nvidia-docker 安装使用

本文记录Nvidia docker的安装与使用方法

root@node04-v100:~# lspci | grep  N
1a:00.0 3D controller: NVIDIA Corporation Device 1df6 (rev a1)
1b:00.0 3D controller: NVIDIA Corporation Device 1df6 (rev a1)
1d:00.0 3D controller: NVIDIA Corporation Device 1df6 (rev a1)
1e:00.0 3D controller: NVIDIA Corporation Device 1df6 (rev a1)
3d:00.0 3D controller: NVIDIA Corporation Device 1df6 (rev a1)
3e:00.0 3D controller: NVIDIA Corporation Device 1df6 (rev a1)
40:00.0 3D controller: NVIDIA Corporation Device 1df6 (rev a1)
41:00.0 3D controller: NVIDIA Corporation Device 1df6 (rev a1)

root@node04-v100:~# nvidia-smi
Fri Jul 29 09:15:02 2022       
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 470.82.01    Driver Version: 470.82.01    CUDA Version: 11.4     |
|-------------------------------+----------------------+----------------------+
| GPU  Name        Persistence-M| Bus-Id        Disp.A | Volatile Uncorr. ECC |
| Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |
|                               |                      |               MIG M. |
|===============================+======================+======================|
|   0  Tesla V100S-PCI...  Off  | 00000000:1A:00.0 Off |                    0 |
| N/A   30C    P0    26W / 250W |      0MiB / 32510MiB |      0%      Default |
|                               |                      |                  N/A |
+-------------------------------+----------------------+----------------------+
|   1  Tesla V100S-PCI...  Off  | 00000000:1B:00.0 Off |                    0 |
| N/A   30C    P0    25W / 250W |      0MiB / 32510MiB |      0%      Default |
|                               |                      |                  N/A |
+-------------------------------+----------------------+----------------------+
|   2  Tesla V100S-PCI...  Off  | 00000000:1D:00.0 Off |                    0 |
| N/A   31C    P0    25W / 250W |      0MiB / 32510MiB |      0%      Default |
|                               |                      |                  N/A |
+-------------------------------+----------------------+----------------------+
|   3  Tesla V100S-PCI...  Off  | 00000000:1E:00.0 Off |                    0 |
| N/A   30C    P0    25W / 250W |      0MiB / 32510MiB |      0%      Default |
|                               |                      |                  N/A |
+-------------------------------+----------------------+----------------------+
|   4  Tesla V100S-PCI...  Off  | 00000000:3D:00.0 Off |                    0 |
| N/A   31C    P0    25W / 250W |      0MiB / 32510MiB |      0%      Default |
|                               |                      |                  N/A |
+-------------------------------+----------------------+----------------------+
|   5  Tesla V100S-PCI...  Off  | 00000000:3E:00.0 Off |                    0 |
| N/A   31C    P0    27W / 250W |      0MiB / 32510MiB |      0%      Default |
|                               |                      |                  N/A |
+-------------------------------+----------------------+----------------------+
|   6  Tesla V100S-PCI...  Off  | 00000000:40:00.0 Off |                    0 |
| N/A   29C    P0    24W / 250W |      0MiB / 32510MiB |      0%      Default |
|                               |                      |                  N/A |
+-------------------------------+----------------------+----------------------+
|   7  Tesla V100S-PCI...  Off  | 00000000:41:00.0 Off |                    0 |
| N/A   29C    P0    26W / 250W |      0MiB / 32510MiB |      0%      Default |
|                               |                      |                  N/A |
+-------------------------------+----------------------+----------------------+
                                                                               
+-----------------------------------------------------------------------------+
| Processes:                                                                  |
|  GPU   GI   CI        PID   Type   Process name                  GPU Memory |
|        ID   ID                                                   Usage      |
|=============================================================================|
|  No running processes found                                                 |

　

配置nvidia-docker

https://github.com/NVIDIA/nvidia-docker/wiki/Installation-(version-2.0)

# 添加源
$ curl -s -L https://nvidia.github.io/nvidia-docker/gpgkey | sudo apt-key add -
$ distribution=$(. /etc/os-release;echo $ID$VERSION_ID)
$ curl -s -L https://nvidia.github.io/nvidia-docker/$distribution/nvidia-docker.list | \
  sudo tee /etc/apt/sources.list.d/nvidia-docker.list

安装nvidia-docker2

# 更新源
$ sudo apt update

# 安装nvidia-docker2
$ sudo apt install -y nvidia-docker2

# 重启Docker daemon 
$ sudo pkill -SIGHUP dockerd

验证nvidia-docker2

$ sudo nvidia-docker run --rm nvidia/cuda nvidia-smi