From mboxrd@z Thu Jan 1 00:00:00 1970 From: Hagen Paul Pfeifer Subject: Re: Time in Queue, bufferbloat, and... our accidentally interplanetary network Date: Wed, 07 Dec 2011 11:15:38 +0100 Message-ID: <9dfc3c5eb811f2774b378fce0158b3e7@localhost> References: <1323082774.2670.40.camel@edumazet-HP-Compaq-6005-Pro-SFF-PC> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Cc: bloat-devel , netdev-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, linux-wireless , bloat To: Eric Dumazet Return-path: In-Reply-To: <1323082774.2670.40.camel@edumazet-HP-Compaq-6005-Pro-SFF-PC> List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: bloat-bounces-JXvr2/1DY2fm6VMwtOF2vx4hnT+Y9+D1@public.gmane.org Errors-To: bloat-bounces-JXvr2/1DY2fm6VMwtOF2vx4hnT+Y9+D1@public.gmane.org List-Id: netdev.vger.kernel.org On Mon, 05 Dec 2011 11:59:34 +0100, Eric Dumazet wrote: > Adding a time limit is possible, all we need is a proper design and > implementation :) > > Here is my suggestion : > > Design a new tfifo/tred qdisc, with following properties : > > Adaptative RED, (ECN enabled + head drop), but instead of using > bytes/packet qlen average, use time_in_queue average. Question one: is anything wrong with sfb or choke as the basis, instead of RED? Question two: I submitted pfast_head_drop to drop more outdated data instead of new data. Back in time I thought TCP _may_ experience benefits because more up-to-date SACK data packets are saved. Are there any other TCP advantages with head drop policy? Hagen