docker-jellyfin VS docker-mods

The container's Dockerfile is based on Ubuntu Jammy and performs a straight-up install of the debs from repo.jellyfin.org, so it'll be the same as on any Debian-based system, indeed /var/lib/jellyfin/plugins.

The Linuxserver.io image is, first of all, a 3rd party unofficial image, but with our blessing. They take a base Ubuntu OS image and install our official Ubuntu packages in the Docker environment. On startup it also executes the same binary in the end, so functionally, to anyone who doesn't know any different, they're the same: you get Jellyfin out in the end.

Are you using Docker? If so you’ll probably need to expose the device through to Docker too. Instructions for Pi here, which may or may not work: https://github.com/linuxserver/docker-jellyfin

I'm on an Arch Linux host with linuxserver image (J4005 with UHD600). OpenCL tone mapping does not work out of the box. I have to add DOCKER_MODS=linuxserver/mods:jellyfin-opencl-intel , per this GitHub issue, as an additional environment flag to my docker-compose.yml file, lest ffmpeg complains about not able to find device ocl@va.

If you don't want to migrate to the official one, just wait for https://github.com/linuxserver/docker-jellyfin/pull/155

Have you tried adding the OpenCL-Intel Dockermod for the LSIO container? I don't believe it'll function properly without it...fair warning it significantly increases startup time. Additionally, it may not matter if you've already verified your hardware acceleration is working as expected, but at one point I did have to specifically indicate both renderD128 and card0 to get everything settled. If it ain't broke, don't fix it, but that's a difference in our compose files I spotted immediately.

Misc - LinuxServer.io images now support mods with multi-digest layers (https://github.com/linuxserver/docker-mods/pull/577)

Are you using a linuxserver container? If so, check this out as well: https://github.com/linuxserver/docker-mods/tree/jellyfin-opencl-intel

If you are running using the lsio container, you could try out this repo which makes the par2 process 2-3 times faster. https://github.com/linuxserver/docker-mods/tree/sabnzbd-par2cmdline-turbo

If you're using the LinuxServer plex image, you're probably facing this issue. https://github.com/linuxserver/docker-mods/issues/575

Following this issue and looking at the code here it appears that the mod identifies running applications on swag by globbing all the conf files (including samples!) and attemting a connection on them. And it does this with ThreadPoolExecutor(max_workers=100) which seems to explain why those DNS queries were being spammed on pihole.

I run a similar set up, but i run jellyfin with linuxserver's docker with this addon: https://github.com/linuxserver/docker-mods/tree/jellyfin-amd