Please provide complete information as applicable to your setup.
• Hardware Platform (Jetson / GPU)
Jetson Nano
• DeepStream Version
6.0.1
• JetPack Version (valid for Jetson only)
4.6.1
• TensorRT Version
8.0.1
• NVIDIA GPU Driver Version (valid for GPU only)
• Issue Type( questions, new requirements, bugs)
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)
Decode RTSP H.264 stream on a Jetson Nano under heavy load
• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)
Most times when the Jetson Nano is under heavy load the RTSP H.264 stream starts producing errors (see image). There are usually no decoding issues when it runs at a reasonable FPS.
I’ve narrowed the issue down to the rtspsrc plugin. I used smart recording to save the H.264 stream and used a different decoder and it had the same issue (which means it’s not a decoder issue).
The settings used on the rtspsrc are latency 200, drop-on-latency TRUE, enable-max-performance TRUE, bufapi-version TRUE`. I’ve tried turning these settings on and off and increasing and decreasing the latency, but I still have the same issues. I’ve also tried setting it to TCP only. Any ideas?
I’ve seen these issues on multiple Nanos and from different camera models (and manufacturers).
My pipeline is: rtspsrc → queue → decodebin → queue → nvvideoconvert → capsfilter (video/x-raw, memory:NVMM) → nvstreammux …
The decodebin becomes rtph264depay → h264parse → nvv4l2decoder.