The OSD video become very choppy after some second. source30_1080p_dec_infer-resnet_tiled_display_int8.txt

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

deepstream-app -c source30_1080p_dec_infer-resnet_tiled_display_int8.txt
The OSD video become very choppy after some second
and terminal will get some output

**PERF:  26.44 (24.68)	26.44 (24.68)	26.64 (24.63)	26.44 (24.61)	26.64 (24.63)	26.44 (24.71)	26.44 (24.71)	26.44 (24.68)	26.44 (24.68)	26.44 (24.68)	26.44 (24.87)	26.24 (24.65)	26.24 (24.61)	26.44 (24.71)	26.24 (24.68)	26.44 (24.71)	26.44 (24.87)	26.24 (24.65)	26.24 (24.65)	26.44 (24.68)	26.44 (24.75)	26.44 (24.87)	26.44 (24.87)	26.64 (24.90)	26.64 (24.90)	26.44 (24.87)	26.44 (24.87)	26.64 (24.78)	26.44 (24.87)	26.44 (24.87)	
WARNING from sink_sub_bin_sink1: A lot of buffers are being dropped.
Debug info: ../libs/gst/base/gstbasesink.c(3143): gst_base_sink_is_too_late (): /GstPipeline:pipeline/GstBin:processing_bin_0/GstBin:sink_bin/GstBin:sink_sub_bin1/GstEglGlesSink:sink_sub_bin_sink1:
There may be a timestamping problem, or this computer is too slow.
**PERF:  26.34 (24.90)	26.34 (24.90)	26.14 (24.83)	26.34 (24.84)	26.34 (24.86)	26.34 (24.93)	26.34 (24.93)	26.34 (24.90)	26.34 (24.90)	26.35 (24.87)	26.34 (25.06)	26.55 (24.87)	26.55 (24.84)	26.34 (24.93)	26.55 (24.90)	26.34 (24.93)	26.34 (25.06)	26.55 (24.87)	26.55 (24.87)	26.34 (24.90)	26.55 (24.96)	26.34 (25.06)	26.34 (25.06)	26.34 (25.09)	26.34 (25.09)	26.34 (25.06)	26.34 (25.06)	26.55 (24.99)	26.34 (25.06)	26.34 (25.06)	
WARNING from sink_sub_bin_sink1: A lot of buffers are being dropped.
Debug info: ../libs/gst/base/gstbasesink.c(3143): gst_base_sink_is_too_late (): /GstPipeline:pipeline/GstBin:processing_bin_0/GstBin:sink_bin/GstBin:sink_sub_bin1/GstEglGlesSink: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: ../libs/gst/base/gstbasesink.c(3143): gst_base_sink_is_too_late (): /GstPipeline:pipeline/GstBin:processing_bin_0/GstBin:sink_bin/GstBin:sink_sub_bin1/GstEglGlesSink: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: ../libs/gst/base/gstbasesink.c(3143): gst_base_sink_is_too_late (): /GstPipeline:pipeline/GstBin:processing_bin_0/GstBin:sink_bin/GstBin:sink_sub_bin1/GstEglGlesSink:sink_sub_bin_sink1:
There may be a timestamping problem, or this computer is too slow.
**PERF:  26.06 (25.07)	26.06 (25.07)	26.26 (25.03)	26.26 (25.04)	26.06 (25.03)	26.26 (25.12)	26.26 (25.12)	26.26 (25.09)	26.06 (25.07)	26.06 (25.07)	26.49 (25.24)	26.06 (25.07)	26.06 (25.04)	26.26 (25.12)	26.06 (25.09)	26.06 (25.09)	26.49 (25.24)	26.06 (25.07)	26.06 (25.07)	26.06 (25.07)	26.29 (25.12)	26.70 (25.24)	26.70 (25.24)	26.50 (25.24)	26.50 (25.24)	26.49 (25.24)	26.70 (25.24)	26.29 (25.15)	26.70 (25.24)	26.49 (25.24)	
WARNING from sink_sub_bin_sink1: A lot of buffers are being dropped.
Debug info: ../libs/gst/base/gstbasesink.c(3143): gst_base_sink_is_too_late (): /GstPipeline:pipeline/GstBin:processing_bin_0/GstBin:sink_bin/GstBin:sink_sub_bin1/GstEglGlesSink: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: ../libs/gst/base/gstbasesink.c(3143): gst_base_sink_is_too_late (): /GstPipeline:pipeline/GstBin:processing_bin_0/GstBin:sink_bin/GstBin:sink_sub_bin1/GstEglGlesSink: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: ../libs/gst/base/gstbasesink.c(3143): gst_base_sink_is_too_late (): /GstPipeline:pipeline/GstBin:processing_bin_0/GstBin:sink_bin/GstBin:sink_sub_bin1/GstEglGlesSink: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: ../libs/gst/base/gstbasesink.c(3143): gst_base_sink_is_too_late (): /GstPipeline:pipeline/GstBin:processing_bin_0/GstBin:sink_bin/GstBin:sink_sub_bin1/GstEglGlesSink: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.

