Date: Tue, 8 Jan 2013 12:16:03 +0100 From: Luigi Rizzo <rizzo@iet.unipi.it> To: Alexander Motin <mav@FreeBSD.org> Cc: Davide Italiano <davide@FreeBSD.org>, freebsd-arch@FreeBSD.org, FreeBSD Current <freebsd-current@FreeBSD.org>, Marius Strobl <marius@alchemy.franken.de> Subject: Re: [RFC/RFT] calloutng Message-ID: <20130108111603.GA30469@onelab2.iet.unipi.it> In-Reply-To: <50EBFB1F.2080708@FreeBSD.org> References: <50CCAB99.4040308@FreeBSD.org> <50CE5B54.3050905@FreeBSD.org> <50D03173.9080904@FreeBSD.org> <20121225232126.GA47692@alchemy.franken.de> <50DB4EFE.2020600@FreeBSD.org> <20130106152313.GD26039@alchemy.franken.de> <20130106162049.GA3640@onelab2.iet.unipi.it> <50EBFB1F.2080708@FreeBSD.org>
next in thread | previous in thread | raw e-mail | index | archive | help
On Tue, Jan 08, 2013 at 12:55:27PM +0200, Alexander Motin wrote: > On 06.01.2013 18:20, Luigi Rizzo wrote: ... > > I think that for the time being it would be useful to run at least > > one set of tests with kern.timecounter.alloweddeviation=0 so we can > > tell how close we get to the required timeouts > > May be just to be sure, because it should not significantly affect > results of the 1us tests, as 5% of 1us is much less then numbers we see > there. to clarify - i don't mind if we are 50-100us (absolute error) off the requested timeout for short intervals, but i want to be sure that this error can be achieved also for large requests. cheers luigi
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20130108111603.GA30469>