From mboxrd@z Thu Jan 1 00:00:00 1970 From: Miroslav Lichvar Subject: Re: TSC to Mono-raw Drift Date: Fri, 2 Nov 2018 12:20:06 +0100 Message-ID: <20181102112006.GM19434@localhost> References: Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: John Stultz , Christopher Hall , "H. Peter Anvin" , linux-rt-users , jesus.sanchez-palencia@intel.com, Gavin Hindman , liam.r.girdwood@intel.com, Peter Zijlstra , LKML To: Thomas Gleixner Return-path: Content-Disposition: inline In-Reply-To: Sender: linux-kernel-owner@vger.kernel.org List-Id: linux-rt-users.vger.kernel.org On Thu, Nov 01, 2018 at 07:03:37PM +0100, Thomas Gleixner wrote: > On Thu, 1 Nov 2018, John Stultz wrote: > > On Thu, Nov 1, 2018 at 10:44 AM, Thomas Gleixner wrote: > > > On Tue, 23 Oct 2018, John Stultz wrote: > > >> However, to be correct, the ntp adjustments made would have to be made > > >> to both the base interval + error, which mucks the math up a fair bit. > > > > > > Hmm, confused as usual. Why would you need to do anything like that? > > > > Because the NTP adjustment is done off of what is now the raw clock. > > If the raw clock is "corrected" the ppb adjustment has to be done off > > of that corrected rate. > > Sure, but why would that require any change? Right now the raw clock is > slightly off and you correct clock monotonic against NTP. So with that > extra correction you just see a slightly different raw clock slew and work > from there. It makes sense to me. I think there are basically two different ways how it could be done. One is to correct the frequency of the raw clock, on which sits the mono/real clock. The other is to create a new raw clock which is separate from the mono/real clock, and add an offset to the NTP frequency to match the frequencies of the two clocks when not synchronized by NTP/PTP. The latter would provide a more stable mono/real clock. clocksource -> MONOTONIC_RAW -> MONOTONIC/REALTIME or clocksource -> ? -> MONOTONIC_RAW -> MONOTONIC/REALTIME -- Miroslav Lichvar