CPU and GPU and MEM is enough
Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU) GPU
• DeepStream Version7.0

how to solve it

3

Could you run the nvidia-smi dmon and check the loading first?

1 Like
5

thank you, dec up to 100%. so in GeForce RTX 3090 ,How many channels of 4k video can be decoded simultaneously?

another question is when set drop-frame-interval=20 in [source0] ,why dec value hasn’t it been reduced?Does it mean that each frame will be decoded?

how to use different gpu id in multi source?

6

It also depends on your codec format. You can refer to our video-codec-sdk to check that based on 1080P.

No. Even if you set this parameter, the number of frames decoded at the same time does not change. It will only reduce the total number of frames.

You can set the gpu-id parameter for the source.

1 Like
7

when set like this in source30_1080p_dec_infer-resnet_tiled_display_int8.txt, different source with diff gpu-id

[source0]
enable=1
#Type - 1=CameraV4L2 2=URI 3=MultiURI 4=RTSP
type=3
uri=file://../../streams/sample_1080p_h264.mp4
num-sources=15
#drop-frame-interval=20
gpu-id=0
# (0): memtype_device   - Memory type Device
# (1): memtype_pinned   - Memory type Host Pinned
# (2): memtype_unified  - Memory type Unified
cudadec-memtype=0

[source1]
enable=1
#Type - 1=CameraV4L2 2=URI 3=MultiURI 4=RTSP
type=3
uri=file://../../streams/sample_1080p_h264.mp4
num-sources=15
gpu-id=1
#drop-frame-interval=20
# (0): memtype_device   - Memory type Device
# (1): memtype_pinned   - Memory type Host Pinned
# (2): memtype_unified  - Memory type Unified
cudadec-memtype=0

deepstream-app -c source30_1080p_dec_infer-resnet_tiled_display_int8.txt will get error

