Deepstream can't sink more than 2 video streams at the same time

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

I get error when run test demo,like this:

deepstream-app -c source4_1080p_dec_infer-resnet_tracker_sgie_tiled_display_int8.txt

my display_int8.txt like this:

# Copyright (c) 2018 NVIDIA Corporation.  All rights reserved.
#
# NVIDIA Corporation and its licensors retain all intellectual property
# and proprietary rights in and to this software, related documentation
# and any modifications thereto.  Any use, reproduction, disclosure or
# distribution of this software and related documentation without an express
# license agreement from NVIDIA Corporation is strictly prohibited.

[application]
enable-perf-measurement=1
perf-measurement-interval-sec=5
#gie-kitti-output-dir=streamscl

[tiled-display]
enable=0
rows=2
columns=2
width=1280
height=720
gpu-id=0
#(0): nvbuf-mem-default - Default memory allocated, specific to particular platform
#(1): nvbuf-mem-cuda-pinned - Allocate Pinned/Host cuda memory, applicable for Tesla
#(2): nvbuf-mem-cuda-device - Allocate Device cuda memory, applicable for Tesla
#(3): nvbuf-mem-cuda-unified - Allocate Unified cuda memory, applicable for Tesla
#(4): nvbuf-mem-surface-array - Allocate Surface Array memory, applicable for Jetson
nvbuf-memory-type=0

[source0]
enable=1
#Type - 1=CameraV4L2 2=URI 3=MultiURI 4=RTSP
type=3
uri=file://../../streams/sample_1080p_h264.mp4
num-sources=1
#drop-frame-interval=2
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=1
#drop-frame-interval=2
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

[source2]
enable=1
#Type - 1=CameraV4L2 2=URI 3=MultiURI 4=RTSP
type=3
uri=file://../../streams/sample_1080p_h264.mp4
num-sources=1
#drop-frame-interval=2
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

[sink0]
enable=0
#Type - 1=FakeSink 2=EglSink 3=File
type=2
sync=1
source-id=0
gpu-id=0
nvbuf-memory-type=0

[sink1]
enable=0
type=3
#1=mp4 2=mkv
container=1
#1=h264 2=h265
codec=1
sync=0
#iframeinterval=10
bitrate=2000000
output-file=out.mp4


[sink2]
enable=1
#Type - 1=FakeSink 2=EglSink 3=File 4=RTSPStreaming
type=4
#1=h264 2=h265
codec=1
sync=0
#iframeinterval=10
bitrate=2000000
# set below properties in case of RTSPStreaming
rtsp-port=8554
udp-port=5400
source-id=0

[sink3]
enable=1
#Type - 1=FakeSink 2=EglSink 3=File 4=RTSPStreaming
type=4
#1=h264 2=h265
codec=1
sync=0
#iframeinterval=10
bitrate=2000000
# set below properties in case of RTSPStreaming
rtsp-port=8555
udp-port=5401
source-id=1

[sink4]
enable=1
#Type - 1=FakeSink 2=EglSink 3=File 4=RTSPStreaming
type=4
#1=h264 2=h265
codec=1
sync=0
#iframeinterval=10
bitrate=2000000
# set below properties in case of RTSPStreaming
rtsp-port=8556
udp-port=5402
source-id=2

[osd]
enable=1
gpu-id=0
border-width=1
text-size=15
text-color=1;1;1;1;
text-bg-color=0.3;0.3;0.3;1
font=Serif
show-clock=0
clock-x-offset=800
clock-y-offset=820
clock-text-size=12
clock-color=1;0;0;0
nvbuf-memory-type=0

[streammux]
gpu-id=0
##Boolean property to inform muxer that sources are live
live-source=0
batch-size=4
##time out in usec, to wait after the first buffer is available
##to push the batch even if the complete batch is not formed
batched-push-timeout=40000
## Set muxer output width and height
width=1920
height=1080
##Enable to maintain aspect ratio wrt source, and allow black borders, works
##along with width, height properties
enable-padding=0
nvbuf-memory-type=0

