Kubernetes集群部署Prometheus和Grafana

Kubernetes集群部署Prometheus和Grafana

一、环境规划

K8S集群角色	Ip	主机名
控制节点	192.168.40.180	k8s-master1
工作节点	192.168.40.181	k8s-node1
工作节点	192.168.40.182	k8s-node2

实验环境规划：

• 操作系统：centos7.6
• 配置： 4Gib内存/4vCPU/100G硬盘
• 网络：Vmware NAT模式
• k8s版本：v1.20.6

[root@k8s-master1 ~]# kubectl get node
NAME          STATUS   ROLES                  AGE     VERSION
k8s-master1   Ready    control-plane,master   2d23h   v1.20.6
k8s-node1     Ready    worker                 2d23h   v1.20.6
k8s-node2     Ready    worker                 2d23h   v1.20.6

二、node-exporter安装和配置

2.1、node-exporter介绍

node-exporter可以采集机器（物理机、虚拟机、云主机等）的监控指标数据，能够采集到的指标包括CPU, 内存，磁盘，网络，文件数等信息。

2.2、node-exporter安装

# 创建监控namespace
[root@k8s-master1 prometheus]# kubectl create ns monitor-sa
namespace/monitor-sa created

# 创建node-export.yaml
[root@k8s-master1 prometheus]# cat node-export.yaml
apiVersion: apps/v1
kind: DaemonSet # 可以保证k8s集群的每个节点都运行完全一样的pod
metadata:
  name: node-exporter
  namespace: monitor-sa
  labels:
    name: node-exporter
spec:
  selector:
    matchLabels:
     name: node-exporter
  template:
    metadata:
      labels:
        name: node-exporter
    spec:
      hostPID: true
      hostIPC: true
      hostNetwork: true
      containers:
      - name: node-exporter
        image: prom/node-exporter:v0.16.0
        ports:
        - containerPort: 9100
        resources:
          requests:
            cpu: 0.15 # 这个容器运行至少需要0.15核cpu
        securityContext:
          privileged: true	# 开启特权模式
        args:
        - --path.procfs
        - /host/proc
        - --path.sysfs
        - /host/sys
        - --collector.filesystem.ignored-mount-points
        - '"^/(sys|proc|dev|host|etc)($|/)"'
        volumeMounts:
        - name: dev
          mountPath: /host/dev
        - name: proc
          mountPath: /host/proc
        - name: sys
          mountPath: /host/sys
        - name: rootfs
          mountPath: /rootfs
      tolerations:
      - key: "node-role.kubernetes.io/master"
        operator: "Exists"
        effect: "NoSchedule"
      volumes:
        - name: proc
          hostPath:
            path: /proc
        - name: dev
          hostPath:
            path: /dev
        - name: sys
          hostPath:
            path: /sys
        - name: rootfs
          hostPath:
            path: /
            
# hostNetwork、hostIPC、hostPID都为True时，表示这个Pod里的所有容器，会直接使用宿主机的网络，直接与宿主机进行IPC（进程间通信）通信，可以看到宿主机里正在运行的所有进程。加入了hostNetwork:true会直接将我们的宿主机的9100端口映射出来，从而不需要创建service 在我们的宿主机上就会有一个9100的端口

# 更新node-exporter.yaml文件
[root@k8s-master1 prometheus]# kubectl apply -f node-export.yaml

# 查看node-exporter是否部署成功
[root@k8s-master1 prometheus]# kubectl get pods -n monitor-sa -o wide
NAME                  READY   STATUS    RESTARTS   AGE   IP               NODE          NOMINATED NODE   READINESS GATES
node-exporter-nl5qz   1/1     Running   0          13s   192.168.40.181   k8s-node1     <none>           <none>
node-exporter-nxwkf   1/1     Running   0          13s   192.168.40.180   k8s-master1   <none>           <none>
node-exporter-x494t   1/1     Running   0          13s   192.168.40.182   k8s-node2     <none>           <none>

# 通过node-exporter采集数据 curl  http://主机ip:9100/metrics
# node-export默认的监听端口是9100，可以看到当前主机获取到的所有监控数据
[root@k8s-master1 prometheus]# curl http://192.168.40.180:9100/metrics | grep node_cpu_seconds
# HELP node_cpu_seconds_total Seconds the cpus spent in each mode.
# TYPE node_cpu_seconds_total counter
node_cpu_seconds_total{cpu="0",mode="idle"} 9429.89
node_cpu_seconds_total{cpu="0",mode="iowait"} 3.96
node_cpu_seconds_total{cpu="0",mode="irq"} 0
node_cpu_seconds_total{cpu="0",mode="nice"} 2.81
node_cpu_seconds_total{cpu="0",mode="softirq"} 45.77
node_cpu_seconds_total{cpu="0",mode="steal"} 0
node_cpu_seconds_total{cpu="0",mode="system"} 527.92
node_cpu_seconds_total{cpu="0",mode="user"} 847.3
node_cpu_seconds_total{cpu="1",mode="idle"} 9432.26
node_cpu_seconds_total{cpu="1",mode="iowait"} 5.12
node_cpu_seconds_total{cpu="1",mode="irq"} 0
node_cpu_seconds_total{cpu="1",mode="nice"} 2.81
node_cpu_seconds_total{cpu="1",mode="softirq"} 58
node_cpu_seconds_total{cpu="1",mode="steal"} 0
node_cpu_seconds_total{cpu="1",mode="system"} 528.33
node_cpu_seconds_total{cpu="1",mode="user"} 814.66

