Streaming on docker issue

Accelerated Computing Intelligent Video Analytics DeepStream SDK
,
1

• Hardware Platform Quadro RTX 6000
• DeepStream 5.0
• TensorRT Version7.1
• Gst-python
• NVIDIA GPU Driver Version 450.57
• [nvcr.io/nvidia/deepstream:5.0-dp-20.04-base]

Hi

I am developing gstreamer pipeline on docker to detect objects.
I have 8 cameras. So, i want to run 8 pipelines on each of dockers(8 pipelines, 8 dockers). It is working well 4 pipelines on 4 dockers each. When trying to run 5 piplelines on 5 dockers each, it is also working but stopped after a few minutes.
Is this resource problem?

[GPU 60%, CPU 40%, memory 20% used when running 4 pipelines on 4 dockers each.]

3

There is no update from you for a period, assuming this is not an issue any more.
Hence we are closing this topic. If need further support, please open a new one.
Thanks

It is hard to tell the reason. Is there any log or GPU loading status when running the failed case?

5