Difference between revisions of "GstRtspSink - NVidia TX2"

From RidgeRun Developer Connection
Jump to: navigation, search
(GstRtspSink Pipeline)
m
 
(9 intermediate revisions by 2 users not shown)
Line 1: Line 1:
{{GstRtspSink/Head|previous=Performance|next=NVidia_TX1_EVM|keywords=}}
+
{{GstRtspSink/Head|previous=Performance|next=NVidia_TX1_EVM|metakeywords=}}
  
 
This wiki presents some performance measurements of a typical GstRtspSink pipeline on the NVidia TX2 running for 2:40 hours.
 
This wiki presents some performance measurements of a typical GstRtspSink pipeline on the NVidia TX2 running for 2:40 hours.
<br>
 
 
<br>
 
<br>
 
<table>
 
<table>
Line 8: Line 7:
 
<td><div class="clear; float:right">__TOC__</div></td>
 
<td><div class="clear; float:right">__TOC__</div></td>
 
<td valign=top>
 
<td valign=top>
{{GStreamer debug}}
+
<td>
 +
{{GStreamer debug}}
 +
</td>
 +
<td>
 +
{{NVIDIA Preferred Partner logo}}
 +
</td>
 +
<td>
 +
{{ContactUs Button}}
 
</td>
 
</td>
 
</table>
 
</table>
Line 16: Line 22:
 
== GstRtspSink Pipeline ==
 
== GstRtspSink Pipeline ==
  
The following GstRtspSink pipeline generates video with a videotestsrc, encodes it using HW accelerated H264 encoder and streams it using GstRtspSink.
+
The following GstRtspSink pipeline generates video with a videotestsrc, encodes it using HW accelerated H264 encoder, and streams it using GstRtspSink.
  
 
<syntaxhighlight lang=bash>
 
<syntaxhighlight lang=bash>
Line 23: Line 29:
 
gst-launch-1.0 videotestsrc ! omxh264enc ! h264parse ! video/x-h264, mapping=${MAPPING}  ! perf print-arm-load=1 ! rtspsink service=${PORT}
 
gst-launch-1.0 videotestsrc ! omxh264enc ! h264parse ! video/x-h264, mapping=${MAPPING}  ! perf print-arm-load=1 ! rtspsink service=${PORT}
 
</syntaxhighlight>
 
</syntaxhighlight>
<!---------
+
 
<pre style="background:yellow">
 
The perf element is optional and its only used to print frame rate and CPU usage. If you are interested in using it, you may find it  at https://github.com/RidgeRun/gst-perf
 
</pre>
 
------>
 
 
{{Ambox
 
{{Ambox
 
|type=notice
 
|type=notice
 
|small=left
 
|small=left
|issue=The [https://github.com/RidgeRun/gst-perf perf element] is optional.  The perf element prints frame rate and CPU usage debug information.
+
|issue='''The [https://github.com/RidgeRun/gst-perf perf element] is optional.  The perf element prints frame rate and CPU usage debug information.'''
|style=width:100%;
+
|style=width:unset;
 
}}
 
}}
  
Line 43: Line 45:
 
The CPU load was measured using '''perf''' element.
 
The CPU load was measured using '''perf''' element.
 
[[File:Cpu usage.png|500px|center|thumb|CPU measured]]
 
[[File:Cpu usage.png|500px|center|thumb|CPU measured]]
 
  
 
== RAM Usage ==
 
== RAM Usage ==

Latest revision as of 22:16, 26 May 2023


Previous: Performance Index Next: NVidia_TX1_EVM




This wiki presents some performance measurements of a typical GstRtspSink pipeline on the NVidia TX2 running for 2:40 hours.

Error something wrong.jpg Problems running the pipelines shown on this page?
Please see our GStreamer Debugging guide for help.

Nvidia-preferred-partner-badge-rgb-for-screen.png

RR Contact Us.png


The pipeline ran without clients, after 1h one client is connected to the stream.

GstRtspSink Pipeline

The following GstRtspSink pipeline generates video with a videotestsrc, encodes it using HW accelerated H264 encoder, and streams it using GstRtspSink.

PORT=5000
MAPPING=/stream1
gst-launch-1.0 videotestsrc ! omxh264enc ! h264parse ! video/x-h264, mapping=${MAPPING}  ! perf print-arm-load=1 ! rtspsink service=${PORT}

Framerate

The frame rate was measured using the perf element.

Framerate measured

CPU Load

The CPU load was measured using perf element.

CPU measured

RAM Usage

The ram usage was measured using massif.

Ram measured



Previous: Performance Index Next: NVidia_TX1_EVM