From mboxrd@z Thu Jan 1 00:00:00 1970 From: David Miller Subject: Re: TSO trimming question Date: Thu, 20 Dec 2007 15:55:18 -0800 (PST) Message-ID: <20071220.155518.42408378.davem@davemloft.net> References: <20071220.040037.48002365.davem@davemloft.net> <20071220140012.GA22495@gondor.apana.org.au> Mime-Version: 1.0 Content-Type: Text/Plain; charset=us-ascii Content-Transfer-Encoding: 7bit Cc: ilpo.jarvinen@helsinki.fi, netdev@vger.kernel.org To: herbert@gondor.apana.org.au Return-path: Received: from 74-93-104-97-Washington.hfc.comcastbusiness.net ([74.93.104.97]:48519 "EHLO sunset.davemloft.net" rhost-flags-OK-FAIL-OK-OK) by vger.kernel.org with ESMTP id S1753499AbXLTXzT (ORCPT ); Thu, 20 Dec 2007 18:55:19 -0500 In-Reply-To: <20071220140012.GA22495@gondor.apana.org.au> Sender: netdev-owner@vger.kernel.org List-ID: From: Herbert Xu Date: Thu, 20 Dec 2007 22:00:12 +0800 > On Thu, Dec 20, 2007 at 04:00:37AM -0800, David Miller wrote: > > > > In the most ideal sense, tcp_window_allows() should probably > > be changed to only return MSS multiples. > > > > Unfortunately this would add an expensive modulo operation, > > however I think it would elimiate this problem case. > > Well you only have to divide in the unlikely case of us being > limited by the receiver window. In that case speed is probably > not of the essence anyway. Agreed, to some extent. I say "to some extent" because it might be realistic, with lots (millions) of sockets to hit this case a lot. There are so many things that are a "don't care" performance wise until you have a lot of stinky connections over crappy links.