kubernetes 监控grafana prometheus node-exporter
kubernetes 监控grafana prometheus node-exporter
#kubernetes 监控grafana prometheus node-exporter #!/bin/bash #git clone https://github.com/kubernetes/kubernetes.git ###安装git，并下载相关yaml文件 #git clone https://github.com/redhatxl/k8s-prometheus-grafana.git docker pull prom/node-exporter docker pull prom/prometheus:v2.0.0 docker pull grafana/grafana:4.2.0 cat <<EOF >node-exporter.yaml --- apiVersion: extensions/v1beta1 kind: DaemonSet metadata: name: node-exporter namespace: kube-system labels: k8s-app: node-exporter spec: template: metadata: labels: k8s-app: node-exporter spec: containers: - image: prom/node-exporter name: node-exporter ports: - containerPort: 9100 protocol: TCP name: http --- apiVersion: v1 kind: Service metadata: labels: k8s-app: node-exporter name: node-exporter namespace: kube-system spec: ports: - name: http port: 9100 nodePort: 31672 protocol: TCP type: NodePort selector: k8s-app: node-exporter EOF # 访问api授权 cat <<EOF >rbac-setup.yaml apiVersion: rbac.authorization.k8s.io/v1 kind: ClusterRole metadata: name: prometheus rules: - apiGroups: [""] resources: - nodes - nodes/proxy - services - endpoints - pods verbs: ["get", "list", "watch"] - apiGroups: - extensions resources: - ingresses verbs: ["get", "list", "watch"] - nonResourceURLs: ["/metrics"] verbs: ["get"] --- apiVersion: v1 kind: ServiceAccount metadata: name: prometheus namespace: kube-system --- apiVersion: rbac.authorization.k8s.io/v1 kind: ClusterRoleBinding metadata: name: prometheus roleRef: apiGroup: rbac.authorization.k8s.io kind: ClusterRole name: prometheus subjects: - kind: ServiceAccount name: prometheus namespace: kube-system EOF # 管理prometheus配置文件 cat <<EOF >configmap.yaml apiVersion: v1 kind: ConfigMap metadata: name: prometheus-config namespace: kube-system data: prometheus.yml: | global: scrape_interval: 15s evaluation_interval: 15s scrape_configs: - job_name: 'kubernetes-apiservers' kubernetes_sd_configs: - role: endpoints scheme: https tls_config: ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token relabel_configs: - source_labels: [__meta_kubernetes_namespace, __meta_kubernetes_service_name, __meta_kubernetes_endpoint_port_name] action: keep regex: default;kubernetes;https - job_name: 'kubernetes-nodes' kubernetes_sd_configs: - role: node scheme: https tls_config: ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token relabel_configs: - action: labelmap regex: __meta_kubernetes_node_label_(.+) - target_label: __address__ replacement: kubernetes.default.svc:443 - source_labels: [__meta_kubernetes_node_name] regex: (.+) target_label: __metrics_path__ replacement: /api/v1/nodes/${1}/proxy/metrics - job_name: 'kubernetes-cadvisor' kubernetes_sd_configs: - role: node scheme: https tls_config: ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token relabel_configs: - action: labelmap regex: __meta_kubernetes_node_label_(.+) - target_label: __address__ replacement: kubernetes.default.svc:443 - source_labels: [__meta_kubernetes_node_name] regex: (.+) target_label: __metrics_path__ replacement: /api/v1/nodes/${1}/proxy/metrics/cadvisor - job_name: 'kubernetes-service-endpoints' kubernetes_sd_configs: - role: endpoints relabel_configs: - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scrape] action: keep regex: true - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scheme] action: replace target_label: __scheme__ regex: (https?) - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_path] action: replace target_label: __metrics_path__ regex: (.+) - source_labels: [__address__, __meta_kubernetes_service_annotation_prometheus_io_port] action: replace target_label: __address__ regex: ([^:]+)(?::\d+)?;(\d+) replacement: $1:$2 - action: labelmap regex: __meta_kubernetes_service_label_(.