Memory leak caused by nvtracker in DeepStream5.1

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU) Jetson
• DeepStream Version 5.1
• JetPack Version (valid for Jetson only) 4.5
• TensorRT Version 7.1.3-1+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)

We found that nvtracker causes memory leak.

Our pipeline recreates nvtracker when reflecting updated nvtracker config.
However, every time nvtracker is removed form the pipeline, some amount of memory is not released.
The amount of leak depends on nvtracker parameters like maxTargetsPerStream. For maxTargetsPerStream~100, abount 100MB memory is leaked.

This issue seems to be the same as Question on nvtracker memory leak.
According to the post, there are some memory leak patches in DS6.0.1

I’m afraid our application is based on DS5.1.
If the patches are available for DS5.1, could you share them?
And, could you tell us what was modified by the patches?

Can you upgrade to latest DeepStream release 6.4 and check if you can reproduce the issue?

Thank you for the reply.
I’m afraid it is difficult to upgrade DS in our application.
So it may take some time to check the issue for the latest DS.
Is it possible to share the memory leak patches beforehand?

Suggest to upgrade to DeepStream 6.4. DeepStream 5.1 is too old. It is hard to identify those patch as we have too many commit during the long period.

Sorry for the late reply.
We are using JetPack4.5.
Do you have any patch to enable DeepStream6.4 on JetPack4.5?

Sorry but there is no patch on old version, we suggest upgrading to the lastst Jetpack for your Jetson module (may be 4.6.4 for your case) and use the corresponding DeepStream on it.

Thank you very much for answering! I’ll try to upgrade.

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