PLEASE TEST: IPI deadlock avoidance patch

[Garance A Drosihn]

At 10:37 AM -0700 8/26/04, Doug White wrote:
>On Mon, 23 Aug 2004, Garance A Drosihn wrote:
>
>  > ...  No panics, but in the second set I
>  > did have one buildworld (-j9) which failed with four processes
>>  apparently getting a "*** Signal 6".  I am not sure what that
>>  was about. Note that all these builds were done with a `make'
>>  that was compiled to USE_KQUEUE , so maybe that's where the
>>  Signal's came from.  In any case, the machine is still running
>>  fine, even after that heavy pounding.
>
>Signal 6 is SIGABRT, which is usually intentional. You'd have to
>check the output for a specific process that abended.  I'd also
>have to scan the make code for any abort() calls.

I have not pinned this down yet, but I have determined that it is
not related to the USE_KQUEUE `make'.  It is only happening if I do
several -j buildworlds in a row, and (at least so far) only if I
also have the folding-at-home client running as a background task.

This combination is not something that I have done before, so I
no way of knowing if it is related to the IPI-fix that you wrote.
I do know that I have not been able to trigger the panic that I
got before, even though I have been hammering the machine MUCH
harder than I usually do.

The "Signal 6"s seem to be hitting various gcc processes, and I
did notice that gcc has plenty of calls to abort() in it.  At the
moment I do not have time to pursue this any farther.  (Our first
day of classes here @RPI is next Monday, and I have about a hundred
things that need to get done before then!).

-- 
Garance Alistair Drosehn            =   gad at gilead.netel.rpi.edu
Senior Systems Programmer           or  gad at freebsd.org
Rensselaer Polytechnic Institute    or  drosih at rpi.edu