Skip site navigation (1)Skip section navigation (2)
Date:      Thu, 14 Sep 2006 23:23:35 +0200
From:      des@des.no (Dag-Erling =?iso-8859-1?Q?Sm=F8rgrav?=)
To:        Gary Corcoran <gcorcoran@rcn.com>
Cc:        freebsd-hackers@freebsd.org
Subject:   Re: numbers don't lie ...
Message-ID:  <86ejuew3ag.fsf@dwp.des.no>
In-Reply-To: <86lkomw3co.fsf@dwp.des.no> (Dag-Erling =?iso-8859-1?Q?Sm=F8r?= =?iso-8859-1?Q?grav's?= message of "Thu, 14 Sep 2006 23:22:15 %2B0200")
References:  <E1GNOLq-000DC2-1Q@cs1.cs.huji.ac.il> <863bauk3gp.fsf@dwp.des.no> <45099123.4000500@rcn.com> <86lkomw3co.fsf@dwp.des.no>

next in thread | previous in thread | raw e-mail | index | archive | help
des@des.no (Dag-Erling Sm=F8rgrav) writes:
> Gary Corcoran <gcorcoran@rcn.com> writes:
> > The confusing thing is that I thought 'real' time should be >=3D 'user'=
 + 'sys'.
> > But here 'user' is much greater than 'real' for both machines!  The sen=
se I
> > got from the other messages in this thread is that 'user' time is somew=
hat
> > meaningless (i.e. unreliable as a measure) in a multi-CPU and/or hypert=
hreading
> > environment.  Can you clarify?
> real >=3D (user + sys) * ncpu

umm, other way around of course.

real * ncpu >=3D (user + sys)

DES
--=20
Dag-Erling Sm=F8rgrav - des@des.no



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?86ejuew3ag.fsf>