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)

log.txt (521.5 KB)

2

Is it possible the issue related with the huge log file size in this topic: Log problem - Intelligent Video Analytics / Metropolis Microservices for Jetson - NVIDIA Developer Forums?

3

No , it is deepstream’s problem [After running deepstream for a period of time, the perf module stopped printing]

4

I remember you said the deepstream works fine after 8 days stress test. How long time you meet this problem in this topic?

5

2 weeks

6

I would like to describe my problem in detail,
Yesterday, there was a situation where perf did not print,
Active sources : 0
Mon Jan 6 20:20:17 2025
**PERF:
0.00 (16.85) 0.00 (16.15) 0.00 (17.08) 0.00 (16.28) 0.00 (15.77) 0.00 (16.91) 0.00 (17.71)
This is the last time,
This problem has been reproduced. The last meeting was on the 2nd
But yesterday I also mentioned that the logs are quite large, and this phenomenon is also difficult to reproduce.
So yesterday’s log issue was a prelude to this problem.
This is a partial log of the situation where perf did not print yesterday.
In fact, the core issue is that Deepstream does not print, and the large logs are just a prelude.
Did I not make myself clear?

7

Because if the log is large, it may be difficult to locate the problem, so we proposed the requirement of storing yesterday’s log size on a daily basis
So let’s see if you can get the message I want to convey on your end

8

So now there are two issues, one is the problem with Deepstream, and the other is to lay the groundwork for better analysis from Deepstream logs

10

I can first solve the requirement of logs, and then when the log size is not large, I can find a way to send more logs for analysis. After running deepstream for a period of time, The perf module stopped printing issue. Extracting only a small portion of the logs may not necessarily provide comprehensive information