Please provide complete information as applicable to your setup. • Hardware Platform (Jetson / GPU): Quadro RTX 4000 • DeepStream Version: 6.1.1 • TensorRT Version: 8.5.3.1 • NVIDIA GPU Driver Version (valid for GPU only): 510.47.03 I experimented on the deepstream_image_meta_test sample. I use…

I tested two pipelines, pipeline1 has memory leak issue, , pipeline2 has no memory leak issue test-h264.txt (18.1 KB). pipeline1: gst-launch-1.0 filesrc location=/home/10720p.mp4 ! qtdemux ! h264parse ! nvv4l2decoder ! fakesink pipeline2: gst-launch-1.0 filesrc location=/home/10720p.h264 ! h26…

can you reproduce the memory leak issue with the origin code(fakesink) and video7-4k-hevc.mp4 in your environment?

This is the result showed by nvmemstat PID: 1645075 16:20:14 Total used hardware memory: 0.0000 KiB hardware memory: 0.0000 KiB VmSize: 23601.2070 MiB VmRSS: 3164.7812 MiB RssFile: 687.2383 MiB RssAnon: 2467.5430 MiB lsof: 5 PID: 1645075 16:20:15 Total used hardware memory: 0.0000 KiB hardware…

As you know, the application will use much memory when loading the model engine, did you start application and nvmemstat at the same time? please start nvmemstat after the application prints “Running…”. are you testing in DS6.2 docker container now? if still can reproduce, please capture a valg…

Here is the result after Running … PID: 1697856 16:51:00 Total used hardware memory: 0.0000 KiB hardware memory: 0.0000 KiB VmSize: 34688.0234 MiB VmRSS: 3721.3867 MiB RssFile: 803.2852 MiB RssAnon: 2503.9414 MiB lsof: 5 PID: 1697856 16:51:01 Total used hardware memory: 0.0000 KiB hardware mem…

[image] fanzh: valgrind --leak-check=full --log-file=leak.log ./depstream-image-meta-test 0 file:///home/video7-4k-hevc.mp4 The output of valgrind is in the following file. leak.log (382.4 KB)

Here is valgrind log from my project that have 1MB/s leak ==465696== LEAK SUMMARY: ==465696== definitely lost: 36,061 bytes in 47 blocks ==465696== indirectly lost: 21,290 bytes in 29 blocks ==465696== possibly lost: 355,480 bytes in 2,723 blocks ==465696== still reachable: 1,466,009,…

I also come to the conclusion that the leak issue comes from other elements of gstreamer, probably from rtspsrc. I am trying to use uridecodebin instead of rtspsrc for my pipeline. I tried simple pipleline like this uridecodebin uri=<src> ! nvstreammux ! fakesink and got the following error Error …

By the way, is there any method to reverse engineering the pipeline that uridecodebin is using under the hood?

I mean which equivalent pipeline can be used instead of uridecodebin like you did in your example with filesrc+h265parse+nvv4l2decoder. The method that you suggested only generate uridecodebin as a block without any detail of what it contains. I want to know what pipeline can be used instead of urid…

Memory leak when testing deepstream sample app

Accelerated Computing Intelligent Video Analytics DeepStream SDK

fanzh April 7, 2023, 9:48am 34

do you want to check the content of uridecodebin? uridecodebin is Gstreamer opensource code, you might dump the media pipeline to check, here is the method: DeepStream SDK FAQ - #10 by mchi

Topic		Replies	Views
Memory leak in DeepStream DeepStream SDK	32	6475	June 27, 2022
DeepStream 5.0 SDK Memory Leak DeepStream SDK nvbugs	17	2269	January 11, 2021
Deepstream pipeline memory leak DeepStream SDK jetson , deepstream	5	285	April 9, 2025
Memory leaks in DeepSteam 5 applications DeepStream SDK cuda	2	1119	June 4, 2020
Default Deepstream app causing memory leaks! DeepStream SDK	2	536	August 26, 2021
Memory Leak of deepstream-test3 (using grpc, triton-server) DeepStream SDK nvbugs	18	922	February 24, 2025
DeepStream 6.0.1 Triton GRPC memory leak DeepStream SDK nvbugs	23	3124	September 2, 2022
Deepstream Sample app deepstream-test3 memory leak DeepStream SDK python , deepstream	1	453	November 27, 2023
Memory leak using new nvstreammux DeepStream SDK nvbugs	7	414	September 11, 2024
Unexpected memory usage in deepstream-test3 DeepStream SDK	24	2469	July 6, 2021

Memory leak when testing deepstream sample app

Related topics