[plug] Using a HDD with Badsectors

[Arie Hol]

On 27 Nov 2006 at 9:04, Bernd Felsche wrote:

> Only HALF the drives will attain the MTBF. The other have will, by
> definition, have failed. It's the centre of the "bell curve" that is
> characteristic of the failure rate.
> 
> Server drives have MTBF of the order of 5 million hours. Well over a
> 500 years. It's not an exercise in one-upmanship that has the
> manufacturers build such drives; it's trying to push the centre of
> the bell curve into the distant future so that the rate of failure
> in operational environments is 
> 

What does MTBF "really" mean ???

How is the MTBF calculated ??

How is the MTBF derived in reference to a particular usage scenario ??

How valid is the MTBF in particular usage scenario ??

For one way of looking at it - goto :

http://en.wikipedia.org/wiki/MTBF

---------------------------

Once you know the rated MTBF of a particular item - how to you apply this 
factor to each and every situation ??

If you have device that is rated at an MTBF of 10,000 hours :

Does it mean that you will get 10,000 hours of use before the device 
suffers a failure ???

NO -  IT DOES NOT mean that at all !!!

If was probably derived by running x numbers of the same devices - until 
one of them failed - and then they just totalled x times the number of 
hours run by all devices to get a figure that was defined as the MTBF.

It makes about as much sense as asking "How long is a piece of string ??"


Regards Arie
------------------------------------------------------------------
 For the concert of life, nobody has a program.
------------------------------------------------------------------