Files
hpc-lab1/gpu01/monitoring/docker-compose.yaml
2026-03-28 03:00:58 +08:00

31 lines
984 B
YAML

---
services:
node_exporter:
image: quay.io/prometheus/node-exporter:v1.10.2
command: ['--path.rootfs=/host']
network_mode: host
pid: host
restart: unless-stopped
volumes:
- '/:/host:ro,rslave'
process_exporter:
image: docker.io/ncabatoff/process-exporter:v0.8.7
privileged: true
command: ['-procfs', '/host/proc', '-config.path', '/config/config.yml']
ports:
- 9256:9256
volumes:
- '/proc:/host/proc:ro,rslave'
- './docker/process_exporter:/config:ro'
nvidia_gpu_exporter:
image: ghcr.io/utkuozdemir/nvidia_gpu_exporter:1.4.1-amd64
ports:
- 9835:9835
devices:
- '/dev/nvidiactl:/dev/nvidiactl'
- '/dev/nvidia0:/dev/nvidia0'
volumes:
- '/usr/lib/x86_64-linux-gnu/libnvidia-ml.so:/usr/lib/x86_64-linux-gnu/libnvidia-ml.so'
- '/usr/lib/x86_64-linux-gnu/libnvidia-ml.so.1:/usr/lib/x86_64-linux-gnu/libnvidia-ml.so.1'
- '/usr/bin/nvidia-smi:/usr/bin/nvidia-smi'