[OpenAFS] Dreadful metadata performance

[Jamie Walker]

On 1/04/2004, at 9:09 PM, Nick Burrett wrote:

> From my experience, MegaRAID controllers are very slow and have 
> accounted for many disk performance bottlenecks on our network.  Your 
> performance figure of '3 times slower' would match a pattern we've 
> seen here, whether it be on a RAID-stripped system (7 disks) or a 
> database on RAID mirror.

In this case it's a RAID 1 mirror. In any case, there weren't anything 
like this number of complaints last year on the same hardware set.

--
Phone: +64-9-373-7599 x84679	Room: 2.315, School of Engineering
Email: jj.walker@auckland.ac.nz	ICQ: 5632563 (or shout loudly)