I use deepstream to implement RTMP streaming, and the CPU usage is very high

Please provide complete information as applicable to your setup.

**• Hardware Platform (Jetson / GPU) Jetson Xavier NX
**• DeepStream Version 6.3
**• JetPack Version (valid for Jetson only) 5.1.2
**• TensorRT Version 8.5.2.2
• NVIDIA GPU Driver Version (valid for GPU only)
**• Issue Type( questions, new requirements, bugs) question
• 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 deepstream to implement RTMP streaming, and the CPU usage is as high as 400%.

here is the pipline png

I use nvv4l2h264enc → parse264 → flvmux → rtmpsink

Anyhow the camera number 1~8 the cpu usage is always very high.

Noticing you are using many plugins in pipeline, could you help to narrow down this high CPU issue? for example, which plugin will cause the high CPU usage? Thanks!

  1. what is dsexample plugin used to do?
  2. if using “rtpsrc->…->nvv4l2decoder->fakesink”, what is the CPU usage?
  3. if using “rtpsrc->…->nvv4l2decoder->…nvifner->fakesink”, what is the CPU usage?
  4. based on on point 3, please add plugin one by one to check which plugin will cause the high CPU usage.

I have do this, and find it seems that flvmux makes the cpu usage high

flvmux is Gstreamer opensource code. It is used to mux different streams into an FLV file. this plugin does not support GPU acceleration. when using “…->h264parse->fakesink” pipeline, what is the CPU utilization?

If I don’t use flvmux plugin the cpu runs 60%.
With flvmux plugin it runs 100%

Thanks for the sharing! flvmux and rtmpsink are opensource plugin and they all only use CPU. you can ask this high CPU issue in Gstreamer forum.