# config-file property is mandatory for any gie section.
# Other properties are optional and if set will override the properties set in
# the infer config file.
[primary-gie]
enable=1
gpu-id=0
model-engine-file=../../models/Primary_Detector/resnet10.caffemodel_b4_int8.engine
batch-size=4
#Required by the app for OSD, not a plugin property
bbox-border-color0=1;0;0;1
bbox-border-color1=0;1;1;1
bbox-border-color2=0;0;1;1
bbox-border-color3=0;1;0;1
interval=0
gie-unique-id=1
nvbuf-memory-type=0
config-file=config_infer_primary.txt

[tracker]
enable=1
tracker-width=640
tracker-height=368
#ll-lib-file=/opt/nvidia/deepstream/deepstream-4.0/lib/libnvds_mot_iou.so
#ll-lib-file=/opt/nvidia/deepstream/deepstream-4.0/lib/libnvds_nvdcf.so
ll-lib-file=/opt/nvidia/deepstream/deepstream-4.0/lib/libnvds_mot_klt.so
#ll-config-file required for DCF/IOU only
#ll-config-file=tracker_config.yml
#ll-config-file=iou_config.txt
gpu-id=0
#enable-batch-process applicable to DCF only
enable-batch-process=1

[secondary-gie0]
enable=1
model-engine-file=../../models/Secondary_VehicleTypes/resnet18.caffemodel_b16_int8.engine
gpu-id=0
batch-size=16
gie-unique-id=4
operate-on-gie-id=1
operate-on-class-ids=0;
config-file=config_infer_secondary_vehicletypes.txt

[secondary-gie1]
enable=1
model-engine-file=../../models/Secondary_CarColor/resnet18.caffemodel_b16_int8.engine
batch-size=16
gpu-id=0
gie-unique-id=5
operate-on-gie-id=1
operate-on-class-ids=0;
config-file=config_infer_secondary_carcolor.txt

[secondary-gie2]
enable=1
model-engine-file=../../models/Secondary_CarMake/resnet18.caffemodel_b16_int8.engine
batch-size=16
gpu-id=0
gie-unique-id=6
operate-on-gie-id=1
operate-on-class-ids=0;
config-file=config_infer_secondary_carmake.txt

[tests]
file-loop=1

and I get this errors:

*** DeepStream: Launched RTSP Streaming at rtsp://localhost:8554/ds-test ***


 *** DeepStream: Launched RTSP Streaming at rtsp://localhost:8555/ds-test ***


 *** DeepStream: Launched RTSP Streaming at rtsp://localhost:8556/ds-test ***

Creating LL OSD context new
Creating LL OSD context new
Creating LL OSD context new
gstnvtracker: Loading low-level lib at /opt/nvidia/deepstream/deepstream-4.0/lib/libnvds_mot_klt.so
gstnvtracker: Optional NvMOT_RemoveStreams not implemented
gstnvtracker: Batch processing is OFF

Runtime commands:
        h: Print this help
        q: Quit

        p: Pause
        r: Resume

** INFO: <bus_callback:189>: Pipeline ready

Creating LL OSD context new
Creating LL OSD context new
Creating LL OSD context new
** INFO: <bus_callback:175>: Pipeline running

