From mboxrd@z Thu Jan 1 00:00:00 1970 From: Lucas Nussbaum Subject: Re: [PATCH] Make CUBIC Hystart more robust to RTT variations Date: Fri, 11 Mar 2011 06:59:18 +0100 Message-ID: <20110311055918.GA10228@xanadu.blop.info> References: <20110308093215.GA23842@xanadu.blop.info> <20110310152848.7b515511@nehalam> Mime-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: QUOTED-PRINTABLE Cc: netdev@vger.kernel.org, Sangtae Ha To: Stephen Hemminger Return-path: Received: from xanadu.blop.info ([178.79.145.134]:58693 "EHLO xanadu.blop.info" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751597Ab1CKGCX (ORCPT ); Fri, 11 Mar 2011 01:02:23 -0500 Content-Disposition: inline In-Reply-To: <20110310152848.7b515511@nehalam> Sender: netdev-owner@vger.kernel.org List-ID: On 10/03/11 at 15:28 -0800, Stephen Hemminger wrote: > On Tue, 8 Mar 2011 10:32:15 +0100 > Lucas Nussbaum wrote: >=20 > > CUBIC Hystart uses two heuristics to exit slow start earlier, befor= e > > losses start to occur. Unfortunately, it tends to exit slow start f= ar too > > early, causing poor performance since convergence to the optimal cw= nd is > > then very slow. This was reported in > > http://permalink.gmane.org/gmane.linux.network/188169 and > > https://partner-bugzilla.redhat.com/show_bug.cgi?id=3D616985 >=20 > Ignore the RHEL bug. RHEL 5 ships with TCP BIC (not CUBIC) by default= =2E > There are many research papers which show that BIC is too aggressive, > and not fair. According to the bug report, the server is running RHEL6 (with CUBIC an= d Hystart), it's the client that is running RHEL5. --=20 | Lucas Nussbaum MCF Universit=E9 Nancy 2 | | lucas.nussbaum@loria.fr LORIA / AlGorille | | http://www.loria.fr/~lnussbau/ +33 3 54 95 86 19 |