Jetson Xavier NX: queue element not-linked (-1) in smart recording with software encoder

Accelerated Computing Intelligent Video Analytics DeepStream SDK
,
1

Hi,

I’m trying to run smart recording with software encoder in Jetson Xavier NX. The code is modified from deepstream-testsr but it reads a source file as input instead of a rtsp stream. According to the error below, a queue element couldn’t be linked.

aaeon@aaeon-desktop:/opt/nvidia/deepstream/deepstream/sources/apps/sample_apps/deepstream-testsr$ sudo ./deepstream-testsr-app /opt/nvidia/deepstream/deepstream/samples/streams/sample_720p.h264
Now playing: /opt/nvidia/deepstream/deepstream/samples/streams/sample_720p.h264
Opening in BLOCKING MODE 
0:00:04.886733366 19092   0x558d235660 INFO                 nvinfer gstnvinfer.cpp:638:gst_nvinfer_logger:<primary-nvinference-engine> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1900> [UID = 1]: deserialized trt engine from :/opt/nvidia/deepstream/deepstream-6.0/samples/models/Primary_Detector/resnet10.caffemodel_b1_gpu0_int8.engine
INFO: [Implicit Engine Info]: layers num: 3
0   INPUT  kFLOAT input_1         3x368x640       
1   OUTPUT kFLOAT conv2d_bbox     16x23x40        
2   OUTPUT kFLOAT conv2d_cov/Sigmoid 4x23x40         

0:00:04.886976409 19092   0x558d235660 INFO                 nvinfer gstnvinfer.cpp:638:gst_nvinfer_logger:<primary-nvinference-engine> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2004> [UID = 1]: Use deserialized engine model: /opt/nvidia/deepstream/deepstream-6.0/samples/models/Primary_Detector/resnet10.caffemodel_b1_gpu0_int8.engine
0:00:04.896856800 19092   0x558d235660 INFO                 nvinfer gstnvinfer_impl.cpp:313:notifyLoadModelStatus:<primary-nvinference-engine> [UID 1]: Load new model:dstestsr_pgie_config.txt sucessfully
Running...
NvMMLiteOpen : Block : BlockType = 261 
NVMEDIA: Reading vendor.tegra.display-size : status: 6 
NvMMLiteBlockCreate : Block : BlockType = 261 
Recording started..
ERROR from element queue-post-osd: Internal data stream error.
Error details: gstqueue.c(988): gst_queue_handle_sink_event (): /GstPipeline:dstest-sr-pipeline/GstQueue:queue-post-osd:
streaming stopped, reason not-linked (-1)
^C

I tried running on x86_64 in the environment below and it worked fine.

Architecture: x86_64
GPU: NVIDIA GeForce GTX 1650 Ti with Max-Q Design
NVIDIA GPU Driver: Driver Version: 495.29.05
DeepStream Version: 6.0 (running on docker image nvcr.io/nvidia/deepstream:6.0-devel)
TensorRT Version: v8001

Code
test_sr.c (19.4 KB)

To reproduce this,

  1. Copy the given source file and place it in /opt/nvidia/deepstream/deepstream/sources/apps/sample_apps/deepstream-testsr.
  2. Modify the Makefile to compile the new source file.
  3. sudo CUDA_VER=10.2 make
  4. sudo ./test_sr /opt/nvidia/deepstream/deepstream/samples/streams/sample_720p.h264

Environment
HW: Jetson Xavier NX
Package: nvidia-jetpack
Version: 4.6-b197
Architecture: arm64
Issue Type: Question

Thanks
Peeranat F.

3
  1. can you run it again after execute “export GST_DEBUG=4”? is there any more infomation?
  2. using test_sr.c I can’t reproduce this issue on xavier deepstream6.
  3. can deepstream-testsr run ok without any modification?
4

I tried to reproduce this issue on Jetson Nano running in Docker (I couldn’t use Docker on my Jetson Xavier NX due to storage issue). I don’t see any errors. I suspect that it is due to environment issue? What do you think? in this case, I might need to reflash the device.

See the answers for your questions below

  1. I don’t see any logs
aaeon@aaeon-desktop:/opt/nvidia/deepstream/deepstream/sources/apps/sample_apps/deepstream-testsr$ export GST_DEBUG=4
aaeon@aaeon-desktop:/opt/nvidia/deepstream/deepstream/sources/apps/sample_apps/deepstream-testsr$ sudo ./deepstream-testsr-app /opt/nvidia/deepstream/deepstream/samples/streams/sample_720p.h264
Now playing: /opt/nvidia/deepstream/deepstream/samples/streams/sample_720p.h264
Opening in BLOCKING MODE 
0:00:04.833428707  5451   0x559ffd7660 INFO                 nvinfer gstnvinfer.cpp:638:gst_nvinfer_logger:<primary-nvinference-engine> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1900> [UID = 1]: deserialized trt engine from :/opt/nvidia/deepstream/deepstream-6.0/samples/models/Primary_Detector/resnet10.caffemodel_b1_gpu0_int8.engine
INFO: [Implicit Engine Info]: layers num: 3
0   INPUT  kFLOAT input_1         3x368x640       
1   OUTPUT kFLOAT conv2d_bbox     16x23x40        
2   OUTPUT kFLOAT conv2d_cov/Sigmoid 4x23x40         

