RELENG_8 / mpt / zpool Errors

[Matt Thyer]

On Sep 7, 2011 8:53 AM, "Tim Gustafson" <tjg at soe.ucsc.edu> wrote:
>
> Hi all,
>
> I'm running RELENG_8:
>
> ----------
> root at bsd-03: uname -a
> FreeBSD bsd-03 8.2-STABLE FreeBSD 8.2-STABLE #0: Mon Aug 22 14:58:58 PDT
2011     root at bsd-03:/usr/obj/usr/src/sys/GENERIC  amd64
> ----------
>
> We've got an MPT controller installed with 32 drives attached:
>
> ----------
> root at bsd-03: dmesg | grep mpt
> mpt0: <LSILogic SAS/SATA Adapter> port 0xec00-0xecff mem
0xef3fc000-0xef3fffff,0xef3e0000-0xef3effff irq 32 at device 0.0 on pci3
> mpt0: [ITHREAD]
> mpt0: MPI Version=1.5.19.0
> ses0 at mpt0 bus 0 scbus1 target 32 lun 0
> ses1 at mpt0 bus 0 scbus1 target 33 lun 0
> da5 at mpt0 bus 0 scbus1 target 0 lun 0
> .....SNIP.....
> da36 at mpt0 bus 0 scbus1 target 31 lun 0
> ----------
>
> We have a zpool on those drives configured into one large zfs file system:

[snip]

> We're seeing some occasional oddness.  About every two weeks it seems the
controller temporarily loses connectivity with the drives and the zpool goes
a bit bonkers and reports a dozen or so corrupted files.  A "zpool scrub"
goes through and reports that everything's been fixed and everything seems
OK again (although I have not 100% confirmed that there is no file
corruption yet, but I'm giving ZFS's check-summing logic the benefit of the
doubt here).

[snip]

> So, is this an OS/driver issue?  Is it a bad controller?  Bad cables?  Bad
disks?
>
> As always, any help is greatly appreciated.  Thanks!
>
>
-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-
> Tim Gustafson
tjg at soe.ucsc.edu
> Baskin School of Engineering
831-459-5354
> UC Santa Cruz                                         Baskin Engineering
317B
>
-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-

What are the drives exactly?

You may have issues like TLER or frequent head parking.

Are these SATA, SCSI or SAS and are port multipliers in use?