k8s集群部署cadvisor+node-exporter+prometheus+grafana监控系统

一、通过daemonset 安装cadvisor

下载cadvisor并上传到harbor
docker tag gcr.io/cadvisor/cadvisor:v0.45.0 harbor.magedu.net/baseimages/cadvisor:v0.45.0
docker push harbor.magedu.net/baseimages/cadvisor:v0.45.0

root@easzlab-deploy:~/20220911# kubectl create ns monitor
namespace/monitor created
root@easzlab-deploy:~/20220911#

cat case1-daemonset-deploy-cadvisor.yaml

apiVersion: apps/v1
kind: DaemonSet
metadata:
  name: cadvisor
  namespace: monitor
spec:
  selector:
    matchLabels:
      app: cAdvisor
  template:
    metadata:
      labels:
        app: cAdvisor
    spec:
      tolerations:    #污点容忍,忽略master的NoSchedule
        - effect: NoSchedule
          key: node-role.kubernetes.io/master
      hostNetwork: true
      restartPolicy: Always   # 重启策略
      containers:
      - name: cadvisor
        image: harbor.magedu.net/baseimages/cadvisor:v0.45.0
        imagePullPolicy: IfNotPresent  # 镜像策略
        ports:
        - containerPort: 8080
        volumeMounts:
          - name: root
            mountPath: /rootfs
          - name: run
            mountPath: /var/run
          - name: sys
            mountPath: /sys
          - name: docker
            mountPath: /var/lib/containerd
      volumes:
      - name: root
        hostPath:
          path: /
      - name: run
        hostPath:
          path: /var/run
      - name: sys
        hostPath:
          path: /sys
      - name: docker
        hostPath:
          path: /var/lib/containerd

验证cadvisor

二、部署node-exporter

cat case2-daemonset-deploy-node-exporter.yaml

apiVersion: apps/v1
kind: DaemonSet
metadata:
  name: node-exporter
  namespace: monitor
  labels:
    k8s-app: node-exporter
spec:
  selector:
    matchLabels:
        k8s-app: node-exporter
  template:
    metadata:
      labels:
        k8s-app: node-exporter
    spec:
      tolerations:
        - effect: NoSchedule
          key: node-role.kubernetes.io/master
      containers:
      - image: prom/node-exporter:v1.3.1 
        imagePullPolicy: IfNotPresent
        name: prometheus-node-exporter
        ports:
        - containerPort: 9100
          hostPort: 9100
          protocol: TCP
          name: metrics
        volumeMounts:
        - mountPath: /host/proc
          name: proc
        - mountPath: /host/sys
          name: sys
        - mountPath: /host
          name: rootfs
        args:
        - --path.procfs=/host/proc
        - --path.sysfs=/host/sys
        - --path.rootfs=/host
      volumes:
        - name: proc
          hostPath:
            path: /proc
        - name: sys
          hostPath:
            path: /sys
        - name: rootfs
          hostPath:
            path: /
      hostNetwork: true
      hostPID: true
apiVersion: v1
kind: Service
metadata:
  annotations:
    prometheus.io/scrape: "true"
  labels:
    k8s-app: node-exporter
  name: node-exporter
  namespace: monitor
spec:
  type: NodePort
  ports:
  - name: http
    port: 9100
    nodePort: 39100
    protocol: TCP
  selector:
    k8s-app: node-exporter

验证node_exporter数据

三、deployment部署Prometheus server

cat case3-1-prometheus-cfg.yaml

kind: ConfigMap apiVersion: v1 metadata: labels: app: prometheus name: prometheus- config namespace : monitor data: prometheus.yml: | global : scrape_interval: 15s scrape_timeout: 10s evaluation_interval: 1m scrape_configs: - job_name: ' kubernetes-node ' kubernetes_sd_configs: - role: node relabel_configs: - source_labels: [__address__] regex: ' (.*):10250 ' replacement: ' ${1}:9100 ' target_label: __address__ action: replace - action: labelmap regex: __meta_kubernetes_node_label_(. + ) - job_name: ' kubernetes-node-cadvisor ' kubernetes_sd_configs: - role: node scheme: https tls_config: ca_file: / var /run/secrets/kubernetes.io/serviceaccount/ ca.crt bearer_token_file: / var /run/secrets/kubernetes.io/serviceaccount/ token relabel_configs: - action: labelmap regex: __meta_kubernetes_node_label_(. + ) - target_label: __address__ replacement: kubernetes. default .svc: 443 - source_labels: [__meta_kubernetes_node_name] regex: (. + ) target_label: __metrics_path__ replacement: /api/v1/nodes/${ 1 }/proxy/metrics/ cadvisor - job_name: ' kubernetes-apiserver ' 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-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_service_name

