From mboxrd@z Thu Jan 1 00:00:00 1970 From: Florian Westphal Subject: Re: [PATCH] allow dctcp alpha to drop to zero Date: Mon, 19 Oct 2015 16:01:35 +0200 Message-ID: <20151019140135.GF4386@breakpoint.cc> References: <20151019045908.GB11368@mininet-vm> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: netdev@vger.kernel.org, "David S. Miller" , Daniel Borkmann , Florian Westphal , Glenn Judd To: Andrew Shewmaker Return-path: Received: from Chamillionaire.breakpoint.cc ([80.244.247.6]:34524 "EHLO Chamillionaire.breakpoint.cc" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751063AbbJSOBj (ORCPT ); Mon, 19 Oct 2015 10:01:39 -0400 Content-Disposition: inline In-Reply-To: <20151019045908.GB11368@mininet-vm> Sender: netdev-owner@vger.kernel.org List-ID: Andrew Shewmaker wrote: > If alpha is strictly reduced by alpha >> dctcp_shift_g and if alpha is less > than 1 << dctcp_shift_g, then alpha may never reach zero. For example, > given shift_g=4 and alpha=15, alpha >> dctcp_shift_g yields 0 and alpha > remains 15. The effect isn't noticeable in this case below cwnd=137, but > could gradually drive uncongested flows with leftover alpha down to > cwnd=137. A larger dctcp_shift_g would have a greater effect. > > This change causes alpha=15 to drop to 0 instead of being decrementing by 1 > as it would when alpha=16. However, it requires one less conditional to > implement since it doesn't have to guard against subtracting 1 from 0U. A > decay of 15 is not unreasonable since an equal or greater amount occurs at > alpha >= 240. > > Signed-off-by: Andrew G. Shewmaker Acked-by: Florian Westphal [ cwnd=137 is quite large so I don't think its important enough for -stable ].