Date: Fri, 16 Jun 2000 02:30:28 +0200 From: "clemensF" <ino-waiting@gmx.net> To: Patrick Bihan-Faou <patrick@mindstep.com> Cc: David Gilbert <dgilbert@velocet.ca>, freebsd-net@freebsd.org Subject: Re: "frag-anyways" knob. Message-ID: <20000616023028.B745@spotteswoode.de> In-Reply-To: <010701bfd718$5917c460$040aa8c0@local.mindstep.com>; from patrick@mindstep.com on Thu, Jun 15, 2000 at 06:23:36PM -0400 References: <14664.60992.300592.147710@trooper.velocet.net> <010701bfd718$5917c460$040aa8c0@local.mindstep.com>
next in thread | previous in thread | raw e-mail | index | archive | help
> Patrick Bihan-Faou: > The easy fix is to set the MTU for windows to be something smaller than the > MTU of the PPPoE link (somewhere around 1400). This has the effect of > setting the MSS option in outbound TCP packets to something that the PPPoE > link can handle. The server then honors that value and no fragmentation > occurs. this problem looks entirely different from a leaf node. but nevertheless i wonder if tcp-flags set by a leaf influences the situation upstream. my throughput is optimal at about 300, but for me it's better to set mru. clemens To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-net" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20000616023028.B745>