FPS drop in deepstream pipeline during input stream downtime

Accelerated Computing Intelligent Video Analytics DeepStream SDK
, ,
1

• DeepStream Version: 7.0 (Docker Deepstream)
• CUDA:12.2

Has been observing FPS drop in Deepstream pipeline during stream downtime
Example- If the pipeline is processing 10 stream at 10 Fps,in case of any one or two stream going down,the fps of the whole pipeline will be going down like 4 or 5 fps per stream
Appsrc→jpegparse→nvv4l2dec→mux→….down stream elements

3

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)

4

Notcing you are testing a custom code, can you use DeepStream sample to reprodcue this issue? are you using old nvstreammux or new nvstreammux? Please refer to this faq How to set parameters reasonably to improve the efficiency of nvstreammux in live mode.
Testing with deepstream-app, I am not able to reproduce this issue, after one rtsp source was closed, the fps of other source did not change. Here is the log deepstream-app.txt (5.4 KB)

5

Hi! Since we haven’t heard back from you for a while, we’re assuming everything is resolved and will close this topic. If you need any further help, don’t hesitate to open a new topic. Thanks!