Date: Sat, 22 Dec 2007 13:40:00 +0100 From: "Claus Guttesen" <kometen@gmail.com> To: "User Ota" <ota@animenfo.com> Cc: stable@freebsd.org Subject: Re: SMP on FreeBSD 6.x and 7.0: Worth doing? freenx@deweyonline.com Message-ID: <b41c75520712220440j333286bcs2c497a22880a1d9b@mail.gmail.com> In-Reply-To: <20071222090553.GB16381@noah.ota.homelinux.net> References: <200712220531.WAA09277@lariat.net> <b41c75520712220008v21bc7b47r8376176b54ab8c7e@mail.gmail.com> <20071222090553.GB16381@noah.ota.homelinux.net>
next in thread | previous in thread | raw e-mail | index | archive | help
> > > It appears, though I'd need to instrument the code more to be sure, > > > that the slowdown is coming from file I/O. Could it be that there > > > less concurrency or more overhead in FreeBSD file operations than > > > there is in Linux? Even with SoftUpdates turned on, the cache > > > volume mounted with -noatime, and aufs (which uses kqueues -- a > > > FreeBSD invention -- to optimize multithreaded disk access), the > > > benchmark shows FreeBSD losing out. Why? > > > > I have noticed an entry in GENERIC called > > > > device cpufreq > > > > Could this have any influence on the performance (on FreeBSD)? > > > > I saw this device late in the 7.0 release-process and I since I'm > > accustomed to comment out any devices and options I don't need I have > > commented this out as well. So I haven't performed any tests with and > > without this device. > > > > Cpufreq is for CPU frequency scaling. In the linux world, the cpufreq > daemon allows you to control your cpu speed and voltage using power > profiles and such, which makes it a definite power saving tool for > laptops. The cpufreq driver is already included with the Linux kernel, > so I'm going to assume that they've just implemented the cpufreq driver > in the kernel recently :) > > If enabled, it probably would have an impact on performance, however I > have lost the ability to test such a function since my laptop decides > not to POST anymore. Yes, I did figure out what the purpose of this device was. :-) My point was that this could lead to lower benchmarks on servers if GENERIC is used. -- regards Claus When lenity and cruelty play for a kingdom, the gentlest gamester is the soonest winner. Shakespeare
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?b41c75520712220440j333286bcs2c497a22880a1d9b>