From owner-freebsd-fs@FreeBSD.ORG Wed Apr 30 22:25:04 2014 Return-Path: Delivered-To: freebsd-fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1 with cipher ADH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 71AFF814 for ; Wed, 30 Apr 2014 22:25:04 +0000 (UTC) Received: from mail.ultra-secure.de (mail.ultra-secure.de [88.198.178.88]) (using TLSv1 with cipher ECDHE-RSA-AES256-SHA (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id CC3791E70 for ; Wed, 30 Apr 2014 22:25:03 +0000 (UTC) Received: (qmail 69241 invoked by uid 89); 30 Apr 2014 22:20:51 -0000 Received: from unknown (HELO ?192.168.1.207?) (rainer@ultra-secure.de@217.71.83.52) by mail.ultra-secure.de with ESMTPA; 30 Apr 2014 22:20:51 -0000 Content-Type: text/plain; charset=windows-1252 Mime-Version: 1.0 (Mac OS X Mail 7.2 \(1874\)) Subject: Re: RFC: using ceph as a backend for an NFSv4.1 pNFS server From: Rainer Duffner In-Reply-To: <507714298.1684844.1398541651089.JavaMail.root@uoguelph.ca> Date: Thu, 1 May 2014 00:20:49 +0200 Content-Transfer-Encoding: quoted-printable Message-Id: References: <507714298.1684844.1398541651089.JavaMail.root@uoguelph.ca> To: Rick Macklem X-Mailer: Apple Mail (2.1874) Cc: FreeBSD Filesystems X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.17 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 30 Apr 2014 22:25:04 -0000 Am 26.04.2014 um 21:47 schrieb Rick Macklem : > Hi, >=20 > The non-pNFS v4.1 server in the projects area is just about ready > for head, I think. However, without pNFS, NFSv4.1 isn't all that > interesting. The problem is that doing a pNFS server is a non-trivial > exercise. I am now somewhat familiar with pNFS (from doing the client > side), but have no expertise w.r.t. cluster file systems, etc. >=20 > For those not familiar with pNFS, the basic idea is that the NFSv4.1 > server becomes a metadata server (MDS) and hands out what are called > layouts and devinfo, so that the client can access data server(s) (DS) > to read/write the file. There are RFCs that define both block/volume > (using iSCSI or similar) and object (using something called ODS2). >=20 > Although I suspect there are many ways to do a pNFS server, I think > that building it on top of a cluster file system may be the simplest. >=20 > So, this leads me to... > At a glance (just the web pages, I haven't looked at the source), > it appears that ceph might be useful as a backend to a pNFS server. The guys at RedHat probably also believe in its usefulness:=20 = http://www.redhat.com/about/news/press-archive/2014/4/red-hat-to-acquire-i= nktank-provider-of-ceph I=92m not sure if this will make it harder to port or easier. ;-) Maybe this is something the FreeBSD Foundation should support? Of course, someone who can actually pull-off the port (and maintain it) = has to come forward first=85 That=92s actually one of the things I consider the worst outcome: a = one-off porting effort that isn=92t maintained and can=92t really be = used in production.