[root@k8s-master1 prometheus]# curl http://192.168.40.180:9100/metrics | grep node_load
# HELP node_load1 1m load average.
# TYPE node_load1 gauge
node_load1 0.44
# HELP node_load15 15m load average.
# TYPE node_load15 gauge
node_load15 0.89
# HELP node_load5 5m load average.
# TYPE node_load5 gauge
node_load5 0.74

三、Prometheus安装和配置

3.1、Prometheus安装

1）创建sa账号，对sa做rbac授权

# 创建一个sa账号monitor
[root@k8s-master1 prometheus]# kubectl create serviceaccount monitor -n monitor-sa

# 把sa账号monitor通过clusterrolebing绑定到clusterrole上
[root@k8s-master1 prometheus]# kubectl create clusterrolebinding monitor-clusterrolebinding -n monitor-sa --clusterrole=cluster-admin  --serviceaccount=monitor-sa:monitor

2）创建prometheus数据存储目录

# 将prometheus调度到k8s-node1节点
[root@k8s-node1 ~]# mkdir /data && chmod 777 /data

3）创建一个configmap存储卷，用来存放prometheus配置信息

[root@k8s-master1 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 

[root@k8s-master1 prometheus]# kubectl apply -f prometheus-cfg.yaml
configmap/prometheus-config created

配置详解：

---
kind: ConfigMap
apiVersion: v1
metadata:
  labels:
    app: prometheus
  name: prometheus-config
  namespace: monitor-sa
data:
  prometheus.yml: |
    global:
      scrape_interval: 15s #采集目标主机监控据的时间间隔
      scrape_timeout: 10s	# 数据采集超时时间，默认10s
      evaluation_interval: 1m 	#触发告警检测的时间，默认是1m
    scrape_configs:	# 配置数据源，称为target，每个target用job_name命名。又分为静态配置和服务发现
    - job_name: 'kubernetes-node'
      kubernetes_sd_configs:	# 使用的是k8s的服务发现
      - role: node	# 使用node角色，它使用默认的kubelet提供的http端口来发现集群中每个node节点
      relabel_configs:	# 重新标记
      - source_labels: [__address__]	# 配置的原始标签，匹配地址
        regex: '(.*):10250'		#匹配带有10250端口的url
        replacement: '${1}:9100'	#把匹配到的ip:10250的ip保留
        target_label: __address__	#新生成的url是${1}获取到的ip:9100
        action: replace	# 动作替换
      - action: labelmap
        regex: __meta_kubernetes_node_label_(.+) #匹配到下面正则表达式的标签会被保留,如果不做regex正则的话，默认只是会显示instance标签
    - job_name: 'kubernetes-node-cadvisor' # 抓取cAdvisor数据，是获取kubelet上/metrics/cadvisor接口数据来获取容器的资源使用情况
      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	# 把匹配到的标签保留
        regex: __meta_kubernetes_node_label_(.+)  #保留匹配到的具有__meta_kubernetes_node_label的标签
      - target_label: __address__	# 获取到的地址：__address__="192.168.40.180:10250"
        replacement: kubernetes.default.svc:443	# 把获取到的地址替换成新的地址kubernetes.default.svc:443
      - source_labels: [__meta_kubernetes_node_name]
        regex: (.+)	# 把原始标签中__meta_kubernetes_node_name值匹配到
        target_label: __metrics_path__	#获取__metrics_path__对应的值
        replacement: /api/v1/nodes/${1}/proxy/metrics/cadvisor	
        # 把metrics替换成新的值api/v1/nodes/k8s-master1/proxy/metrics/cadvisor
        # ${1}是__meta_kubernetes_node_name获取到的值
        # 新的url就是https://kubernetes.default.svc:443/api/v1/nodes/k8s-master1/proxy/metrics/cadvisor
    - job_name: 'kubernetes-apiserver'
      kubernetes_sd_configs:
      - role: endpoints	# 使用k8s中的endpoint服务发现，采集apiserver 6443端口获取到的数据
      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]
        # endpoint这个对象的名称空间,endpoint对象的服务名,exnpoint的端口名称
        action: keep	# 采集满足条件的实例，其他实例不采集
        regex: default;kubernetes;https	#正则匹配到的默认空间下的service名字是kubernetes，协议是https的endpoint类型保留下来
    - 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
        # 重新打标仅抓取到的具有 "prometheus.io/scrape: true" 的annotation的端点，意思是说如果某个service具有prometheus.io/scrape = true annotation声明则抓取，annotation本身也是键值结构，所以这里的源标签设置为键，而regex设置值true，当值匹配到regex设定的内容时则执行keep动作也就是保留，其余则丢弃。
      - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scheme]
        action: replace
        target_label: __scheme__
        regex: (https?)
        # 重新设置scheme，匹配源标签__meta_kubernetes_service_annotation_prometheus_io_scheme也就是prometheus.io/scheme annotation，如果源标签的值匹配到regex，则把值替换为__scheme__对应的值。
      - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_path]
        action: replace
        target_label: __metrics_path__
        regex: (.+)
        # 应用中自定义暴露的指标，也许你暴露的API接口不是/metrics这个路径，那么你可以在这个POD对应的service中做一个"prometheus.io/path = /mymetrics" 声明，上面的意思就是把你声明的这个路径赋值给__metrics_path__，其实就是让prometheus来获取自定义应用暴露的metrices的具体路径，不过这里写的要和service中做好约定，如果service中这样写 prometheus.io/app-metrics-path: '/metrics' 那么你这里就要__meta_kubernetes_service_annotation_prometheus_io_app_metrics_path这样写。
      - source_labels: [__address__, __meta_kubernetes_service_annotation_prometheus_io_port]
        action: replace
        target_label: __address__
        regex: ([^:]+)(?::d+)?;(d+)
        replacement: $1:$2
        # 暴露自定义的应用的端口，就是把地址和你在service中定义的 "prometheus.io/port = <port>" 声明做一个拼接，然后赋值给__address__，这样prometheus就能获取自定义应用的端口，然后通过这个端口再结合__metrics_path__来获取指标，如果__metrics_path__值不是默认的/metrics那么就要使用上面的标签替换来获取真正暴露的具体路径。
      - action: labelmap	#保留下面匹配到的标签
        regex: __meta_kubernetes_service_label_(.+)
      - source_labels: [__meta_kubernetes_namespace]
        action: replace	 # 替换__meta_kubernetes_namespace变成kubernetes_namespace
        target_label: kubernetes_namespace
      - source_labels: [__meta_kubernetes_service_name]
        action: replace
        target_label: kubernetes_name 