ERROR from src_bin_muxer: Memory Compatibility Error:Input surface gpu-id doesnt match with configured gpu-id for element, please allocate input using unified memory, or use same gpu-ids OR, if same gpu-ids are used ensure appropriate Cuda memories are used
Debug info: gstnvstreammux.cpp(1784): copy_data_cuda (): /GstPipeline:pipeline/GstBin:multi_src_bin/GstNvStreamMux:src_bin_muxer:
surface-gpu-id=1,src_bin_muxer-gpu-id=0
ERROR from src_bin_muxer: Memory Compatibility Error:Input surface gpu-id doesnt match with configured gpu-id for element, please allocate input using unified memory, or use same gpu-ids OR, if same gpu-ids are used ensure appropriate Cuda memories are used
Debug info: gstnvstreammux.cpp(1784): copy_data_cuda (): /GstPipeline:pipeline/GstBin:multi_src_bin/GstNvStreamMux:src_bin_muxer:
surface-gpu-id=1,src_bin_muxer-gpu-id=0
ERROR from queue: Internal data stream error.
Debug info: ../plugins/elements/gstqueue.c(992): gst_queue_handle_sink_event (): /GstPipeline:pipeline/GstBin:multi_src_bin/GstBin:src_sub_bin10/GstQueue:queue:
streaming stopped, reason error (-5)
ERROR from queue: Internal data stream error.
Debug info: ../plugins/elements/gstqueue.c(992): gst_queue_handle_sink_event (): /GstPipeline:pipeline/GstBin:multi_src_bin/GstBin:src_sub_bin14/GstQueue:queue:
streaming stopped, reason error (-5)
ERROR from multiqueue13: Internal data stream error.
Debug info: ../plugins/elements/gstmultiqueue.c(2381): gst_multi_queue_loop (): /GstPipeline:pipeline/GstBin:multi_src_bin/GstBin:src_sub_bin13/GstURIDecodeBin:src_elem/GstDecodeBin:decodebin13/GstMultiQueue:multiqueue13:
streaming stopped, reason error (-5)
ERROR from multiqueue12: Internal data stream error.
Debug info: ../plugins/elements/gstmultiqueue.c(2381): gst_multi_queue_loop (): /GstPipeline:pipeline/GstBin:multi_src_bin/GstBin:src_sub_bin12/GstURIDecodeBin:src_elem/GstDecodeBin:decodebin12/GstMultiQueue:multiqueue12:
streaming stopped, reason error (-5)
ERROR from multiqueue11: Internal data stream error.
Debug info: ../plugins/elements/gstmultiqueue.c(2381): gst_multi_queue_loop (): /GstPipeline:pipeline/GstBin:multi_src_bin/GstBin:src_sub_bin11/GstURIDecodeBin:src_elem/GstDecodeBin:decodebin11/GstMultiQueue:multiqueue11:
streaming stopped, reason error (-5)
ERROR from multiqueue15: Internal data stream error.
Debug info: ../plugins/elements/gstmultiqueue.c(2381): gst_multi_queue_loop (): /GstPipeline:pipeline/GstBin:multi_src_bin/GstBin:src_sub_bin15/GstURIDecodeBin:src_elem/GstDecodeBin:decodebin15/GstMultiQueue:multiqueue15:
streaming stopped, reason error (-5)
App run failed
8

Could you try to set the cudadec-memtype=2? If you use multiple gpus, you need to set the memtype to Unified.

9

could you share an example?

[source0]
enable=1
#Type - 1=CameraV4L2 2=URI 3=MultiURI 4=RTSP
type=3
uri=file://../../streams/sample_1080p_h264.mp4
num-sources=15
#drop-frame-interval=20
gpu-id=2
# (0): memtype_device   - Memory type Device
# (1): memtype_pinned   - Memory type Host Pinned
# (2): memtype_unified  - Memory type Unified
cudadec-memtype=2

[source1]
enable=1
#Type - 1=CameraV4L2 2=URI 3=MultiURI 4=RTSP
type=3
uri=file://../../streams/sample_1080p_h264.mp4
num-sources=15
gpu-id=1
#drop-frame-interval=20
# (0): memtype_device   - Memory type Device
# (1): memtype_pinned   - Memory type Host Pinned
# (2): memtype_unified  - Memory type Unified
cudadec-memtype=2

get error

ERROR from src_bin_muxer: Memory Compatibility Error:Input surface gpu-id doesnt match with configured gpu-id for element, please allocate input using unified memory, or use same gpu-ids OR, if same gpu-ids are used ensure appropriate Cuda memories are used
Debug info: gstnvstreammux.cpp(1784): copy_data_cuda (): /GstPipeline:pipeline/GstBin:multi_src_bin/GstNvStreamMux:src_bin_muxer:
surface-gpu-id=1,src_bin_muxer-gpu-id=0
10

source30_1080p_dec_infer-resnet_tiled_display_int8.txt (4.6 KB)

1 Like
11

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