prometheus手动添加k8s集群外的node-exporter监控

1、部署node-exporter

1）helm方式部署

bash 复制代码

root@iZj6c72dzbei17o2cuksmeZ:~# helm repo add prometheus-community https://prometheus-community.github.io/helm-charts
"prometheus-community" has been added to your repositories
root@iZj6c72dzbei17o2cuksmeZ:~# helm repo update
Hang tight while we grab the latest from your chart repositories...
...Successfully got an update from the "prometheus-community" chart repository
Update Complete. ⎈Happy Helming!⎈
root@iZj6c72dzbei17o2cuksmeZ:~# helm install prometheus-node-exporter prometheus-community/prometheus-node-exporter
NAME: prometheus-node-exporter
LAST DEPLOYED: Sun Apr 27 10:56:21 2025
NAMESPACE: default
STATUS: deployed
REVISION: 1
TEST SUITE: None
NOTES:
1. Get the application URL by running these commands:
  export POD_NAME=$(kubectl get pods --namespace default -l "app.kubernetes.io/name=prometheus-node-exporter,app.kubernetes.io/instance=prometheus-node-exporter" -o jsonpath="{.items[0].metadata.name}")
  echo "Visit http://127.0.0.1:9100 to use your application"
  kubectl port-forward --namespace default $POD_NAME 9100

2）docker-compose部署

yaml 复制代码

root@iZj6c2vhsafoay7j7vyy89Z:~# cat /data/docker-compose/node-exporter/docker-compose.yaml 
version: '3.8'

services:
  node-exporter:
    image: prom/node-exporter:latest
    container_name: node-exporter
    restart: unless-stopped
    ports:
      - "9100:9100"
    network_mode: "host"   # 使用宿主机网络，方便采集真实的主机数据
    pid: "host"            # 让容器可以访问宿主机的 /proc
    volumes:
      - /proc:/host/proc:ro
      - /sys:/host/sys:ro
      - /:/rootfs:ro
    command:
      - '--path.procfs=/host/proc'
      - '--path.sysfs=/host/sys'
      - '--path.rootfs=/rootfs'
      - '--collector.filesystem.ignored-mount-points=^/(sys|proc|dev|host|etc)($$|/)'

部署

bash 复制代码

root@iZj6c2vhsafoay7j7vyy89Z:/data/docker-compose/node-exporter# docker-compose up -d
Pulling node-exporter (prom/node-exporter:latest)...
latest: Pulling from prom/node-exporter
9fa9226be034: Pull complete
1617e25568b2: Pull complete
c6e37428e3b3: Pull complete
Digest: sha256:d00a542e409ee618a4edc67da14dd48c5da66726bbd5537ab2af9c1dfc442c8a
Status: Downloaded newer image for prom/node-exporter:latest
Creating node-exporter ... done

2、部署endpoints、service、ServiceMonitor

endpoints的yaml文件
root@iZj6c72dzbei17o2cuksmeZ:~/yaml# cat zjj-endpoints.yaml

yaml 复制代码

apiVersion: v1
kind: Endpoints
metadata:
  annotations: {}        
  labels:
    app: zjj
    jobname: node-exporter
    source: external
  name: zjj 
  namespace: monitoring
subsets:
- addresses:
  - hostname: zjj
    ip: 172.16.0.20
  ports:
  - name: metrics
    port: 9100 
    protocol: TCP

service的yaml文件
root@iZj6c72dzbei17o2cuksmeZ:~/yaml# cat zjj-nodeporter-service.yaml

yaml 复制代码

---
apiVersion: v1
kind: Service
metadata:
  annotations: {}
  labels:
    app: zjj 
    jobname: node-exporter
    source: external
  name: zjj
  namespace: monitoring
  resourceVersion: '552219945'
spec:
  internalTrafficPolicy: Cluster
  ipFamilies:
    - IPv4
  ipFamilyPolicy: SingleStack
  ports:
    - name: metrics
      port: 9100 
      protocol: TCP
      targetPort: 9100
  sessionAffinity: None
  type: ClusterIP

ServiceMonitor的yaml文件
root@iZj6c72dzbei17o2cuksmeZ:~/yaml# cat zjj-servicemonitor.yaml

yaml 复制代码

---
apiVersion: monitoring.coreos.com/v1
kind: ServiceMonitor
metadata:
  annotations: {}
  labels:
    app: zjj 
    release: kube-prometheus
    source: external
  name: zjj
  namespace: monitoring
  resourceVersion: '294048548'
spec:
  endpoints:
    - port: metrics
  jobLabel: jobname
  namespaceSelector:
    matchNames:
      - monitoring
  selector:
    matchLabels:
      app: zjj
      source: external

启动对应的服务

bash 复制代码

root@iZj6c72dzbei17o2cuksmeZ:~/yaml# kubectl apply -f zjj-endpoints.yaml 
endpoints/zjj created
root@iZj6c72dzbei17o2cuksmeZ:~/yaml# kubectl apply -f zjj-nodeporter-service.yaml 
service/zjj created
root@iZj6c72dzbei17o2cuksmeZ:~/yaml# kubectl apply -f zjj-servicemonitor.yaml 
servicemonitor.monitoring.coreos.com/zjj created

bash 复制代码

root@iZj6c72dzbei17o2cuksmeZ:~/yaml# kubectl get endpoints zjj -n monitoring
NAME   ENDPOINTS          AGE
zjj    172.16.0.20:9100   55m
root@iZj6c72dzbei17o2cuksmeZ:~/yaml# kubectl get service zjj -n monitoring
NAME   TYPE        CLUSTER-IP     EXTERNAL-IP   PORT(S)    AGE
zjj    ClusterIP   10.68.140.25   <none>        9100/TCP   54m
root@iZj6c72dzbei17o2cuksmeZ:~/yaml# kubectl get servicemonitor zjj -n monitoring
NAME   AGE
zjj    55m

3、创建alertmanager报警模块
root@iZj6c72dzbei17o2cuksmeZ:~/kube-prometheus-0.14.0# cat manifests/zjj-nodeExporter-prometheusRule.yaml

yaml 复制代码

apiVersion: monitoring.coreos.com/v1
kind: PrometheusRule
metadata:
  labels:
    app.kubernetes.io/component: nodeInstances
    app.kubernetes.io/name: NodeInstances
    app.kubernetes.io/part-of: kube-prometheus
    app.kubernetes.io/version: 1.8.2
    prometheus: k8s
    role: alert-rules
  name: node-instances-rules
  namespace: monitoring
spec:
  groups:
  - name: zjj-rules
    rules:
    - alert: NodeInstancesDown
      annotations:
        description: Failed to scrape {{ $labels.job }} on {{ $labels.instance }} for
          more than 1 minutes. Node seems down.
        title: Node {{ $labels.instance }} is down
      expr: up{job="node-exporter"} == 0
      for: 1m
      labels:
        severity: critical

启动新的规则

bash 复制代码

root@iZj6c72dzbei17o2cuksmeZ:~/kube-prometheus-0.14.0# kubectl apply -f manifests/zjj-nodeExporter-prometheusRule.yaml