No announcement yet.

The Cost Of Running Compiz

  • Filter
  • Time
  • Show
Clear All
new posts

  • #41
    Correction time...
    Originally posted by V!NCENT View Post
    So how many times slower is compiz?
    So by what percentage is Compiz slower?

    14.56 / 25.34 = 0.57% the speed of Compiz, so 100 - 57 = 43% slower...
    14.56 / 25.34 = 0.57 times the speed of Metacity, so 100 - 57 = 43% slower...


    • #42
      I play quakelive and it is mandatory to turn off compiz, I do so by pressing alt+f2 and typing metacity --replace. with metacity quakelive runs at 125 fps with compiz its fluctuates between 50-125 also input is much slower from the mouse. Which in quakelive input is very important. When done playing I hit alt+f2 again and type compiz --replace to restore compiz.


      • #43
        Originally posted by Zhick View Post
        Uhm how about Shift+Alt+F12?
        I use my script for the same reason you make symlinks to programs for example...


        • #44
          rewrite OSX vs MS WOS vs Ubuntu Ogl

          After this artile you must rewrite your older, perhaps including ATI cards in your review.
          Mac OS X 10.6.3 vs. Windows 7 vs. Ubuntu 10.04 Benchmarks

          You should include ATI / NVIDIA metacity / compiz, and of course run all tests in a Mac or in a Hackintosh same hardware please.


          • #45
            Originally posted by Eazy View Post
            I use my script for the same reason you make symlinks to programs for example...
            Okay, but seems a little clumsy to always kill/restart kwin when starting a game. Maybe there's a way to do this with dbus?
            Just had a look, qdbus org.kde.kwin /KWin toggleCompositing does the trick.


            • #46
              Everything seems to be slower with compiz; responsiveness, mouse cursor, web browsing...


              • #47
                Originally posted by hax0r View Post
                Everything seems to be slower with compiz; responsiveness, mouse cursor, web browsing...
                While I do agree to some point there is some benefit to it, like the time it takes an application to load, is masked by the compiz animation for the window showing up on screen. Web browsing and mouse cursor has unnoticeable performance hits in most cases. I run a core 2 duo with a 9500gt with 3GB of rams. on lower end hardware I can see how compiz would affect browsing and the mouse cursor, I ran compiz on a G4 1.4Ghz with a radeon 9200 once, talk about slow. I have always liked the graying out of windows when something becomes unresponsive.


                • #48
                  Originally posted by Sacha View Post
                  This article is a response to another article that shows Arch Linux having almost double the frame rate in a game compared to Ubuntu.

                  They brushed it off saying it was due to Compiz.

                  However, these results show quite the opposite. Worst case scenario, you're running nVidia and get a 20% performance drop.
                  If you're using Intel, maybe a 15% performance drop.
                  Using ATI and you're either gaining from Compiz or having no change at all.

                  So where does this 40-50% performance drop come from in Ubuntu? I'm guessing you can't blame Ubuntu.

                  So can you run the Arch vs Ubuntu videogame test again with Compiz on/off?
                  Yeah I found it INCREDIBLY lazy that he just dismissed it as compiz's fault rather than simply re-running that test with compiz off.


                  • #49
                    so what - compiz is a highly unstable product and installing/activating it by default was/is a desperate move by ubuntu and the gnome crowd. Why not just ignore the crap altogether?


                    • #50
                      It would seem to me that Compiz almost "must" use more power. My interest is not in games but power efficiency. My system is a couple of years old now and uses an AMD 4850e, DDR2 ram, WD Green power, onboard ATI grahics (HD3200) and a 80Plus power supply. It idles at around 48w (just the box, excluding monitor etc) and rarely passes 60w in normal usage, even video rendering just makes it into the 70s.

                      So the big test for me is how many extra watts are we using for just a few fade effects and shadows?

                      Maybe an interesting next article for Phoronix.