At 10:07 AM 4/11/2004 +1100, I wrote:

>At the moment, I'm
>trying to determine if delivering the overflow number sent by the OS just
>before Windows assassinates the service is what the server is expected to
>do. I posted your previous message to firebird-devel, since it would be
>handy to get some overflow scenarios.

Well, Vlad Horsun has wrecked the theory that it's the OS killing the
service. He wrote:

4294967295UL == 0xFFFFFFFF == -1L, i.e. this is process exit code (-1)
printed as unsigned long

Regards,
Vlad

So, you're back to looking at conditions known to cause crashes: bad UDFs,
inflating the TSB beyond the capacity of RAM, external forces (bad
hardware, etc.) - or another theory. :-)

./hb