新版本Prometheus+grafana实战-摩杜云开发者社区

安装node-exporter

所有节点导入镜像

[root@k8sm1 ~]# ctr -n k8s.io image import node-exporter.tar.gz

创建node采集Pod

apiVersion: v1
kind: Namespace
metadata:
  name: monitor-sa
---
apiVersion: apps/v1
kind: DaemonSet
metadata:
  name: node-exporter
  namespace: monitor-sa
  labels:
    name: node-exporter
spec:
  selector:
    matchLabels:
      name: node-exporter
  template:
    metadata:
      labels:
        name: node-exporter
    spec:
      hostIPC: true
      hostNetwork: true
      hostPID: true
      containers:
      - name: node-exporter
        image: docker.io/prom/node-exporter:v0.16.0
        imagePullPolicy: IfNotPresent
        ports:
        - containerPort: 9100
        resources:
          requests:
            cpu: 0.15
        securityContext:
          privileged: true
        volumeMounts:
        - name: dev
          mountPath: /host/dev
        - name: proc
          mountPath: /host/proc
        - name: sys
          mountPath: /host/sys
        args:
        - --path.procfs
        - /host/proc
        - --path.sysfs
        - /host/sys
        - --collector.filesystem.ignored-mount-points
        - '""^/(sys|proc|dev|host|etc)($|/)"'
      tolerations:
      - key: node-role.kubernetes.io/control-plane
        operator: "Exists"
        effect: "NoSchedule"
      volumes:
      - name: proc
        hostPath:
          path: /proc
      - name: dev
        hostPath:
          path: /dev
      - name: sys
        hostPath:
          path: /sys
      - name: rootfs
        hostPath:
          path: /

部署完成，本机测试

[root@k8sm1 prometheus]# curl http://192.168.1.181:9100/metrics | grep node_cpu_seconds
  % Total    % Received % Xferd  Average Speed   Time    Time     Time  Current
                                 Dload  Upload   Total   Spent    Left  Speed
100# HELP node_cpu_seconds_total Seconds the cpus spent in each mode.
 62# TYPE node_cpu_seconds_total counter
259node_cpu_seconds_total{cpu="0",mode="idle"} 429035.72
  node_cpu_seconds_total{cpu="0",mode="iowait"} 28.4
10node_cpu_seconds_total{cpu="0",mode="irq"} 0
0 node_cpu_seconds_total{cpu="0",mode="nice"} 0.92
622node_cpu_seconds_total{cpu="0",mode="softirq"} 36.76

安装Prometheus

创建SA并授权

[root@k8sm1 prometheus]# cat sa.yaml 
apiVersion: v1
kind: ServiceAccount
metadata:
  namespace: monitor-sa
  name: monitor

---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
  namespace: monitor-sa
  name: monitor-clusterrolebinding
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: ClusterRole
  name: cluster-admin
subjects:
- kind: ServiceAccount
  namespace: monitor-sa
  name: monitor

---

apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
  name: monitor-clusterrolebinding1
  namespace: monitor-sa
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: ClusterRole
  name: cluster-admin
subjects:
- kind: User
  namespace: monitor-sa
  name: system:serviceaccount:monitor

宿主机创建数据目录

[root@k8sm1 prometheus]# mkdir -p /prometheus/data
[root@k8sm1 prometheus]# chmod 777 /prometheus/data/

解压镜像

[root@k8sm1 prometheus]# crictl images list                                                                    TAG                 IMAGE ID            SIZE

docker.io/prom/prometheus                                                     v2.33.5             7ae78dc7a8114       77.6MB

创建prometheus配置文件

[root@k8sm1 prometheus]# cat prometheus-cfg.yaml 
kind: ConfigMap
apiVersion: v1
metadata:
  labels:
    app: prometheus
  name: prometheus-config
  namespace: monitor-sa
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_name

