Performance Discrepancy in DeepStream: Single Pipeline vs. Independent Pipelines for RTSP Streams

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

Hi, I’m encountering a performance inconsistency in DeepStream when processing two simulated RTSP streams and would appreciate your insights.

Issue Description

  • Setup: Two RTSP streams (simulated) processed via:
    • Single pipeline (using nvurisrcbin + new streammux)
    • Two independent pipelines (one per stream)
  • Observation:
    • Single pipeline: Missed detections (496 total vs. baseline 596) .
    • Independent pipelines: Better accuracy (576 detections, 0 misses).
  • Config: Streammux settings prioritize batch processing (max-num-frames-per-batch=1/2). Full config [attached/pasted in link].

Questions

  1. Why does the single pipeline underperform despite identical streams? Could it relate to:
  • Resource contention in streammux?
  • Suboptimal batching for multi-stream in one pipeline?
  1. How can I tune the single pipeline to match the performance of independent pipelines?

Additional Context

  • Local PC: Results differ (as above).
  • Cloud Server: Both approaches perform equally well (likely due to higher resources).
  • Goal: Achieve consistent accuracy regardless of pipeline architecture.

I’d appreciate any suggestions to balance performance or debug the single-pipeline bottleneck. Thank you!

config_mux_source3_ancien.txt (2.5 KB)

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

• Hardware Platform : GPU
• DeepStream Version : deepstream 7.1

5

plese refer to this faq How to set parameters reasonably to improve the efficiency of nvstreammux in live mode