Announcement

Collapse
No announcement yet.

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

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

  • Astronaut In Orbit
    replied
    "2x"

    "2x" performance boost? Ok, to really benchmark the difference you have to ofcourse understand that X is dependant on configuration.

    First of all, ATLEAST renice it to -20, to not have it be a bottleneck. And then with lower interrupts, more time is spent rendering. Try 100 hz kernel. Also latencies, mean rendering is not happening with X being subject to latency. Turn on low-latency desktop.

    Those should be minimal requirement for any comparison, since an X running inside the kernel, might be closer to this.

    Leave a comment:


  • ArneBab
    replied
    A non-free kernel module. Reminds me of Linus' Finger for nvidia.

    Leave a comment:


  • daniels
    replied
    Originally posted by Delgarde View Post
    Oh, ok... hadn't noticed that. I guess that means it needs a different set of userspace libraries too, then - not just the in-kernel module? API/ABI compatible, but not usable with the existing X libraries?
    exactly. or with xcb.

    Leave a comment:


  • Delgarde
    replied
    Originally posted by daniels View Post
    also note that it's just a reimplementation of the libX11/libXext API, not the actual X11 protocol. so no network support.
    Oh, ok... hadn't noticed that. I guess that means it needs a different set of userspace libraries too, then - not just the in-kernel module? API/ABI compatible, but not usable with the existing X libraries?

    Leave a comment:


  • daniels
    replied
    also note that it's just a reimplementation of the libX11/libXext API, not the actual X11 protocol. so no network support.

    Leave a comment:


  • Delgarde
    replied
    Originally posted by RealNC View Post
    Can this thing actually work with X.Org drivers? Everybody in this thread seems to assume it, but it wasn't stated. So, can you run AMD Catalyst, NVidia's driver, or the OSS drivers with it?
    As I said earlier, I assume not. If nothing else, because they're all written as user-space code, and coded to an API defined by the Xorg implementation, not by the X11 spec. I'm guessing this doesn't do drivers at all, and just renders to a kernel-provided framebuffer.

    Leave a comment:


  • Vim_User
    replied
    Originally posted by HeavensRevenge View Post
    But it's license is an MIT license, not GPLv3. So MIT licensed software can also be closed source making this not an issue.
    Its license will always stay MIT. It can be used in closed-source software, but it will always remain free. This embedded Xserver is closed from the beginning.

    Leave a comment:


  • HeavensRevenge
    replied
    I also hope X will be obsoleted by some newer X-like system, but to all of you complaining about licensing, honestly "X" is probably the oldest piece of software still in use today, it was born what... 30 years ago and is a true monstrosity of complexity. But it's license is an MIT license, not GPLv3. So MIT licensed software can also be closed source making this not an issue.

    Leave a comment:


  • migizi
    replied
    The idea and execution work. Will it ever see wide adoption? Probably not. We are seeing a move to get away from X not embed it into the kernel. I can see where embedded systems would benefit from this, but everyday users won't adopt it. I haven't even looked up licensing costs but I bet you it exceeds a Windows license. At that point I might as well use Windows to save money and have better support for games. Oh heck I looked at the site and it specifically says "X-Windows for Embedded Systems" I don't even see a point in pursuing any benchmarks, we know that embedded is supposed to work faster and leaner.

    Leave a comment:


  • DeepDayze
    replied
    Originally posted by DebianLinuxero View Post
    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.
    Something like this would definitely be great for smartphones and tablets I would say. However such code needs to be very robust as well as having strong error recovery in order to keep the kernel from panicking if this X server module were to fail.

    Now what about trying to put Wayland/Weston into the kernel?

    Leave a comment:

Working...
X