From owner-freebsd-fs@FreeBSD.ORG Wed Feb 8 19:28:20 2012 Return-Path: Delivered-To: freebsd-fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 12E11106564A for ; Wed, 8 Feb 2012 19:28:20 +0000 (UTC) (envelope-from ronald-freebsd8@klop.yi.org) Received: from smtp-out0.tiscali.nl (smtp-out0.tiscali.nl [195.241.79.175]) by mx1.freebsd.org (Postfix) with ESMTP id C779E8FC14 for ; Wed, 8 Feb 2012 19:28:19 +0000 (UTC) Received: from [212.182.167.131] (helo=sjakie.klop.ws) by smtp-out0.tiscali.nl with esmtp (Exim) (envelope-from ) id 1RvCqJ-000805-44; Wed, 08 Feb 2012 20:06:11 +0100 Received: from 212-182-167-131.ip.telfort.nl (localhost [127.0.0.1]) by sjakie.klop.ws (Postfix) with ESMTP id AF6BA1006C; Wed, 8 Feb 2012 20:05:53 +0100 (CET) Content-Type: text/plain; charset=utf-8; format=flowed; delsp=yes To: freebsd-fs@freebsd.org, =?utf-8?Q?Peter_Ankerst=C3=A5l?= References: <4F2FF72B.6000509@pean.org> Date: Wed, 08 Feb 2012 20:05:53 +0100 MIME-Version: 1.0 From: "Ronald Klop" Message-ID: In-Reply-To: <4F2FF72B.6000509@pean.org> User-Agent: Opera Mail/11.61 (FreeBSD) Content-Transfer-Encoding: quoted-printable Cc: Subject: Re: HPC and zfs. X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 08 Feb 2012 19:28:20 -0000 On Mon, 06 Feb 2012 16:52:11 +0100, Peter Ankerst=C3=A5l = wrote: > Hi, > > I want to investigate if it is possible to create your own usable HPC =20 > storage using zfs and some > network filesystem like nfs. > > Just a thought experiment.. > A machine with 2 6 core XEON, 3.46Ghz 12MB and 192GB of ram (or more) > I addition the machine will use 3-6 SSD drives for ZIL and 3-6 SSD =20 > deives for cache. > Preferrably in mirror where applicable. > > Connected to this machine we will have about 410 3TB drives to give =20 > approx > 1PB of usable storage in a 8+2 raidz configuration. > > Connected to this will be a ~800 nodes big HPC cluster that will access= =20 > the storage in parallell > is this even possible or do we need to distribute the meta data load =20 > over many servers? If that is the case, > does it exist any software for FreeBSD that could accomplish this =20 > distribution (pNFS dosent seem to be > anywhere close to usable in FreeBSD) or do I need to call NetApp or =20 > Panasas right away? It would be > really nice if I could build my own storage solution. > > Other possible solutions to this problem is extremley welcome. > > Best Regards > Peter Ankerst=C3=A5l You might make a call to Backblaze. http://blog.backblaze.com/2009/09/01/petabytes-on-a-budget-how-to-build-c= heap-cloud-storage/ Ronald.