From owner-freebsd-questions@FreeBSD.ORG Mon May 18 20:29:52 2009 Return-Path: Delivered-To: freebsd-questions@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 82668106566B for ; Mon, 18 May 2009 20:29:52 +0000 (UTC) (envelope-from yuri@rawbw.com) Received: from shell.rawbw.com (shell.rawbw.com [198.144.192.42]) by mx1.freebsd.org (Postfix) with ESMTP id 6D7A18FC1C for ; Mon, 18 May 2009 20:29:52 +0000 (UTC) (envelope-from yuri@rawbw.com) Received: from eagle.syrec.org (ppp-71-139-35-171.dsl.snfc21.pacbell.net [71.139.35.171]) (authenticated bits=0) by shell.rawbw.com (8.13.6/8.13.6) with ESMTP id n4IKTokA075940; Mon, 18 May 2009 13:29:51 -0700 (PDT) Message-ID: <4A11C53C.3090008@rawbw.com> Date: Mon, 18 May 2009 13:29:48 -0700 From: Yuri User-Agent: Thunderbird 2.0.0.21 (X11/20090419) MIME-Version: 1.0 To: Wojciech Puchar References: <4A00B3FA.5050905@rawbw.com> In-Reply-To: Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: freebsd-questions@freebsd.org Subject: Re: What is the highest hard drive read/write speed you were able to achieve by entire disk mirroring or striping? X-BeenThere: freebsd-questions@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: yuri@rawbw.com List-Id: User questions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 18 May 2009 20:29:52 -0000 Wojciech Puchar wrote: >> I am seeing 85MB/s as a speed of a single Hitachi 1TB HD. >> How high can you go by mirroring or striping 2, 3, 4 harddrives? > > mirroring - the same, just with 2 processes reading both can get the > bandwidth. make sure you use -s high enough (like 1048576) doing > gmirror label > > stripping - the same, or 2,3,4 times, depends how you configure. > for highest transfer and lowest concurrency (you mostly read huge > files with one process) - use small stripe size. > for lowest transfer (=1 disk) and highest concurency - use very huge > stripe size like 512MB, so simply different process reading different > things can hit different drives, but each I/O isn't spread. So if I will put 6 hard drives with stripping each of them is 85MB/s (in the beginning sectors) I will get 6X85MB/s=4.08Gb/s? Is it reasonable to expect this kind of speed? Something tells me that there will be some other factors like bus speed that would potentially limit the speed in such case. Yuri