安装nvidia_gpu_exporter服务

# VERSION=0.3.0​
# wget ​​https://github.com/utkuozdemir/nvidia_gpu_exporter/releases/download/v${VERSION}/nvidia_gpu_exporter_${VERSION}_linux_x86_64.tar.gz​​
# tar -xvzf nvidia_gpu_exporter_${VERSION}_linux_x86_64.tar.gz​
# mv nvidia_gpu_exporter /usr/local/bin​
# ./nvidia_gpu_exporter

此时通过web页面就可查看此台GPU服务器的gpu-metircs信息，如下图​

可以看到GPU相关信息​

创建nvidia_gpu_exporter服务​

# vim /etc/systemd/system/nvidia_gpu_exporter.service ​

[Unit]​
Description=Nvidia GPU Exporter​
After=network-online.target​

[Service]​
Type=simple​

User=nvidia_gpu_exporter​
Group=nvidia_gpu_exporter​

ExecStart=/usr/local/bin/nvidia_gpu_exporter​

SyslogIdentifier=nvidia_gpu_exporter​

Restart=always​
RestartSec=1​

NoNewPrivileges=yes​

ProtectHome=yes​
ProtectSystem=strict​
ProtectControlGroups=true​
ProtectKernelModules=true​
ProtectKernelTunables=yes​
ProtectHostname=yes​
ProtectKernelLogs=yes​
ProtectProc=yes​

[Install]​
WantedBy=multi-user.target​
# systemctl daemon-reload ​
[root@k8s-gpu4 ~]# systemctl enable nvidia_gpu_exporter​
[root@k8s-gpu4 ~]# systemctl start nvidia_gpu_exporter.service ​
[root@k8s-gpu4 ~]# systemctl status nvidia_gpu_exporter.service ​
● nvidia_gpu_exporter.service - Nvidia GPU Exporter​
 Loaded: loaded (/etc/systemd/system/nvidia_gpu_exporter.service; enabled; vendor preset: disabled)​
 Active: active (running) since Fri 2022-05-13 17:36:03 CST; 5s ago​
 Main PID: 80178 (nvidia_gpu_expo)​
 Tasks: 6​
 Memory: 5.6M​
 CGroup: /system.slice/nvidia_gpu_exporter.service​
 └─80178 /usr/local/bin/nvidia_gpu_exporter​

May 13 17:36:03 k8s-gpu4 systemd[1]: Started Nvidia GPU Exporter.​
May 13 17:36:04 k8s-gpu4 nvidia_gpu_exporter[80178]: ts=2022-05-13T09:36:04.005Z caller=main.go:68 level=info msg="Listening on add...=:9835​
May 13 17:36:04 k8s-gpu4 nvidia_gpu_exporter[80178]: ts=2022-05-13T09:36:04.006Z caller=tls_config.go:195 level=info msg="TLS is di...=false​
Hint: Some lines were ellipsized, use -l to show in full.​

服务启动成功，通过页面查看​

1. 创建endpoints​

# cat gpu-exporter-endpoint.yaml 
apiVersion: v1
kind: Endpoints
metadata:
 name: nvidia-gpu-exporter
 namespace: monitoring
subsets:
 - addresses:
 - ip: 10.1.12.17
 ports:
 - name: http
 port: 9835
 protocol: TCP

上面的ip为GPU服务器地址，如果是多台GPU，可在下面继续添加，如
- ip: *.*.*.*
- ip: *.*.*.*

# kubectl create -f gpu-exporter-endpoint.yaml 
endpoints/nvidia-gpu-exporter created
# kubectl get endpoints -n monitoring nvidia-gpu-exporter 
NAME ENDPOINTS AGE
nvidia-gpu-exporter 10.1.12.17:9835 39s
# kubectl describe endpoints -n monitoring nvidia-gpu-exporter 
Name: nvidia-gpu-exporter
Namespace: monitoring
Labels: <none>
Annotations: <none>
Subsets:
 Addresses: 10.1.12.17
 NotReadyAddresses: <none>
 Ports:
 Name Port Protocol
 ---- ---- --------
 http 9835 TCP