4）通过deployment部署prometheus

[root@k8s-master1 prometheus]# cat prometheus-deploy.yaml 
---
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: k8s-node1	# 指定pod调度到哪个节点上	
      serviceAccountName: monitor
      containers:
      - name: prometheus
        image: prom/prometheus:v2.2.1
        imagePullPolicy: IfNotPresent
        command:
          - prometheus
          - --config.file=/etc/prometheus/prometheus.yml
          - --storage.tsdb.path=/prometheus	# 数据存储目录
          - --storage.tsdb.retention=720h	# 数据保存时长
          - --web.enable-lifecycle	# 开启热加载
        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
           type: Directory

[root@k8s-master1 prometheus]# kubectl apply -f prometheus-deploy.yaml
deployment.apps/prometheus-server created
[root@k8s-master1 prometheus]# kubectl get pods -o wide -n monitor-sa 
NAME                                 READY   STATUS    RESTARTS   AGE   IP               NODE          NOMINATED NODE   READINESS GATES
node-exporter-nl5qz                  1/1     Running   0          38m   192.168.40.181   k8s-node1     <none>           <none>
node-exporter-nxwkf                  1/1     Running   0          38m   192.168.40.180   k8s-master1   <none>           <none>
node-exporter-x494t                  1/1     Running   0          38m   192.168.40.182   k8s-node2     <none>           <none>
prometheus-server-689fb8cdbc-j4qq5   1/1     Running   0          9s    10.244.36.69     k8s-node1     <none>           <none>

5）给prometheus pod创建一个service

[root@k8s-master1 prometheus]# cat prometheus-svc.yaml 
apiVersion: v1
kind: Service
metadata:
  name: prometheus
  namespace: monitor-sa
  labels:
    app: prometheus
spec:
  type: NodePort
  ports:
    - port: 9090
      targetPort: 9090
      protocol: TCP
  selector:
    app: prometheus
    component: server
    
[root@k8s-master1 prometheus]# kubectl apply -f prometheus-svc.yaml
service/prometheus created

# 查看service在物理机映射的端口
[root@k8s-master1 prometheus]# kubectl get svc -n monitor-sa
NAME         TYPE       CLUSTER-IP      EXTERNAL-IP   PORT(S)          AGE
prometheus   NodePort   10.99.104.223   <none>        9090:32367/TCP   48s