ERROR from sink_sub_bin_encoder1: Device '/dev/nvhost-msenc' failed during initialization
Debug info: gstv4l2object.c(4050): gst_v4l2_object_set_format_full (): /GstPipeline:pipeline/GstBin:processing_bin_0/GstBin:sink_bin/GstBin:sink_sub_bin1/nvv4l2h264enc:sink_sub_bin_encoder1:
Call to S_FMT failed for YM12 @ 1920x1080: Unknown error -1
ERROR from sink_sub_bin_encoder1: Device '/dev/nvhost-msenc' failed during initialization
Debug info: gstv4l2object.c(4050): gst_v4l2_object_set_format_full (): /GstPipeline:pipeline/GstBin:processing_bin_0/GstBin:sink_bin/GstBin:sink_sub_bin1/nvv4l2h264enc:sink_sub_bin_encoder1:
Call to S_FMT failed for YM12 @ 1920x1080: Unknown error -1
ERROR from sink_sub_bin_encoder1: Device '/dev/nvhost-msenc' failed during initialization
Debug info: gstv4l2object.c(4050): gst_v4l2_object_set_format_full (): /GstPipeline:pipeline/GstBin:processing_bin_0/GstBin:sink_bin/GstBin:sink_sub_bin1/nvv4l2h264enc:sink_sub_bin_encoder1:
Call to S_FMT failed for YM12 @ 1920x1080: Unknown error -1
Quitting
ERROR from sink_sub_bin_encoder1: Device '/dev/nvhost-msenc' failed during initialization
Debug info: gstv4l2object.c(4050): gst_v4l2_object_set_format_full (): /GstPipeline:pipeline/GstBin:processing_bin_0/GstBin:sink_bin/GstBin:sink_sub_bin1/nvv4l2h264enc:sink_sub_bin_encoder1:
Call to S_FMT failed for YM12 @ 1920x1080: Unknown error -1
ERROR from sink_sub_bin_encoder1: Device '/dev/nvhost-msenc' failed during initialization
Debug info: gstv4l2object.c(4050): gst_v4l2_object_set_format_full (): /GstPipeline:pipeline/GstBin:processing_bin_0/GstBin:sink_bin/GstBin:sink_sub_bin1/nvv4l2h264enc:sink_sub_bin_encoder1:
Call to S_FMT failed for YM12 @ 1920x1080: Unknown error -1
ERROR from sink_sub_bin_encoder1: Device '/dev/nvhost-msenc' failed during initialization
Debug info: gstv4l2object.c(4050): gst_v4l2_object_set_format_full (): /GstPipeline:pipeline/GstBin:processing_bin_0/GstBin:sink_bin/GstBin:sink_sub_bin1/nvv4l2h264enc:sink_sub_bin_encoder1:
Call to S_FMT failed for YM12 @ 1920x1080: Unknown error -1
App run failed

but deepstream can sink 2 video streams at the same time, the config_file.txt like this:

[application]
enable-perf-measurement=1
perf-measurement-interval-sec=5
#gie-kitti-output-dir=streamscl

[tiled-display]
enable=0
rows=2
columns=2
width=1280
height=720
gpu-id=0
#(0): nvbuf-mem-default - Default memory allocated, specific to particular platform
#(1): nvbuf-mem-cuda-pinned - Allocate Pinned/Host cuda memory, applicable for Tesla
#(2): nvbuf-mem-cuda-device - Allocate Device cuda memory, applicable for Tesla
#(3): nvbuf-mem-cuda-unified - Allocate Unified cuda memory, applicable for Tesla
#(4): nvbuf-mem-surface-array - Allocate Surface Array memory, applicable for Jetson
nvbuf-memory-type=0

[source0]
enable=1
#Type - 1=CameraV4L2 2=URI 3=MultiURI 4=RTSP
type=3
uri=file://../../streams/sample_1080p_h264.mp4
num-sources=1
#drop-frame-interval=2
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=1
#drop-frame-interval=2
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

[source2]
enable=1
#Type - 1=CameraV4L2 2=URI 3=MultiURI 4=RTSP
type=3
uri=file://../../streams/sample_1080p_h264.mp4
num-sources=1
#drop-frame-interval=2
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

[sink0]
enable=0
#Type - 1=FakeSink 2=EglSink 3=File
type=2
sync=1
source-id=0
gpu-id=0
nvbuf-memory-type=0

