How to decrease the latency of pushing streaming to the local

[13713996904]

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU)
x86-64 Ubuntu 20.04 LTS machine with Geforce GTX 3060
• DeepStream Version
6.1
• TensorRT Version
8.2.5.1
• NVIDIA GPU Driver Version (valid for GPU only)
515.48.07
• Issue Type( questions, new requirements, bugs)
I use the example to push stream to the local, it has a lot of latency , and I decrease the number of cameras from 30 to 6, it still has a lot of latency, is it normal, and how to decrease the latency?

[fanzh]

please measure the latency, please refer to DeepStream Reference Application - deepstream-app — DeepStream 6.1.1 Release documentation
To enable frame latency measurement, run this command on the console:
$ export NVDS_ENABLE_LATENCY_MEASUREMENT=1
To enable latency for all plugins, run this command on the console:
$ export NVDS_ENABLE_COMPONENT_LATENCY_MEASUREMENT=1

[mchi]

if you developed your own DS C++ code, you could also refer to DeepStream SDK FAQ - #12 by bcao to measure the latency of the pipeline comonents

[13713996904]

I use the example of deepstream, and to measure the latency, I run this command on the ubuntu terminal: export NVDS_ENABLE_LATENCY_MEASUREMENT=1, but nothing happened

[fanzh]

1. If you are using deepstream-app, you need to set that two env, then run the applicaiton, you will see this kind of printing:
   Comp name = primary_gie in_system_timestamp = 1663206875358.702881 out_system_timestamp = 1663206875360.052002 component latency= 1.349121
   …
2. If you are using other deepstream sample apps such as deepstream-test3, you need to apply the patch and set the env, then run the applicaiton, please refer to DeepStream SDK FAQ - #12 by bcao