5.2RC1 Read+Write data corruption (with SeagateBarracuda ATAV120G (ST3120023A) + VIA 8237)

[Soren Schmidt]

> Also, it was significantly worse *before* ataNG went in, and its much 
> worse on RELENG_4 than 5.x for us.

Acutally it went away for me on ATAng until I got the AMD64 box.

> Something else just occurred to me..  I think all the problems we've 
> been seeing are on *fast* machines.  (p4/xeon/amd64).  I wonder if
> that is something significant?  I'll see if I can confirm this.

I think you are pretty much on the money, I've been researching this 
problem for quite some time (as you know :) ), and I'm pretty confident
that it is timing related. However I have not been able to find out
exactly where the problem is, and I've tried just about any possible way
to changes timing to get a grip on this. However with that nice amd64
box on my shelf it is alot easier to hunt, as that fails reliably :)

-Søren
                     Yes I know it works under windows!!