Jetpack 4.2, deepstream samples giving error

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

/usr/bin/deepstream-app -c configs/deepstream-app/source30_720p_dec_infer-resnet_tiled_display_int8.txt
Error: Can’t initialize nvrm channel
Error: Can’t initialize nvrm channel
Couldn’t create ddkvic Session: Cannot allocate memory
nvbuf_utils: Could not create Default NvBufferSession
Error: Can’t initialize nvrm channel
Error: Can’t initialize nvrm channel
Couldn’t create ddkvic Session: Cannot allocate memory
nvbuf_utils: Could not create Default NvBufferSession
Error: Can’t initialize nvrm channel
Error: Can’t initialize nvrm channel
Couldn’t create ddkvic Session: Cannot allocate memory
nvbuf_utils: Could not create Default NvBufferSession
Error: Can’t initialize nvrm channel
Error: Can’t initialize nvrm channel
Couldn’t create ddkvic Session: Cannot allocate memory
nvbuf_utils: Could not create Default NvBufferSession
Error: Can’t initialize nvrm channel
Error: Can’t initialize nvrm channel
Couldn’t create ddkvic Session: Cannot allocate memory
nvbuf_utils: Could not create Default NvBufferSession
Error: Can’t initialize nvrm channel
Error: Can’t initialize nvrm channel
Couldn’t create ddkvic Session: Cannot allocate memory
nvbuf_utils: Could not create Default NvBufferSession
Error: Can’t initialize nvrm channel
Error: Can’t initialize nvrm channel
Couldn’t create ddkvic Session: Cannot allocate memory
nvbuf_utils: Could not create Default NvBufferSession
Error: Can’t initialize nvrm channel
Error: Can’t initialize nvrm channel
Couldn’t create ddkvic Session: Cannot allocate memory
nvbuf_utils: Could not create Default NvBufferSession
Error: Can’t initialize nvrm channel
Error: Can’t initialize nvrm channel
Couldn’t create ddkvic Session: Cannot allocate memory
nvbuf_utils: Could not create Default NvBufferSession
Error: Can’t initialize nvrm channel
Error: Can’t initialize nvrm channel
Couldn’t create ddkvic Session: Cannot allocate memory
nvbuf_utils: Could not create Default NvBufferSession

(gst-plugin-scanner:24868): GStreamer-WARNING **: 22:44:14.643: Failed to load plugin ‘/usr/lib/aarch64-linux-gnu/gstreamer-1.0/libgstopenglmixers.so’: /usr/lib/aarch64-linux-gnu/libgbm.so.1: undefined symbol: drmGetDevice2
Error: Can’t initialize nvrm channel
Error: Can’t initialize nvrm channel
Couldn’t create ddkvic Session: Cannot allocate memory
nvbuf_utils: Could not create Default NvBufferSession
Error: Can’t initialize nvrm channel
Error: Can’t initialize nvrm channel
Couldn’t create ddkvic Session: Cannot allocate memory
nvbuf_utils: Could not create Default NvBufferSession

(gst-plugin-scanner:24870): GStreamer-WARNING **: 22:44:14.857: Failed to load plugin ‘/usr/lib/aarch64-linux-gnu/gstreamer-1.0/libgstopengl.so’: /usr/lib/aarch64-linux-gnu/libgbm.so.1: undefined symbol: drmGetDevice2
Error: Can’t initialize nvrm channel
Error: Can’t initialize nvrm channel
Couldn’t create ddkvic Session: Cannot allocate memory
nvbuf_utils: Could not create Default NvBufferSession
Error: Can’t initialize nvrm channel
Error: Can’t initialize nvrm channel
Couldn’t create ddkvic Session: Cannot allocate memory
nvbuf_utils: Could not create Default NvBufferSession
Error: Can’t initialize nvrm channel

2

Hi harpreet8rb5h,

DeepStream3.0 is specific to R31.1. We will have new release for r32.1.
For R31.1, please install the system with Jetpack 4.1.1

[url]https://developer.nvidia.com/embedded/jetpack-4-1-1[/url]

Thanks

3

Hi kayccc

I tried installing 4.1.1

giving same issues as

https://devtalk.nvidia.com/default/topic/1045444/fresh-flash-on-xavier-out-of-box-fail-error-cuda-cannot-be-installed-on-device/

4

Hi harpreet8rb5h,
Do you mean you cannot install CUDA via Jetpack?

