From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:37840) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1VHaX0-0000JW-Pm for qemu-devel@nongnu.org; Thu, 05 Sep 2013 10:27:40 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1VHaWu-0005Ys-RE for qemu-devel@nongnu.org; Thu, 05 Sep 2013 10:27:34 -0400 Message-ID: <1378391219.4321.191.camel@pasglop> From: Benjamin Herrenschmidt Date: Fri, 06 Sep 2013 00:26:59 +1000 In-Reply-To: <522891C2.8020107@suse.de> References: <1378193502-4968-1-git-send-email-aik@ozlabs.ru> <20130905043059.GC10158@voom.redhat.com> <52280E96.1030402@ozlabs.ru> <350E3728-BF3A-4B43-8E43-2622033970D0@suse.de> <52285369.1040907@ozlabs.ru> <1378381449.4321.158.camel@pasglop> <1378388164.4321.176.camel@pasglop> <17161D2C-8CAE-40D9-B4E2-EBCE69D69FAA@suse.de> <522891C2.8020107@suse.de> Content-Type: text/plain; charset="UTF-8" Mime-Version: 1.0 Content-Transfer-Encoding: quoted-printable Subject: Re: [Qemu-devel] [RFC PATCH] spapr: support time base offset migration List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Andreas =?ISO-8859-1?Q?F=E4rber?= Cc: Alexey Kardashevskiy , qemu-devel@nongnu.org, Alexander Graf , qemu-ppc@nongnu.org, Paolo Bonzini , Paul Mackerras , David Gibson On Thu, 2013-09-05 at 16:14 +0200, Andreas F=C3=A4rber wrote: > Are you thinking of POWER8 having a different frequency than POWER8 in > compat mode? Because migration from one -cpu to another is not supporte= d > elsewhere. >=20 > Even if we want to migrate from one POWER7 revision to another, we > should let the destination use the revision of the source (guest ABI!), > via property if need be. Anything else will lead to confusion as to wha= t > is supported and what is not. That -cpu host is the default for > convenience shouldn't relieve admins/libvirt to think about sensible > setups like they have to on x86. Besides POWER8 uses 512Mhz too :-) It's been architected so it's unlikely to change from now on. Cheers, Ben. > Andreas >=20 > >=20 > > But yes, without frequency adjustment I see where you're coming from.= We still only need the timebase the guest sees, not the offset. But we a= lso need the host wall clock to allow for adjustments :). > >=20 > >=20 > > Alex > >=20 >=20 >=20