From mboxrd@z Thu Jan 1 00:00:00 1970 From: Horms Subject: Bug#337089: linux-image-2.6.14-1-powerpc: add CONFIG_TCP_CONG_BIC=y Date: Fri, 4 Nov 2005 12:27:27 +0900 Message-ID: <20051104032726.GD4708@verge.net.au> References: <20051102162451.0002CF64E@ibook.free.fr> Reply-To: Horms , 337089@bugs.debian.org Mime-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: quoted-printable Cc: NetDev Return-path: Resent-Message-ID: To: =?UTF-8?Q?Beno=C3=AEt?= Dejean , 337089@bugs.debian.org Content-Disposition: inline In-Reply-To: <20051102162451.0002CF64E@ibook.free.fr> List-Post: List-Help: List-Subscribe: List-Unsubscribe: List-Id: netdev.vger.kernel.org On Wed, Nov 02, 2005 at 05:24:50PM +0100, Beno=EEt Dejean wrote: > Package: linux-image-2.6.14-1-powerpc > Version: 2.6.14-1 > Severity: normal >=20 > Hi, > Linux < 2.6.14 used to have every TCP congestion algorithms as builtins= but > NewReno + BIC was default. >=20 > Linux 2.6.14 has splitted these features into modules. But default rema= ins > NewReno + BIC accordint to CONFIG_TCP_CONG_ADVANCED help message : >=20 > "Nearly all users can safely say no here, and a safe default selection = will > be made (BIC-TCP with new Reno as a fallback)." >=20 > And indeed NewReno+BIC is a good and safe default. Much better than New= Reno >=20 > But Debian .config has CONFIG_TCP_CONG_BIC=3Dm (CONFIG_TCP_CONG_*=3Dm) = which > makes NewReno default. So this is like a "regression". I'd like debian = kernel > to have CONFIG_TCP_CONG_BIC=3Dy provided that one can easily switch to = another > algorithm (using /proc/sys/net/ipv4/tcp_congestion_control). Hi Netdev, could someone please comment on what a good default congestion algorithm setup for distribution kernels is? Thanks --=20 Horms