Deadlocks with recent SMP current

[Robert Watson]

On Fri, 13 Aug 2004, Doug White wrote:

> On Fri, 13 Aug 2004, Martin Blapp wrote:
> 
> > Since yesterday I'm getting complete deadlocks. This time unrelated
> > the servers are nor loaded at all, the just freeze after a while.
> > No break into DDB possible at all.
> 
> Welcome to the club; I've been having them on my -curent builder since
> Aug 4. I'm going to set up a duplicate box and start binary-searching
> for the offending commit(s). 
> 
> Preemption is the default, disabled. 
> 
> My box is a dual-600MHz P3 with 1GB RAM and running kde. A make -j3
> buildworld will lock it up 75% of the time. It'll survive a nonparallel
> build, and it'll survive a kernel build. 
> 
> Haven't tried WITNESS+INVARIANTS yet since it really dogs the machine.
> :) 

If I leave SMP boxes running large parallel kernel builds overnight, I
will eventually get a solid hang.  I tried it on a new SMP box with an NMI
button I received yesterday but was unable to get into the debugger.  I'm
in the process of de-obfuscating the NMI path to increase the chances of
successfully getting into the debugger and then I'll try again to see what
I can figure out. 

Robert N M Watson             FreeBSD Core Team, TrustedBSD Projects
robert at fledge.watson.org      Principal Research Scientist, McAfee Research