RE: Named PTF's - was CPF324A

[Justin Haase <JHaase@xxxxxxxxxxxxx>]

Seriously, I remember reading an IBM doc somewhere that mentioned those rays
and why IBM memory was soooo good.

Anyone got my back on this one?  I can't remember where I saw it tho...

jch

-----Original Message-----
From: Joe Pluta [mailto:joepluta@PlutaBrothers.com]
Sent: Monday, December 09, 2002 5:20 PM
To: midrange-l@midrange.com
Subject: RE: Named PTF's - was CPF324A


> From: Steve Landess
>
> This may be stuff of urban legend, but I heard about it in the mid-90's, I
> believe...
>
> Apparently some AS/400 customers were having intermittent problems with
> their systems crashing.  After investigation, it was found that if the
> system was located above a certain elevation, gamma rays would zap memory
> bits between refresh cycles, causing the system to go down.
>
> The  fix was a PTF that caused memory refresh to occur more frequently

At the risk that you're doing a VERY good tongue-in-cheek, Steve, I'll
answer that this is almost assuredly an urban myth, or someone pulling your
leg.  First, elevation would have nothing to do with gamma rays, it would be
cosmic rays, which actually aren't electromagnetic rays at all, but are in
fact particles from such events as supernovae in distant galaxies.

Second, while cosmic ray zaps do indeed occur, they're accounted for by
error correction logic.  The standard background rate for cosmic radiation
is about one particle per square centimeter per second.  The chances of
cosmic ray hits coincident enough to overcome even the simplest ECC logic
are so remote as to be mind-boggling.

Joe

_______________________________________________
This is the Midrange Systems Technical Discussion (MIDRANGE-L) mailing list
To post a message email: MIDRANGE-L@midrange.com
To subscribe, unsubscribe, or change list options,
visit: http://lists.midrange.com/cgi-bin/listinfo/midrange-l
or email: MIDRANGE-L-request@midrange.com
Before posting, please take a moment to review the archives
at http://archive.midrange.com/midrange-l.