LWN: Comments on "What to merge for 2.6.13?" https://lwn.net/Articles/140975/ This is a special feed containing comments posted to the individual LWN article titled "What to merge for 2.6.13?". en-us Sat, 25 Oct 2025 16:04:13 +0000 Sat, 25 Oct 2025 16:04:13 +0000 https://www.rssboard.org/rss-specification lwn@lwn.net Fast clocks on slow hardware https://lwn.net/Articles/142431/ https://lwn.net/Articles/142431/ dmag It's probably the CPU type your kernel is compiled for. Nowadays, most distros optimize for recent CPUs. This code will run on your Pentium, but much slower. Having a slow CPU running a non-optimized program is a double whammy. A kernel recompile (telling it exactly which CPU you have) will give your 'slow' CPU a speed boost. <p> I've seen some distos targeted at older computers, but I don't think they go far enough. Here's what I would do: <ul> <li>Use the <a href='http://www.pps.jussieu.fr/~jch/software/kdrive.html'>KDrive</a> X Server. I think the new X.Org server is based on this, but I'm not sure if it's still as minimalist.</li> <li>Don't run KDE/GNOME. I'd use <a href='http://projects.o-hand.com/matchbox/'>Matchbox</a> if you're targeting grandma, or maybe <a href='http://ede.sourceforge.net/'>EDE</a>. If you still like lots of eye candy and compatibility with the fun KDE/GNOME desktop toys, use <a href='http://windowmaker.org/'>WindowMaker</a>.</li> <li>Boot with <a href='http://busybox.org'>BusyBox</a>. Maybe have a 'real' environment in a chroot. Get rid of all that silly SysV init stuff and must have a simple rcS script start what you need.</li> <li>If <a href='http://www.spreadfirefox.com/'>FireFox</a> is too slow, try <a href='http://www.dillo.org/'>Dillo</a>.</li> <li>Maybe avoid <a href='http://www.namesys.com/'>ReiserFS</a>, unless your disk is really slow too. ReiserFS tends to use a lot of CPU to avoid disk access, which won't always be a win. Ext3 should be fine, I think.</li> <li>There are also many other performance-enhancing techniques, such as <a href='http://freshmeat.net/projects/prelink/'>prelinking</a>.</li> </ul> I'm too lazy to make this distro just to turn my old laptop into an in-car MP3 player and GPS mapper.. Hopefully, someone else will :) Sun, 03 Jul 2005 04:12:56 +0000 Fast clocks on slow hardware https://lwn.net/Articles/142122/ https://lwn.net/Articles/142122/ xorbe As a long time Mandrake user (recently switched back when x86_64 mdk arrived), there is definitely something wrong with FC3 I can tell you. It. Is. So. Slow. Clicking, saving, typing, argggh! I have no idea what the underlying issue is there.<br> Thu, 30 Jun 2005 18:09:28 +0000 Fast clocks on slow hardware https://lwn.net/Articles/141390/ https://lwn.net/Articles/141390/ pflugstad I run a 2.6 kernel on a P5/133 MHz laptop - Debian distro (slimmed down) - with 96MB of RAM. At runlevel 3, it's plenty fast for just about everything I do. I even run fvwm and that works fine for a GUI.<br> <p> I do compile a custom kernel to remove a lot of the stuff I don't need and disable things like HIGHMEM (or whatever it is) that impact things. I'm also very careful to turn off as much stuff as I can.<br> <p> Heck, suspend even works on this thing.<br> <p> So it's very possible - it may not work "out of the box" but it runs just fine on slow systems. <br> <p> <p> Fri, 24 Jun 2005 18:51:09 +0000 Fast clocks on slow hardware https://lwn.net/Articles/141351/ https://lwn.net/Articles/141351/ evgeny As others have put it, it's hardly the clock rate that made the difference.<br> <p> Recently, I've installed Ubuntu on an old 266MHz PII PC. The thing was so dreadfully slow that even the pointer motion had an observable delay (sure enough, the default animated pointer theme didn't help). Then I recompiled the kernel enabling only the needed features/drivers - and it literally flies since then! I highly recommend you try recompiling the kernel; I do it for all systems I own/administer (and of course for Gentoo and like this is the normal setup procedure). The stock kernels of modern binary distros have so much mess enabled by default that I sometimes wonder how these work at all ;-)<br> Fri, 24 Jun 2005 13:53:44 +0000 reiser https://lwn.net/Articles/141344/ https://lwn.net/Articles/141344/ jschrod quantum improvement?<br> <p> You mean, like, the smallest measureable distance?