From mboxrd@z Thu Jan 1 00:00:00 1970 From: Thomas Jarosch Subject: Re: TCP connection stalls under 2.6.24.7 Date: Thu, 17 Jul 2008 17:15:14 +0200 Message-ID: <200807171715.16265.thomas.jarosch@intra2net.com> References: <47EA0DAB.7080205@securenet.de> <200807161103.07821.thomas.jarosch@intra2net.com> Mime-Version: 1.0 Content-Type: text/plain; charset=iso-8859-15 Content-Transfer-Encoding: QUOTED-PRINTABLE Cc: Jozsef Kadlecsik , Netdev , Patrick McHardy , Sven Riedel , Netfilter Developer Mailing List , "=?iso-8859-15?q?D=E2niel?= Fraga" , David Miller To: "Ilpo =?iso-8859-15?q?J=E4rvinen?=" Return-path: In-Reply-To: Content-Disposition: inline Sender: netfilter-devel-owner@vger.kernel.org List-Id: netdev.vger.kernel.org On Thursday, 17. July 2008 15:55:25 Ilpo J=E4rvinen wrote: > It would quite interesting to know more details about the mail server= and > why the duplicate ACKs are not generated or don't ever reach the send= er > but I guess the details are out of reach? It will be quite difficult to get more details as it's the SMTP relay s= ever of Germany's biggest ISP. There's a comment about them in Patrick's blog from 2008-06-23 if you are curious ;-) We see the same issue with a MX server from "United Internet". Normally they are pretty accurate about standards (they run GMX), so I guess this must be a problem of a router in between. This is also supported by the fact that 935 of our boxes already update= d to kernel 2.6.24.7, yet the problem occured only at three sites and I g= uess there are more people out there using that SMTP relay server. Could you somehow "probe" the servers to see if they normally send duplicated ACKs by faking/forcing a retransmission? Though I guess this would invole writing some TCP "test" code. > One option would be to disable reentry to FRTO when some progress was > made... Please try with the patch below... Thanks for the patch. It seemed to help a bit. Here are two more traces= : http://www.intra2net.com/de/download/tcpdump/tcp_frto_with_patch.tar.bz= 2 The first connection somehow made it after 400 seconds, the second one stalled and timed out :-( Hope they dumps are useful to you. Chers, Thomas -- To unsubscribe from this list: send the line "unsubscribe netfilter-dev= el" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html