On Thu, 10 May 2012, Jim Maas wrote:
> I'm getting the following error when running an open-mpi job on a
> LSF cluster using a new version of R 2.15. I didn't get the error
> message when running previously using R 2.13. Could anyone point me
> to the possible cause, or how to find the offending co
I'm afraid I don't know the inner workings of R at all. They must have changed
something between 2.13 and 2.15 such that they're now calling fork() after
MPI_Init()...
The problem is that OpenFabrics-based networks do things that make fork()...
unstable (for lack of a longer description). Tha
I'm getting the following error when running an open-mpi job on a LSF
cluster using a new version of R 2.15. I didn't get the error message
when running previously using R 2.13. Could anyone point me to the
possible cause, or how to find the offending code? I'm not a sysop,
just a user.
Th
