Yet another RAID Question (YARQ)

[Ted Mittelstaedt]

>-----Original Message-----
>From: owner-freebsd-questions at freebsd.org
>[mailto:owner-freebsd-questions at freebsd.org]On Behalf Of Sandy
>Rutherford
>Sent: Thursday, June 23, 2005 1:15 AM
>To: Ted Mittelstaedt
>Cc: freebsd-questions at freebsd.org
>Subject: RE: Yet another RAID Question (YARQ)
>
>
>>>>>> On Wed, 22 Jun 2005 23:37:20 -0700, 
>>>>>> "Ted Mittelstaedt" <tedm at toybox.placo.com> said:
>
> > Seagate wrote a paper on this titled:
>
> > "Seagate Technology Paper 338.1 Estimating Drive Reliability in
> > Desktop Computers and Consumer Electronic Systems"
>
> > that explains how they define MTBF.  Basically, they define MTBF as
> > what percentage of disks will fail in the FIRST year.
>
>Is this in the public domain?  I wouldn't mind having a look at it.
>

I don't think it is but you can find ANYTHING on the Internet no
matter how embarassing or private:

http://www.digit-life.com/articles/storagereliability/

>
> > Ain't statistics grand?  You can make them say anything!  
>For an encore
> > Seagate went on to prove that their CEO would live 3 centuries
> > by statistical grouping. :-)
>
>Now don't knock statistics.  The problem does not lie with statistics,
>but with its misuse by people who do not understand what they are
>doing.  No, I am not a statistician; however, I am a mathematician.
>

Then I am expecting you to read Seagates paper and after laughing your
ass off, post a review of it here. :-)

> > So, in getting back to the gist of what I was saying, the issue is
> > as you mentioned standard deviation.  I think we all understand that
> > in a disk drive assembly line that it's all robotic, and that there
> > is an extremely high chance that disk drives that are within a few
> > serial numbers of each other are going to have virtually identical
> > characteristics.  In fact I would say using the Seagate MTBF 
>definition,
> > that 1 in every 160 drives manufactured in a particular run is going
> > to have a significant enough deviation to fail at a significantly
> > different
> > period of time, given identical workload.
>
>I am not so sure.  If we were talking about can openers, I would
>agree.  However, a disk drive is basically a mechanical object which
>performs huge numbers of mechanical actions over the course of a
>number of years.  Even extremely minute variations in the
>physical characteristics of the materials could lead to substantive
>variations over time.  However, the operative word here is "could".
>Real data is required.  I tried to google for a relevant study, but
>came up empty.  This surprised me as it seems like the sort of thing
>that masses of data should have been collected for.
>

I'm sure they are but it's all going to be useful to the competitors
so I doubt the companies that collected the data will let it out.

What your asking for are nothing less than the recipie for setting
costs levels to make a disk drive assembly line profitable - and that
is an assembly line that even at the best of it, operates with a razor
thin margin.

Getting back to the physical characteristics, yes I had thought of
that too and it is a consideration on reliability.  However, the
speed and tolerances of these things is so tight that any significant
manufacturing deviation from the design is going to have the effect
of seriously shortening lifetime.

Consider also the typical automobile engine - by comparison to
drive manufacturing the allowable variations are huge - yet for
most cars, the engines all fail around the 200,000 mile mark.

I think manufacturing deviations effects are staggered - during the
first year they matter the most, then in successive years they
don't matter much.


Ted