At 06:16 PM 2/23/99 +0200, Osma Ahvenlampi wrote:
>[EMAIL PROTECTED] (Alvin Oga) writes:
>Fine. I don't know exactly what happens if one CPU in a multi-CPU
>system completely drops dead in the middle of everything, but I don't
>think Linux will like that. Not even on hardware built to be more
>error-tolerant than the usual x86 junk. And in any case, a subtle
>malfunction (executing corrupt code, for instance) will certainly end
>up in a crash.
>
As an owner of several multi-CPU (SPARC based) platforms running linux, I
will tell you that second (or third or fourth) processor doesn't even have
to die to toast the entire machine, it just has to vie for a resource that
one of the other processors doesn't want to give up. With the 2.2.X
release of code for Sparc, I'm very familiar with the dreaded CPU #X Spin
lock problem. Solution is to basically "reset" the system, dealing with
the nasty problem of taking your drives offline in the middle of whatever
they were doing.
There are some RAID manufacturers who build external raid controllers which
allow you to place two controllers on the same chain. Upon failure of the
operational controller, the backup controller will "spring to life"
masquerading as the primary controller...
-Chris
Chris A. Icide / [EMAIL PROTECTED]
VP Engineering/Operations
SkyCache / www.skycache.com
(v) 301-598-0500 x2235
