From mboxrd@z Thu Jan 1 00:00:00 1970 From: Andi Kleen Subject: Re: [GIT PULL] AlacrityVM guest drivers for 2.6.33 Date: Wed, 23 Dec 2009 20:50:52 +0100 Message-ID: <873a31cvvn.fsf@basil.nowhere.org> References: <4B1D4F29.8020309@gmail.com> <20091218215107.GA14946@elte.hu> <4B2F9582.5000002@gmail.com> <20091222075742.GB26467@elte.hu> <4B3103B4.4070708@gmail.com> <4B3254B4.2080602@gmail.com> <20091223192808.GA30700@ovro.caltech.edu> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: Gregory Haskins , Kyle Moffett , Ingo Molnar , Avi Kivity , kvm@vger.kernel.org, Andrew Morton , torvalds@linux-foundation.org, "linux-kernel@vger.kernel.org" , netdev@vger.kernel.org, "alacrityvm-devel@lists.sourceforge.net" To: "Ira W. Snyder" Return-path: In-Reply-To: <20091223192808.GA30700@ovro.caltech.edu> (Ira W. Snyder's message of "Wed, 23 Dec 2009 11:28:08 -0800") Sender: kvm-owner@vger.kernel.org List-Id: netdev.vger.kernel.org "Ira W. Snyder" writes: > (You'll quickly find that you must use DMA to transfer data across PCI. > AFAIK, CPU's cannot do burst accesses to the PCI bus. I get a 10+ times AFAIK that's what write-combining on x86 does. DMA has other advantages of course. -Andi -- ak@linux.intel.com -- Speaking for myself only.