Deepstream docker on HPC with tiled display

Accelerated Computing Intelligent Video Analytics DeepStream SDK
#1

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU) A100 GPU
• DeepStream Version 6.1
• JetPack Version (valid for Jetson only)
• TensorRT Version
• NVIDIA GPU Driver Version (valid for GPU only) 510.47.03
• Issue Type( questions, new requirements, bugs)
Debug info: gsturidecodebin.c(920): unknown_type_cb (): /GstPipeline:pipeline/GstBin:multi_src_bin/GstBin:src_sub_bin2/GstURIDecodeBin:src_elem
cuGraphicsGLRegisterBuffer failed with error(219) gst_eglglessink_cuda_init texture = 1
** INFO: <bus_callback:180>: Pipeline running

**PERF: 281.53 (0.52) 151.38 (1.29) 151.38 (1.29) 281.57 (0.52)
ERROR from secondary_gie_bin_queue: Internal data stream error.
Debug info: gstqueue.c(988): gst_queue_handle_sink_event (): /GstPipeline:pipeline/GstBin:secondary_gie_bin/GstQueue:secondary_gie_bin_queue:
streaming stopped, reason not-negotiated (-4)
Quitting
ERROR from sink_bin_queue: Internal data stream error.
Debug info: gstqueue.c(988): gst_queue_handle_sink_event (): /GstPipeline:pipeline/GstBin:processing_bin_0/GstBin:sink_bin/GstQueue:sink_bin_queue:
streaming stopped, reason not-negotiated (-4)
[NvMultiObjectTracker] De-initialized
App run failed

I am trying to set up Deepstream app(source4_1080p_dec_infer-resnet_tracker_sgie_tiled_display_int8.txt) on one of the cluster which has A100 GPU, whenever I set the sink type to fakesink app works however, app crashes when I set it to eglsink.

I am currently accessing deepstream in docker container which is running on gpu node with tigervnc.

What should i do to run the apps.

#2

Seems there is no X server on your server, please refer explanation here: Quickstart Guide — DeepStream 6.1.1 Release documentation

#4

I do have X server running, that’s how I am accessing the machine.
when I do echo $DISPLAY I get reply back as : localhost:10.0

#5

Can you run deepstream-app with nveglglessink in your host?

#7

I am only allowed to use docker on HPC. So cannot really do that and It should not matter as well. I am trying nveglglessink in docker deepstream app but getting error. I only have this much access

#8

There is no update from you for a period, assuming this is not an issue anymore.
Hence we are closing this topic. If need further support, please open a new one.
Thanks

It matters. Is there a physical monitor connected with Nvidia GPU with the HPC?

Can you refer to Troubleshooting — DeepStream 6.1.1 Release documentation (nvidia.com)?