From owner-freebsd-questions@FreeBSD.ORG Mon Nov 21 20:15:45 2005 Return-Path: X-Original-To: freebsd-questions@freebsd.org Delivered-To: freebsd-questions@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id B7A9F16A41F for ; Mon, 21 Nov 2005 20:15:45 +0000 (GMT) (envelope-from wojtek@tensor.3miasto.net) Received: from chylonia.3miasto.net (chylonia.3miasto.net [213.192.74.6]) by mx1.FreeBSD.org (Postfix) with ESMTP id EFA9B43D62 for ; Mon, 21 Nov 2005 20:15:44 +0000 (GMT) (envelope-from wojtek@tensor.3miasto.net) Received: from chylonia.3miasto.net (localhost [127.0.0.1]) by chylonia.3miasto.net (8.13.4/8.13.4) with ESMTP id jALKFaUU061888; Mon, 21 Nov 2005 21:15:36 +0100 (CET) (envelope-from wojtek@tensor.3miasto.net) Received: from localhost (wojtek@localhost) by chylonia.3miasto.net (8.13.4/8.13.4/Submit) with ESMTP id jALKFarx061885; Mon, 21 Nov 2005 21:15:36 +0100 (CET) (envelope-from wojtek@tensor.3miasto.net) X-Authentication-Warning: chylonia.3miasto.net: wojtek owned process doing -bs Date: Mon, 21 Nov 2005 21:15:36 +0100 (CET) From: Wojciech Puchar X-X-Sender: wojtek@chylonia.3miasto.net To: Vasiliy Khodyrev In-Reply-To: <4381e9d7.3d18910c.6238.1a2a@mx.gmail.com> Message-ID: <20051121205835.X60588@chylonia.3miasto.net> References: <4381e9d7.3d18910c.6238.1a2a@mx.gmail.com> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII; format=flowed Cc: freebsd-questions@freebsd.org Subject: Re: Question about ZFS support X-BeenThere: freebsd-questions@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: User questions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 21 Nov 2005 20:15:45 -0000 > > Are you planning to include support for ZFS(link below) into FreeBSD in any > future releases? > > > > http://www.opensolaris.org/os/community/zfs/docs/ > while i'm not FreeBSD coder i would ask question - how does it REALLY work - contrary to information. i mean how it works in practice. IMHO checksumming every data (not just metadata) is nonsense if it cannot be turned off. this makes every transfer not just I/O bound but CPU and memory transfer/cache bound too. while disk and memory bandwidth in todays machines are quite comparable (memory is faster but not THAT faster than linear disk I/O) it isn't just "a little thing". built in compression isn't good idea IMHO - of course it doesn't hurt if it's optional. today disk space is rarely a problem, while huge files are often not much compressible. by general description filesystem looks very nice. thats theory - did anyone made a real test on real system?