Subject: Re: lazy mlock?
To: M. Warner Losh <firstname.lastname@example.org>
From: Bill Studenmund <email@example.com>
Date: 04/18/2002 13:20:21
On Wed, 17 Apr 2002, M. Warner Losh wrote:
> In message: <20020416161327.S9863@dr-evil.shagadelic.org>
> Jason R Thorpe <firstname.lastname@example.org> writes:
> : On Tue, Apr 16, 2002 at 11:48:32PM +0100, David Laight wrote:
> : > If it isn't a silly question, why should ntpd 'lock down' any code at all?
> : Because it is very sensitve to being able to react to a message. Making
> : it wait to page in something will skew its results.
> It isn't so much that it needs to react quickly to a message, but it
> needs to react in a time period that has a low standard deviation from
> packet to packet. Having to swap in first increases the standard
> deviation of response time quite a bit, which lowers the performance
> of NTP.
Would it be reasonable for ntp to make a few trials, to get the parts of
it that it needs paged in, and then do "real" timings? That way the parts
that are actually used are locked down but not everything else.