Announcement

Collapse
No announcement yet.

Power & Memory Usage Of GNOME, KDE, LXDE & Xfce

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

  • Awesome, mugginz. I think you earned (almost) everybody's cookies.

    The Kubuntu figure is in agreement with what Kano reported for 64 bits. Which makes sense if you are also on 64 bits...which you are, I think?

    So your tests give 19% of Ubuntu-KDE over Ubuntu-Gnome, and 33-64% (!) of Kubuntu over Ubuntu-Gnome, if I understood your numbers right. Phoronix results, including caches, give an average of 30% for Ubuntu-KDE over Ubuntu-Gnome. Now, the reason why the numbers are reduced is because KDE 4 caches more than Gnome. If the amount of cached memory was the same, the differences would be of course greater, according to the supreme laws of division. And the same would happen if you subtracted the memory consumed by all the other processes in the system, which are common to both DEs--adding a constant changes the percentages, only that in favour of the loser, reducing the differences ; )

    Originally posted by V!NCENT
    Which is, in turn, resulting from not constantly looping a function in the brain that tries to trace what caused (result from logic) the sentences spoken out by people who are also taking part of the conversation that he is part of and instead the person only obeserves the sentences and tries to correct them while they are not part of this 'greater whole' or "larger argument".
    Very lucid, V!NCENT. Does that mean that you now realize why these past comments of yours were so out of place that I didn't bother replying to them?

    Originally posted by V!NCENT
    @Yotabien:
    You FAIL.

    Too bad there's a 1min edit tinme limit, because I would have demanded you took away my quotes.

    Nice BS theory of stages, but don't quote me in the WRONG ORDER!

    I said from the beginning the resulst were expected. Kwin was compared to Compiz which has NOTHING to do with Gnome.

    Then you quoted that I said "I don't care for the RAM usage because I have 8GB", but you failed to miss the point COMPLETELY.

    *Oh BTW... I guess this is my denial stage... yeah you fail terribly*

    My point was that one should look at what RAM is executed. The entire idea of sucking up RAM doesn't mean using/changed it and thus means absolutely zero in speed/performance, energy consumption and CPU load. I'm saying it again; you failed.

    Furthermore KDE has shown in the past (with KDE 3.5.x) that when it's feature stripped to the low point of Gnome it has less RAM, less CPU load and thus less battery consumption and is faster. What that means is that Gnome should get first to the point of KDE 4.4.x's features before even being allowed the right to speak out/spoken for.

    But like BlackStar said: this is amusing. Although correction half-truths and half-quotes tires me, it's endless satisfaction XD

    Comment


    • I should've noted that the above figures are as follows:

      All distros are x64
      Above tests are with all current updates applied
      Configuration, software, etc are as per default install.
      Memory usage is as per that reported by the free command.
      Buffers and cache are not included and don't belong in that measurement in my view.
      Overhead of the script performing the bench is approx 1.5MB for bash, etc.


      The Ubuntu 10.04 test is the standard Gnome desktop on Ubuntu 10.04
      The Kubuntu 9.04 test is the standard KDE desktop on Kubuntu 9.04
      The Kubuntu 10.04 test is the standard KDE desktop on Kubuntu 10.04

      My objective is to try and determine how much RAM is made unavailable by the standard software suite of a particular distro.

      For the Gnome test the terminal used is gnome-terminal and the Video playback is performed by Totem.
      For the KDE test the terminal used is Konsole and the Video playback is performed by Dragon Player.

      The video file is a 320x240 ogg theora video.
      The desktop is running at 1024x768 24bits/pixel

      Tests werre run in a KVM virtual machine as per:
      • 1024M RAM
      • 8096M HDD
      • Cirrus CL 5446 VGA
      • ENSONIQ AudioPCI ES1370 sound card

      A virtual machine was used because the only fast machine I have here at the moment is my desktop and I need that up at all times. Now that I'm happy with the test methodology I'll be running them on a Celeron 1.2G, 512M RAM, 40G HHD machine in order to get an idea for 32bit results. I've got some figures for unpatched Kubuntu 10.04 x64 but the KDE fans out there wouldn't want to read those.

      Comment


      • Is Compiz and/or the KWin compositor enabled? This can affect memory usage quite a bit (around 30MB or so for 1024x768).

        Comment


        • Originally posted by BlackStar View Post
          Is Compiz and/or the KWin compositor enabled? This can affect memory usage quite a bit (around 30MB or so for 1024x768).
          Not for those tests but I'll soon have numbers including with & without compiz when I finish the benches on bare metal.

          Comment


          • Post 200!

            It's interesting to note that when you start an application, it takes a larger chuck of memory in GNOME than KDE. Not enough to make up the difference, but I wonder if you could come up with a heavier use scenario that had a few apps running at the same time. Maybe try a console app + file manager + video player and see what happens.

            Comment


            • While running some memory benches for Ubuntu 10.04 Alpha3 i386 on a crusty old PIII based Celeron 1.2GHz box with 512M it became obvious how good the boot times are now even on old gear.





              Given how unwise it is to run a Windows box without anti-malware, comparing a Compiz enabled Ubuntu desktop to crusty Windows XP with AVG running on it is a bit of an eye opener. The Windows install was a clean build with SP3, nVidia blob and AVGfree. The Ubuntu install was a clean build with all updates, nVidia blob and Compiz running happy as a pig in mud.