[sink1]
enable=0
type=3
#1=mp4 2=mkv
container=1
#1=h264 2=h265
codec=1
sync=0
#iframeinterval=10
bitrate=2000000
output-file=out.mp4


[sink2]
enable=1
#Type - 1=FakeSink 2=EglSink 3=File 4=RTSPStreaming
type=4
#1=h264 2=h265
codec=1
sync=0
#iframeinterval=10
bitrate=2000000
# set below properties in case of RTSPStreaming
rtsp-port=8554
udp-port=5400
source-id=0

[sink3]
enable=1
#Type - 1=FakeSink 2=EglSink 3=File 4=RTSPStreaming
type=4
#1=h264 2=h265
codec=1
sync=0
#iframeinterval=10
bitrate=2000000
# set below properties in case of RTSPStreaming
rtsp-port=8555
udp-port=5401
source-id=1

[sink4]
enable=0
#Type - 1=FakeSink 2=EglSink 3=File 4=RTSPStreaming
type=4
#1=h264 2=h265
codec=1
sync=0
#iframeinterval=10
bitrate=2000000
# set below properties in case of RTSPStreaming
rtsp-port=8556
udp-port=5402
source-id=2

[osd]
enable=1
gpu-id=0
border-width=1
text-size=15
text-color=1;1;1;1;
text-bg-color=0.3;0.3;0.3;1
font=Serif
show-clock=0
clock-x-offset=800
clock-y-offset=820
clock-text-size=12
clock-color=1;0;0;0
nvbuf-memory-type=0

[streammux]
gpu-id=0
##Boolean property to inform muxer that sources are live
live-source=0
batch-size=4
##time out in usec, to wait after the first buffer is available
##to push the batch even if the complete batch is not formed
batched-push-timeout=40000
## Set muxer output width and height
width=1920
height=1080
##Enable to maintain aspect ratio wrt source, and allow black borders, works
##along with width, height properties
enable-padding=0
nvbuf-memory-type=0

# config-file property is mandatory for any gie section.
# Other properties are optional and if set will override the properties set in
# the infer config file.
[primary-gie]
enable=1
gpu-id=0
model-engine-file=../../models/Primary_Detector/resnet10.caffemodel_b4_int8.engine
batch-size=4
#Required by the app for OSD, not a plugin property
bbox-border-color0=1;0;0;1
bbox-border-color1=0;1;1;1
bbox-border-color2=0;0;1;1
bbox-border-color3=0;1;0;1
interval=0
gie-unique-id=1
nvbuf-memory-type=0
config-file=config_infer_primary.txt

[tracker]
enable=1
tracker-width=640
tracker-height=368
#ll-lib-file=/opt/nvidia/deepstream/deepstream-4.0/lib/libnvds_mot_iou.so
#ll-lib-file=/opt/nvidia/deepstream/deepstream-4.0/lib/libnvds_nvdcf.so
ll-lib-file=/opt/nvidia/deepstream/deepstream-4.0/lib/libnvds_mot_klt.so
#ll-config-file required for DCF/IOU only
#ll-config-file=tracker_config.yml
#ll-config-file=iou_config.txt
gpu-id=0
#enable-batch-process applicable to DCF only
enable-batch-process=1

[secondary-gie0]
enable=1
model-engine-file=../../models/Secondary_VehicleTypes/resnet18.caffemodel_b16_int8.engine
gpu-id=0
batch-size=16
gie-unique-id=4
operate-on-gie-id=1
operate-on-class-ids=0;
config-file=config_infer_secondary_vehicletypes.txt

[secondary-gie1]
enable=1
model-engine-file=../../models/Secondary_CarColor/resnet18.caffemodel_b16_int8.engine
batch-size=16
gpu-id=0
gie-unique-id=5
operate-on-gie-id=1
operate-on-class-ids=0;
config-file=config_infer_secondary_carcolor.txt

