After running deepstream for a period of time, the perf module stopped printing

Accelerated Computing Intelligent Video Analytics Metropolis Microservices for Jetson
,
1

Please provide complete information as applicable to your setup.

**• Hardware Platform (Jetson / GPU)6.1
**• DeepStream Version 7.1
**• JetPack Version (valid for Jetson only)6.1
**• TensorRT Version 10.3
**• NVIDIA GPU Driver Version (valid for GPU only)540.4.0
• Issue Type( questions, new requirements, bugs)
The Type of this mechine is Orin AGX 64G
• 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)

After running deepstream for a period of time, the perf module stopped printing

In the new version, this issue has occurred twice. I will upgrade the log level again later to confirm if this issue has been resolved?

2

logger.zip (1006.6 KB)

3

Please also share the configure files. Thanks!

4

test5_config_file_nvmultiurisrcbin_src_list_attr_all.txt (8.4 KB)

5

Frequent addition and deletion may be one of the factors that cause trackers. From these two logs, it seems that there are some other reasons as well.

6

2024-12-16 164512
2024-12-16 164512980×918 48.9 KB

There is a very strange phenomenon in the picture above,
0.00 (18.83)
Question 0.00 is a real-time value, 18.83 is an average value, right?
0.00 (18.82) lasted for a long time, with no decrease in the average value and no automatic deletion

7

I don’t know if it has anything to do with the instability of the flow here?

8

I found you don’t enable model which can run on DLA. New JPS which based on DeepStream 7.1 will release soon. Is it possible to wait new JPS release and test on the new JPS release?

9

I have used DLA

10

config_infer_primary.txt (3.4 KB)
I added it here

11

I try it

12

Can you answer my question?
Question 0.00 is a real-time value, 18.83 is an average value, right?

13

Yes, you are right.

14

Kevin， This phenomenon has occurred for the third time. Below are the logs. Please take a look, they are quite large
Link: https://pan.baidu.com/s/1ttvSr9WfghaXWYtJkdI_rg?pwd=abcd Extract code: abcd

I will also analyze it

15

It doesn’t seem to be a track issue

16

I have some issue to download it. Can you share less log which the issue happen?

17

I try it
you try downloading it on either side as well
I set the log level to 4

18

I suggest you download it if possible, as this log is more comprehensive

19

logger.txt (875.3 KB)

This is the last time the nearby logs were printed

21

Please use below setting to do your test. Seems you removed “select-rtp-protocol=4” in your configure file.

rtsp-reconnect-interval-sec=10
select-rtp-protocol=4
rtsp-reconnect-attempts=1