From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S932646Ab1IICSH (ORCPT ); Thu, 8 Sep 2011 22:18:07 -0400 Received: from shards.monkeyblade.net ([198.137.202.13]:33960 "EHLO shards.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932548Ab1IICSG (ORCPT ); Thu, 8 Sep 2011 22:18:06 -0400 Date: Thu, 08 Sep 2011 22:17:46 -0400 (EDT) Message-Id: <20110908.221746.534664053184784881.davem@davemloft.net> To: jun.kondo@ctc-g.co.jp Cc: linux-kernel@vger.kernel.org, omega-g1@ctc-g.co.jp, notsuki@redhat.com, motokazu.kozaki@hp.com, htaira@redhat.com, netdev@vger.kernel.org, tomohiko.takahashi@ctc-g.co.jp, kotaro.sakai@ctc-g.co.jp, ken.sugawara@ctc-g.co.jp Subject: Re: [omega-g1:11110] Re: [PATCH] net: configurable sysctl parameter "net.core.tcp_lowat" for sk_stream_min_wspace() From: David Miller In-Reply-To: <4E696D06.3000003@ctc-g.co.jp> References: <4E55D3C2.40308@ctc-g.co.jp> <20110824.220016.781758659534965980.davem@davemloft.net> <4E696D06.3000003@ctc-g.co.jp> X-Mailer: Mew version 6.3 on Emacs 23.2 / Mule 6.0 (HANACHIRUSATO) Mime-Version: 1.0 Content-Type: Text/Plain; charset=us-ascii Content-Transfer-Encoding: 7bit X-Greylist: Sender succeeded SMTP AUTH, not delayed by milter-greylist-4.2.6 (shards.monkeyblade.net [198.137.202.13]); Thu, 08 Sep 2011 19:17:51 -0700 (PDT) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org From: "Jun.Kondo" Date: Fri, 09 Sep 2011 10:33:58 +0900 > - In normal situation, acquire large default transmission > buffer value, and ensure high throughput from the > beginning of tcp connection You should never do this. You should use the default buffer sizes and as a result the kernel's TCP stack automatically adjusts the send and receive buffers in response to the link characteristics. When you set explicit buffer sizes, this turns off the TCP stack's auto-tuning mechanism. Every argument made in support of your proposed feature is based upon a false premise of one kind of another, and this is yet another example of this.