From mboxrd@z Thu Jan 1 00:00:00 1970 From: Stephen Hemminger Subject: Re: dynamic TCP algorithms switching Date: Sat, 23 Nov 2013 16:42:20 -0800 Message-ID: <20131123164220.0992c445@nehalam.linuxnetplumber.net> References: <20131122145621.344fa999@nehalam.linuxnetplumber.net> <20131122155303.68da12ec@nehalam.linuxnetplumber.net> Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Cc: netdev@vger.kernel.org To: yan cui Return-path: Received: from mail-pd0-f171.google.com ([209.85.192.171]:40005 "EHLO mail-pd0-f171.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1756390Ab3KXAmY (ORCPT ); Sat, 23 Nov 2013 19:42:24 -0500 Received: by mail-pd0-f171.google.com with SMTP id z10so3225047pdj.16 for ; Sat, 23 Nov 2013 16:42:24 -0800 (PST) In-Reply-To: Sender: netdev-owner@vger.kernel.org List-ID: On Fri, 22 Nov 2013 22:56:10 -0500 yan cui wrote: > Thanks for the quick reply! > Do you have the real-world workload results that demonstrate > that cubic has the best performance among all the available congestion > algorithms? If so, could you please post some? > > > Thanks, Yan > > > 2013/11/22 Stephen Hemminger : > > On Fri, 22 Nov 2013 18:21:12 -0500 > > yan cui wrote: > > > >> Then, why include so many (current Linux has 10+ TCP congestion algorithms) > >> algorithms? For users who want to deploy their application on Linux > >> and if the applications > >> are system resource intensive, they always want to tune the > >> configurations of the operating systems for the last piece of > >> performance. If they do so, maybe they are confused > >> about which TCP congestion algorithm to use for their environment. So, > >> the only way is to try each algorithm one by one. I understand the > >> setting of the default TCP congestion > >> algorithm to be Cubic means that it works well for most environments. > >> But if others > >> are seldom used, or can be replace with another implementation. > >> Why not just remove from the kernel? > >> > >> Yan > > > > Most are intended for research and testing only. > > Only a few are worth considering in a production environment. > > That is also why there so many qdisc algorithms as well. > > > > > If you did a little searching around, you would find that there has been extensive research in this area. http://netsrv.csc.ncsu.edu/wiki/index.php/TCP_Testing is a good place to start.