Date: Sat, 29 Oct 2005 00:23:38 +0200 From: "Poul-Henning Kamp" <phk@phk.freebsd.dk> To: "Steven Hartland" <killing@multiplay.co.uk> Cc: Michael VInce <mv@roq.com>, John-Mark Gurney <gurney_j@resnet.uoregon.edu>, current@freebsd.org Subject: Re: Timers and timing, was: MySQL Performance 6.0rc1 Message-ID: <35758.1130538218@critter.freebsd.dk> In-Reply-To: Your message of "Fri, 28 Oct 2005 22:36:19 BST." <005d01c5dc0c$7ad2c9c0$b3db87d4@multiplay.co.uk>
next in thread | previous in thread | raw e-mail | index | archive | help
In message <005d01c5dc0c$7ad2c9c0$b3db87d4@multiplay.co.uk>, "Steven Hartland"
writes:
>For interest I ran truss on a typical game server we run under
>FreeBSD to get a feel for how much this issue would affect
>their performance.
>Below is a small snippet from truss with -D which indicates
>that they would also benefit from work in this area.
Yes, by about a factor of 0.000005 seconds every .5 seconds
or a factor of 1/100000 :-)
>0.000010894 gettimeofday({1130534881 790912},0xbfbfe9f0) = 0 (0x0)
Grab timestamp
>0.009520674 nanosleep({0 5000000}) = 0 (0x0)
Sleep half a second
(rinse, repeat)
It would have been much more interesting if the server was doing
something...
--
Poul-Henning Kamp | UNIX since Zilog Zeus 3.20
phk@FreeBSD.ORG | TCP/IP since RFC 956
FreeBSD committer | BSD since 4.3-tahoe
Never attribute to malice what can adequately be explained by incompetence.
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?35758.1130538218>