Announcement

Collapse
No announcement yet.

GNOME Shell vs. KDE Plasma Graphics Tests On Wayland vs. X.Org Server

Collapse
X
  • Filter
  • Time
  • Show
Clear All
new posts

  • GNOME Shell vs. KDE Plasma Graphics Tests On Wayland vs. X.Org Server

    Phoronix: GNOME Shell vs. KDE Plasma Graphics Tests On Wayland vs. X.Org Server

    A premium member this week had requested some benchmarks of openSUSE Tumbleweed when looking at the performance of KDE Plasma vs. GNOME Shell in some open-source graphics/gaming tests while also looking at the Wayland vs. X.Org Server performance...

    http://www.phoronix.com/scan.php?pag...-Wayland-Feb18

  • #2
    It's important to consider that KWin doesn't auto-unredirect when the application doesn't tell it to do so. So it might be that in fullscreen tests, compositing doesn't get turned off unless done manually or via KWin rule. Gnome does always auto-unredirect in fullscreen (unless there is a bug preventing it).

    Edit: At least that's true for a Xorg session.
    Last edited by aufkrawall; 02-25-2018, 07:51 AM.

    Comment


    • #3
      Yea, benchmarks are great and all, but there's a lot they don't tell us. Previous benchmarks on GNOME Wayland were pretty much "on par" with x.org but in reality GNOME on Wayland had and still has a lot of issues for gaming, and the frame-rate you saw on the FPS counter wasn't the final frame-rate you saw on the actual screen because xwayland on GNOME is actually locked to 60fps regardless of your monitors refresh rate and thus it throws away a lot of frames which were counted by the benchmark but never made it on screen. There are jitter issues, input lag issues and so on...

      Comment


      • #4
        Originally posted by Brisse View Post
        Yea, benchmarks are great and all, but there's a lot they don't tell us. Previous benchmarks on GNOME Wayland were pretty much "on par" with x.org but in reality GNOME on Wayland had and still has a lot of issues for gaming, and the frame-rate you saw on the FPS counter wasn't the final frame-rate you saw on the actual screen because xwayland on GNOME is actually locked to 60fps regardless of your monitors refresh rate and thus it throws away a lot of frames which were counted by the benchmark but never made it on screen. There are jitter issues, input lag issues and so on...
        Sources please..

        Comment


        • #5
          Very impressive performance by both KDE and Gnome.
          My laptop rund really well on gnome-wayland. But my desktop has a Nvidia GFX card, so here i must wait a little longer :|

          Comment


          • #6
            Good to see that the results are so close and there are no major issues. I switched to Plasma Wayland as my default desktop months ago, but only since 5.12 it feels really stable.

            Comment


            • #7
              Originally posted by Sethox View Post

              Sources please..
              Gnome compositor on Wayland is limited to 60fps, leading to stuttery desktop with refreshrates above. This is not the case with KWin.
              However, also KWin can't do anything against the XWayland limitation of 60fps, so X applications will stutter as well.

              Comment


              • #8
                KDe PLASMA is the best environment both on desktop and mobile. It is superlative on desktop adding also the KDe Connect App to interact between desktop and mobile devices.

                Comment


                • #9
                  (is) The test utility is compliant with wayland standards? Or is it use xwayland?

                  Comment


                  • #10
                    If only gnome wouldn't lag that hard...

                    Comment

                    Working...
                    X