From owner-freebsd-questions@FreeBSD.ORG Fri Nov 28 21:55:50 2008 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 7DAEC1065670 for ; Fri, 28 Nov 2008 21:55:50 +0000 (UTC) (envelope-from SRS0=TiVw6V=4D=shell.siscom.net=vogelke@siscom.net) Received: from lamorack.siscom.net (lamorack.siscom.net [209.251.2.116]) by mx1.freebsd.org (Postfix) with ESMTP id 4D9178FC14 for ; Fri, 28 Nov 2008 21:55:50 +0000 (UTC) (envelope-from SRS0=TiVw6V=4D=shell.siscom.net=vogelke@siscom.net) Received: from shell.siscom.net ([209.251.2.80]) by lamorack.siscom.net with esmtp (Exim 4.62) (envelope-from ) id 1L6BJS-0005I2-F0 for freebsd-questions@freebsd.org; Fri, 28 Nov 2008 16:55:46 -0500 Received: by shell.siscom.net (Postfix, from userid 2198) id 3717B115529; Fri, 28 Nov 2008 16:55:46 -0500 (EST) Received: by kev.msw.wpafb.af.mil (Postfix, from userid 32768) id 35F4BB7C5; Fri, 28 Nov 2008 16:55:28 -0500 (EST) To: freebsd-questions@freebsd.org In-reply-to: <20081128212753.D6715@wojtek.tensor.gdynia.pl> (message from Wojciech Puchar on Fri, 28 Nov 2008 21:28:51 +0100 (CET)) Organization: Oasis Systems Inc. X-Disclaimer: I don't speak for the USAF or Oasis. X-GPG-ID: 1024D/711752A0 2006-06-27 Karl Vogel X-GPG-Fingerprint: 56EB 6DBF 4224 C953 F417 CC99 4C7C 7D46 7117 52A0 References: <20081128194531.7B17FB7C5@kev.msw.wpafb.af.mil> <20081128212753.D6715@wojtek.tensor.gdynia.pl> Message-Id: <20081128215528.35F4BB7C5@kev.msw.wpafb.af.mil> Date: Fri, 28 Nov 2008 16:55:28 -0500 (EST) From: vogelke+software@pobox.com (Karl Vogel) Subject: Re: 5 TB server X-BeenThere: freebsd-questions@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: vogelke+software@pobox.com List-Id: User questions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 28 Nov 2008 21:55:50 -0000 >> On Fri, 28 Nov 2008 14:45:31 -0500, >> I spewed something along the lines of: K> In my experience, completely new filesystems or operating systems need at K> least 5 years in the field to weed out all the weird corner-cases. I might K> trust ZFS on Sun hardware (*with* vendor support) at this point, but I'd K> wait awhile before trying it on anything else. >> On Fri, 28 Nov 2008 21:28:51 +0100, >> Wojciech Puchar said: W> if it will ever be good filesystem, it will be no longer ZFS. just the W> ideas is in big part wrong. I'm not trying to start a religious war, but at least one idea in ZFS is worth its weight in platinum: end-to-end file-integrity checks. ZFS can (and does) find and correct file errors introduced by disk firmware and media problems. With the sheer volume of stuff being stored these days, that capability (in any filesystem) is going to be crucial. -- Karl Vogel I don't speak for the USAF or my company I think that's how Chicago got started. A bunch of people in New York said, "Gee, I'm enjoying the crime and the poverty, but it just isn't cold enough. Let's go west." --Richard Jeni