Announcement

Collapse
No announcement yet.

Running The Latest GNOME Wayland Shell On Fedora 20

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

  • Running The Latest GNOME Wayland Shell On Fedora 20

    Phoronix: Running The Latest GNOME Wayland Shell On Fedora 20

    With the Fedora 20 beta coming up I decided to see where the latest Fedora 20 packages are now at for their support of Wayland and the GNOME Shell Wayland session. In particular, looking at whether the session is still buggy and how the XWayland performance is for Linux gaming.

    http://www.phoronix.com/vr.php?view=19265

  • #2
    fullscreen

    Are these benchmarks running in fullscreen mode?

    Are there options for gnome-shell under xorg and wayland not to composite fullscreen windows....and are on or off?

    Comment


    • #3
      Originally posted by bofh80 View Post
      Are these benchmarks running in fullscreen mode?

      Are there options for gnome-shell under xorg and wayland not to composite fullscreen windows....and are on or off?
      XWayland is rootless, meaning EVERY window is fullscreen in the eyes of X11. But no, sadly the one thing that we really need in XWayland (composite bypass for "fullscreen" (AKA all) windows) has not arrived. Because it runs rootless, it would improve performance for every application you opened with XWayaland, not just the ones that look fullscreen to you :/

      Comment


      • #4
        Performance difference could be much worse I suppose, I'd probably take that if it meant I could run a tear-free desktop

        Comment


        • #5
          Originally posted by Daktyl198 View Post
          XWayland is rootless, meaning EVERY window is fullscreen in the eyes of X11. But no, sadly the one thing that we really need in XWayland (composite bypass for "fullscreen" (AKA all) windows) has not arrived. Because it runs rootless, it would improve performance for every application you opened with XWayaland, not just the ones that look fullscreen to you :/
          Thanks for the info Daktyl .

          Comment


          • #6
            How many fps you can do is not all the story on performance. Smooth experience on desktop should be the focus right now, who cares how many fps you can do in games? sorry for my reaction, but I've tried wayland and the desktop experience is shocking. X sucks in every way.

            Comment


            • #7
              Meh. The benchmarks would be more interesting if the games were running natively on Wayland (SDL has been ported to Wayland) and then compared against their X11 versions…

              Comment


              • #8
                i care

                Originally posted by sp82 View Post
                How many fps you can do is not all the story on performance. Smooth experience on desktop should be the focus right now, who cares how many fps you can do in games? sorry for my reaction, but I've tried wayland and the desktop experience is shocking. X sucks in every way.
                i care, if a game work with 60 fps on x and a 30 on wayland...! and like inittial with xmir we have a noticiable regression on fps

                Comment


                • #9
                  Originally posted by Awesomeness View Post
                  Meh. The benchmarks would be more interesting if the games were running natively on Wayland (SDL has been ported to Wayland) and then compared against their X11 versions…
                  Eeeeeeeeeh... SDL2--- TWO -- has been ported to Wayland. Not SDL1. So we need some apps that are written against SDL2 in order to actually test them accurately.

                  Comment


                  • #10
                    It should be compared with Mir. That would be interesting

                    Comment


                    • #11
                      Originally posted by Ericg View Post
                      Eeeeeeeeeh... SDL2--- TWO -- has been ported to Wayland. Not SDL1. So we need some apps that are written against SDL2 in order to actually test them accurately.
                      Considering how long SDL2 has been in development, the games' programmers had plenty of time to port to it. I'd be surprised if no game is there yet (at least in some dev branch).

                      Comment


                      • #12
                        Porting a game to use the Wayland-capable SDL shouldn't be too difficult. Let's see what's on the horizon- I wonder if SDL can change the backend at runtime (like GTK), or if you need to have either an X11 package or Wayland package.

                        Comment


                        • #13
                          Originally posted by Andrecorreia View Post
                          i care, if a game work with 60 fps on x and a 30 on wayland...! and like inittial with xmir we have a noticiable regression on fps
                          the xwayland performances are 80% of performance in X, not bad after all, xwayland is young and there is room for performance improvement expecialy if you port the game wayland.

                          Comment


                          • #14
                            Originally posted by edoantonioco View Post
                            It should be compared with Mir. That would be interesting
                            Erhm, no. XWayland, what is tested here, should be compared with XMir. As it stands, both have an overhead penalty over native X.org.

                            When both native Mir and native Wayland software appears (and hopefully that software runs on both), Mir should be compared to Wayland.

                            Comparing a compatibility layer with a native display stack is apples and oranges.

                            Comment


                            • #15
                              There is something strange with these benchmarks. I imagine that some driver optimization or something else is perturbing the results.

                              For example the last test has 57.86 fps on X, and 50.38 fps on Fedora XWayland + Gnome.
                              This looks strange, because in theory, the main different should be an additional copy in XWayland case, and it shouldn't be more than 2-3 fps here.

                              And a similar test I did makes me think it is a driver optimization.

                              I have tested XWayland vs XWayland + AsyncSwap (avoid the additional copy) on my dedicated card (Amd hd 7730m) on an embedded compositor running under Prime (compositor copy + XWayland copy / no XWayland copy (if AsyncSwap)).


                              Each time I restart the computer between the tests.

                              It gives:

                              Reaction Quake 3 1.0 Beta - pts/reaction-1.0.4 (Resolution 1920x1080)

                              Embedded Weston compositor + AsyncSwap:
                              Code:
                              Test Results:
                                      53.2
                                      53.3
                                      53.8
                              
                                  Average: 53.43 Frames Per Second
                                  Minimum: 53.2
                                  Maximum: 53.8
                              Without AsyncSwap:

                              Code:
                              Test Results:
                                      49.8
                                      50
                                      42
                                      41.7
                                      41.4
                                      41.6
                              
                                  Average: 44.42 Frames Per Second
                                  Minimum: 41.4
                                  Maximum: 50
                              On X (with Prime):

                              Code:
                              Test Results:
                                      52,1
                                      42,1
                                      43,9
                                      44
                                      43,9
                                      44
                              
                                  Average: 45,17 Frames Per Second
                                  Minimum: 43,1
                                  Maximum: 52,1
                              So after a few time, with two copies instead of one (embedded Weston + AsyncSwap / bare X with Prime), there is a high fps drop after the benchmark run for a few minutes.

                              Since here we compare two copies(Gnome (no compositing bypass) + XWayland) vs one (bare X (no prime)), I can't held imagine we see a similar optimization issue here (even if Michael benchmarks are on an intel card and not an AMD card as I tested)

                              Comment

                              Working...
                              X