[Tfug] OT: Disk testing

[Bexley Hall]

Hi, Ronald,

--- Ronald Sutherland <rsutherland at epccs.com> wrote:

> I don't have much time during week days.. between a
> Pima class and work I can't even do proper lurking.

Ah, well... first you need a long, dark RAINCOAT;
then, a fedora of similar coloring... keep your
hands in your pockets, head tipped down slightly...
and practice "shifty eyes"...

Given time, I'm sure you'll be able to get it!  :>

> But some fast comments, current limit .. ya .. its
> no fun to plug into a hot source with high current
> limit (pop .. ekk .. wait for sight to return... a
> good day).

<grin>  I worked on a CPU "chip" many years ago
(man, MANY!  :< ) that drew (drawed?  :< ) 500W+
(100A @ -5.2 plus who knows how much Ibb, etc.)
You *quickly* learned how important it is to
remove all jewelry (wedding band, class ring, etc.),
belt buckles, even EYEGLASSES (wire rims) when
working around things like that!  You could short
the power supply with a screwdriver and it didn't
care -- it would just melt the screwdriver!  :<

> So a number of smaller independent sources with 
> lower current limit is much better. At any rate
> I don't think power usage should be a concern,

<frown>  I have a hard time *not* thinking about
power.  I.e. running N machines (with monitors)
when you could do the same thing with far less
power *wasted*... as a society, we are far too
quick to waste energy so I would prefer not to
get lumped into that class  :<

[I'll get off my soapbox here...  :> ]

> the real issue is elegance or lack of, and big 
> globs of wires lose in that competition 
> every day. Even so...
> 
> Not sure if you were going to do the testing or
> someone else, or how many units needed tested. 

This is an ongoing process.  I am just trying to
address a time/space/energy inefficiency.  I.e.
if more drives can get tested using less tabletop
space, less power AND less time...

> What I have in my mind is a PC (or more as 
> needed) with 2-5 mobile docks. The operator installs
> the HD's in dock, plugs them in PC and turns on the
> power. The test runs automatically after boot and
> unmounts all HD's at end of test, leaving PASS/FAIL
> info on screen and log (or stuffs it into a network
> server). The test operator then powers off the PC
> and removes HD's. If a surface scan is anything
> like mirroring then that takes me a long time on
> >60GB HD's.

Yup.  But, you need to find PC(s) with 2-5 exposed
drive bays (nowadays, even *2* is often hard!) and
a dock for each.  I.e. if you want to do 10 drives
concurrently, you need 10 docks (just like my
USB scheme would need 10 external USB drives  :< )

If you treat this as a batch process (i.e. no hot
swap), then you can get rid of the need for
"twice as many" IDE controllers -- as you can leave
masters and slaves on each controller.  The bottleneck
would then be the PCI bus -- and, if you limit this
to ~5 drives per host, that wouldn't be an issue
(i.e. figure out *what* the limit would be and just
limit the number of docks to that number!)

The problem with treating it as a batch process is
that the longest drive determines the throughput.
I.e. if you test four 10G drives and a 20G drive,
the time for the 20G drive defines the time 
"required" by the 10G drives.  I.e. now you have to
have the operator think carefully about which
drives he tests together (not an unrealistic
scenario but any time you can remove criteria
from operation is a bonus).  The external USB
approach worked around this by letting you unplug
each drive as it was done -- irregardless (:> my
favorite NONword!) of what the other drives were
doing at the time.

> The test PC(s) ATX supply could be smaller
> (200-350W) if fewer HD's are used, that keeps a
> reasonable current limit and is cheep, also no
> cards or extra boards needed (just mobile docks).

Yes, the idea of using some *small* PC's (i.e.
everything on the motherboard) has appeal.  As I
mentioned in a previous post; even if only 2
drives sat on the machine at a time, boot it
diskless, etc.  This is far preferable to
(me!) designing an SBC to do the job -- I
don't seem to have any existing designs with
a wide enough PIO to handle the i/f  :<
Otherwise, I could just modify "that" for the job.

> Don't know about you but I 
> have a few extra PC's at work (and home), putting
> them (the work ones) 
> to use like that would be my path of least
> resistance, although I would 
> expect them to self destruct from power cycling. I'm
> not sure power 
> cycling USB hardware is any better but it may be,
> most of this consumer 
> crap is full of low end electrolytic capacitors and
> is not really tested for reliability.

But, you needn't use the crappy little power module
that comes with such devices!  You could grab a
surplus PC power supply and use it to power several
of the USB devices.  Most that I have seen already
have provisions for a power switch *in* the drive
enclosure so they expect to be operated this way...

--don

__________________________________________________
Do You Yahoo!?
Tired of spam?  Yahoo! Mail has the best spam protection around 
http://mail.yahoo.com