Please provide complete information as applicable to your setup. **• Hardware Platform GPU - 2 x A2 **• DeepStream Version 6.3 **• TensorRT Version 8.5.3.1 **• NVIDIA GPU Driver Version - 535.129.03 **• Issue Type - bug I’m trying to debug an issue that I am struggling to find the route cause of. I have a deepstream 6.3 pipeline (created with Python bindings) that roughly goes: nvurisrcbin -> muxer -> pgie -> tracker -> analytics -> nvstreamdemux -> nvvideoconvert -> nvdsosd -> nvvideoconvert -> h264parse -> rtph264pay -> udpsink I am then using GstRtspServer.RTSPServer to serve RTSP streams. My pipeline takes 7 input RTSP streams from live cameras on my local network and serves 7 annotated RTSP streams via a single GstRtspServer. This works fine for a period of time (around 30 mins), after which the pipeline seems to falter, the streams die and the console output shows periodic “Resetting source” messages from the rtsp-reconnect-interval configured in nvurisrcbin. The load on the GPU is a steady 60% or so, which drops to around 40% after it gets into this state. Can anyone think of a good way to debug this? I have a feeling that it is something to do with time synchronisation between the streams in my pipeline. Are there elements or configuration changes that I can make to try to improve the robustness? I will also try upgrading to 6.4 I think.

Many thanks, I have modified the batched-push-timeout to accommodate our frame rate and set the environment variable as suggested. The streams seem to be holding fine now. Do you have documentation on that environment variable and will it take effect in DS 6.3 or will I need to upgrade our pipeline to 6.4? Cheers.

[image] rory.hughes1: Do you have documentation on that environment variable and will it take effect in DS 6.3 or will I need to upgrade our pipeline to 6.4? Cheers. sorry for the late reply. it takes effects in DS6.3 and the latter version. please refer to the faq mentioned above. you don’ t need to upgrade to DS6.4 if only testing RTSP reconnectiong.

Deepstream RTSP streams fail over long run periods

Accelerated Computing Intelligent Video Analytics DeepStream SDK

fanzh January 19, 2024, 2:02am 3

please refer to this topic . you can modify batched-push-timeout to improve. please refer to this FAQ to improve. especially please set “export NVSTREAMMUX_ADAPTIVE_BATCHING=yes” .

Topic		Replies	Views
Deepstream with RTSP Cameras DeepStream SDK	3	583	January 5, 2024
Deepstream-app rtsp reconnect issue DeepStream SDK	1	2672	February 25, 2021
RTSP doesn't reconnect DeepStream SDK	3	656	January 4, 2024
DeepStream doesn't reconnect to RTSP stream DeepStream SDK	2	407	August 20, 2024
RTSP Stream Pulling Problem DeepStream SDK deepstream	17	441	November 7, 2025
Deepstream 6.0 RTSP Re-Connection Issue DeepStream SDK rtsp , gstreamer , deepstream	14	1965	August 31, 2022
Deepstream 6.4 with high number of Cameras DeepStream SDK	5	729	February 7, 2024
Deepstream pipeline with RTSP stream stalled time to time and stoped permanently DeepStream SDK rtsp , gstreamer	9	1429	January 16, 2023
Frame rate drop, some on rtsp cameras DeepStream SDK cudnn , deepstream	9	341	April 14, 2025
No frames send from rtsp server to deepstream_test3 DeepStream SDK	9	761	February 29, 2024

Deepstream RTSP streams fail over long run periods

Related topics