From owner-freebsd-stable@FreeBSD.ORG Tue Jul 12 11:17:28 2005 Return-Path: X-Original-To: freebsd-stable@freebsd.org Delivered-To: freebsd-stable@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 285A116A41C; Tue, 12 Jul 2005 11:17:28 +0000 (GMT) (envelope-from danny@cs.huji.ac.il) Received: from cs1.cs.huji.ac.il (cs1.cs.huji.ac.il [132.65.16.10]) by mx1.FreeBSD.org (Postfix) with ESMTP id B108243D45; Tue, 12 Jul 2005 11:17:27 +0000 (GMT) (envelope-from danny@cs.huji.ac.il) Received: from pampa.cs.huji.ac.il ([132.65.80.32]) by cs1.cs.huji.ac.il with esmtp id 1DsIbz-000DjF-MH; Tue, 12 Jul 2005 14:07:39 +0300 X-Mailer: exmh version 2.7.0 06/18/2004 with nmh-1.0.4 To: Noritoshi Demizu In-Reply-To: Message from Noritoshi Demizu of "Tue, 12 Jul 2005 18:53:04 +0900." <20050712.185304.32727687.Noritoshi@Demizu.ORG> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Tue, 12 Jul 2005 14:07:38 +0300 From: Danny Braniss Message-ID: Cc: David Malone , freebsd-net@freebsd.org, freebsd-stable@freebsd.org, Luigi Rizzo Subject: Re: tcp troughput weirdness X-BeenThere: freebsd-stable@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Production branch of FreeBSD source code List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 12 Jul 2005 11:17:28 -0000 > > combining > > sysctl net.inet.tcp.sendspace=131072 > > and > > sysctl net.inet.tcp.inflight.enable=0 > > > > did the trick! > > Congratulations! But I wonder why the throughput of FreeBSD=>Linux > was almost equal to that of Linux=>FreeBSD. If the settings above > improves the throughput of FreeBSD=>FreeBSD, the throughput of > FreeBSD=>Linux would also be improved with them. Is it improved? > i did the sysctl on the client/sender :-) > > now can someone remind me what inflight does? > > In my understanding, it tries to estimate bandwidth-delay product and > tries to avoid injecting too much data segments into networks. > So, if it underestimates bandwidth-delay product, throughtput may be > reduced. > > Regards, > Noritoshi Demizu