Re: [tlug] SSDs

[Lyle H Saxon <llletters@example.com>]

On Fri, Aug 14, 2009 at 6:07 PM, Curt Sampson<cjs@example.com> wrote:
> it seems the manufacturers believe that one of my notebook drives has
> an estimated life of 4.5 years of continuous use, and one of my desktop
> drives has an estimated life of 10 years.
>
> Given one's ever-expanding storage and speed requirements, I can't
> imagine going for more than about 4 years without replacing the drive
> in a computer, even if I keep the computer itself. Thus, wearing it out
> faster doesn't really seem to be a big worry to me.

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).

I just remembered an article I read regarding Google's experience with
hard drives, and as I remember the article, it stated that there
didn't seem to be any particular factor that led to long life or short
life with hard drives.  It's just a gamble.  Some last seemingly
forever, and some die very young deaths.

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 guess I should just stop thinking about it and
continue to pull the slot machine handle....

Here's a quote (following paragraph) from the report (which I found
after writing the above).  Note in particular this sentence:
"Surprisingly, we found that temperature and activity levels were much
less correlated with drive failures than previously reported."


"It is estimated that over 90% of all new information produced in the
world is being stored on magnetic media, most of it on hard disk
drives. Despite their importance, there is relatively little published
work on the failure patterns of disk drives, and the key factors that
affect their lifetime. Most available data are either based on
extrapolation from accelerated aging experiments or from relatively
modest sized field studies. Moreover, larger population studies rarely
have the infrastructure in place to collect health signals from
components in operation, which is critical information for detailed
failure analysis. We present data collected from detailed observations
of a large disk drive population in a production Internet services
deployment. The population observed is many times larger than that of
previous studies. In addition to presenting failure statistics, we
analyze the correlation between failures and several parameters
generally believed to impact longevity. Our analysis identifies several
parameters from the drive’s self monitoring facility (SMART) that
correlate highly with failures. Despite this high correlation, we
conclude that models based on SMART parameters alone are unlikely to
be useful for predicting individual drive failures. Surprisingly, we
found that temperature and activity levels were much less correlated
with drive failures than previously reported."


The full report can be seen here:
http://docs.google.com/gview?a=v&q=cache:q7nqEvSwhZIJ:labs.google.com/papers/disk_failures.pdf+google+hard+disk+failure&hl=en