5

Hi DaneLLL

Yes, Neither cuda nor tensorRT

6

Hi Hi harpreet8rb5h,
We don’t hit the issue. Do you use Jetpack4.1.1 and Xavier?

7

Yes DaneLLL

8

Hi harpreet8rb5h,

Can you try to install CUDA by manually?
Steps: [url]https://devtalk.nvidia.com/default/topic/1045444/jetson-agx-xavier/fresh-flash-on-xavier-out-of-box-fail-error-cuda-cannot-be-installed-on-device/post/5304913/#5304913[/url]

1 Like
9

Hi Carolyuu,

I am able to run deepstream app.

but getting below error now:
agx-xavier:~/deepstream_sdk_on_jetson$ sudo rm ${HOME}/.cache/gstreamer-1.0/registry.aarch64.bin
agx-xavier:~/deepstream_sdk_on_jetson$ sudo rm -rf ~/-cache/
agx-xavier:~/deepstream_sdk_on_jetson$ sudo deepstream-app -c configs/deepstream-app/config_infer_secondary_carcolor.txt

(gst-plugin-scanner:13996): GStreamer-WARNING **: 03:20:11.772: Failed to load plugin ‘/usr/lib/aarch64-linux-gnu/gstreamer-1.0/libgstopenglmixers.so’: /usr/lib/aarch64-linux-gnu/libgbm.so.1: undefined symbol: drmGetDevice2

(gst-plugin-scanner:13996): GStreamer-WARNING **: 03:20:12.507: Failed to load plugin ‘/usr/lib/aarch64-linux-gnu/gstreamer-1.0/libgstkms.so’: /usr/lib/aarch64-linux-gnu/gstreamer-1.0/libgstkms.so: undefined symbol: drmModeGetFB

(gst-plugin-scanner:13996): GStreamer-WARNING **: 03:20:12.886: Failed to load plugin ‘/usr/lib/aarch64-linux-gnu/gstreamer-1.0/libcluttergst3.so’: /usr/lib/aarch64-linux-gnu/libgbm.so.1: undefined symbol: drmGetDevice2

(gst-plugin-scanner:13996): GStreamer-WARNING **: 03:20:13.078: Failed to load plugin ‘/usr/lib/aarch64-linux-gnu/gstreamer-1.0/libgstopengl.so’: /usr/lib/aarch64-linux-gnu/libgbm.so.1: undefined symbol: drmGetDevice2
** ERROR: <parse_config_file:1289>: parse_config_file failed
** ERROR: main:584: Failed to parse config file ‘configs/deepstream-app/config_infer_secondary_carcolor.txt’
Quitting
App run failed

10

Resolved ** ERROR: <parse_config_file:1289>: parse_config_file failed , by giving correct path:

ran, and got below error now:

agx-xavier:~/deepstream_sdk_on_jetson$ sudo deepstream-app -c samples/configs/deepstream-app/config_infer_secondary_carcolor.txt
** ERROR: main:613: Failed to set pipeline to PAUSED
Quitting
ERROR from src_bin_muxer: Output width not set
Debug info: /dvs/git/dirty/git-master_linux/multimedia/nvgstreamer/gst-nvmultistream/gstnvstreammux.c(1633): gst_nvstreammux_change_state (): /GstPipeline:pipeline/GstBin:multi_src_bin/GstNvStreamMux:src_bin_muxer
App run failed

11

Hi harpreet8rb5h,

Are you install JetPack-4.1.1 all packages? (include CUDA, cuDNN, TensorRT, OpenCV, VisionWorks)
And install prerequisites packages:

