On Sep 21, 2009, at 5:50 AM, Brice Goglin wrote:
> I am playing with mx__regcache_clean() in Open-MX so as to have
> cleanup the Open-MX regcache when needed. It causes some deadlocks
> OpenMPI intercepts Open-MX' own free() calls. Is there a "safe" way to
> have Open-MX free/munmap calls not invoke OpenMPI interception hooks?
Not ATM, no.
> is there a way to detect the caller of free/munmap so that my
> regcache_clean does nothing in this case? Otherwise, I guess I'll have
> to add a private malloc implementation inside Open-MX and hope OpenMPI
> won't see it.
Can you structure your code to not call free/munmap inside the handler?