https://github.com/BugRoger/nvidia-exporter with cuda 9.x
10K+
FROM dlaas-service-base:ubuntu16.04
LABEL vendor=kaisawind
LABEL product=adax
RUN mkdir -p /etc/ld.so.conf.d
RUN echo "/usr/local/cuda/lib64" >> /etc/ld.so.conf.d/cuda.conf
RUN echo "/usr/local/nvidia/lib64" >> /etc/ld.so.conf.d/nvidia.conf
ENV PATH $PATH:/usr/local/nvidia/bin:/usr/local/cuda/bin
ENV LD_LIBRARY_PATH $LD_LIBRARY_PATH:/usr/local/nvidia/lib64/:/usr/local/cuda/lib64/
COPY ./bin/linux/* /
COPY ./nvidia-smi /bin/
COPY ./libnvidia-ml.so.1 /lib/
RUN chmod 755 /nvidia-exporter
ENTRYPOINT ["/nvidia-exporter"]
DaemonSet.yaml
apiVersion: apps/v1
kind: DaemonSet
metadata:
name: nvidia-exporter
labels:
app: nvidia-exporter
spec:
selector:
matchLabels:
app: nvidia-exporter
template:
metadata:
labels:
app: nvidia-exporter
spec:
hostNetwork: true
hostPID: true
restartPolicy: Always
containers:
- name: nvidia-exporter
securityContext:
privileged: true
image: kaisawind/nvidia-exporter
imagePullPolicy: IfNotPresent
ports:
- containerPort: 9401
hostPort: 9401
name: nvidia-exporter
volumeMounts:
- name: nvidia
mountPath: /lib/modules
readOnly: true
volumes:
- name: nvidia
hostPath:
path: /lib/modules
Service.yaml
apiVersion: v1
kind: Service
metadata:
labels:
name: nvidia-exporter
annotations:
prometheus.io/scrape: "true"
prometheus.io/port: "9401"
name: nvidia-exporter
spec:
clusterIP: None
ports:
- name: nvidia-exporter
port: 9401
protocol: TCP
selector:
app: nvidia-exporter
Content type
Image
Digest
Size
88.5 MB
Last updated
almost 8 years ago
docker pull kaisawind/nvidia-exporter