This is for Plex Server Version#: 1.40.0.7998
System: Debian Bookworm
Nvidia Version: 545.23.06
CUDA Version: 12.3
The server has the NVENC and NvFBC patches which remove the 2x stream cap from Nvidia drivers, and they are functional, as demonstrated below.
No matter what is set on ‘Settings → Transcoder’, the server will never transcode more than two downloads. While transcoding, the GPU sits at 39% utilization and the CPU will jump to 50% utilization. It also does not matter if they come from multiple clients or a single client. I can queue up a whole season for my ipad…it will churn through 2 episdoes at a time…or I can have 4x mobile clients do 1x episode of different shows…same thing. 2 episodes at a time max.
Transcoding for streaming is different. There can be 5x streaming clients and all will be receiving HW transcodes and the CPU will be at around 10-15% utilization.
Settings → Transcoder:
Transcoder quality: Automatic
Transcoder temporary directory: /dev/shm
Transcoder default throttle buffer: 120
Background transcoding x264 preset: Medium
Enable HDR tone mapping: Checked
Disable video stream transcoding: Not Checked
Use hardware acceleration when available: Checked
Use hardware-accelerated video encoding: Checked
Hardware transcoding device: GP107GL [Quadro P620]
Maximum simultaneous video transcode: 10
nvidia-smi output with queue of 10 transcodes pending (CPU @ 50% util):
+---------------------------------------------------------------------------------------+
| NVIDIA-SMI 545.23.06 Driver Version: 545.23.06 CUDA Version: 12.3 |
|-----------------------------------------+----------------------+----------------------+
| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|=========================================+======================+======================|
| 0 Quadro P620 Off | 00000000:01:00.0 Off | N/A |
| 39% 53C P0 N/A / N/A | 311MiB / 2048MiB | 20% Default |
| | | N/A |
+-----------------------------------------+----------------------+----------------------+
+---------------------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=======================================================================================|
| 0 N/A N/A 1072594 C ...lib/plexmediaserver/Plex Transcoder 154MiB |
| 0 N/A N/A 1072597 C ...lib/plexmediaserver/Plex Transcoder 154MiB |
+---------------------------------------------------------------------------------------+
Verifying that GPU is unlocked and can do more than 2x transcodes:
./patch-tester.sh
ffmpeg version 5.1.3-1 Copyright (c) 2000-2022 the FFmpeg developers
built with gcc 12 (Debian 12.2.0-14)
configuration: --prefix=/usr --extra-version=1 --toolchain=hardened --libdir=/usr/lib/x86_64-linux-gnu --incdir=/usr/include/x86_64-linux-gnu --arch=amd64 --enable-gpl --disable-stripping --enable-gnutls --enable-ladspa --enable-libaom --enable-libass --enable-libbluray --enable-libbs2b --enable-libcaca --enable-
libcdio --enable-libcodec2 --enable-libdav1d --enable-libflite --enable-libfontconfig --enable-libfreetype --enable-libfribidi --enable-libglslang --enable-libgme --enable-libgsm --enable-libjack --enable-libmp3lame --enable-libmysofa --enable-libopenjpeg --enable-libopenmpt --enable-libopus --enable-libpulse --ena
ble-librabbitmq --enable-librist --enable-librubberband --enable-libshine --enable-libsnappy --enable-libsoxr --enable-libspeex --enable-libsrt --enable-libssh --enable-libsvtav1 --enable-libtheora --enable-libtwolame --enable-libvidstab --enable-libvorbis --enable-libvpx --enable-libwebp --enable-libx265 --enable-
libxml2 --enable-libxvid --enable-libzimg --enable-libzmq --enable-libzvbi --enable-lv2 --enable-omx --enable-openal --enable-opencl --enable-opengl --enable-sdl2 --disable-sndio --enable-libjxl --enable-pocketsphinx --enable-librsvg --enable-libmfx --enable-libdc1394 --enable-libdrm --enable-libiec61883 --enable-c
hromaprint --enable-frei0r --enable-libx264 --enable-libplacebo --enable-librav1e --enable-shared
libavutil 57. 28.100 / 57. 28.100
libavcodec 59. 37.100 / 59. 37.100
libavformat 59. 27.100 / 59. 27.100
libavdevice 59. 7.100 / 59. 7.100
libavfilter 8. 44.100 / 8. 44.100
libswscale 6. 7.100 / 6. 7.100
libswresample 4. 7.100 / 4. 7.100
libpostproc 56. 6.100 / 56. 6.100
-vsync is deprecated. Use -fps_mode
Passing a number to -vsync is deprecated, use a string argument as described in the manual.
