From mboxrd@z Thu Jan 1 00:00:00 1970 From: Rusty Russell Subject: Re: [PATCH v2] Driver for Inter-VM shared memory device for KVM supporting interrupts. Date: Wed, 20 May 2009 12:28:38 +0930 Message-ID: <200905201228.38718.rusty@rustcorp.com.au> References: <1241713567-17256-1-git-send-email-cam@cs.ualberta.ca> <4A127776.9030400@redhat.com> <4A12E37C.700@cs.ualberta.ca> Mime-Version: 1.0 Content-Type: Text/Plain; charset=utf-8 Content-Transfer-Encoding: QUOTED-PRINTABLE Cc: Avi Kivity , Christian =?utf-8?q?Borntr=C3=A4ger?= , kvm@vger.kernel.org, Christian Ehrhardt To: Cam Macdonell Return-path: Received: from ozlabs.org ([203.10.76.45]:53345 "EHLO ozlabs.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751960AbZETC6l convert rfc822-to-8bit (ORCPT ); Tue, 19 May 2009 22:58:41 -0400 In-Reply-To: <4A12E37C.700@cs.ualberta.ca> Content-Disposition: inline Sender: kvm-owner@vger.kernel.org List-ID: On Wed, 20 May 2009 02:21:08 am Cam Macdonell wrote: > Avi Kivity wrote: > > Christian Borntr=C3=A4ger wrote: > >>> To summarize, Anthony thinks it should use virtio, while I believ= e > >>> virtio is useful for exporting guest memory, not for importing ho= st > >>> memory. Yes, precisely. But what's it *for*, this shared memory? Implementing shared memory is= =20 trivial. Using it is harder. For example, inter-guest networking: you= 'd have=20 to copy packets in and out, making it slow as well as losing abstractio= n. The only interesting idea I can think of is exposing it to userspace, a= nd=20 having that run some protocol across it for fast app <-> app comms. Bu= t if=20 that's your plan, you still have a lot of code the write! So I guess I'm missing the big picture here? Thanks, Rusty.