Increasing memory usage in deepstream-app with RTSP stream input

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU) Jetson
• DeepStream Version 6.0.1
• JetPack Version (valid for Jetson only) 4.6.1
• TensorRT Version 8.2.1+cuda10.2
• NVIDIA GPU Driver Version (valid for GPU only)
• Issue Type( questions, new requirements, bugs) questions
• 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 am suffering from growing memory usage in deepstream-app when inputting a mp4 file via an RTSP server.
This issue does not occur when reading the same mp4 file instead of RTSP streaming.

Here are results (config, valgrind log, memory log and plot of VmRSS)

information and conditions:

In the both cases, valgrind logs show some memory leak, and the amount is larger in the case of rtsp.
Could you please reproduce this issue?
And is there any way to suppress the growing memory usage.

Can you upgrade the DeepStream to the latest version? We continue to fix a lot of memory leaks from 6.0.1 to 6.4 version.

Thank you for the reply!
We would like to use deepstream for our production, so deepstream6.4 that requires JetPack6.0DP is not suitable.

Is there any version except 6.4 that can solve the issue?
Or, if the issue has been solved only in deepstream6.4, could you share any patch to deepstream6.0.1?

There are many fixes for memory leaks issues from the 6.0 to 6.4. Much of the code involved is not open source. We can’t provide all the patches separately because of incompatibility issues.

Sorry for the late reply.
OK, I will use newer versions of DeepStream.

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.