[secondary-gie2]
enable=1
model-engine-file=../../models/Secondary_CarMake/resnet18.caffemodel_b16_int8.engine
batch-size=16
gpu-id=0
gie-unique-id=6
operate-on-gie-id=1
operate-on-class-ids=0;
config-file=config_infer_secondary_carmake.txt

[tests]
file-loop=1

and the output like this

*** DeepStream: Launched RTSP Streaming at rtsp://localhost:8554/ds-test ***


 *** DeepStream: Launched RTSP Streaming at rtsp://localhost:8555/ds-test ***

Creating LL OSD context new
Creating LL OSD context new
gstnvtracker: Loading low-level lib at /opt/nvidia/deepstream/deepstream-4.0/lib/libnvds_mot_klt.so
gstnvtracker: Optional NvMOT_RemoveStreams not implemented
gstnvtracker: Batch processing is OFF

Runtime commands:
        h: Print this help
        q: Quit

        p: Pause
        r: Resume

** INFO: <bus_callback:189>: Pipeline ready


(deepstream-app:1054): GLib-GObject-WARNING **: 09:50:29.139: g_object_get_is_valid_property: object class 'GstUDPSrc' has no property named 'pt'

(deepstream-app:1054): GLib-GObject-WARNING **: 09:50:29.147: g_object_get_is_valid_property: object class 'GstUDPSrc' has no property named 'pt'
Creating LL OSD context new
Creating LL OSD context new
** INFO: <bus_callback:175>: Pipeline running

KLT Tracker Init
KLT Tracker Init
KLT Tracker Init

(deepstream-app:1054): GLib-GObject-WARNING **: 09:50:29.663: g_object_get_is_valid_property: object class 'GstUDPSrc' has no property named 'pt'

(deepstream-app:1054): GLib-GObject-WARNING **: 09:50:29.666: g_object_get_is_valid_property: object class 'GstUDPSrc' has no property named 'pt'

**PERF: FPS 0 (Avg)     FPS 1 (Avg)     FPS 2 (Avg)
**PERF: 62.12 (62.12)   60.12 (60.12)   61.12 (61.12)
**PERF: 58.26 (59.36)   59.06 (59.36)   58.26 (59.07)
**PERF: 59.84 (59.56)   59.03 (59.22)   59.23 (59.14)
**PERF: 59.51 (59.54)   59.51 (59.31)   59.91 (59.37)
**PERF: 58.97 (59.41)   59.17 (59.28)   58.37 (59.14)
**PERF: 60.46 (59.61)   60.66 (59.53)   59.06 (59.13)
^C** ERROR: <_intr_handler:140>: User Interrupted.. 

Quitting
App run successful

this is my computer :

cuda 10.1
driver: 418.113
docker deepstream 4.0.1
gpu 2080ti

2

HI
I can run successful with docker version 4.0.2, GPU T4, and use same config with you. can you try to run without docker to rule out if any environments of docker?

3

I also have the same problem. When I save more than 2 sinks, it failed. But I didn’t use docker. My GPU is 2080Ti. Is this GPU support?

4

Please check this,

search 2080 ti, from the table, you can see Max # of concurrent sessions for encode supported is 2, that why when you run more than 3 sinks of rtsp streaming failed.

1 Like
5

Hello, as I saw in the figure, the max # of concurrent sessions for supported is 3. Not 2

image
image916×440 32.6 KB

6

Seems duplicated with Cannot start the application with 3 RTSP Streaming - Intelligent Video Analytics / DeepStream SDK - NVIDIA Developer Forums
I see the issue gone after change to another stream, did this still be an issue then?

7

Hello amycao,

I was wrong because this topic was created on Feb 13, 2020. The NVIDIA at that time still supported 2 concurrent sessions.

After June 2020, NVIDIA silently changed the maximum number from 2 to 3.

My issue was solved because I found that this issue is coming from NVIDIA software, not the Deepstream App.

8

Got it, thanks.

My issue was solved because I found that this issue is coming from NVIDIA software, not the Deepstream App.

May i know which software?