Announcement

Collapse
No announcement yet.

Kernel-Based X11 Server Claims 2x Performance Over X.Org

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

  • Kernel-Based X11 Server Claims 2x Performance Over X.Org

    Phoronix: Kernel-Based X11 Server Claims 2x Performance Over X.Org

    MicroXwin is an X.Org Server alternative for an X Windows System implementation for Unix/Linux desktop. The developers behind MicroXwin are claiming that by implementing their X Server in the kernel they are getting a 2x performance advantage while using less memory and being binary compatible with Xlib...

    http://www.phoronix.com/vr.php?view=MTM5NDU

  • #2
    A Xserver in the kernel? Doesn't that mean that the kernel panics when the Xserver crashes?

    Comment


    • #3
      So kernel developers rant about how difficult is maintain the code due its complexity and here it goes one pal that adds a lot more code.

      And what code ...

      Even if it's leaner, it stands X, with all that complex architecture and stuff.

      Now in kernel ...


      Maybe would be usefull in embeded systems. But for desktop and servers ... well.

      Comment


      • #4
        Originally posted by phoronix View Post
        Phoronix: Kernel-Based X11 Server Claims 2x Performance Over X.Org

        MicroXwin is an X.Org Server alternative for an X Windows System implementation for Unix/Linux desktop. The developers behind MicroXwin are claiming that by implementing their X Server in the kernel they are getting a 2x performance advantage while using less memory and being binary compatible with Xlib...

        http://www.phoronix.com/vr.php?view=MTM5NDU
        I'm sure we'll hear about all the downsides of such a thing in this thread. But for a hard core gamer, an X server that provides this much of a performance win would be worth it.

        Comment


        • #5
          So, um, benchmarks?

          Comment


          • #6
            Originally posted by Vim_User View Post
            A Xserver in the kernel? Doesn't that mean that the kernel panics when the Xserver crashes?
            Definitely sounds like it is a step backwards for everything except performance. Also, f you upgrade your kernel, there is probably more likelihood that the Xserver will need a recompiled/to be patched to work again.

            In contrast, on Windows with Nvidia (and maybe other drivers), and possibly Wayland, if the graphics driver crashes, it may be possible to recover automatically without a reboot / work-loss.

            Technically, its easier to get better performance probably out of anything by sticking it into the kernel, but, with a good design, you could probably obtain similar performance from user-land anyway (along with better security).

            Comment


            • #7
              Raspberry Pi Support?

              Would be cool to see this running on a raspberry pi since this kind of hardware would definitely show if the performance is really that great

              Comment


              • #8
                Anyone else wonder why the video is running on a VM under Windows?

                Just saying... I would expect a linux dev to be working under linux.

                Comment


                • #9
                  Anyone want to build a distro on this for the lolz?

                  Comment


                  • #10
                    Originally posted by ShadowBane View Post
                    Anyone else wonder why the video is running on a VM under Windows?

                    Just saying... I would expect a linux dev to be working under linux.
                    It's honestly just insulting.

                    They are
                    • dangerously rewriting X as a kernel module
                    • keeping this unverified source code completely closed
                    • somehow not breaking the GPL by the above statement
                    • and to top it off, they're running this all in a VM on Windows 7.

                    They need to re-evaluate their priorities, and I'd like someone to explain to me how they're able to do this in-kernel without releasing the source code?

                    Comment


                    • #11
                      Originally posted by david_lynch View Post
                      I'm sure we'll hear about all the downsides of such a thing in this thread. But for a hard core gamer, an X server that provides this much of a performance win would be worth it.
                      Games already bypass the X server entirely, afaik, with the DRI2 protocol, so this is really just for desktop performance.

                      Anyway, the main downside for me wouldn't be possible instability, it would be the security holes.

                      Remember, X is network transparent, as so many people like to remind us. It would be like sticking a web browser in your kernel and expecting it to be secure.

                      Comment


                      • #12
                        Originally posted by coder543 View Post
                        [*]dangerously rewriting X as a kernel module

                        [sic] I'd like someone to explain to me how they're able to do this in-kernel without releasing the source code?
                        You answered you own question, it's a kernel module they can license it however they like.

                        Originally posted by coder543 View Post
                        [*]and to top it off, they're running this all in a VM on Windows 7.
                        I don't see your point, just because the guy who uploaded the youtube video is running Windows doesn't mean they always run in it VMs or Windows. Even if they did, why do you get a say in how they develop?

                        Comment


                        • #13
                          Originally posted by coder543 View Post
                          It's honestly just insulting.

                          They are
                          • dangerously rewriting X as a kernel module
                          • keeping this unverified source code completely closed
                          • somehow not breaking the GPL by the above statement
                          • and to top it off, they're running this all in a VM on Windows 7.

                          They need to re-evaluate their priorities, and I'd like someone to explain to me how they're able to do this in-kernel without releasing the source code?
                          Citations needed for dangerously, relating specifically to this project. I find it interesting that you use this adjective without actually knowing the workings of the project in question.

                          2 & 3 are the same for any proprietary kernel module, as long as it's installed by the end user there is no distribution with GPL code, which means it doesn't come into effect.

                          Comment


                          • #14
                            Originally posted by smitty3268 View Post
                            Games already bypass the X server entirely, afaik, with the DRI2 protocol, so this is really just for desktop performance.

                            Anyway, the main downside for me wouldn't be possible instability, it would be the security holes.

                            Remember, X is network transparent, as so many people like to remind us. It would be like sticking a web browser in your kernel and expecting it to be secure.
                            IIRC, the network transparency has been stripped out of microXwin, but that in itself might not mitigate the security risk.
                            I imagine this would be more suited towards offline equipment.

                            Comment


                            • #15
                              As an Ubuntu gamer..

                              I'd use this if the performance is really that much better. I've got an i7-3770 and a GeForce GTX 660Ti.. I use nVidia drivers as it is and I have no objection to it. I paid good money for this rig, I want to get that value out of it. I'd prefer this be open source so I could feel, like, secure-- but hell, I could dual boot Ubuntu with a distro for this and just use the same Steam partition. Dual booting for games is fine with me, I just don't like *Windows*. Like the PS4 OS, Orbis BSD. If I could play PS4 games that way, heck yeah I'd do it. I am very interested to see benchmarks for this.

                              Even if no one wants to use it because it's proprietary, it's a proof of concept either way. We may as well know how much performance you can wrangle out of this. Also, when my X crashes, I restart. So does everyone else in my family who is less tech savvy, so this "Oh, but an X crash doesn't take down the whole OS...." ...entirely irrelevant from a layman's perspective, and irrelevant to me. Compiz, on the other hand.. that crashes enough that I'm glad I can just restart it.

                              Comment

                              Working...
                              X