From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1758164Ab2GNIbq (ORCPT ); Sat, 14 Jul 2012 04:31:46 -0400 Received: from 1wt.eu ([62.212.114.60]:4706 "EHLO 1wt.eu" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1757386Ab2GNIbn (ORCPT ); Sat, 14 Jul 2012 04:31:43 -0400 Date: Sat, 14 Jul 2012 10:31:36 +0200 From: Willy Tarreau To: Eric Dumazet Cc: Hillf Danton , Johannes Truschnigg , linux-kernel@vger.kernel.org, Linux-Netdev Subject: Re: PROBLEM: Silent data corruption when using sendfile() Message-ID: <20120714083136.GO16256@1wt.eu> References: <20120713171835.GA26052@vault.local> <1342254042.3265.9017.camel@edumazet-glaptop> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <1342254042.3265.9017.camel@edumazet-glaptop> User-Agent: Mutt/1.4.2.3i Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Sat, Jul 14, 2012 at 10:20:41AM +0200, Eric Dumazet wrote: > > On Tue, Jul 3, 2012 at 8:02 AM, Willy Tarreau wrote: > > > > > > In fact it has been true zero copy in 2.6.25 until we faced a large > > > amount of data corruption and the zero copy was disabled in 2.6.25.X. > > > Since then it remained that way until you brought your patches to > > > re-instantiate it. > > Might be, or not (could be a NIC bug) I may be wrong but what I recall from this bug was an issue when forwarding TCP between two NICs, related to linear vs non-linear data (I have memories of something around data not yet ACKed being replaced before being retransmitted but I may be wrong). Anyway, the way it was fixed consisted in simply disabling the zero-copy code path. So this should be something different from what Johannes reports. Maybe a regression since then though. > Please Johannes could you try latest kernel tree ? It would be useful, especially given the amount of changes you performed in this area in latest version, it could be very possible that this new bug got fixed as a side effect ! Regards, Willy