ZFS SATA problems
in [Solaris]
|
From: Thomas Tornblom on 15 Sep 2009 01:56 Michael Laajanen <michael_laajanen(a)yahoo.com> writes: > Hi, > > Thomas Tornblom wrote: >> Michael Laajanen <michael_laajanen(a)yahoo.com> writes: >>> Just back from office and the test with 8 UFS filesystems has been >>> going on for some 20 hours without any problem so one way pr the other >>> it seams to be ZFS related and maybe the way ZFS driver handles >>> read/write errors compared to UFS? Or could it be that ZFS check the >>> files on the disk i a better way perhaps? >>> >>> /michael >> ZFS does end to end data integrity checking, including checksumming >> all data, so ZFS detects data corruption even if the hardware says >> everything is OK. UFS does no such checking. >> > Right, that is how I have understood ZFS and also liked :) > >> But the errors yoou've showed before indicates that the driver has >> detected a problem, and that is done below either of ZFS or UFS. >> One thing that is different is that if ZFS is given a whole disk it >> will enable the disk cache, while it is disabled (if possible) if the >> disk is used with normal partitioning, which is how UFS use it. Some >> disks have caches that can't be disabled. > Is there some easy way to enable the cache under UFS, I assume that > this is write cache. The write cache is disabled for a reason, and I'm not aware of any simple way of enabling it, besides giving the whole disk to zfs :-) >> Have you run the tests in "format"? >> Thomas > Nope, the UFS test was choosen and done in a hurry in the weekend but > will try that tomorrow. > > /michael Thomas
From: Chris Ridd on 15 Sep 2009 03:16 On 2009-09-15 06:56:05 +0100, Thomas Tornblom <thomas(a)Hax.SE> said: > The write cache is disabled for a reason, and I'm not aware of any > simple way of enabling it, besides giving the whole disk to zfs :-) I think the format command can enable it, but you need to start it with the -e flag. <http://www.sun.com/bigadmin/content/submitted/format_utility.jsp> -- Chris
From: Thomas Tornblom on 15 Sep 2009 10:39 Chris Ridd <chrisridd(a)mac.com> writes: > On 2009-09-15 06:56:05 +0100, Thomas Tornblom <thomas(a)Hax.SE> said: > >> The write cache is disabled for a reason, and I'm not aware of any >> simple way of enabling it, besides giving the whole disk to zfs :-) > > I think the format command can enable it, but you need to start it > with the -e flag. > > <http://www.sun.com/bigadmin/content/submitted/format_utility.jsp> > -- > Chris Ah, thanks. I thought format -e would have it, but I looked under "scsi" and found nothing. Anyway, enabling the write cache on UFS disks is not recommended, unless the disks have uninterruptible power.
From: Michael Laajanen on 15 Sep 2009 17:47 Hi, Thomas Tornblom wrote: > Chris Ridd <chrisridd(a)mac.com> writes: > >> On 2009-09-15 06:56:05 +0100, Thomas Tornblom <thomas(a)Hax.SE> said: >> >>> The write cache is disabled for a reason, and I'm not aware of any >>> simple way of enabling it, besides giving the whole disk to zfs :-) >> I think the format command can enable it, but you need to start it >> with the -e flag. >> >> <http://www.sun.com/bigadmin/content/submitted/format_utility.jsp> >> -- >> Chris > > Ah, thanks. I thought format -e would have it, but I looked under > "scsi" and found nothing. > > Anyway, enabling the write cache on UFS disks is not recommended, > unless the disks have uninterruptible power. Thanks I will try that, sure I understand atleast that reason for not having cache enable :) but this is just a test. /michael
From: Michael Laajanen on 15 Sep 2009 17:51
HI, Thomas Tornblom wrote: > Michael Laajanen <michael_laajanen(a)yahoo.com> writes: >> Just back from office and the test with 8 UFS filesystems has been >> going on for some 20 hours without any problem so one way pr the other >> it seams to be ZFS related and maybe the way ZFS driver handles >> read/write errors compared to UFS? Or could it be that ZFS check the >> files on the disk i a better way perhaps? >> >> /michael > > ZFS does end to end data integrity checking, including checksumming > all data, so ZFS detects data corruption even if the hardware says > everything is OK. UFS does no such checking. > > But the errors yoou've showed before indicates that the driver has > detected a problem, and that is done below either of ZFS or UFS. > > One thing that is different is that if ZFS is given a whole disk it > will enable the disk cache, while it is disabled (if possible) if the > disk is used with normal partitioning, which is how UFS use it. Some > disks have caches that can't be disabled. > > Have you run the tests in "format"? > > Thomas Now I have test with format and analyzed the disk, no errrors on any disk, so still only ZFS reports errors and reports it quickly say after 15 minutes of intensive copy. Next I will try the same tests with some internal drives in the u24 under ZFS. If that goes well it gets closer to some serious Oscilloscope measurements... /michael |