Got Docker error after try to run roboflow inference server on Jetson

Hi All,

I have tried to build Roboflow inference server in jetson nano following this
https://wiki.seeedstudio.com/Roboflow-Jetson-Getting-Started/
(Local Docker Build Method)

after I cloned a project and try to run
docker run --privileged --net=host --runtime=nvidia roboflow/roboflow-inference-server-jetson-5.1.1:seeed1

then I got

docker: Error response from daemon: failed to create task for container: failed to create shim task: OCI runtime create failed: runc create failed: unable to start container process: error during container init: error running hook #1: error running hook: exit status 1, stdout: , stderr: time="2024-12-12T16:08:32+07:00" level=info msg="Symlinking /var/lib/docker/overlay2/d7ea998d2ef1fd099474e8bf75ae040fc7da4f16f777b518364bb0cbda0030b9/merged/usr/lib/aarch64-linux-gnu/tegra/libcuda.so to libcuda.so.1.1"
time="2024-12-12T16:08:32+07:00" level=info msg="Symlinking /var/lib/docker/overlay2/d7ea998d2ef1fd099474e8bf75ae040fc7da4f16f777b518364bb0cbda0030b9/merged/usr/lib/aarch64-linux-gnu/tegra/libgstnvcustomhelper.so to libgstnvcustomhelper.so.1.0.0"
time="2024-12-12T16:08:32+07:00" level=info msg="Symlinking /var/lib/docker/overlay2/d7ea998d2ef1fd099474e8bf75ae040fc7da4f16f777b518364bb0cbda0030b9/merged/usr/lib/aarch64-linux-gnu/tegra/libnvidia-kms.so to libnvidia-kms.so.35.4.1"
time="2024-12-12T16:08:32+07:00" level=info msg="Symlinking /var/lib/docker/overlay2/d7ea998d2ef1fd099474e8bf75ae040fc7da4f16f777b518364bb0cbda0030b9/merged/usr/lib/aarch64-linux-gnu/tegra/libnvidia-nvvm.so.4 to libnvidia-nvvm.so.35.4.1"
time="2024-12-12T16:08:32+07:00" level=info msg="Symlinking /var/lib/docker/overlay2/d7ea998d2ef1fd099474e8bf75ae040fc7da4f16f777b518364bb0cbda0030b9/merged/usr/lib/aarch64-linux-gnu/tegra/libnvidia-ptxjitcompiler.so.1 to libnvidia-ptxjitcompiler.so.35.4.1"
time="2024-12-12T16:08:32+07:00" level=info msg="Symlinking /var/lib/docker/overlay2/d7ea998d2ef1fd099474e8bf75ae040fc7da4f16f777b518364bb0cbda0030b9/merged/usr/lib/aarch64-linux-gnu/tegra/libnvidia-vksc-core.so to libnvidia-vksc-core.so.35.4.1"
time="2024-12-12T16:08:32+07:00" level=info msg="Symlinking /var/lib/docker/overlay2/d7ea998d2ef1fd099474e8bf75ae040fc7da4f16f777b518364bb0cbda0030b9/merged/usr/share/glvnd/egl_vendor.d/10_nvidia.json to ../../../lib/aarch64-linux-gnu/tegra-egl/nvidia.json"
time="2024-12-12T16:08:32+07:00" level=error msg="failed to create link [../../../lib/aarch64-linux-gnu/tegra-egl/nvidia.json /usr/share/glvnd/egl_vendor.d/10_nvidia.json]: failed to create symlink: failed to remove existing file: remove /var/lib/docker/overlay2/d7ea998d2ef1fd099474e8bf75ae040fc7da4f16f777b518364bb0cbda0030b9/merged/usr/share/glvnd/egl_vendor.d/10_nvidia.json: device or resource busy": unknown.
ERRO[0000] error waiting for container:

I am not sure what is missing for NVIDIA container or docker.
Please advise me how to resolve it.

Thank you in advance.

This topic was automatically closed 10 days after the last reply. New replies are no longer allowed.