On Wed, 26 Jul 2000, Ken Hornstein wrote:

> (This isn't really port-i386 related anymore ...)
> 
> >Newer models have sense pages that contain both the number of spinups to
> >data and the estimated maximum number of spinups.  That way you are
> >supposed to be able to detect an aging disk and leave it alone.  
> 
> I'm curious ... does anyone know what are some typical "maximum spinups"
> numbers?

It's been quite some time since I was worried about that issue, but I 
think there was some talk about 2000-5000.  Over a 5 year life of a disk
that comes to 5-10 spinups/day.

> >But realistically, if you really want to do power management on any sort
> >of disk drive you should have backups/mirroring and be prepared to replace
> >it after a while.
> 
> I'm wondering if anyone has any hard data on this.  I hear a lot of
> conjecture, but nothing definitive.  I haven't experienced any problems
> yet on my laptop, but I fully realize this is only one datapoint.

Your disk will fail.  It's just a question of when.  Deal.

Eduardo Horvath