From owner-freebsd-cluster@FreeBSD.ORG Mon May 16 02:23:11 2005 Return-Path: Delivered-To: freebsd-cluster@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 2821F16A4CE for ; Mon, 16 May 2005 02:23:11 +0000 (GMT) Received: from mh2.centtech.com (moat3.centtech.com [207.200.51.50]) by mx1.FreeBSD.org (Postfix) with ESMTP id 6640943DC3 for ; Mon, 16 May 2005 02:23:10 +0000 (GMT) (envelope-from anderson@centtech.com) Received: from [192.168.42.23] (andersonbox3.centtech.com [192.168.42.23]) by mh2.centtech.com (8.13.1/8.13.1) with ESMTP id j4G2MiXI028393; Sun, 15 May 2005 21:23:02 -0500 (CDT) (envelope-from anderson@centtech.com) Message-ID: <428803F2.5060000@centtech.com> Date: Sun, 15 May 2005 21:22:42 -0500 From: Eric Anderson User-Agent: Mozilla/5.0 (X11; U; FreeBSD i386; en-US; rv:1.7.7) Gecko/20050504 X-Accept-Language: en-us, en MIME-Version: 1.0 To: yfyoufeng@263.net References: <3EA9E48804411F41941A18169042D10401469D@omega3.ebaseweb.com> <1115864757.3938.19.camel@localhost.localdomain> <4282D173.1040805@centtech.com> <1116148430.3920.10.camel@localhost.localdomain> <428716C2.6090307@buz.ch> <42879B35.6020307@centtech.com> <1116208152.3929.10.camel@localhost.localdomain> In-Reply-To: <1116208152.3929.10.camel@localhost.localdomain> Content-Type: text/plain; charset=UTF-8; format=flowed Content-Transfer-Encoding: quoted-printable cc: FreeBSD Clustering List Subject: Re: FreeBSD Clustering wishlist - Was: Introduction & RE:Clustering with Freebsd X-BeenThere: freebsd-cluster@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Clustering FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 16 May 2005 02:23:11 -0000 yf-263 wrote: > =E5=9C=A8 2005-05-15=E6=97=A5=E7=9A=84 13:55 -0500=EF=BC=8CEric Anderso= n=E5=86=99=E9=81=93=EF=BC=9A >=20 >>Gabriel Ambuehl wrote: >> >>>yf-263 wrote: >>> >>> >>> >>>>=E5=9C=A8 2005-05-11=E4=B8=89=E7=9A=84 22:45 -0500=EF=BC=8CEric Ander= son=E5=86=99=E9=81=93=EF=BC=9A >>>> >>>> >>>> >>>> >>>>>Ok - I'm changing the subject here in an attempt to gather informati= on. >>>>> >>>>>Here's my wishlist: >>>>> =20 >>>>> >>>> >>>>As for your wishlists, how about the MogileFS of >>>>http://www.danga.com/mogilefs/ >>>> >>>>And what do you think about our GoogleFS like && MogileFS features >>>>Clustre FS ? >>>> >>>> >>>> >>> >>> >>> >>>"Yes, this means your application has to specifically use a MogileFS >>>client library to store and retrieve files." >>> >>>I don't call that a filesystem, really. Stuff like this has its uses,= >>>but for general use, you need something that's entirely transparent to= >>>the app. >> >> >>I agree. It has to look and feel like an OS to my apps. I need to NFS= =20 >>share it to systems so they can access it as NFS clients. Besides,=20 >=20 >=20 > For our FS in the paper now only ;), you need no NFS. As two years > before, I have implemented a NFS like server in userspace, and a NFS > like client (kernel module) for Linux, AIX, and Solaris, which has been= > saled to a big user two years ago. I can bring it onto various platform= , > so no NFS is need;) Are you the one that has written the paper, and developed the code? It=20 appears as a regular filesystem to apps? >>MogileFS doesn't even sound like a filesystem: >=20 >=20 > Maybe I should add the missing one, we want to supply the MogileFS > features in our FS. >> From the website: >>=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D >>MogileFS is not: >> >> * POSIX Compliant -- you don't run regular Unix applications or=20 >>databases against MogileFS. It's meant for archiving write-once files=20 >>and doing only sequential reads. (though you can modify a file by way o= f=20 >>overwriting it with a new version) >>=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D >> >>As far as your clustre fs goes, I need to see more info. You mentioned= =20 >>it's wonderful features to me, but I'd like to see a website to read=20 >=20 >=20 > We are consideration and prepare for that. And now we are gathering and= > proof our concepts. >=20 > Last quarter we got some initial idea about it, and this quarter we wil= l > put our first module within that onto our product environment to proof > its right or not. If we succeed, I will try to open it to get a > worldwide improvement :) What company/organization do you work for? Eric --=20 ------------------------------------------------------------------------ Eric Anderson Sr. Systems Administrator Centaur Technology A lost ounce of gold may be found, a lost moment of time never. ------------------------------------------------------------------------