FPS reduced to 0.2 -0.6 FPS from 10 FPS while running 4 rtsp streams on a single pipeline on nano

Accelerated Computing Intelligent Video Analytics DeepStream SDK
, , ,
1

• Hardware Platform (Jetson / GPU) Jetson Nano 4GB arm64
• DeepStream Version Deepstream-6.0_6.0.0-1
• JetPack Version (valid for Jetson only) Jetpack version-4.6-b199
• TensorRT Version 8.2.1.8-1+cuda10.2
• 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)

Running 4 rtsp streams on a single deepstream pipeline including tracker , the pipeline initially runs on max of 8-10 fps but after 30-45 mins it reduced to 0.2-0.6 and even 0 fps sometimes , and it looks like the system is getting choked because it slowed down every process. Why this thing is happening ? any comments or solution would be appreciated.
Thanks

2

any idea , or any suggestion or anything @nvidiaAI @team-nvidia

3

Moving this topic to the Deepstream category for better visibility.

7

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

Anything component in the pipeline will impact the performance of the whole pipeline. E.G. the network efficiency since you are using rtsp sources, the model GPU performance, the complexity of the postprocessing … etc.

You need to check the performance of each component to find out the bottleneck.

9

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.