Thanks.

Given that you, also, refer to SCSI and ATA133 performance (which has
``nothing'' to do with my system), maybe I should point out:

pcib0: VIA Technologies VT82C686A (Apollo KX133) PCI-ISA Bridge (rev. 0x22)
pciide0 at pci0 dev 7 function 1: VIA Tech VT82C586A IDE Controller (rev. 0x10)

...the 133 above refers to the memory speed, not the ATA speed.  The ATA
is a 33/66 ``Ultra'' ATA interface, supposedly.

As one of my professors at KU said of himself, I am alergic to electrons
(i.e., I don't do hardware).  I'm not really sure what a ``northbridge''
is or does, as compared with a ``southbridge'', but one of the chips on my
Athlon system is a 686A, which you say you use as a ``southbridge''.  I
have no idea what, if any, ``northbridge'' I may have in here.


Re. the meuktracker page: Okay, it's not German, then.  I still can't read
it.  (^&

From the confusion over which chipset is under discussion, and the
comments about the patch not fixing all of the data corruption problems
(so that where I have *none* now, I may wind up with problems should I
apply the patch), I'm not eager to bother with the patch.

The moreso since my system is rarely I/O bound.  Mostly it's idle.  When
it's busy, it tends to be compute-bound (ray-tracing, Mesa rendering,
etc.).  If it takes a little longer to load Emacs the first time, that's
not a real problem.


You mention trying other chipsets, though---do you have in mind that I'm
evaluating systems (or am about to buy a new system)?  If so, I must have
conveyed the the wrong impression.  Or do you mean to suggest that I
should try a new motherboard?  If the latter, I can think of better uses
for the money at the moment, given what the computer's tasks are.  This is
an annoyance factor, not a critical failure.


  ``I probably don't know what I'm talking about.'' --rauch@math.rice.edu