$ sudo apt-get install libssl1.0.0 libgstreamer1.0-0 gstreamer1.0-tools gstreamer1.0-plugins-good gstreamer1.0-plugins-bad gstreamer1.0-plugins-ugly gstreamer1.0-libav libgstrtspserver-1.0-0 libjansson4
12

Hi carolyuu,

Was able to get one config working with below steps:
sudo rm ${HOME}/.cache/gstreamer-1.0/registry.aarch64.bin
sudo rm -rf ~/-cache/
export DISPLAY=:0
change sink type to fake sink in all sinks in config file
sudo deepstream-app -c $HOME/deepstream_sdk_on_jetson/samples/configs/deepstream-app/source30_720p_dec_infer-resnet_tiled_display_int8.txt

below is the log:

vMMLiteOpen : Block : BlockType = 261
NvMMLiteBlockCreate : Block : BlockType = 261
NvMMLiteOpen : Block : BlockType = 261
Allocating new output: 1280x720 (x 12), ThumbnailMode = 0
OPENMAX: HandleNewStreamFormat: 3528: Send OMX_EventPortSettingsChanged: nFrameWidth = 1280, nFrameHeight = 720
Allocating new output: 1280x720 (x 12), ThumbnailMode = 0
OPENMAX: HandleNewStreamFormat: 3528: Send OMX_EventPortSettingsChanged: nFrameWidth = 1280, nFrameHeight = 720
Allocating new output: 1280x720 (x 12), ThumbnailMode = 0
OPENMAX: HandleNewStreamFormat: 3528: Send OMX_EventPortSettingsChanged: nFrameWidth = 1280, nFrameHeight = 720
NvMMLiteBlockCreate : Block : BlockType = 261
NvMMLiteOpen : Block : BlockType = 261
Allocating new output: 1280x720 (x 12), ThumbnailMode = 0
OPENMAX: HandleNewStreamFormat: 3528: Send OMX_EventPortSettingsChanged: nFrameWidth = 1280, nFrameHeight = 720
NvMMLiteBlockCreate : Block : BlockType = 261
NvMMLiteOpen : Block : BlockType = 261
NvMMLiteBlockCreate : Block : BlockType = 261
Allocating new output: 1280x720 (x 12), ThumbnailMode = 0
OPENMAX: HandleNewStreamFormat: 3528: Send OMX_EventPortSettingsChanged: nFrameWidth = 1280, nFrameHeight = 720
NvMMLiteOpen : Block : BlockType = 261
Allocating new output: 1280x720 (x 12), ThumbnailMode = 0
OPENMAX: HandleNewStreamFormat: 3528: Send OMX_EventPortSettingsChanged: nFrameWidth = 1280, nFrameHeight = 720
NvMMLiteBlockCreate : Block : BlockType = 261
NvMMLiteOpen : Block : BlockType = 261
NvMMLiteBlockCreate : Block : BlockType = 261
Allocating new output: 1280x720 (x 12), ThumbnailMode = 0
OPENMAX: HandleNewStreamFormat: 3528: Send OMX_EventPortSettingsChanged: nFrameWidth = 1280, nFrameHeight = 720
Allocating new output: 1280x720 (x 12), ThumbnailMode = 0
OPENMAX: HandleNewStreamFormat: 3528: Send OMX_EventPortSettingsChanged: nFrameWidth = 1280, nFrameHeight = 720
Allocating new output: 1280x720 (x 12), ThumbnailMode = 0
OPENMAX: HandleNewStreamFormat: 3528: Send OMX_EventPortSettingsChanged: nFrameWidth = 1280, nFrameHeight = 720
** INFO: <bus_callback:84>: Pipeline running

