Re: Timers and timing, was: MySQL Performance 6.0rc1

From: Poul-Henning Kamp <phk_at_phk.freebsd.dk>
Date: Sat, 29 Oct 2005 00:23:38 +0200
In message <005d01c5dc0c$7ad2c9c0$b3db87d4_at_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_at_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.
Received on Fri Oct 28 2005 - 20:23:41 UTC

This archive was generated by hypermail 2.4.0 : Wed May 19 2021 - 11:38:46 UTC