[Beowulf] Are disk MTBF ratings at all useful?

Joe Landman landman at scalableinformatics.com
Fri Apr 19 17:27:17 PDT 2013

On 04/19/2013 07:38 PM, mathog wrote:
> Joe Landman <landman at scalableinformatics.com> wrote


> Unfortunately the MTBF is nonsense because the AFR will not
> stay at 0.63%, and most likely would not be measured at 0.63% at

Ask a vendor what their AFR measurements are.  They aren't 0.63%.


> the spec.  Hard to say because the disk spec sheets do not actually
> disclose
> where the AFR number came from, and few people keep disks that long.

We see 2-4% on the good drives, 5+ on the bad ones.  This is from our 
return data.  Typically 1 drive death per 25-50 drives, per year.

> The ratings I would really like the industry to use might be called
> ef1, ef5, and ef10, where each  is the percent of disks that are

Look at AFR from vendor returns.  Not from the manufacturer.

Joseph Landman, Ph.D
Founder and CEO
Scalable Informatics, Inc.
email: landman at scalableinformatics.com
web  : http://scalableinformatics.com
phone: +1 734 786 8423 x121
fax  : +1 866 888 3112
cell : +1 734 612 4615

More information about the Beowulf mailing list