From mboxrd@z Thu Jan 1 00:00:00 1970 From: Ben Hutchings Subject: Re: RFC: MTU for serving NFS on Infiniband Date: Tue, 24 Aug 2010 18:57:27 +0100 Message-ID: <1282672647.2302.15.camel@achroite.uk.solarflarecom.com> References: <20100823080543.319143e3@nehalam> Mime-Version: 1.0 Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: 7bit Cc: Stephen Hemminger , linux-kernel@vger.kernel.org, netdev@vger.kernel.org, "David S. Miller" , Alexey Kuznetsov , "Pekka Savola (ipv6)" , James Morris , Hideaki YOSHIFUJI , Patrick McHardy To: Marc Aurele La France Return-path: Received: from mail.solarflare.com ([216.237.3.220]:56008 "EHLO exchange.solarflare.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755287Ab0HXR5c (ORCPT ); Tue, 24 Aug 2010 13:57:32 -0400 In-Reply-To: Sender: netdev-owner@vger.kernel.org List-ID: On Tue, 2010-08-24 at 09:14 -0600, Marc Aurele La France wrote: > On Mon, 23 Aug 2010, Stephen Hemminger wrote: > > On Mon, 23 Aug 2010 08:44:37 -0600 (MDT) > > Marc Aurele La France wrote: > >> In regrouping for my next tack at this, I noticed that all stack traces go > >> through ip_append_data(). This would be ipv6_append_data() in the IPv6 case. > >> A _very_ rough draft that would have ip_append_data() temporarily drop down > >> to a smaller fake MTU follows ... > > > Why doesn't NFS generate page size fragments? Does Infiniband or your > > device not support this? Any thing that requires higher order allocation > > is going to unstable under load. Let's fix the cause not the apply bandaid > > solution to the symptom. > > From what I can tell, IP fragmentation is done centrally. [...] Stephen and I are not talking about IP fragmentation, but about the ability to append 'fragments' to an skb rather than putting the entire packet payload in a linear buffer. See . Ben. -- Ben Hutchings, Senior Software Engineer, Solarflare Communications Not speaking for my employer; that's the marketing department's job. They asked us to note that Solarflare product names are trademarked.