From owner-freebsd-questions@FreeBSD.ORG Fri Sep 9 04:04:36 2005 Return-Path: X-Original-To: freebsd-questions@freebsd.org Delivered-To: freebsd-questions@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id C509C16A41F for ; Fri, 9 Sep 2005 04:04:36 +0000 (GMT) (envelope-from kdk@daleco.biz) Received: from ezekiel.daleco.biz (southernuniform.com [66.76.92.18]) by mx1.FreeBSD.org (Postfix) with ESMTP id 607F343D46 for ; Fri, 9 Sep 2005 04:04:35 +0000 (GMT) (envelope-from kdk@daleco.biz) Received: from [192.168.2.2] ([69.27.149.254]) by ezekiel.daleco.biz (8.13.1/8.13.1) with ESMTP id j8943Kul067072; Thu, 8 Sep 2005 23:03:43 -0500 (CDT) (envelope-from kdk@daleco.biz) Message-ID: <4321097D.8080203@daleco.biz> Date: Thu, 08 Sep 2005 23:03:09 -0500 From: Kevin Kinsey User-Agent: Mozilla/5.0 (X11; U; FreeBSD i386; en-US; rv:1.7.10) Gecko/20050823 X-Accept-Language: en-us, en MIME-Version: 1.0 To: Tom Pepper References: In-Reply-To: Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: freebsd-questions@freebsd.org Subject: Re: NFS client performance against MS SFU 3.5 NFS Server X-BeenThere: freebsd-questions@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: User questions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 09 Sep 2005 04:04:36 -0000 Tom Pepper wrote: > All: > > Anyone having any good fortune with performance of NFS shares > in a current 5-STABLE against Windows 2003 Services For Unix 3.5 > server? I'm able to, with some pretty extreme tuning, get as much > as 1MB/sec out of a 100Mbps link, but I'm able to FTP to and from > the same host at 8-10MB/sec. I've tried different send/receive windows, > NFSv2, NFSv3, forcing TCP/UDP, and setting the tcp windows to some > pretty outrageous sizes. None of the above really seems to net me > performance above 500-600kB/sec (testing via rsync --progress -av / > local/dir /mnt/nfsshare). > > mount_smbfs is also incapable of going beyond 1MB/sec in a similar > arrangement. Why on earth is performance sucking so bad? > > Thanks, > -t I have similar secret doubts, but I've not gone to the lengths that you have, and I've not tested against Win2k3 server. One question: is there any chance it is an rsync problem? Kevin Kinsey