Re: SMP bugs ( was Re: Severe deadlock issues with 5.0/MP )

[Eduardo Horvath <eeh%NetBSD.org@localhost>]

On Wed, 4 Feb 2009, Michael wrote:

> Hello,
> 
> On Feb 4, 2009, at 11:40 AM, Eduardo Horvath wrote:
> 
> > On Wed, 4 Feb 2009, Michael wrote:
> > 
> > > Externally Initiated Reset (XIR):
> > 
> > This is an external reset line usually used for debugging.  On most
> > desktop machines this terminates in a header on the motherboard to which
> > you can attach an external pushbutton.  Some servers have this line
> > controlled by a service processor.  JBUS machines (USIIIi) have this
> > controlled by the PCI controller in a rather complicated mess.
> 
> Since I see these on my U60, which is rather stuffed with hardware ( 2x
> 450MHz/4MB CPUs, 2 SCA disks, 2 Creator3D, 2GB RAM, two PCI graphics boards,
> USB and a gigabit ethernet card ), should I take a few cards out and see if
> things improve? Is there any way to spuriously trigger this? Can it be masked?
> Since these resets always correlate with high load and IO activity it might
> just be the power supply.

It's worth a try.  The only way to tell for sure is to get hold of the 
schematics, stick a scope on the XIR line or power rails, and look for 
some sort of glitch.  But if removing hardware solves the problem it's 
much easier to do.

Eduardo