On Tue, 2009-09-29 at 14:50 +0200, Simon Matter wrote: [...] > The interesting point is that the discussion started as a ZFS vs. > $ANY_OTHER_FS thing but it quickly turns out that the filesystem is only > one part of the picture. If your storage fails on the block level I doubt > the filesystem matters that much. ACK. Unless the filesystem driver as such has means to cope with failed block of the lower level (like ZFS has as they have RAID-support integrated the filesystem driver AFAIK. Please correct if I'm wrong). Most filesystems don't do that (for whatever reason) and (almost?) none of the not-experimental ones in the Linux world. > One of the biggest issues is the cheap big drives which are put together > into huge RAID arrrays. There is a good chance that if one disk fails, > errors show up on another disk. The storage industries mantra is than usually "use RAID6". SCNR .... If you buy several disks of the same type at the same shop, they are very probably from the same production charge and they are equally old. For most (if not all) RAID uses, they are probably pretty equally used. A quite systematic failure IMHO (and often ignored) violating lots of presumptions of maths and theory. And I expect/assume that pretty every 3rd party storage system seller is doing that BTW. [...] > I end here before getting too OT. Me too;-) Bernd -- Firmix Software GmbH http://www.firmix.at/ mobil: +43 664 4416156 fax: +43 1 7890849-55 Embedded Linux Development and Services ---- Cyrus Home Page: http://cyrusimap.web.cmu.edu/ Cyrus Wiki/FAQ: http://cyrusimap.web.cmu.edu/twiki List Archives/Info: http://asg.web.cmu.edu/cyrus/mailing-list.html
