WHAT: Enable both OPAL and libevent thread support by default
WHY: We need to support threaded operations for MPI-3, and for
MPI_THREAD_MULTIPLE.
Enabling thread support by default is the only way to ensure
we fix all the problems.
WHEN: COB, Thurs Dec 13
This was a decision reached at the OMPI Developers meeting, so the RFC is
mostly just a "heads up" to everyone that this will happen. We spent some time
recently profiling the impact on performance and found it to be significant:
100ns in shared memory latency, and a similar number to TCP message latency.
However, without setting the support "on" by default, we will never address
those problems. Thus, the group decided that we would enable support by default
and being a concerted effort to reduce and/or remove the performance impact.
