Output video will drop a lot of buffers while multi-sources on TX2

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

I’m using deepstream 4.0 on tx2. I’m running the SSD sample. I just found that when I enter two or more sources，it runs smoothly at first, but drop lots of frames after a while, just like the following:

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/GstEglGlesSink:sink_sub_bin_sink1:
There may be a timestamping problem, or this computer is too slow.

My config file is like the following:

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

[tiled-display]
enable=1
rows=2
columns=2
width=1280
height=720
gpu-id=0
nvbuf-memory-type=0

[source0]
enable=1
#Type - 1=CameraV4L2 2=URI 3=MultiURI
type=3
num-sources=2
uri=file://../../samples/streams/sample_1080p_h264.mp4
gpu-id=0
cudadec-memtype=0

[source1]
enable=0
#Type - 1=CameraV4L2 2=URI 3=MultiURI 4=RTSP
type=3
uri=file://../../samples/streams/sample_720p.mp4
num-sources=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


[streammux]
gpu-id=0
batch-size=1
batched-push-timeout=-1
## Set muxer output width and height
width=1920
height=1080
nvbuf-memory-type=0

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

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

[osd]
enable=1
gpu-id=0
border-width=3
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

[primary-gie]
enable=1
gpu-id=0
batch-size=1
gie-unique-id=1
interval=0
labelfile-path=ssd_coco_labels.txt
model-engine-file=sample_ssd_relu6.uff_b1_fp32.engine
config-file=config_infer_primary_ssd.txt
nvbuf-memory-type=0

If I set “sync” in “sink0” as “0”, it will not drop frames but will run at 0.5 times speed of original video.

2

Hi,
Have you tried to execute jetson_clocks to run GPU at max clocks?

3

Yes I tried. But didn’t work.

4

Hi,
Please refer to source12_1080p_dec_infer-resnet_tracker_tiled_display_fp16_tx2.txt, which is reference config file for TX2. You may try

[sink0]
enable=1
#Type - 1=FakeSink 2=EglSink 3=File
type=5
sync=1
source-id=0
gpu-id=0
qos=0
nvbuf-memory-type=0
overlay-id=1