From: Alexey Kuznetsov Subject: Re: [PATCH][RFC] Re: high latency with TCP connections Date: Tue, 19 Sep 2006 02:51:23 +0400 Message-ID: <20060918225123.GA22150@ms2.inr.ac.ru> References: <20060830100734.GA22235@isil.ipib.msu.ru> <20060904160045.GA15599@ms2.inr.ac.ru> <44FDBA04.3080104@hp.com> <20060918.003938.26278728.davem@davemloft.net> <450ED337.8000700@hp.com> <20060918204105.GA31333@ms2.inr.ac.ru> <450F0EA5.2020109@hp.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: David Miller , alex@sectorb.msk.ru, netdev@vger.kernel.org Return-path: Received: from minus.inr.ac.ru ([194.67.69.97]:29116 "HELO ms2.inr.ac.ru") by vger.kernel.org with SMTP id S1030239AbWIRWvc (ORCPT ); Mon, 18 Sep 2006 18:51:32 -0400 To: Rick Jones Content-Disposition: inline In-Reply-To: <450F0EA5.2020109@hp.com> Sender: netdev-owner@vger.kernel.org List-Id: netdev.vger.kernel.org Hello! > There isn't any sort of clever short-circuiting in loopback is there? No, from all that I know. > I > do like the convenience of testing things over loopback, but always fret > about not including drivers and actual hardware interrupts etc. Well, if the test is right, it should show cost of redundant ACKs. > Regardless, kudos for running the test. The only thing missing is the > -c and -C options to enable the CPU utilization measurements which will > then give the service demand on a CPU time per transaction basis. Or > was this a UP system that was taken to CPU saturation? It is my notebook. :-) Of course, cpu consumption is 100%. (Actally, netperf shows 100.10 :-)) I will redo test on a real network. What range of -b should I test? > What i'm thinking about isn't so much about the latency I understand. Actually, I did those tests ages ago for a pure throughput case, when nothing goes in the opposite direction. I did not find a difference that time. And nobody even noticed that Linux sends ACKs _each_ small segment for unidirectional connections for all those years. :-) Alexey