cluster monitoring components

Author: marcel-dempers

prometheus-monitoring/kubernetes/1.14.8/grafana/grafana.dashboards.configmap.yaml

@@ -0,0 +1,15 @@
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRoleBinding
+metadata:
+  labels:
+    app.kubernetes.io/name: kube-state-metrics
+    app.kubernetes.io/version: v1.8.0
+  name: kube-state-metrics
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: ClusterRole
+  name: kube-state-metrics
+subjects:
+- kind: ServiceAccount
+  name: kube-state-metrics
+  namespace: monitoring

prometheus-monitoring/kubernetes/1.14.8/kube-state-metrics/cluster-role-binding.yaml

@@ -0,0 +1,110 @@
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRole
+metadata:
+  labels:
+    app.kubernetes.io/name: kube-state-metrics
+    app.kubernetes.io/version: v1.8.0
+  name: kube-state-metrics
+rules:
+- apiGroups:
+  - ""
+  resources:
+  - configmaps
+  - secrets
+  - nodes
+  - pods
+  - services
+  - resourcequotas
+  - replicationcontrollers
+  - limitranges
+  - persistentvolumeclaims
+  - persistentvolumes
+  - namespaces
+  - endpoints
+  verbs:
+  - list
+  - watch
+- apiGroups:
+  - extensions
+  resources:
+  - daemonsets
+  - deployments
+  - replicasets
+  - ingresses
+  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
+  verbs:
+  - list
+  - watch

prometheus-monitoring/kubernetes/1.14.8/kube-state-metrics/cluster-role.yaml

@@ -0,0 +1,42 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  labels:
+    k8s-app: kube-state-metrics
+    app.kubernetes.io/name: kube-state-metrics
+    app.kubernetes.io/version: v1.8.0
+  name: kube-state-metrics
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app.kubernetes.io/name: kube-state-metrics
+  template:
+    metadata:
+      labels:
+        app.kubernetes.io/name: kube-state-metrics
+        app.kubernetes.io/version: v1.8.0
+    spec:
+      containers:
+      - image: quay.io/coreos/kube-state-metrics:v1.8.0
+        livenessProbe:
+          httpGet:
+            path: /healthz
+            port: 8080
+          initialDelaySeconds: 5
+          timeoutSeconds: 5
+        name: kube-state-metrics
+        ports:
+        - containerPort: 8080
+          name: http-metrics
+        - containerPort: 8081
+          name: telemetry
+        readinessProbe:
+          httpGet:
+            path: /
+            port: 8081
+          initialDelaySeconds: 5
+          timeoutSeconds: 5
+      nodeSelector:
+        kubernetes.io/os: linux
+      serviceAccountName: kube-state-metrics

prometheus-monitoring/kubernetes/1.14.8/kube-state-metrics/deployment.yaml

@@ -0,0 +1,7 @@
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  labels:
+    app.kubernetes.io/name: kube-state-metrics
+    app.kubernetes.io/version: v1.8.0
+  name: kube-state-metrics

prometheus-monitoring/kubernetes/1.14.8/kube-state-metrics/service-account.yaml

@@ -0,0 +1,22 @@
+apiVersion: monitoring.coreos.com/v1
+kind: ServiceMonitor
+metadata:
+  name: kube-state-metrics
+  labels:
+    prometheus: cluster-monitoring
+    k8s-app: kube-state-metrics
+spec:
+  targetLabels:
+  - cluster
+  jobLabel: kube-state-metrics
+  selector:
+    matchLabels:
+      k8s-app: kube-state-metrics
+  namespaceSelector:
+    matchNames:
+    - monitoring
+  endpoints:
+  - port: http-metrics
+    honorLabels: true
+    scheme: http
+    interval: 60s

prometheus-monitoring/kubernetes/1.14.8/kube-state-metrics/service-monitor.yaml

@@ -0,0 +1,20 @@
+apiVersion: v1
+kind: Service
+metadata:
+  labels:
+    app.kubernetes.io/name: kube-state-metrics
+    app.kubernetes.io/version: v1.8.0
+    k8s-app: kube-state-metrics
+    cluster: docker-for-desktop
+  name: kube-state-metrics
+spec:
+  clusterIP: None
+  ports:
+  - name: http-metrics
+    port: 8080
+    targetPort: http-metrics
+  - name: telemetry
+    port: 8081
+    targetPort: telemetry
+  selector:
+    app.kubernetes.io/name: kube-state-metrics

prometheus-monitoring/kubernetes/1.14.8/kube-state-metrics/service.yaml

@@ -0,0 +1,24 @@
+apiVersion: monitoring.coreos.com/v1
+kind: ServiceMonitor
+metadata:
+  name: kube-apiserver
+  labels:
+    prometheus: cluster-monitoring
+    k8s-app: apiserver
+spec:
+  jobLabel: component
+  selector:
+    matchLabels:
+      component: apiserver
+      provider: kubernetes
+  namespaceSelector:
+    matchNames:
+    - default
+  endpoints:
+  - port: https
+    interval: 60s
+    scheme: https
+    tlsConfig:
+      caFile: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
+      serverName: kubernetes
+    bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token

prometheus-monitoring/kubernetes/1.14.8/prometheus-cluster-monitoring/apiserver.servicemonitor.yaml

@@ -0,0 +1,77 @@
+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

prometheus-monitoring/kubernetes/1.14.8/prometheus-cluster-monitoring/kubelet.servicemonitor.yaml

@@ -16,16 +16,6 @@ spec:
       operator: In
       values:
       - apps
-  #     - kube-state-metrics
-  #     - apiserver
-  #     - kubelet
-  # ruleSelector:
-  #   matchLabels:
-  #     role: alert-rules
-  #     prometheus: k8s
-  # resources:
-  #   requests:
-  #     memory: 400Mi
 ---
 apiVersion: v1
 kind: ServiceAccount