From mboxrd@z Thu Jan 1 00:00:00 1970 From: Saku Ytti Subject: Re: TCP and reordering Date: Wed, 28 Nov 2012 20:44:38 +0200 Message-ID: <20121128184438.GA26814@pob.ytti.fi> References: <50B4F2DA.8020206@hp.com> <20121127.210611.1127622873924794001.davem@davemloft.net> <20121128072611.GA26010@pob.ytti.fi> <20121128085404.GB26010@pob.ytti.fi> <50B656CC.1040001@hp.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii To: netdev@vger.kernel.org Return-path: Received: from mail-la0-f46.google.com ([209.85.215.46]:35380 "EHLO mail-la0-f46.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754712Ab2K1Sop (ORCPT ); Wed, 28 Nov 2012 13:44:45 -0500 Received: by mail-la0-f46.google.com with SMTP id p5so7985001lag.19 for ; Wed, 28 Nov 2012 10:44:43 -0800 (PST) Content-Disposition: inline In-Reply-To: <50B656CC.1040001@hp.com> Sender: netdev-owner@vger.kernel.org List-ID: On (2012-11-28 10:24 -0800), Rick Jones wrote: > By increasing net.ipv4.tcp_reordering you make the sending TCP less > "sensitive" to duplicate ACKs and so less sensitive to reordering > detected by the receiver. The receiver is generating as many > (duplicate) ACKs as before, it is just that the sender is ignoring > them a bit more. Thanks, I didn't know this. -- ++ytti