[FFmpeg-user] How to properly test FFmpeg CPU usage.

[Wodzu]

Hi,   I would like to test FFmpeg CPU usage in the following conditions:  1. FFmpeg grabs RTSP stream (h264)  2.Decodes each frame and converts it to BGR24.   I am interested only in these two points, I don't want to output anything. Am I doing it correctly?   $ ffmpeg -i 'rtsp://xavier:8554/1600x1200_15_CU001' -vf format=bgr24 -f null -  ffmpeg version n6.0.1-5-g511b844423 Copyright (c) 2000-2023 the FFmpeg developers    built with gcc 11 (Ubuntu 11.4.0-1ubuntu1~22.04)    configuration: --pkg-config-flags=--static --enable-gpl --enable-libx264 --enable-libx265 --enable-pic --enable-nonfree    libavutil      58.  2.100 / 58.  2.100    libavcodec     60.  3.100 / 60.  3.100    libavformat    60.  3.100 / 60.  3.100    libavdevice    60.  1.100 / 60.  1.100    libavfilter     9.  3.100 /  9.  3.100    libswscale      7.  1.100 /  7.  1.100    libswresample   4. 10.100 /  4. 10.100    libpostproc    57.  1.100 / 57.  1.100  [h264 @ 0x5556464bdd40] co located POCs unavailable  Input #0, rtsp, from 'rtsp://xavier:8554/1600x1200_15_CU001':    Metadata:      title           : No Name    Duration: N/A, start: 0.235533, bitrate: N/A    Stream #0:0: Video: h264 (Main), yuv420p(progressive), 1600x1200, 15 fps, 15 tbr, 90k tbn  Stream mapping:    Stream #0:0 -> #0:0 (h264 (native) -> wrapped_avframe (native))  Press [q] to stop, [?] for help  [h264 @ 0x555646572500] co located POCs unavailable  [swscaler @ 0x555646d29f00] [swscaler @ 0x555646d36ea0] No accelerated colorspace conversion found from yuv420p to bgr24.  [swscaler @ 0x555646d29f00] [swscaler @ 0x555646d43e40] No accelerated colorspace conversion found from yuv420p to bgr24.  [swscaler @ 0x555646d29f00] [swscaler @ 0x555646d52790] No accelerated colorspace conversion found from yuv420p to bgr24.  [swscaler @ 0x555646d29f00] [swscaler @ 0x555646d618f0] No accelerated colorspace conversion found from yuv420p to bgr24.  [swscaler @ 0x555646d29f00] [swscaler @ 0x555646d70a50] No accelerated colorspace conversion found from yuv420p to bgr24.  Output #0, null, to 'pipe:':    Metadata:      title           : No Name      encoder         : Lavf60.3.100    Stream #0:0: Video: wrapped_avframe, bgr24(pc, gbr/unknown/unknown, progressive), 1600x1200, q=2-31, 200 kb/s, 15 fps, 15 tbn      Metadata:        encoder         : Lavc60.3.100 wrapped_avframe  frame= 7635 fps= 15 q=-0.0 Lsize=N/A time=00:08:28.93 bitrate=N/A speed=   1x     x  video:3579kB audio:0kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: unknown  Exiting normally, received signal 2.   The thing is that when I am using libav in my C++ application, the exact task is taking around 4% CPU and ffmpeg application takes 7%. The results are consistent, there are no fluctuations here.   Average:      UID       PID    %usr %system  %guest   %wait    %CPU   CPU  Command  Average:     1002   1938685   26.10    1.00    0.00    1.00    6.82     -  ffmpeg  Average:      UID       PID  minflt/s  majflt/s     VSZ     RSS   %MEM  Command  Average:     1002   1938685      0.20      0.00  654528   69056   0.84  ffmpeg   Average:      UID       PID    %usr %system  %guest   %wait    %CPU   CPU  Command  Average:        0   1938996   15.70    0.10    0.00    0.00    3.95     -  my_app  Average:      UID       PID  minflt/s  majflt/s     VSZ     RSS   %MEM  Command  Average:        0   1938996      8.50      0.00  234880   44470   0.54  my_app   Thanks for any ideas.