Deepstream hangs during pipeline running

[user130795]

Please provide complete information as applicable to your setup.

**• Hardware Platform (Jetson / GPU) GPU
• DeepStream Version 5.01
• JetPack Version (valid for Jetson only)
• TensorRT Version 7.2
• NVIDIA GPU Driver Version (valid for GPU only) 450.80.02
• Issue Type( questions, new requirements, bugs) bugs
• 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)

hi, my deepstream app sometime hangs, here is some bt of gdb:

any suggession?

[fanzh]

1 what is your GPU product model?
2 are you using deepstream-app to test? what is your start command?
3 did you do some code modification? please upload your diff.

[user130795]

I use a Tesla P4 GPU product, and write my own pipeline, it is just a simple IVA pipeline, but i have so many short mp4 file to process, so every time i create a new pipeline, and process a mp4 file. after this file is processed done, i destory this pipeline, and create another pipeline to process another mp4 file.

my pipeline is like this:

qtmux name=qtmux faststart=false qtmux.src ! filesink location=xxx.mp4 nvstreammux name=mux width=1920 height=1080 batch-size=1 ! nvinfer name=pgie interval=0 config-file-path=dstensor_pgie_config.txt ! queue name=queue ! nvstreamdemux name=demux urisourcebin name=src ! qtdemux name=qtdemux qtdemux.video_0 ! h264parse name=h264parseI ! video/x-h264,stream-format=(string)byte-stream,alignment=(string)au ! nvv4l2decoder ! video/x-raw(memory:NVMM) ! mux.sink_0 demux.src_0 ! nvvideoconvert ! video/x-raw(memory:NVMM),format=RGBA ! nvdsosd ! nvvideoconvert ! capsfilter name=caps0 ! nvv4l2h264enc name=enc iframeinterval=25 ! h264parse name=h264parse ! video/x-h264,stream-format=(string)avc,alignment=(string)au ! qtmux.video_0

and i add a probe in the queue element, in the probe, i add some post-process of the ai model.

sometimes the pipeline run into this hang case, and the progrom just hangs.

[fanzh]

don’t recommend to always recreate pipeline, here are some solutions:
1 you can input many files at once, please refer to /opt/nvidia/deepstream/deepstream/sources/apps/sample_apps/deepstream-app

2 You user can run detection on folder full of images using multifilesrc
You can refer to the sample /opt/nvidia/deepstream/deepstream/sources/apps/sample_apps/deepstream-image-decode-test
and this link
https://gstreamer.freedesktop.org/data/doc/gstreamer/head/gst-plugins-good/html/gst-plugins-good-plugins-multifilesrc.html

[fanzh]

@user130795 Back to your hang issue,
1 please upgrade to deepstream6.0.1 because we have fixed some bugs, and check if there is still that hang issue. here is the link:Quickstart Guide — DeepStream 6.1.1 Release documentation
2 please provide your code, we will reproduce this hang issue by your code.