Date: Mon, 21 Nov 2005 21:15:36 +0100 (CET) From: Wojciech Puchar <wojtek@tensor.3miasto.net> To: Vasiliy Khodyrev <i.am.berserk@gmail.com> Cc: freebsd-questions@freebsd.org Subject: Re: Question about ZFS support Message-ID: <20051121205835.X60588@chylonia.3miasto.net> In-Reply-To: <4381e9d7.3d18910c.6238.1a2a@mx.gmail.com> References: <4381e9d7.3d18910c.6238.1a2a@mx.gmail.com>
next in thread | previous in thread | raw e-mail | index | archive | help
> > 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?
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20051121205835.X60588>