部署Prometheus 的 Pod节点

apiVersion: apps/v1
kind: Deployment
metadata:
  name: prometheus-server
  namespace: monitor-sa
  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: k8sm1
      serviceAccountName: monitor
      containers:
      - name: prometheus
        image: prom/prometheus:v2.33.5
        imagePullPolicy: IfNotPresent
        command:
          - prometheus
          - --config.file=/etc/prometheus/prometheus.yml
          - --storage.tsdb.path=/prometheus
          - --storage.tsdb.retention=720h
          - --web.enable-lifecycle
        ports:
        - containerPort: 9090
          protocol: TCP
        volumeMounts:
        - mountPath: /etc/prometheus
          name: prometheus-config
        - mountPath: /prometheus/
          name: prometheus-storage-volume
      volumes:
        - name: prometheus-config
          configMap:
            name: prometheus-config
        - name: prometheus-storage-volume
          hostPath:
           path: /prometheus/data
           type: Directory

创建prometheus的Service服务

apiVersion: v1
kind: Service
metadata:
  name: prometheus
  namespace: monitor-sa
  labels:
    app: prometheus
spec:
  selector:
    app: prometheus
    component: server
  type: NodePort
  ports:
  - port: 9090
    targetPort: 9090
    nodePort: 30268

安装Grafana

导入新版镜像

[root@k8sm1 ~]# ctr -n k8s.io image import grafana_8.4.5.tar.gz

宿主机创建grafana持久化存储目录

[root@k8sm1 data]# mkdir -p /var/lib/grafana/
[root@k8sm1 data]# chmod 777 /var/lib/grafana/

创建grafana 的Pod 文件

[root@k8sm1 prometheus]# vim grafana.yaml 

apiVersion: apps/v1
kind: Deployment
metadata:
  name: monitoring-grafana
  namespace: kube-system
spec:
  replicas: 1
  selector:
    matchLabels:
      task: monitoring
      k8s-app: grafana
  template:
    metadata:
      labels:
        task: monitoring
        k8s-app: grafana
    spec:
      nodeName: k8sm1
      containers:
      - name: grafana
        image: grafana/grafana:8.4.5
        imagePullPolicy: IfNotPresent
        ports:
        - containerPort: 3000
          protocol: TCP
        volumeMounts:
        - mountPath: /etc/ssl/certs
          name: ca-certificates
          readOnly: true
        - mountPath: /var
          name: grafana-storage
        - mountPath: /var/lib/grafana/
          name: lib
        env:
        - name: INFLUXDB_HOST
          value: monitoring-influxdb
        - name: GF_SERVER_HTTP_PORT
          value: "3000"
          # The following env variables are required to make Grafana accessible via
          # the kubernetes api-server proxy. On production clusters, we recommend
          # removing these env variables, setup auth for grafana, and expose the grafana
          # service using a LoadBalancer or a public IP.
        - name: GF_AUTH_BASIC_ENABLED
          value: "false"
        - name: GF_AUTH_ANONYMOUS_ENABLED
          value: "true"
        - name: GF_AUTH_ANONYMOUS_ORG_ROLE
          value: Admin
        - name: GF_SERVER_ROOT_URL
          # If you're only using the API Server proxy, set this value instead:
          # value: /api/v1/namespaces/kube-system/services/monitoring-grafana/proxy
          value: /
      volumes:
      - name: ca-certificates
        hostPath:
          path: /etc/ssl/certs
      - name: grafana-storage
        emptyDir: {}
      - name: lib
        hostPath:
         path: /var/lib/grafana/
         type: DirectoryOrCreate

创建grafana 的Service服务

apiVersion: v1
kind: Service
metadata:
  labels:
    kubernetes.io/name: monitoring-grafana
  name: monitoring-grafana
  namespace: kube-system
spec:
  # In a production setup, we recommend accessing Grafana through an external Loadbalancer
  # or through a public IP.
  # type: LoadBalancer
  # You could also use NodePort to expose the service at a randomly-generated port
  # type: NodePort
  ports:
  - port: 80
    targetPort: 3000
  selector:
    k8s-app: grafana
  type: NodePort