From mboxrd@z Thu Jan 1 00:00:00 1970 From: Stephen Hemminger Subject: Re: 16% regression on 10G caused by TCP small queues Date: Wed, 23 Oct 2013 21:45:57 -0700 Message-ID: <20131023214557.386aad1a@nehalam.linuxnetplumber.net> References: <20131023192954.3dd9c784@nehalam.linuxnetplumber.net> <20131023.233816.1396918839771657154.davem@davemloft.net> Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Cc: ncardwell@google.com, eric.dumazet@gmail.com, dave.taht@bufferbloat.net, netdev@vger.kernel.org To: David Miller Return-path: Received: from mail-pb0-f44.google.com ([209.85.160.44]:56084 "EHLO mail-pb0-f44.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751136Ab3JXEqC (ORCPT ); Thu, 24 Oct 2013 00:46:02 -0400 Received: by mail-pb0-f44.google.com with SMTP id xa7so1999353pbc.17 for ; Wed, 23 Oct 2013 21:46:01 -0700 (PDT) In-Reply-To: <20131023.233816.1396918839771657154.davem@davemloft.net> Sender: netdev-owner@vger.kernel.org List-ID: On Wed, 23 Oct 2013 23:38:16 -0400 (EDT) David Miller wrote: > From: Stephen Hemminger > Date: Wed, 23 Oct 2013 20:09:49 -0700 > > > I will check 3.12, but what about users on 3.10 which is the LTS > > kernel used by most distros? 3.12-rc6 gets line rate again (9.41 Gbit/sec) > The fix will be backported to -stable, relax Stephen. Sorry, thought sk_pacing_rate depended on FQ qdisc but it is other way around. In which case doing merge of these two was sufficient to fix the problem. With a minor manual fix up to tcp.h. commit 95bd09eb27507691520d39ee1044d6ad831c1168 Author: Eric Dumazet Date: Tue Aug 27 05:46:32 2013 -0700 tcp: TSO packets automatic sizing commit c9eeec26e32e087359160406f96e0949b3cc6f10 Author: Eric Dumazet Date: Fri Sep 27 03:28:54 2013 -0700 tcp: TSQ can use a dynamic limit