              Comment


              • I might add that even though XP took about a week and a half to boot, unlike Ubuntu it was far from as responsive and settled for quite a while after the start menu was available for use.

                Comment


                • Originally posted by karl View Post
                  First of: ppl. with arch/gentoo asking for vanilla tests please do it yourself and post here the results you get. I think this approach is better and doing so you will contribute more knowledge and help ppl. be more informed about this issue.

                  Second, I think that (at least for me) the results are as expected.

                  LXDE is the lightest DE because it offers the least amount of gfx candy and least amount of functionality. But guess what, for some ppl. this is exactly what they are looking for.

                  Then we have Gnome, which is between LXDE and KDE. It's a full DE, plenty of apps., some gfx candy (if you want more you get it with compiz) and middle resource usage. For some ppl. this middle ground is the sweet spot.

                  Then you get KDE: the full DE platform. You get lots of gfx candy, lots of apps/services/addons/widgets. Ppl. that like customization will feel @ home here.

                  So they all fill a "niche" and there is place for all of them.
                  Here is a test. My laptop running Gentoo Linux uses 148MB of RAM in KDE 4.4.1 with only konsole open (and all of the various stuff that is set to auto-start running in the background, including Wicd), which is far below than any of the figures that Phoronix presented, even for LXDE.

                  All of the stuff Ubuntu runs in the background is skewing the results. The only reason KDE does so poorly in memory footprint on Ubuntu is probably more of an indication that someone did not properly replace Gnome with KDE (perhaps the Kubuntu people) prior Phoronix's tests than it is of any deficiency in KDE.

                  Comment


                  • It seems today's updates have further reduced the memory footprint of my system to 139MB. My system is still running KDE 4.4.1, so the only change has been in background libraries. The ability for me to get this sort of memory footprint calls the numbers Phoronix provides into question. There is no way that the desktop environments, even the lightest weight one, LXDE, are using the majority of the RAM being reported in use.

                    Comment


                    • I think the problems with the numbers provided by Phoronix have been exposed several pages (and many days) ago. And I think it's also clear that KDE4 consumes more memory than the other DEs. I don't want to discuss that again. However, it is quite funny that you bring the updates you did today as some sort of argument against a benchmark performed two weeks ago.

                      Comment


                      • Battery usage

                        I don't care much about the memory usage of KDE, what concerns me is the battery usage. I've noticed (monitoring cpu load when doing various tasks) that KDE seems to be, in general, more of a cpu pig than gnome, even with compositing disabled. E.g. hovering over the Task Manager widget in KDE (also Smooth Tasks and the like) is quite cpu intensive, whereas hovering over Window List in a gnome panel is far less intensive. I find that odd.

                        And text editing long lines in a Qt based editor (whether the lines are *dynamically* wrapped or not, but with syntax highlighting on) is unbearable (a bug in QTextEngine). Actually the same is true of gedit but not other GTK editors.

                        I really like the latest KDE but seeing results like this and being primarily a laptop user, one sometimes gets the urge to switch back to gnome.

                        Comment


                        • Is consuming the same as utilising? Sometimes not.

                          All I know is that one slot of 2GB of RAM costs 47 bucks:
                          http://www.newegg.com/Product/Produc...82E16820148221
                          And I know that KDE is much faster in running multiple apps at the same time than Gnome.

                          Computers these days can handle anything if ran at full speed, utilising an entire core (no timeslicing). Thus todays law is no Longer Moore's; it is load.

                          Memory footprint and speed (Enlightenment is set to run at 30fps, not 1000fps) is totaly out of the question today. Get over it and replace your 10yo PC with a 500 dollar one from Dell and never again worry about anything for the next 6 years.

                          Comment


                          • Originally posted by V!NCENT View Post
                            Is consuming the same as utilising? Sometimes not.

                            All I know is that one slot of 2GB of RAM costs 47 bucks:
                            http://www.newegg.com/Product/Produc...82E16820148221
                            And I know that KDE is much faster in running multiple apps at the same time than Gnome.

                            Computers these days can handle anything if ran at full speed, utilising an entire core (no timeslicing). Thus todays law is no Longer Moore's; it is load.

                            Memory footprint and speed (Enlightenment is set to run at 30fps, not 1000fps) is totaly out of the question today. Get over it and replace your 10yo PC with a 500 dollar one from Dell and never again worry about anything for the next 6 years.
                            That's some unthoughtful advice. Some people have better things to spend their money on.

                            Comment


                            • Originally posted by molecule-eye View Post
                              And text editing long lines in a Qt based editor (whether the lines are *dynamically* wrapped or not, but with syntax highlighting on) is unbearable (a bug in QTextEngine). Actually the same is true of gedit but not other GTK editors.
                              This is horrible. And it's been like this since I first tried the KDE4 versions of Kate and Kile, way, way before I actually installed the whole thing. Do you have a link for the actual bug?

                              I really like the latest KDE but seeing results like this and being primarily a laptop user, one sometimes gets the urge to switch back to gnome.
                              I observed that CPU spikes while doing what one would consider to be stupidly simple tasks are way less common now than a couple of releases ago (I don't want to imagine what KDE4 <= 4.2 was like, and I thank those poor bas...testers who got most of the bugs out of the way). My only complain about KDE4 now is the startup time really.

                              Comment


                              • All I know is that one slot of 2GB of RAM costs 47 bucks:
                                Which is a horrible price hike when ~2 years ago it cost 20$.

                                Comment

                                Working...
                                X