**PERF: 20.85 (20.85) 20.92 (20.92) 20.85 (20.85) 20.85 (20.85) 21.13 (21.13) 21.48 (21.48) 21.48 (21.48) 20.92 (20.92) 20.92 (20.92) 21.13 (21.13) 20.85 (20.85) 20.85 (20.85) 20.85 (20.85) 20.87 (20.87) 20.85 (20.85) 21.13 (21.13) 20.85 (20.85) 20.92 (20.92) 20.87 (20.87) 20.92 (20.92) 21.48 (21.48) 20.85 (20.85) 20.92 (20.92) 21.13 (21.13) 20.92 (20.92) 21.13 (21.13) 20.85 (20.85) 21.13 (21.13) 20.85 (20.85) 20.85 (20.85)
**PERF: 21.72 (21.47) 21.72 (21.49) 21.72 (21.47) 21.72 (21.47) 21.72 (21.55) 21.72 (21.66) 21.72 (21.66) 21.72 (21.49) 21.72 (21.49) 21.72 (21.55) 21.72 (21.47) 21.72 (21.47) 21.72 (21.47) 21.72 (21.48) 21.72 (21.47) 21.72 (21.55) 21.72 (21.47) 21.72 (21.49) 21.72 (21.48) 21.72 (21.49) 21.72 (21.66) 21.72 (21.47) 21.72 (21.49) 21.72 (21.55) 21.72 (21.49) 21.72 (21.55) 21.72 (21.47) 21.72 (21.55) 21.72 (21.47) 21.72 (21.47)
**PERF: 21.85 (21.63) 21.85 (21.64) 21.85 (21.63) 21.85 (21.63) 21.85 (21.67) 21.85 (21.74) 21.85 (21.74) 21.85 (21.64) 21.85 (21.64) 21.85 (21.67) 21.85 (21.63) 21.85 (21.63) 21.85 (21.63) 21.85 (21.64) 21.85 (21.63) 21.85 (21.67) 21.85 (21.63) 21.85 (21.64) 21.85 (21.64) 21.85 (21.64) 21.85 (21.74) 21.85 (21.63) 21.85 (21.64) 21.85 (21.67) 21.85 (21.64) 21.85 (21.67) 21.85 (21.63) 21.85 (21.67) 21.85 (21.63) 21.85 (21.63)
WARNING from sink_sub_bin_sink1: A lot of buffers are being dropped.
Debug info: gstbasesink.c(2902): gst_base_sink_is_too_late (): /GstPipeline:pipeline/GstBin:processing_bin_0/GstBin:sink_bin/GstBin:sink_sub_bin1/GstFakeSink:sink_sub_bin_sink1:
There may be a timestamping problem, or this computer is too slow.
**PERF: 21.91 (21.71) 21.91 (21.72) 21.91 (21.71) 21.91 (21.71) 21.91 (21.74) 21.91 (21.79) 21.91 (21.79) 21.91 (21.72) 21.91 (21.72) 21.91 (21.74) 21.91 (21.71) 21.91 (21.71) 21.91 (21.71) 21.91 (21.72) 21.91 (21.71) 21.91 (21.74) 21.91 (21.71) 21.91 (21.72) 21.91 (21.72) 21.91 (21.72) 21.91 (21.79) 21.91 (21.71) 21.91 (21.72) 21.91 (21.74) 21.91 (21.72) 21.91 (21.74) 21.91 (21.71) 21.91 (21.74) 21.91 (21.71) 21.91 (21.71)
WARNING from sink_sub_bin_sink1: A lot of buffers are being dropped.
Debug info: gstbasesink.c(2902): gst_base_sink_is_too_late (): /GstPipeline:pipeline/GstBin:processing_bin_0/GstBin:sink_bin/GstBin:sink_sub_bin1/GstFakeSink:sink_sub_bin_sink1:
There may be a timestamping problem, or this computer is too slow.
WARNING from sink_sub_bin_sink1: A lot of buffers are being dropped.
Debug info: gstbasesink.c(2902): gst_base_sink_is_too_late (): /GstPipeline:pipeline/GstBin:processing_bin_0/GstBin:sink_bin/GstBin:sink_sub_bin1/GstFakeSink:sink_sub_bin_sink1:
There may be a timestamping problem, or this computer is too slow.
WARNING from sink_sub_bin_sink1: A lot of buffers are being dropped.
Debug info: gstbasesink.c(2902): gst_base_sink_is_too_late (): /GstPipeline:pipeline/GstBin:processing_bin_0/GstBin:sink_bin/GstBin:sink_sub_bin1/GstFakeSink:sink_sub_bin_sink1:
There may be a timestamping problem, or this computer is too slow.
WARNING from sink_sub_bin_sink1: A lot of buffers are being dropped.
Debug info: gstbasesink.c(2902): gst_base_sink_is_too_late (): /GstPipeline:pipeline/GstBin:processing_bin_0/GstBin:sink_bin/GstBin:sink_sub_bin1/GstFakeSink:sink_sub_bin_sink1:
There may be a timestamping problem, or this computer is too slow.
**PERF: 21.82 (21.74) 21.82 (21.74) 21.82 (21.74) 21.82 (21.74) 21.82 (21.76) 21.82 (21.80) 21.82 (21.80) 21.82 (21.74) 21.82 (21.74) 21.82 (21.76) 21.82 (21.74) 21.82 (21.74) 21.82 (21.74) 21.82 (21.74) 21.82 (21.74) 21.82 (21.76) 21.82 (21.74) 21.82 (21.74) 21.82 (21.74) 21.82 (21.74) 21.82 (21.80) 21.82 (21.74) 21.82 (21.74) 21.82 (21.76) 21.82 (21.74) 21.82 (21.76) 21.82 (21.74) 21.82 (21.76) 21.82 (21.74) 21.82 (21.74)
WARNING from sink_sub_bin_sink1: A lot of buffers are being dropped.
Debug info: gstbasesink.c(2902): gst_base_sink_is_too_late (): /GstPipeline:pipeline/GstBin:processing_bin_0/GstBin:sink_bin/GstBin:sink_sub_bin1/GstFakeSink:sink_sub_bin_sink1:
There may be a timestamping problem, or this computer is too slow.

