[Cialug] Google Hard Drive Study

[Nathan Stien]

On 3/7/07, Nathan C. Smith <smith at ipmvs.com> wrote:
> Hard drive issues seem to keep popping up here.  I found this study by
> Google and thought I would share it.  After all, Google is one giant disk
> testing facility.  Consumer-type drives, not SCSI too.
>
> http://labs.google.com/papers/disk_failures.pdf

Google was oddly stingy about some of the results:

  3.2    Manufacturers, Models, and Vintages
  Failure rates are known to be highly correlated with drive
  models, manufacturers and vintages [18]. Our results do
  not contradict this fact. For example, Figure 2 changes
  significantly when we normalize failure rates per each
  drive model. Most age-related results are impacted by
  drive vintages. However, in this paper, we do not show a
  breakdown of drives per manufacturer, model, or vintage
  due to the proprietary nature of these data.

Proprietary nature of these data?  Observed failure rates of various
hardware models doesn't seem proprietary to me.  (I don't see a lot of
vendors suing tomshardware.com...)  This would be one of the most
interesting parts -- I'm sure we'd all like to know which particular
drives did best out of such a huge population.

It also seems like it would help the market punish bad drive vendors
and encourage them to do better.  Survival of the fittest drives.
Everyone wins (except people who make bad drives).

So I guess I don't understand their reasoning for withholding this.
Can anyone else here disabuse me of my naivete?

-- 
Nathan P. Stien
Consulting Engineer / Software Developer
Embedded Systems Electronics and Software
http://linkedin.com/in/nathanstien
Mobile: 309.241.2581