0:00:04.833680869  5451   0x559ffd7660 INFO                 nvinfer gstnvinfer.cpp:638:gst_nvinfer_logger:<primary-nvinference-engine> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2004> [UID = 1]: Use deserialized engine model: /opt/nvidia/deepstream/deepstream-6.0/samples/models/Primary_Detector/resnet10.caffemodel_b1_gpu0_int8.engine
0:00:04.842195231  5451   0x559ffd7660 INFO                 nvinfer gstnvinfer_impl.cpp:313:notifyLoadModelStatus:<primary-nvinference-engine> [UID 1]: Load new model:dstestsr_pgie_config.txt sucessfully
Running...
NvMMLiteOpen : Block : BlockType = 261 
NVMEDIA: Reading vendor.tegra.display-size : status: 6 
NvMMLiteBlockCreate : Block : BlockType = 261 
Recording started..
ERROR from element queue-post-osd: Internal data stream error.
Error details: gstqueue.c(988): gst_queue_handle_sink_event (): /GstPipeline:dstest-sr-pipeline/GstQueue:queue-post-osd:
streaming stopped, reason not-linked (-1)
^C
  1. I got the following error.
aaeon@aaeon-desktop:/opt/nvidia/deepstream/deepstream/sources/apps/sample_apps/deepstream-testsr$ sudo ./deepstream-testsr-app rtsp://xxx
Now playing: rtsp://xxx

Using winsys: x11 
Opening in BLOCKING MODE 
Opening in BLOCKING MODE 
0:00:04.998157412 24328   0x558916a470 INFO                 nvinfer gstnvinfer.cpp:638:gst_nvinfer_logger:<primary-nvinference-engine> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1900> [UID = 1]: deserialized trt engine from :/opt/nvidia/deepstream/deepstream-6.0/samples/models/Primary_Detector/resnet10.caffemodel_b1_gpu0_int8.engine
INFO: [Implicit Engine Info]: layers num: 3
0   INPUT  kFLOAT input_1         3x368x640       
1   OUTPUT kFLOAT conv2d_bbox     16x23x40        
2   OUTPUT kFLOAT conv2d_cov/Sigmoid 4x23x40         

0:00:04.998375398 24328   0x558916a470 INFO                 nvinfer gstnvinfer.cpp:638:gst_nvinfer_logger:<primary-nvinference-engine> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2004> [UID = 1]: Use deserialized engine model: /opt/nvidia/deepstream/deepstream-6.0/samples/models/Primary_Detector/resnet10.caffemodel_b1_gpu0_int8.engine
0:00:05.008059209 24328   0x558916a470 INFO                 nvinfer gstnvinfer_impl.cpp:313:notifyLoadModelStatus:<primary-nvinference-engine> [UID 1]: Load new model:dstestsr_pgie_config.txt sucessfully
Running...
In cb_newpad
NvMMLiteOpen : Block : BlockType = 261 
NVMEDIA: Reading vendor.tegra.display-size : status: 6 
NvMMLiteBlockCreate : Block : BlockType = 261 
NvMMLiteOpen : Block : BlockType = 4 
===== NVMEDIA: NVENC =====
NvMMLiteBlockCreate : Block : BlockType = 4 
H264: Profile = 66, Level = 0 
0:00:05.439852994 24328   0x5589789400 WARN                 nvinfer gstnvinfer.cpp:2288:gst_nvinfer_output_loop:<primary-nvinference-engine> error: Internal data stream error.
0:00:05.439918051 24328   0x5589789400 WARN                 nvinfer gstnvinfer.cpp:2288:gst_nvinfer_output_loop:<primary-nvinference-engine> error: streaming stopped, reason error (-5)
ERROR from element primary-nvinference-engine: Internal data stream error.
Error details: /dvs/git/dirty/git-master_linux/deepstream/sdk/src/gst-plugins/gst-nvinfer/gstnvinfer.cpp(2288): gst_nvinfer_output_loop (): /GstPipeline:dstest-sr-pipeline/GstNvInfer:primary-nvinference-engine:
streaming stopped, reason error (-5)
Returned, stopping playback
NVMEDIA_ENC: bBlitMode is set to TRUE 
Deleting pipeline

Thanks

5

the log’s information is not enough, it seemed to be an environment issue because there will be many printing after “export GST_DEBUG=4”, you can redirect it to a file, like this:
./deepstream-testsr-app rtsp://xx
0:00:00.000126055 769573 0xaaaad7350c00 INFO GST_INIT gst.c:586:init_pre: Initializing GStreamer Core Library version 1.16.3

6

I reinstalled GStreamer and now everything worked as expected

apt-get install libgstreamer1.0-dev libgstreamer-plugins-base1.0-dev libgstreamer-plugins-bad1.0-dev gstreamer1.0-plugins-base gstreamer1.0-plugins-good gstreamer1.0-plugins-bad gstreamer1.0-plugins-ugly gstreamer1.0-libav gstreamer1.0-doc gstreamer1.0-tools gstreamer1.0-x gstreamer1.0-alsa gstreamer1.0-gl gstreamer1.0-gtk3 gstreamer1.0-qt5 gstreamer1.0-pulseaudio

However, for some reason, I don’t see any additional logs with export GST_DEBUG=4
Thanks

7

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.