Date: Tue, 12 Jul 2005 09:39:30 -0500 From: Dan Nelson <dnelson@allantgroup.com> To: David Malone <dwmalone@maths.tcd.ie> Cc: freebsd-net@freebsd.org, freebsd-stable@freebsd.org, Noritoshi Demizu <demizu@dd.iij4u.or.jp>, Luigi Rizzo <rizzo@icir.org> Subject: Re: tcp troughput weirdness Message-ID: <20050712143930.GJ5116@dan.emsphone.com> In-Reply-To: <200507121048.ab72454@salmon.maths.tcd.ie> References: <E1DsGx9-0008Xc-GW@cs1.cs.huji.ac.il> <200507121048.ab72454@salmon.maths.tcd.ie>
next in thread | previous in thread | raw e-mail | index | archive | help
In the last episode (Jul 12), David Malone said: > > did the trick! now can someone remind me what inflight does? and > > could someone explain why increasing sendspace alone did not do the > > trick? (i had it at 64k, which got things better, but not > > sufficient). > > TCP inflight limiting is supposed to guess the bandwidth-delay > product for a TCP connection and stop the window expanding much > above this. It's a pretty neat idea for DSL links that often have > huge buffers at the far end, where inflight limiting can prevent > delays to interactive traffic. > > However, some of the guys I know that work on TCP dynamics reckon > that they can they can come up with situations where inflight > limiting will break. Unfortunately, I haven't had time to talk > this through with them. I guess you may have found one of those > situations ;-) You might want to apply the patch at the bottom of http://www.freebsd.org/cgi/query-pr.cgi?pr=kern/75122 ; without it, new connections get a random initial bandwidth. -- Dan Nelson dnelson@allantgroup.com
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20050712143930.GJ5116>