From mboxrd@z Thu Jan 1 00:00:00 1970 From: Avi Kivity Subject: Re: [PATCH] MMIO: Make coalesced mmio use a device per zone Date: Wed, 20 Jul 2011 11:58:25 +0300 Message-ID: <4E2698B1.5090001@redhat.com> References: <1311063011-4430-1-git-send-email-levinsasha928@gmail.com> <4E2544F3.9030203@redhat.com> <1311069182.9174.1.camel@lappy> <4E255584.1030003@redhat.com> <1311070673.9174.4.camel@lappy> <4E255D44.8000107@redhat.com> <4E25BB6B.90907@siemens.com> <4E25BC46.1040200@redhat.com> <4E25BD8D.1030509@siemens.com> <4E2690B5.9050206@redhat.com> <4E26954B.6000606@siemens.com> <4E26975C.1090402@redhat.com> <4E269808.7050606@siemens.com> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: Sasha Levin , "kvm@vger.kernel.org" , Marcelo Tosatti To: Jan Kiszka Return-path: Received: from mx1.redhat.com ([209.132.183.28]:48295 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751120Ab1GTI6e (ORCPT ); Wed, 20 Jul 2011 04:58:34 -0400 In-Reply-To: <4E269808.7050606@siemens.com> Sender: kvm-owner@vger.kernel.org List-ID: On 07/20/2011 11:55 AM, Jan Kiszka wrote: > On 2011-07-20 10:52, Avi Kivity wrote: > > On 07/20/2011 11:43 AM, Jan Kiszka wrote: > >>> > >>> How do you implement this 3a, if your consumers are outside the main > >>> process? I guess you could have an additional synchonize API (for > >>> in-kernel consumers) or RPC (for external process consumers), but then > >>> this is no longer a simple API. > >> > >> I'm not planning to leave the hypervisor process for now, not to speak > >> of in-kernel models. Already for many other reasons, a synchronization > >> API between a hypothetical decoupled device model and the core will be > >> quite complex. The first step is to get it scalable using a single process. > > > > If we design a new kvm API, we must look a little more into the future > > than satisfying immediate needs. > > That's true, but synchronization requirements are widely unrelated to > this API and will have to by satisfied generically anyway. I'm trying to see if they can be satisfied at all, for the more esoteric consumers, and if so, if it's in a palatable way and performant way. -- error compiling committee.c: too many arguments to function