From mboxrd@z Thu Jan 1 00:00:00 1970 From: Eric Dumazet Subject: Re: [PATCH] net_sched: sfq: add optional RED on top of SFQ Date: Fri, 06 Jan 2012 18:07:59 +0100 Message-ID: <1325869679.2911.27.camel@edumazet-laptop> References: <1325766316.2415.18.camel@edumazet-HP-Compaq-6005-Pro-SFF-PC> <1325770777.2415.35.camel@edumazet-HP-Compaq-6005-Pro-SFF-PC> <1325867504.2911.23.camel@edumazet-laptop> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: QUOTED-PRINTABLE Cc: David Miller , netdev , Stephen Hemminger , Kathleen Nichols , Jim Gettys To: Dave Taht Return-path: Received: from mail-ww0-f44.google.com ([74.125.82.44]:45814 "EHLO mail-ww0-f44.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1758820Ab2AFRII (ORCPT ); Fri, 6 Jan 2012 12:08:08 -0500 Received: by wgbdr13 with SMTP id dr13so1950572wgb.1 for ; Fri, 06 Jan 2012 09:08:07 -0800 (PST) In-Reply-To: Sender: netdev-owner@vger.kernel.org List-ID: Le vendredi 06 janvier 2012 =C3=A0 17:56 +0100, Dave Taht a =C3=A9crit = : > On Fri, Jan 6, 2012 at 5:31 PM, Eric Dumazet = wrote: > > Adds an optional Random Early Detection on each SFQ flow queue. >=20 > netperf -t TCP_RR is useful > -t TCP_MAERTS will be interesting. > simultaneous ping? >=20 I dont know what you expect from pings, since they are already coming i= n new flows (unless a ping flood is in effect), so RED doesnt fire for these packets. Same for TCP_RR : Since at most one packet is in flight per flow, RED cannot fire. So there is no differences for them.