+) - source_labels: [__meta_kubernetes_namespace] action: replace target_label: kubernetes_namespace - source_labels: [__meta_kubernetes_service_name] action: replace target_label: kubernetes_name - job_name: 'kubernetes-services' kubernetes_sd_configs: - role: service metrics_path: /probe params: module: [http_2xx] relabel_configs: - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_probe] action: keep regex: true - source_labels: [__address__] target_label: __param_target - target_label: __address__ replacement: blackbox-exporter.example.com:9115 - source_labels: [__param_target] target_label: instance - action: labelmap regex: __meta_kubernetes_service_label_(.+) - source_labels: [__meta_kubernetes_namespace] target_label: kubernetes_namespace - source_labels: [__meta_kubernetes_service_name] target_label: kubernetes_name - job_name: 'kubernetes-ingresses' kubernetes_sd_configs: - role: ingress relabel_configs: - source_labels: [__meta_kubernetes_ingress_annotation_prometheus_io_probe] action: keep regex: true - source_labels: [__meta_kubernetes_ingress_scheme,__address__,__meta_kubernetes_ingress_path] regex: (.+);(.+);(.+) replacement: ${1}://${2}${3} target_label: __param_target - target_label: __address__ replacement: blackbox-exporter.example.com:9115 - source_labels: [__param_target] target_label: instance - action: labelmap regex: __meta_kubernetes_ingress_label_(.+) - source_labels: [__meta_kubernetes_namespace] target_label: kubernetes_namespace - source_labels: [__meta_kubernetes_ingress_name] target_label: kubernetes_name - job_name: 'kubernetes-pods' kubernetes_sd_configs: - role: pod relabel_configs: - source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_scrape] action: keep regex: true - source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_path] action: replace target_label: __metrics_path__ regex: (.+) - source_labels: [__address__, __meta_kubernetes_pod_annotation_prometheus_io_port] action: replace regex: ([^:]+)(?::\d+)?;(\d+) replacement: $1:$2 target_label: __address__ - action: labelmap regex: __meta_kubernetes_pod_label_(.+) - source_labels: [__meta_kubernetes_namespace] action: replace target_label: kubernetes_namespace - source_labels: [__meta_kubernetes_pod_name] action: replace target_label: kubernetes_pod_name EOF # 将prometheus暴露访问 cat <<EOF >prometheus-service.yaml apiVersion: apps/v1 kind: StatefulSet metadata: name: prometheus # 部署命名空间 namespace: kube-system labels: k8s-app: prometheus kubernetes.io/cluster-service: "true" addonmanager.kubernetes.io/mode: Reconcile version: v2.2.1 spec: serviceName: "prometheus" replicas: 1 podManagementPolicy: "Parallel" updateStrategy: type: "RollingUpdate" selector: matchLabels: k8s-app: prometheus template: metadata: labels: k8s-app: prometheus annotations: scheduler.alpha.kubernetes.io/critical-pod: '' spec: priorityClassName: system-cluster-critical serviceAccountName: prometheus # 初始化容器 initContainers: - name: "init-chown-data" image: "busybox:latest" imagePullPolicy: "IfNotPresent" command: ["chown", "-R", "65534:65534", "/data"] volumeMounts: - name: prometheus-data mountPath: /data subPath: "" containers: - name: prometheus-server-configmap-reload image: "jimmidyson/configmap-reload:v0.1" imagePullPolicy: "IfNotPresent" args: - --volume-dir=/etc/config - --webhook-url=http://localhost:9090/-/reload volumeMounts: - name: config-volume mountPath: /etc/config readOnly: true resources: limits: cpu: 10m memory: 10Mi requests: cpu: 10m memory: 10Mi - name: prometheus-server # 主要使用镜像 image: "prom/prometheus:v2.2.1" imagePullPolicy: "IfNotPresent" args: - --config.file=/etc/config/prometheus.yml - --storage.tsdb.path=/data - --web.console.libraries=/etc/prometheus/console_libraries - --web.console.templates=/etc/prometheus/consoles - --web.enable-lifecycle ports: - containerPort: 9090 readinessProbe: # 健康检查 httpGet: path: /-/ready port: 9090 initialDelaySeconds: 30 timeoutSeconds: 30 livenessProbe: httpGet: path: /-/healthy port: 9090 initialDelaySeconds: 30 timeoutSeconds: 30 # based on 10 running nodes with 30 pods each resources: limits: cpu: 200m memory: 1000Mi requests: cpu: 200m memory: 1000Mi # 数据卷 volumeMounts: - name: config-volume mountPath: /etc/config - name: prometheus-data mountPath: /data subPath: "" terminationGracePeriodSeconds: 300 volumes: - name: config-volume configMap: name: prometheus-config volumeClaimTemplates: - metadata: name: prometheus-data spec: # 使用动态PV、修改为已创建的PV动态存储 storageClassName: managed-nfs-storage accessModes: - ReadWriteOnce resources: requests: storage: "16Gi" EOF # 通过有状态的形式将prometheus部署 cat <<EOF >prometheus.deploy.yml --- apiVersion: apps/v1beta2 kind: Deployment metadata: labels: name: prometheus-deployment name: prometheus namespace: kube-system spec: replicas: 1 selector: matchLabels: app: prometheus template: metadata: labels: app: prometheus spec: containers: - image: prom/prometheus:v2.0.0 name: prometheus command: - "/bin/prometheus" args: - "--config.file=/etc/prometheus/prometheus.yml" - "--storage.tsdb.path=/prometheus" - "--storage.tsdb.retention=24h" ports: - containerPort: 9090 protocol: TCP volumeMounts: - mountPath: "/prometheus" name: data - mountPath: "/etc/prometheus" name: config-volume resources: requests: cpu: 100m memory: 100Mi limits: cpu: 500m memory: 2500Mi serviceAccountName: prometheus volumes: - name: data emptyDir: {} - name: config-volume configMap: name: prometheus-config EOF cat <<EOF >prometheus.svc.yml --- kind: Service apiVersion: v1 metadata: labels: app: prometheus name: prometheus namespace: kube-system spec: type: NodePort ports: - port: 9090 targetPort: 9090 nodePort: 30003 selector: app: prometheus EOF kubectl create -f node-exporter.yaml kubectl create -f rbac-setup.yaml kubectl create -f configmap.yaml kubectl create -f prometheus-service.yaml kubectl create -f prometheus.deploy.yml kubectl create -f prometheus.svc.yml cat <<EOF >grafana-deploy.yaml apiVersion: extensions/v1beta1 kind: Deployment metadata: name: grafana-core namespace: kube-system labels: app: grafana component: core spec: replicas: 1 template: metadata: labels: app: grafana component: core spec: containers: - image: grafana/grafana:4.2.0 name: grafana-core imagePullPolicy: IfNotPresent # env: resources: # keep request = limit to keep this container in guaranteed class limits: cpu: 100m memory: 100Mi requests: cpu: 100m memory: 100Mi env: # The following env variables set up basic auth twith the default admin user and admin password. - name: GF_AUTH_BASIC_ENABLED value: "true" - name: GF_AUTH_ANONYMOUS_ENABLED value: "false" # - name: GF_AUTH_ANONYMOUS_ORG_ROLE # value: Admin # does not really work, because of template variables in exported dashboards: # - name: GF_DASHBOARDS_JSON_ENABLED # value: "true" readinessProbe: httpGet: path: /login port: 3000 # initialDelaySeconds: 30 # timeoutSeconds: 1 volumeMounts: - name: grafana-persistent-storage mountPath: /var volumes: - name: grafana-persistent-storage emptyDir: {} EOF cat <<EOF >grafana-svc.yaml apiVersion: v1 kind: Service metadata: name: grafana namespace: kube-system labels: app: grafana component: core spec: type: NodePort ports: - port: 3000 selector: app: grafana component: core EOF cat <<EOF >grafana-ing.yaml apiVersion: extensions/v1beta1 kind: Ingress metadata: name: grafana namespace: kube-system spec: rules: - host: k8s.grafana http: paths: - path: / backend: serviceName: grafana servicePort: 3000 EOF kubectl create -f grafana-deploy.yaml kubectl create -f grafana-svc.yaml kubectl create -f grafana-ing.yaml
