From mboxrd@z Thu Jan 1 00:00:00 1970 From: David Miller Subject: Re: [PATCH] [TCP] FRTO: Limit snd_cwnd if TCP was application limited Date: Tue, 13 Nov 2007 21:02:33 -0800 (PST) Message-ID: <20071113.210233.42884295.davem@davemloft.net> References: Mime-Version: 1.0 Content-Type: Text/Plain; charset=iso-8859-1 Content-Transfer-Encoding: QUOTED-PRINTABLE Cc: netdev@vger.kernel.org To: ilpo.jarvinen@helsinki.fi Return-path: Received: from 74-93-104-97-Washington.hfc.comcastbusiness.net ([74.93.104.97]:34376 "EHLO sunset.davemloft.net" rhost-flags-OK-FAIL-OK-OK) by vger.kernel.org with ESMTP id S1750727AbXKNFCe convert rfc822-to-8bit (ORCPT ); Wed, 14 Nov 2007 00:02:34 -0500 In-Reply-To: Sender: netdev-owner@vger.kernel.org List-Id: netdev.vger.kernel.org =46rom: "Ilpo_J=E4rvinen" Date: Wed, 14 Nov 2007 00:08:18 +0200 (EET) >=20 > Otherwise TCP might violate packet ordering principles that FRTO > is based on. If conventional recovery path is chosen, this won't > be significant at all. In practice, any small enough value will > be sufficient to provide proper operation for FRTO, yet other > users of snd_cwnd might benefit from a "close enough" value. >=20 > FRTO's formula is now equal to what tcp_enter_cwr() uses. >=20 > FRTO used to check application limitedness a bit differently but > I changed that in commit 575ee7140dabe9b9c4f66f4f867039b97e548867 > and as a result checking for application limitedness became > completely non-existing. >=20 > Signed-off-by: Ilpo J=E4rvinen Applied to net-2.6, thanks Ilpo.