13

Why I am getting below warning on Jetson Xavier?

WARNING from sink_sub_bin_sink1: A lot of buffers are being dropped.
Debug info: gstbasesink.c(2902): gst_base_sink_is_too_late (): /GstPipeline:pipeline/GstBin:processing_bin_0/GstBin:sink_bin/GstBin:sink_sub_bin1/GstFakeSink:sink_sub_bin_sink1:
There may be a timestamping problem, or this computer is too slow.
WARNING from sink_sub_bin_sink1: A lot of buffers are being dropped.
Debug info: gstbasesink.c(2902): gst_base_sink_is_too_late (): /GstPipeline:pipeline/GstBin:processing_bin_0/GstBin:sink_bin/GstBin:sink_sub_bin1/GstFakeSink:sink_sub_bin_sink1:
There may be a timestamping problem, or this computer is too slow.
WARNING from sink_sub_bin_sink1: A lot of buffers are being dropped.
Debug info: gstbasesink.c(2902): gst_base_sink_is_too_late (): /GstPipeline:pipeline/GstBin:processing_bin_0/GstBin:sink_bin/GstBin:sink_sub_bin1/GstFakeSink:sink_sub_bin_sink1:
There may be a timestamping problem, or this computer is too slow.
WARNING from sink_sub_bin_sink1: A lot of buffers are being dropped.
Debug info: gstbasesink.c(2902): gst_base_sink_is_too_late (): /GstPipeline:pipeline/GstBin:processing_bin_0/GstBin:sink_bin/GstBin:sink_sub_bin1/GstFakeSink:sink_sub_bin_sink1:
There may be a timestamping problem, or this computer is too slow.

14

Hi harpreet8rb5h,

Before running DeepStream, please set your device to MAX performance.

sudo nvpmodel -m 0
sudo ./jetson_clocks.sh
15

Hi carolyuu,

Thanks it worked.

Please help me understand whats does this config do?

source30_720p_dec_infer-resnet_tiled_display_int8.txt

Does it use tensorRT?
Does it use hardware decoding?

16

Hi,

Yes. you can check with

$ export GST_DEBUG=*FACTORY*:4

nvinfer plugin runs TensorRT engine.
omxh264dec and nvv4l2decoder plugins run hardware decoding engine.