Events: <none>

2. 创建service​

# cat gpu-exporter-svc.yaml ​
apiVersion: v1​
kind: Service​
metadata:​
 labels:​
 app: nvidia-gpu-exporter​
 name: nvidia-gpu-exporter​
 namespace: monitoring​
spec:​
 ports:​
 - name: http​
 protocol: TCP​
 port: 9835​
 targetPort: http​
 type: ClusterIP​
# kubectl delete -f gpu-exporter-svc.yaml ​
service "nvidia-gpu-exporter" deleted​
kubectl create -f gpu-exporter-svc.yaml ​
service/nvidia-gpu-exporter created​
# kubectl get svc -n monitoring nvidia-gpu-exporter ​
NAME TYPE CLUSTER-IP EXTERNAL-IP PORT(S) AGE​
nvidia-gpu-exporter ClusterIP 10.10.75.226 <none> 9835/TCP 12s​
# kubectl describe svc -n monitoring nvidia-gpu-exporter ​
Name: nvidia-gpu-exporter​
Namespace: monitoring​
Labels: app=nvidia-gpu-exporter​
Annotations: <none>​
Selector: <none>​
Type: ClusterIP​
IP: 10.10.235.70​
Port: http 9835/TCP​
TargetPort: http/TCP​
Endpoints: 10.1.12.17:9835​
Session Affinity: None​
Events: <none>

上面的endpioins一定要为上面创建的endpoints中的IP和port

2. 创建servicemonitor

#cat gpu-exporter-serviceMonitor.yaml 
apiVersion: monitoring.coreos.com/v1
kind: ServiceMonitor
metadata:
 labels:
 app: nvidia-gpu-exporter
 name: nvidia-gpu-exporter
 namespace: monitoring
spec:
 endpoints:
 - interval: 30s
 port: http
 jobLabel: app
 selector:
 matchLabels:
 app: nvidia-gpu-exporter
kubectl create -f gpu-exporter-serviceMonitor.yaml 
servicemonitor.monitoring.coreos.com/nvidia-gpu-exporter created
[root@k8s-master dongtai]# kubectl get servicemonitors.monitoring.coreos.com -n monitoring nvidia-gpu-exporter 
NAME AGE
nvidia-gpu-exporter 12s
# kubectl describe servicemonitors.monitoring.coreos.com -n monitoring nvidia-gpu-exporter 
Name: nvidia-gpu-exporter
Namespace: monitoring
Labels: app=nvidia-gpu-exporter
Annotations: <none>
API Version: monitoring.coreos.com/v1
Kind: ServiceMonitor
Metadata:
 Creation Timestamp: 2022-05-13T09:50:35Z
 Generation: 1
 Managed Fields:
 API Version: monitoring.coreos.com/v1
 Fields Type: FieldsV1
 fieldsV1:
 f:metadata:
 f:labels:
 .:
 f:app:
 f:spec:
 .:
 f:endpoints:
 f:jobLabel:
 f:selector:
 .:
 f:matchLabels:
 .:
 f:app:
 Manager: kubectl-create
 Operation: Update
 Time: 2022-05-13T09:50:35Z
 Resource Version: 14080381
 Self Link: /apis/monitoring.coreos.com/v1/namespaces/monitoring/servicemonitors/nvidia-gpu-exporter
 UID: 7fdb365b-8bcd-4fc2-9772-9ad7de6155bf
Spec:
 Endpoints:
 Interval: 30s
 Port: http
 Job Label: app
 Selector:
 Match Labels:
 App: nvidia-gpu-exporter
Events: <none>

4. prometheus页面验证​

在prometheus页面的targets中查看nvidia_gpu_exporter​

​

在Graph页面中进行nvidia搜索​

​

通过搜索可以得到这台GPU服务器有两张3090GPU​

在grafana导入官方提供的json文件​

导入官方的json文件会出现错误提示，原因是这个json文件配置有问题，我们需要进行修改。​

点击右上角进行修改​

点击Variables，点击gpu​

将Query改成如下，改完后，可以得到GPU服务器的IP，最后点击update​

返回监控页后，可以得到如下图：​

最终GPU相关的性能指标能得到很好展示​