Date: Fri, 23 May 2003 11:07:28 +0200 (CEST) From: Heiko Schaefer <hschaefer@fto.de> To: Poul-Henning Kamp <phk@phk.freebsd.dk> Cc: current@freebsd.org Subject: Re: gbde performance question Message-ID: <20030523110255.A78432@daneel.foundation.hs> In-Reply-To: <798.1053625220@critter.freebsd.dk> References: <798.1053625220@critter.freebsd.dk>
next in thread | previous in thread | raw e-mail | index | archive | help
On Thu, 22 May 2003, Poul-Henning Kamp wrote: > I just ran a real simple test on my laptop: > > critter# grep CPU: /var/run/dmesg.boot > CPU: Intel Pentium III (651.48-MHz 686-class CPU) > critter# dd if=/dev/ad0s1f bs=1m of=/dev/null count=10 > 10+0 records in > 10+0 records out > 10485760 bytes transferred in 0.501567 secs (20906000 bytes/sec) > critter# dd if=/dev/ad0s1f.bde bs=1m of=/dev/null count=10 > 10+0 records in > 10+0 records out > 10485760 bytes transferred in 1.191878 secs (8797678 bytes/sec) ...sounds consistent with my numbers, as far as i can tell. if you ever do anything like profiling or so, i'd be very curious to hear if there is any space left for optimization (i'm, thinking about factor two or higher, not about peanuts :)). somehow i am still suspecting that this can't be the most that our cpus could do. loopaes seems to beat gbde's throughput by a factor from what i hear. assuming that gbde is not computationally more complex by that factor, it would be nice to be on par :) regards, Heiko -- Free Software. Why put up with inferior code and antisocial corporations? http://www.gnu.org/philosophy/why-free.html
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20030523110255.A78432>