Re: [tlug] SSDs

[Curt Sampson <cjs@example.com>]

On 2009-08-15 08:59 +0900 (Sat), Lyle H Saxon wrote:

> Well, what has made me worry about this in the first place are a
> couple of new drives that I bought, used intermittently, and had
> catastrophically die on me within one year - not ten years (one
> Seagate and one Hitachi).

Oh, that's perfectly expected. Since I've started buying significant
quantities of drives in the mid-90s, it's always been the case that
manufacturers will occasionally produce batches of drives that are prone
to early failure.

> Having had a couple die very young deaths though, I can't help but try
> to think of some way to make things easier on the drives in order to
> prolong their lives.

I'm not sure that that's a good idea at all. Extending the life a drive
bound to fail is merely going to make it more likely to fail after the
warranty has expired and lengthen the amount of time it takes before
you're confident that the drive is not one of those that's going to
suffer from infant mortality.

> http://docs.google.com/gview?a=v&q=cache:q7nqEvSwhZIJ:labs.google.com/papers/disk_failures.pdf+google+hard+disk+failure&hl=en

That's an interesting paper. Thanks.

cjs
-- 
Curt Sampson       <cjs@example.com>        +81 90 7737 2974
           Functional programming in all senses of the word:
                   http://www.starling-software.com