Input #0, lavfi, from 'testsrc':
Duration: N/A, start: 0.000000, bitrate: N/A
Stream #0:0: Video: rawvideo (RGB[24] / 0x18424752), rgb24, 320x240 [SAR 1:1 DAR 4:3], 25 tbr, 25 tbn
Stream mapping:
Stream #0:0 -> #0:0 (rawvideo (native) -> h264 (h264_nvenc))
Stream #0:0 -> #1:0 (rawvideo (native) -> h264 (h264_nvenc))
Stream #0:0 -> #2:0 (rawvideo (native) -> h264 (h264_nvenc))
Stream #0:0 -> #3:0 (rawvideo (native) -> h264 (h264_nvenc))
Stream #0:0 -> #4:0 (rawvideo (native) -> h264 (h264_nvenc))
Stream #0:0 -> #5:0 (rawvideo (native) -> h264 (h264_nvenc))
Press [q] to stop, [?] for help
Output #0, null, to 'pipe:':
Metadata:
encoder : Lavf59.27.100
Stream #0:0: Video: h264 (Main), cuda(pc, gbr/unknown/unknown, progressive), 320x240 [SAR 1:1 DAR 4:3], q=2-31, 4000 kb/s, 25 fps, 25 tbn
Metadata:
encoder : Lavc59.37.100 h264_nvenc
Side data:
cpb: bitrate max/min/avg: 0/0/4000000 buffer size: 8000000 vbv_delay: N/A
Output #1, null, to 'pipe:':
Metadata:
encoder : Lavf59.27.100
Stream #1:0: Video: h264 (Main), cuda(pc, gbr/unknown/unknown, progressive), 320x240 [SAR 1:1 DAR 4:3], q=2-31, 1000 kb/s, 25 fps, 25 tbn
Metadata:
encoder : Lavc59.37.100 h264_nvenc
Side data:
cpb: bitrate max/min/avg: 0/0/1000000 buffer size: 2000000 vbv_delay: N/A
Output #2, null, to 'pipe:':
Metadata:
encoder : Lavf59.27.100
Stream #2:0: Video: h264 (Main), cuda(pc, gbr/unknown/unknown, progressive), 320x240 [SAR 1:1 DAR 4:3], q=2-31, 8000 kb/s, 25 fps, 25 tbn
Metadata:
encoder : Lavc59.37.100 h264_nvenc
Side data:
cpb: bitrate max/min/avg: 0/0/8000000 buffer size: 16000000 vbv_delay: N/A
Output #3, null, to 'pipe:':
Metadata:
encoder : Lavf59.27.100
Stream #3:0: Video: h264 (Main), cuda(pc, gbr/unknown/unknown, progressive), 320x240 [SAR 1:1 DAR 4:3], q=2-31, 6000 kb/s, 25 fps, 25 tbn
Metadata:
encoder : Lavc59.37.100 h264_nvenc
Side data:
cpb: bitrate max/min/avg: 0/0/6000000 buffer size: 12000000 vbv_delay: N/A
Output #4, null, to 'pipe:':
Metadata:
encoder : Lavf59.27.100
Stream #4:0: Video: h264 (Main), cuda(pc, gbr/unknown/unknown, progressive), 320x240 [SAR 1:1 DAR 4:3], q=2-31, 5000 kb/s, 25 fps, 25 tbn
Metadata:
encoder : Lavc59.37.100 h264_nvenc
Side data:
cpb: bitrate max/min/avg: 0/0/5000000 buffer size: 10000000 vbv_delay: N/A
Output #5, null, to 'pipe:':
Metadata:
encoder : Lavf59.27.100
Stream #5:0: Video: h264 (Main), cuda(pc, gbr/unknown/unknown, progressive), 320x240 [SAR 1:1 DAR 4:3], q=2-31, 7000 kb/s, 25 fps, 25 tbn
Metadata:
encoder : Lavc59.37.100 h264_nvenc
Side data:
cpb: bitrate max/min/avg: 0/0/7000000 buffer size: 14000000 vbv_delay: N/A
frame= 1250 fps=262 q=8.0 Lq=9.0 q=9.0 q=9.0 q=9.0 q=9.0 size=N/A time=00:02:15.52 bitrate=N/A speed=28.4x
video:12550kB audio:0kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: unknown
Exiting normally, received signal 2.
I’ve gone through every setting in the admin interface, every .xml file I can find, and even poured over the tables in com.plexapp.plugins.library.db but cannot find where this limit is being imposed. Does anyone have any ideas how to fix this?
