Bazzite comes ready to rock with Steam and Lutris pre-installed, HDR support, BORE CPU scheduler for smooth and responsive gameplay, and numerous community-developed tools for your gaming needs.

  • @poki
    link
    24
    edit-2
    3 days ago

    TLE did a performance test on this distro and it was pretty much the same in terms of FPS as other distros.

    Without measuring any 1% lows or 0.1% lows.

    I enjoy TLE’s content, but that video is far from exhaustive on this.

    Unless a better comparison comes out, we should reserve ourselves from making any judgements on this particular subject.

    • I still don’t think there will be a difference. I tried distros with various schedulers and didn’t notice a major positive difference except for the DE smoothness that was unbeatable on CachyOS.

        • @poki
          link
          62 days ago

          Thank you for sharing! If you remember, could you share your findings?

      • @poki
        link
        2
        edit-2
        3 days ago

        So…, you don’t think it will make a difference. However, you do affirm that whatever CachyOS does is noticably better than the rest.

        Perhaps more importantly, have you actually measured 1% lows or 0.1% lows on games. And did you compare how different distros fared in this regard?

        • I didn’t measure 1% lows but I noticed that regular distros (specifically Fedora and Arch based ones) performed noticeably better in terms of overall FPS.

          • @poki
            link
            13 days ago

            Thank you for mentioning that! Did the slower distros you tested come with older kernels?

            • Fedora did have an older kernel but other distros were Arch based so always new kernels. Also I have to mention that CachyOS focuses on x86_64-v3 that my machine doesn’t support so results can be very different on newer hardware.

    • On one hand, I think some data is better than no data, so I think its fair to say that there is a lack of evidence for it being better in terms of in-game performance after setup based on it and that should just be the null assumption anyways.

      On the other hand, its been over a decade since its been pretty well known that average FPS is not necessarily reflective of overall performance and throwing the frametime data into a spreadsheet and doing =percentile([range],.99) and =percentile([range],.999) and then dragging it to neighboring cells seems like a pretty minimal extra work for a commercialized channel. For niche testing like this, I’m less bothered by it because having some results seems better than nothing, but its still nice to see it pointed out.