(Hi, I'm the first hand info on this particular case. ;-)

seebs@solutions.solon.com:
> I dunno, but the BSD/OS people reported a *very* significant error rate
> with most 64 meg SIMMs, and at this point, my understanding is that we
> don't suggest anyone even try it without ECC simms.  One of our engineers
> was getting a few errors a day on the 64-meg models.  *sigh*.

Yup, I heard this too.

> I suspect this is a fairly portable probmproblem.  :)

Always a comfort. :-)

How do the work station guys (Sun, DEC-Alpha!, HP, ...) handle it?

Turning off ECC was just a shot in the dark. It didn't run stable with
it turned on either, and the peculiarities noted with cp/cksum *might*
be due to a bad kernel in possible combination with bad memory. I'll
try a more reliable kernel (1.2.1-REL) as soon as I have the
opportunity.

For now I'm trying to pin-point the problem by turning knobs and
watching output.

Anyone know about a good program for exercising large amounts of
memory in a controlled fashion?

				Cheers,
				  /Liman
#-------------------------------------------------------------------------
# Lars-Johan Liman			 ! Internet: liman@sunet.se
# Ebone/NORDUnet/SUNET Operations Centre ! BITNET  : LIMAN@SEARN
# Royal Institute of Technology, Sweden	 ! HTTP    : //www.sunet.se/~liman
#					 ! Voice   : Int +46 8 - 790 65 60
#-------------------------------------------------------------------------