# 通过上面可以看到service在宿主机上映射的端口是32367，这样我们访问k8s集群的master1节点的ip:32367，就可以访问到prometheus的web ui界面了

点击页面的Status->Targets，可看到如下,说明我们配置的服务发现可以正常采集数据

3.2、Prometheus热加载

# 为了每次修改配置文件可以热加载prometheus，也就是不停止prometheus，就可以使配置生效，想要使配置生效可用如下热加载命令：
[root@k8s-master1 prometheus]# kubectl get pods -n monitor-sa -o wide -l app=prometheus
NAME                                 READY   STATUS    RESTARTS   AGE     IP             NODE        NOMINATED NODE   READINESS GATES
prometheus-server-689fb8cdbc-kcsw2   1/1     Running   0          5m39s   10.244.36.70   k8s-node1   <none>           <none>

# 想要使配置生效可用如下命令热加载：
[root@k8s-master1 prometheus]# curl -X POST http://10.244.36.70:9090/-/reload

# 查看log
[root@k8s-master1 prometheus]# kubectl logs -n monitor-sa prometheus-server-689fb8cdbc-kcsw2

# 热加载速度比较慢，可以暴力重启prometheus，如修改上面的prometheus-cfg.yaml文件之后，可执行如下强制删除：
[root@k8s-master1 prometheus]# kubectl delete -f prometheus-cfg.yaml
[root@k8s-master1 prometheus]# kubectl delete -f prometheus-deploy.yaml
# 然后再通过apply更新：
[root@k8s-master1 prometheus]# kubectl apply -f prometheus-cfg.yaml
[root@k8s-master1 prometheus]# kubectl apply -f prometheus-deploy.yaml
#注意：线上最好热加载，暴力删除可能造成监控数据的丢失

四、Grafana的安装和配置

4.1、Grafana介绍

Grafana是一个跨平台的开源的度量分析和可视化工具，可以将采集的数据可视化的展示，并及时通知给告警接收方。它主要有以下六大特点：

1）展示方式：快速灵活的客户端图表，面板插件有许多不同方式的可视化指标和日志，官方库中具有丰富的仪表盘插件，比如热图、折线图、图表等多种展示方式；

2）数据源：Graphite，InfluxDB，OpenTSDB，Prometheus，Elasticsearch，CloudWatch和KairosDB等；

3）通知提醒：以可视方式定义最重要指标的警报规则，Grafana将不断计算并发送通知，在数据达到阈值时通过Slack、PagerDuty等获得通知；

4）混合展示：在同一图表中混合使用不同的数据源，可以基于每个查询指定数据源，甚至自定义数据源；

5）注释：使用来自不同数据源的丰富事件注释图表，将鼠标悬停在事件上会显示完整的事件元数据和标记。

4.2、Grafana安装

# 准备yaml文件
[root@k8s-master1 prometheus]# cat 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:
      containers:
      - name: grafana
        image: hujinzhong/heapster-grafana-amd64:v5.0.4
        ports:
        - containerPort: 3000
          protocol: TCP
        volumeMounts:
        - mountPath: /etc/ssl/certs
          name: ca-certificates
          readOnly: true
        - mountPath: /var
          name: grafana-storage
        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: {}
---
apiVersion: v1
kind: Service
metadata:
  labels:
    # For use as a Cluster add-on (https://github.com/kubernetes/kubernetes/tree/master/cluster/addons)
    # If you are NOT using this as an addon, you should comment out this line.
    kubernetes.io/cluster-service: 'true'
    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

# 更新yaml文件：
[root@k8s-master1 prometheus]# kubectl apply -f grafana.yaml

# 查看grafana是否创建成功：
[root@k8s-master1 prometheus]# kubectl get pods -n kube-system -l task=monitoring -o wide
NAME                                  READY   STATUS    RESTARTS   AGE   IP               NODE        NOMINATED NODE   READINESS GATES
monitoring-grafana-675798bf47-z9dpx   1/1     Running   0          19s   10.244.169.135   k8s-node2   <none>           <none>

# 查看grafana前端的service
[root@k8s-master1 prometheus]# kubectl get svc -n kube-system | grep grafana  
monitoring-grafana   NodePort    10.105.174.145   <none>        80:31715/TCP             63s

4.3、配置Grafana

1）登陆grafana，在浏览器访问http://192.168.40.180:31715

2）开始配置grafana的web界面：选择Create your first data source

4.4、导入监控模板

官方链接搜索：https://grafana.com/dashboards?dataSource=prometheus&search=kubernetes

4.4.1、监控node状态

点击左侧+号下面的Import，导入node_exporter.json模板

4.4.2、监控容器状态

点击左侧+号下面的Import，导入docker_rev1.json模板