<br> <p> Sorry, couldn't resist... :-) :-)<br> Fri, 24 Jun 2005 12:21:33 +0000 Fast clocks on slow hardware https://lwn.net/Articles/141310/ https://lwn.net/Articles/141310/ set hmmm. I dont see why a 2.6 kernel would be inherently slower than a<br> 2.4 or 2.2 kernel on old hardware. (And Ive run 2.6 kernels on much<br> older, slower boxes than you describe;) (other than in extreme low<br> memory situations...)<br> Definitely, I could see userspace bloat causing a problem, though.<br> (not just desktops, but all the other crap that might be running in<br> a modern distro). I would also not be running a vender kernel on old<br> hardware; its probably not optimised for it, and who knows what all<br> theyve configured it for. Well, at least not a major vendor; maybe<br> one of the distros designed to be small and lean...<br> My current desktop is a pIIx2@400, and it feels better with a 2.6 vs.<br> a 2.4 kernel. Ive also just tested Ubuntu and fc3 on a k6@333, and<br> the only thing slow was gnome;)<br> Fri, 24 Jun 2005 04:26:29 +0000 Fast clocks on slow hardware https://lwn.net/Articles/141303/ https://lwn.net/Articles/141303/ giraffedata In fact, the only time I've ever heard anyone complain about the clock tick overhead is on systems where lots of Linux systems share the same CPU and are designed for most of those Linux systems to be idle most the time (the clock ticks even on an idle system). <p> In this case, I'd bet money the myriad differences in the kernel between 2.4 and 2.6 all taken together have nothing to do with the slowdown. A whole lot of other software has changed here too. <p> Remember that when CPUs were about 1000 times slower than this 200 MHz thing, Unix systems were already performing reasonably at 100 Hz. So processing 10 times as many ticks ought to be OK. Fri, 24 Jun 2005 02:22:57 +0000 reiser https://lwn.net/Articles/141206/ https://lwn.net/Articles/141206/ ccyoung I _really_ like what's going on with the reiser fs. however, I'm clueless how to merge without stepping on toes. maybe a temporary fix would be a special flavor such as Xen. I think the most important thing is to get his ideas out so people can begin using them. in the end I think they will be a quantum improvement.<br> Thu, 23 Jun 2005 19:34:38 +0000 Fast clocks on slow hardware https://lwn.net/Articles/141207/ https://lwn.net/Articles/141207/ larryr <p>I would be surprised if going from 100Hz to 1000Hz made the system more than 10% slower as far as total throughput. The main area where the change should be noticeable is improvement in interactive response.</p> <p>The scheduling in 2.6 is significantly different from 2.4, independent of the time slice value.</p> <p>Larry</p> Thu, 23 Jun 2005 19:29:17 +0000 Fast clocks on slow hardware https://lwn.net/Articles/141177/ https://lwn.net/Articles/141177/ a9db0 You're not the only one with that concern. I run a P90 as a firewall machine, and a P233 as a file server. Heck, my web server is only a PII400. Those minor performance hits on fast machines quickly get magnified on slower boxes.<br> <p> Thu, 23 Jun 2005 16:01:44 +0000 Fast clocks on slow hardware https://lwn.net/Articles/141158/ https://lwn.net/Articles/141158/ utoddl That should be "250Hz", not "250<b>K</b>Hz". <small>A 250KHz clock would leave it a smoking pile of slag.</small> Thu, 23 Jun 2005 14:28:25 +0000 Fast clocks on slow hardware https://lwn.net/Articles/141155/ https://lwn.net/Articles/141155/ utoddl I'd like to get an idea of how much apparent difference the proposed timer changes would make to users on extremely old/slow machines. I used to run 2.2 and early 2.4 kernels on my kids' 200MHz 586, and they seemed pretty peppy (the kernels, not the kids). I just installed Fedora Core 4 on it (Hey, they wanted the games), and... it... is... -- heck, I can't type slow enough to express how slow it is. Slug races are more engaging. (I doubled the RAM last night on a lark; no difference. And I'm not talking about the GUI bloat in KDE and GNOME and the accompanying slugishness, I'm just talking about getting to runlevel 3.) <p>I know the new kernels do a lot of stuff, and on newer hardware with lots of resources to manage they are plenty fast enough. But the old boxes really make the cumulative effects of spent cycles stand out noticeably, even if those cycles are doing neat things. This hardware predates 1KHz clocks by eons. So, how much difference would you expect a 250kHz (or even slower) clock to make on a system like this? <p>When I get around to trying it out, I'll let you know what I find. In the mean time, what benchmarks would you suggest to help quantify these differences? Thu, 23 Jun 2005 14:24:12 +0000