[Linux-cluster] Shared storage problems with LSI controller

[Jos Vos]

On Wed, Jan 24, 2007 at 11:39:52AM -0500, Lon Hohberger wrote:

> I've seen abysmal performance in some megaraid+jbod configurations (e.g.
> 50+ seconds to get 2 block reads and 2 block writes on RHEL2.1), but
> I've never seen corruption like what you're describing.  Of course, it's
> been almost 4 years since I used a host-RAID configuration, and I
> haven't ever used one with GFS... ;(

Correction: I'm *not* using host-RAID.  The cabinet does the RAID
internally (configured via network interface) and is just a SAN
(the LV's on the cabinet show up as disks) for the connected hosts
and the LSI 22320R is only used as an "ordinary" SCSI controller.

I'm using the MPT Fusion (mpt*) driver.

> Your controllers are in "cluster mode" and/or "have cache entirely
> disabled", right?

The first yes, w.r.t. cache settings I have to check all settings on
both the controller and the cabinet.

-- 
--    Jos Vos <jos at xos.nl>
--    X/OS Experts in Open Systems BV   |   Phone: +31 20 6938364
--    Amsterdam, The Netherlands        |     Fax: +31 20 6948204