[Beowulf] Are disk MTBF ratings at all useful?

[Lux, Jim (337C)]

On 4/22/13 9:11 AM, "Joe Landman" <landman at scalableinformatics.com> wrote:

>On 04/22/2013 12:07 PM, mathog wrote:
>> In partial answer to the subject question, let us apply the mode of
>> analysis used by the drive manufacturers
>> to human life expectancy, as if Humans were one of their products.
>> That is, what is the Human AFR and
>> MTBF? Unlike for disk drives, we can easily obtain a table of USA
>
>[...]
>
>> So the MTBF for the humans (in years, not hours), is 1/.000676 = 1479
>> years.
>> This number is just as nonsensical for people as 150 years is for
>> disks.
>
>Paraphrasing that great philosopher, Yoda ...
>
>"If into the MTBF calculations you go, only pain will you find."
>
>MTBF may be more of a statement of wishful thinking.  Not unlike IOP and
>bandwidth numbers on SSDs.  Oh I didn't go there ... oh wait ... I did ...


MTBF calculations are good for comparing designs, but not predicting
actual life.

MTBF statistics observed on actual devices, in sufficient numbers, are
useful for determining things like sparing quantities, and replacement
budgets.