitoring/prometheus-operator/0 (1/1 up)

manifests/prometheus-operator-serviceMonitor.yaml

apiVersion: monitoring.coreos.com/v1
kind: ServiceMonitor
metadata:
  labels:
    app.kubernetes.io/component: controller
    app.kubernetes.io/name: prometheus-operator
    app.kubernetes.io/version: v0.38.1
  name: prometheus-operator
  namespace: monitoring
spec:
  endpoints:
  - bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token
    honorLabels: true
    port: https
    scheme: https
    tlsConfig:
      insecureSkipVerify: true
  selector:
    matchLabels:
      app.kubernetes.io/component: controller
      app.kubernetes.io/name: prometheus-operator
      app.kubernetes.io/version: v0.38.1

11.monitoring/prometheus/0 (2/2 up)

11.1 manifests/prometheus-serviceMonitor.yaml

apiVersion: monitoring.coreos.com/v1
kind: ServiceMonitor
metadata:
  labels:
    k8s-app: prometheus
  name: prometheus
  namespace: monitoring
spec:
  endpoints:
  - interval: 30s
    port: web
  selector:
    matchLabels:
      prometheus: k8s

11.2 Grafana - Default/Prometheus