From owner-freebsd-stable@FreeBSD.ORG Thu Feb 18 19:14:05 2010 Return-Path: Delivered-To: freebsd-stable@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id A0888106566C for ; Thu, 18 Feb 2010 19:14:05 +0000 (UTC) (envelope-from hurds@sasktel.net) Received: from neutron.sasknet.sk.ca (neutron.sasknet.sk.ca [142.165.20.180]) by mx1.freebsd.org (Postfix) with ESMTP id 6368F8FC1F for ; Thu, 18 Feb 2010 19:14:05 +0000 (UTC) Received: from pps.filterd (neutron [127.0.0.1]) by neutron.sasknet.sk.ca (8.14.3/8.14.3) with SMTP id o1IIwGDY025365 for ; Thu, 18 Feb 2010 13:00:25 -0600 Received: from bgmpomr1.sasknet.sk.ca (bgmpOMR1.sasknet.sk.ca [142.165.72.22]) by neutron.sasknet.sk.ca with ESMTP id m19ud5519-1 for ; Thu, 18 Feb 2010 13:00:25 -0600 Received: from sasktel.net ([192.168.234.97]) by bgmpomr1.sasknet.sk.ca (SaskTel eMessaging Service) with ESMTP id <0KY100HBDWSPK870@bgmpomr1.sasknet.sk.ca> for freebsd-stable@freebsd.org; Thu, 18 Feb 2010 13:00:25 -0600 (CST) Received: from [192.168.234.25] (Forwarded-For: [216.31.211.11]) by cgmail1.sasknet.sk.ca (mshttpd); Thu, 18 Feb 2010 11:00:25 -0800 Date: Thu, 18 Feb 2010 11:00:25 -0800 From: Stephen Hurd To: Harald Schmalzbauer Message-id: <5c00c4d917943.4b7d1dc9@sasktel.net> MIME-version: 1.0 X-Mailer: Sun Java(tm) System Messenger Express 6.1 HotFix 0.20 (built Feb 27 2006) Content-type: multipart/mixed; boundary="Boundary_(ID_kDTlApuHY4uYbHwcgladwg)" Content-language: en X-Accept-Language: en Priority: normal X-Proofpoint-Virus-Version: vendor=fsecure engine=1.12.8161:2.4.5, 1.2.40, 4.0.166 definitions=2010-02-18_14:2010-02-06, 2010-02-18, 2010-02-18 signatures=0 X-Proofpoint-Spam-Details: rule=outbound_notspam policy=default score=0 spamscore=0 ipscore=0 phishscore=0 bulkscore=0 adultscore=0 classifier=spam adjust=0 reason=mlx engine=5.0.0-0908210000 definitions=main-1002180143 Cc: Patrick Mahan , freebsd-stable@freebsd.org, Stephen Hurd Subject: Re: RELENG_8 ignoring TCP window size? [Was: Re: Help for TCP understanding wanted, ACK-MSS-Window [Was: Re: best practice to watch TCP parms of established sockets]] X-BeenThere: freebsd-stable@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Production branch of FreeBSD source code List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 18 Feb 2010 19:14:05 -0000 This is a multi-part message in MIME format. --Boundary_(ID_kDTlApuHY4uYbHwcgladwg) Content-type: text/plain; charset=us-ascii Content-transfer-encoding: 7BIT Content-disposition: inline All those duplicate ACKs look like a problme to me... I would be inclined to capture from the other end or from a monitor port on the switch to make sure those are actually hitting the wire. The only explination I can think of is that the system sending the duplicate ACKs is assuming that it's lost a segment for some reason and is trying to trigger fast recovery early. --Boundary_(ID_kDTlApuHY4uYbHwcgladwg) Content-type: multipart/mixed; boundary="Boundary_(ID_K7VhZx6vpNouByAbQ57Thg)" --Boundary_(ID_K7VhZx6vpNouByAbQ57Thg) Content-type: text/plain; charset=ISO-8859-1; format=flowed Content-transfer-encoding: 7BIT Stephen Hurd schrieb am 18.02.2010 17:18 (localtime): ... > one retransmit per five packets). Is this what you're seeing? If you > have a capture you could share covering a few seconds, I could take a > look and provide a better opinion. Thanks for your help, here's a small snippet of the iperf session. There are hundreds od duplicate ACKs. I'm not sure how to understand that. Like mentioned, I have to refresh some TCP basics before I can do usefull tests. But perhaps you can confirm that this behaviour is intendend, or where the problem could be... Thanks, -Harry --Boundary_(ID_K7VhZx6vpNouByAbQ57Thg)-- --Boundary_(ID_kDTlApuHY4uYbHwcgladwg)--