Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1765046AbXEYU27 (ORCPT ); Fri, 25 May 2007 16:28:59 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1755974AbXEYU2u (ORCPT ); Fri, 25 May 2007 16:28:50 -0400 Received: from lollipop.listbox.com ([208.210.124.78]:53786 "EHLO lollipop.listbox.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755947AbXEYU2u (ORCPT ); Fri, 25 May 2007 16:28:50 -0400 In-Reply-To: <200705250751.45738.ak@suse.de> References: <200705122146.l4CLkH6q012322@fire-2.osdl.org> <20070524213157.1d39458f.akpm@linux-foundation.org> <200705250751.45738.ak@suse.de> Mime-Version: 1.0 (Apple Message framework v752.3) Content-Type: text/plain; charset=US-ASCII; delsp=yes; format=flowed Message-Id: <036B6511-FC30-4F81-98E7-C86F6993D618@lundell-bros.com> Cc: Andrew Morton , "Eric W. Biederman" , Greg Kroah-Hartman , Jay Cliburn , Grzegorz Krzystek , ninex@o2.pl, linux-kernel@vger.kernel.org, linux-pci@atrey.karlin.mff.cuni.cz, Michael Ellerman , David Miller , Tony Luck , Linus Torvalds Content-Transfer-Encoding: 7bit From: Jonathan Lundell Subject: Re: [PATCH 1/2] msi: Invert the sense of the MSI enables. Date: Fri, 25 May 2007 13:16:57 -0700 To: Andi Kleen X-Mailer: Apple Mail (2.752.3) Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 893 Lines: 22 On May 24, 2007, at 10:51 PM, Andi Kleen wrote: >> Do we have a feel for how much performace we're losing on those >> systems which _could_ do MSI, but which will end up defaulting >> to not using it? > > At least on 10GB ethernet it is a significant difference; you usually > cannot go anywhere near line speed without MSI > > I suspect it is visible on high performance / multiple GB NICs too. Why would that be? As the packet rate goes up and NAPI polling kicks in, wouldn't MSI make less and less difference? I like the fact that MSI gives us finer control over CPU affinity than many INTx implementations, but that's a different issue. - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/