From mboxrd@z Thu Jan 1 00:00:00 1970 From: "Lachlan Andrew" Subject: Re: [RFC] TCP illinois max rtt aging Date: Mon, 3 Dec 2007 17:23:35 -0800 Message-ID: References: <001001c83063$9adbc9d0$d5897e82@csp.uiuc.edu> <20071128154725.29af2852@freepuppy.rosehill> <474E0B33.2060108@linux-foundation.org> <001b01c83248$604f4120$20edc360$@edu> <20071203145207.40e4ac57@freepuppy.rosehill> <002f01c83608$8a2fb600$9e8f2200$@edu> <20071203163217.27e4df3f@freepuppy.rosehill> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Cc: shaoliu@princeton.edu, "David S. Miller" , "Herbert Xu" , "Douglas Leith" , "Robert Shorten" , netdev@vger.kernel.org To: "Stephen Hemminger" Return-path: Received: from py-out-1112.google.com ([64.233.166.179]:16426 "EHLO py-out-1112.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751060AbXLDBXh (ORCPT ); Mon, 3 Dec 2007 20:23:37 -0500 Received: by py-out-1112.google.com with SMTP id u77so6853534pyb for ; Mon, 03 Dec 2007 17:23:36 -0800 (PST) In-Reply-To: <20071203163217.27e4df3f@freepuppy.rosehill> Content-Disposition: inline Sender: netdev-owner@vger.kernel.org List-ID: Greetings, On 03/12/2007, Stephen Hemminger wrote: > On Mon, 3 Dec 2007 15:59:23 -0800 > "Shao Liu" wrote: > > And also a question, why the samples when SACK is active are outliers? > > Any sample with SACK is going to mean a loss or reordering has occurred. > So shouldn't the SACK values be useful, but RTT values from retransmits > are not useful. When SACK is active, the per-packet processing becomes more involved, tracking the list of lost/SACKed packets. This causes a CPU spike just after a loss, which increases the RTTs, at least in my experience. This is a separate issue from the fact that it is hard to get RTT measurements from lost/retransmitted packets themselves. Cheers, Lachlan -- Lachlan Andrew Dept of Computer Science, Caltech 1200 E California Blvd, Mail Code 256-80, Pasadena CA 91125, USA Ph: +1 (626) 395-8820 Fax: +1 (626) 568-3603 http://netlab.caltech.edu/~lachlan