Failed to load plugin '/usr/lib/x86_64-linux-gnu/gstreamer-1.0/deepstream/libnvdsgst_multistream.so' on Kubernete

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU)
• DeepStream Version
• JetPack Version (valid for Jetson only)
• TensorRT Version
• NVIDIA GPU Driver Version (valid for GPU only)
• Issue Type( questions, new requirements, bugs)
**•
I can not load plugin ‘/usr/lib/x86_64-linux-gnu/gstreamer-1.0/deepstream/libnvdsgst_multistream.so’ on Kubernete cluster

I want some helps from you

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU)
• DeepStream Version
• JetPack Version (valid for Jetson only)
• TensorRT Version
• NVIDIA GPU Driver Version (valid for GPU only)
• Issue Type( questions, new requirements, bugs)
• How to reproduce the issue ? (This is for bugs. Including which sample app is using, the configuration files content, the command line used and other details for reproducing)
• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)

I use the hardwares and softwares:
• Hardware Platform GPU GTX 2080Ti
• DeepStream Version 5.0
• NVIDIA GPU Driver Version: 455.45.01 CUDA Version: 11.1
When I deploy the deepstream app to kubernete I have met this problem. The streamux can not read the rtsp or file input cause of the issue above. But when I run with local docker, it worked

Thank for your respone

Seems miss libcuda.so from the log. Please below guide.

1 Like

Thank you, I followed these links and meet other issue when I run deepstream_test_3.py

My input is rtsp.
I run in docker local is good. The result is


When deploy to kubernete I met this issue

Log show libcuda.so is wrong.

How to fix it? I do not have any ideas. :((

Please refer the setup which I post in Sep 16.