指定172.16.88.156 node-01 节点为Prometheus 数据存放路径
mkdir -p /data/prometheusdata
root@easzlab-k8s-master-03:~# chmod 777 /data/prometheusdata
root@easzlab-k8s-master-03:~# chown 65534.65534 /data/prometheusdata -R #否则Prometheus pod会报错

cat case3-2-prometheus-deployment.yaml

apiVersion: apps/ v1 kind: Deployment metadata: name: prometheus - server namespace : monitor labels: app: prometheus spec: replicas: 1 selector: matchLabels: app: prometheus component: server #matchExpressions: # - {key: app, operator : In, values: [prometheus]} # - {key: component, operator : In, values: [server]} template: metadata: labels: app: prometheus component: server annotations: prometheus.io /scrape: ' false ' spec: nodeName: 172.16 . 88.156 serviceAccountName: monitor containers: - name: prometheus image: prom /prometheus:v2. 31.2 imagePullPolicy: IfNotPresent command: - prometheus - --config.file=/etc/prometheus/ prometheus.yml - --storage.tsdb.path=/ prometheus - --storage.tsdb.retention= 720h ports: - containerPort: 9090 protocol: TCP volumeMounts: - mountPath: /etc/prometheus/ prometheus.yml name: prometheus - config subPath: prometheus.yml - mountPath: /prometheus/ name: prometheus -storage- volume volumes: - name: prometheus- config configMap: name: prometheus - config items: - key: prometheus.yml path: prometheus.yml mode: 0644 - name: prometheus-storage- volume hostPath: path: /data/ prometheusdata type: Directory

root@easzlab-deploy:~/20220911# kubectl create serviceaccount monitor -n monitor
serviceaccount/monitor created
root@easzlab-deploy:~/20220911# kubectl create clusterrolebinding monitor-clusterrolebinding -n monitor --clusterrole=cluster-admin --serviceaccount=monitor:monitor
clusterrolebinding.rbac.authorization.k8s.io/monitor-clusterrolebinding created
root@easzlab-deploy:~/20220911# 
root@easzlab-deploy:~/20220911# kubectl apply -f case3-2-prometheus-deployment.yaml
deployment.apps/prometheus-server created
root@easzlab-deploy:~/20220911#

创建Prometheus service

cat case3-3-prometheus-svc.yaml

apiVersion: v1 kind: Service metadata: name: prometheus namespace : monitor labels: app: prometheus spec: type: NodePort ports: - port: 9090 targetPort: 9090 nodePort: 30090 protocol: TCP selector: app: prometheus component: server kubernetes.io/service-account.name: " prometheus " apiVersion: rbac.authorization.k8s.io/ v1 kind: ClusterRole metadata: name: prometheus rules: - apiGroups: resources: - nodes - services - endpoints - pods - nodes/ proxy verbs: - get - list - watch - apiGroups: - " extensions " resources: - ingresses verbs: - get - list - watch - apiGroups: resources: - configmaps - nodes/ metrics verbs: - get - nonResourceURLs: - / metrics verbs: - get #apiVersion: rbac.authorization.k8s.io/ v1beta1 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 : monitor

四、安装kube-state-metrics

cat case5-kube-state-metrics-deploy.yaml

apiVersion: apps/v1
kind: Deployment
metadata:
  name: kube-state-metrics
  namespace: kube-system
spec:
  replicas: 1
  selector:
    matchLabels:
      app: kube-state-metrics
  template:
    metadata:
      labels:
        app: kube-state-metrics
    spec:
      serviceAccountName: kube-state-metrics
      containers:
      - name: kube-state-metrics
        image: registry.cn-hangzhou.aliyuncs.com/zhangshijie/kube-state-metrics:v2.6.0 
        ports:
        - containerPort: 8080
apiVersion: v1
kind: ServiceAccount
metadata:
  name: kube-state-metrics
  namespace: kube-system
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
  name: kube-state-metrics
rules:
- apiGroups: [""]
  resources: ["nodes", "pods", "services", "resourcequotas", "replicationcontrollers", "limitranges", "persistentvolumeclaims", "persistentvolumes", "namespaces", "endpoints"]
  verbs: ["list", "watch"]
- apiGroups: ["extensions"]
  resources: ["daemonsets", "deployments", "replicasets"]
  verbs: ["list", "watch"]
- apiGroups: ["apps"]
  resources: ["statefulsets"]
  verbs: ["list", "watch"]
- apiGroups: ["batch"]
  resources: ["cronjobs", "jobs"]
  verbs: ["list", "watch"]
- apiGroups: ["autoscaling"]
  resources: ["horizontalpodautoscalers"]
  verbs: ["list", "watch"]
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
  name: kube-state-metrics
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: ClusterRole
  name: kube-state-metrics
subjects:
- kind: ServiceAccount
  name: kube-state-metrics
  namespace: kube-system
apiVersion: v1
kind: Service
metadata:
  annotations:
    prometheus.io/scrape: 'true'
  name: kube-state-metrics
  namespace: kube-system
  labels:
    app: kube-state-metrics
spec:
  type: NodePort
  ports:
  - name: kube-state-metrics
    port: 8080
    targetPort: 8080
    nodePort: 31666
    protocol: TCP
  selector:
    app: kube-state-metrics