Date: Sun, 24 Jun 2012 15:43:12 -0700 From: Edward M <eam1edward@gmail.com> To: Wojciech Puchar <wojtek@wojtek.tensor.gdynia.pl>, freebsd-questions@freebsd.org Subject: Re: Is ZFS production ready? Message-ID: <4FE79800.8000200@gmail.com> In-Reply-To: <alpine.BSF.2.00.1206240734190.42787@wojtek.tensor.gdynia.pl> References: <20120624001622.17052.qmail@joyce.lan> <4FE6602C.2050800@gmail.com> <alpine.BSF.2.00.1206240734190.42787@wojtek.tensor.gdynia.pl>
next in thread | previous in thread | raw e-mail | index | archive | help
On 06/23/2012 10:38 PM, Wojciech Puchar wrote:
>> last binary production ready, used version 14; i also found it
>> to be stable
>> Any opensource zfs pool verisons beyound that, i am not really sure
>> about their stablity compared
>> to UFS rock solid filesystem.
>
> No ZFS pool version can be as trusty as UFS because of ZFS on disk
> structure that is plain dangerous.
>
> ZFS use tree-like structure for everything. If upper part of tree is
> corrupted, everything below "disappears" and cannot be found.
>
> Having 2,3 or even 100 copies of metadata doesn't help if you would
> have (maybe transient) hardware problem and bad metadata would be
> writen 2,3 or even 100 times. with proper checksum of course.
>
> UFS uses flat structure - inodes in known places. superblocks are used
> to find info about placement, and there are many copies of which only
> first is updated under normal operation.
>
> In really unlikely case of all superblocks corrupted just use newfs on
> virtual device (may be md) of same size, with same block and fragment
> size, and byte per inode, and copy superblock from here.
>
Dont email me privately. I like ZFS design however i was only
questioning v28 stability for production
compared to a mature production tested UFS.
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?4FE79800.8000200>