atom feed10 messages in org.freebsd.freebsd-fsRe: Odd file system corruption in ZFS...
FromSent OnAttachments
Andrew ReillyApr 24, 2012 7:29 am 
Peter MaloneyApr 24, 2012 7:37 am 
Andrew ReillyApr 24, 2012 4:21 pm 
Bob FriesenhahnApr 25, 2012 6:58 am 
Peter MaloneyApr 25, 2012 8:36 am 
Andrew ReillyApr 25, 2012 8:32 pm 
Andrew ReillyApr 25, 2012 8:44 pm 
Bob FriesenhahnApr 26, 2012 7:23 am 
Peter JeremyApr 26, 2012 2:06 pm 
Andrew ReillyApr 28, 2012 5:05 am 
Subject:Re: Odd file system corruption in ZFS pool
From:Bob Friesenhahn (bfri@simple.dallas.tx.us)
Date:Apr 26, 2012 7:23:56 am
List:org.freebsd.freebsd-fs

On Thu, 26 Apr 2012, Andrew Reilly wrote:

On Wed, Apr 25, 2012 at 08:58:41AM -0500, Bob Friesenhahn wrote:

With properly implemented hardware (i.e. drives which obey the cache flush request) it should not be possible to corrupt zfs due to power failure.

Does that comment apply to enerprise-class SATA drives? I was under the impression that all SATA drives lied about cache flush status. Hence the notion that I need to get myself a UPS.

A blanket statement like that (about SATA drives) would not be very accurate.

UPSs are quite valuable in that they help the system avoid marginal operating conditions.

If power is lost while a drive is currently writing, perhaps it will move the head to the wrong position and write to the wrong place on the disk, or perhaps the data it does write will be junk.

Bob