From mboxrd@z Thu Jan 1 00:00:00 1970 From: Paul Brook Subject: Re: [Qemu-devel] [PATCH] Inter-VM shared memory PCI device Date: Wed, 10 Mar 2010 17:41:47 +0000 Message-ID: <201003101741.47300.paul@codesourcery.com> References: <1267833161-25267-1-git-send-email-cam@cs.ualberta.ca> <4B97D349.1030105@codemonkey.ws> <4B97D752.3080700@redhat.com> Mime-Version: 1.0 Content-Type: Text/Plain; charset="iso-8859-15" Content-Transfer-Encoding: 7bit Cc: Anthony Liguori , qemu-devel@nongnu.org, Cam Macdonell , kvm@vger.kernel.org To: Avi Kivity Return-path: Received: from mail.codesourcery.com ([38.113.113.100]:34024 "EHLO mail.codesourcery.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932527Ab0CJRl5 (ORCPT ); Wed, 10 Mar 2010 12:41:57 -0500 In-Reply-To: <4B97D752.3080700@redhat.com> Sender: kvm-owner@vger.kernel.org List-ID: > > You're much better off using a bulk-data transfer API that relaxes > > coherency requirements. IOW, shared memory doesn't make sense for TCG > > Rather, tcg doesn't make sense for shared memory smp. But we knew that > already. In think TCG SMP is a hard, but soluble problem, especially when you're running guests used to coping with NUMA. TCG interacting with third parties via shared memory is probably never going to make sense. Paul From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from mailman by lists.gnu.org with tmda-scanned (Exim 4.43) id 1NpPuy-0001n7-Aa for qemu-devel@nongnu.org; Wed, 10 Mar 2010 12:42:00 -0500 Received: from [199.232.76.173] (port=44450 helo=monty-python.gnu.org) by lists.gnu.org with esmtp (Exim 4.43) id 1NpPux-0001mV-ON for qemu-devel@nongnu.org; Wed, 10 Mar 2010 12:41:59 -0500 Received: from Debian-exim by monty-python.gnu.org with spam-scanned (Exim 4.60) (envelope-from ) id 1NpPuw-0007Zb-0h for qemu-devel@nongnu.org; Wed, 10 Mar 2010 12:41:58 -0500 Received: from mx20.gnu.org ([199.232.41.8]:24201) by monty-python.gnu.org with esmtps (TLS-1.0:RSA_AES_256_CBC_SHA1:32) (Exim 4.60) (envelope-from ) id 1NpPuv-0007ZV-Qb for qemu-devel@nongnu.org; Wed, 10 Mar 2010 12:41:57 -0500 Received: from mail.codesourcery.com ([38.113.113.100]) by mx20.gnu.org with esmtp (Exim 4.60) (envelope-from ) id 1NpPuu-0000mA-Bc for qemu-devel@nongnu.org; Wed, 10 Mar 2010 12:41:56 -0500 From: Paul Brook Subject: Re: [Qemu-devel] [PATCH] Inter-VM shared memory PCI device Date: Wed, 10 Mar 2010 17:41:47 +0000 References: <1267833161-25267-1-git-send-email-cam@cs.ualberta.ca> <4B97D349.1030105@codemonkey.ws> <4B97D752.3080700@redhat.com> In-Reply-To: <4B97D752.3080700@redhat.com> MIME-Version: 1.0 Content-Type: Text/Plain; charset="iso-8859-15" Content-Transfer-Encoding: 7bit Message-Id: <201003101741.47300.paul@codesourcery.com> List-Id: qemu-devel.nongnu.org List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Avi Kivity Cc: Cam Macdonell , qemu-devel@nongnu.org, kvm@vger.kernel.org > > You're much better off using a bulk-data transfer API that relaxes > > coherency requirements. IOW, shared memory doesn't make sense for TCG > > Rather, tcg doesn't make sense for shared memory smp. But we knew that > already. In think TCG SMP is a hard, but soluble problem, especially when you're running guests used to coping with NUMA. TCG interacting with third parties via shared memory is probably never going to make sense. Paul