Brian Barrett 49bcec64e4 More sm startup time reduction ...

* The real fix, don't leave the OOB in blocking mode during comm_dyn_init(),
    as it means no progressing MPI events while the event library is waiting
    for TCP stuff to come in.
  * Add many comments explaining the reasons for the current ordering

This commit was SVN r13422.

2007-02-01 18:47:43 +00:00

..

help-mpi-runtime.txt

The mpi_leave_pinned and mpi_leave_pinned_pipeline MCA parameters were

2007-01-21 14:02:06 +00:00

Makefile.am

Bring over r10877 and r10881 from the /tmp/tbird branch:

2006-08-04 14:41:31 +00:00

mpiruntime.h

Bring over r10877 and r10881 from the /tmp/tbird branch:

2006-08-04 14:41:31 +00:00

ompi_mpi_abort.c

* Before this commit, if we called ompi_mpi_abort() before MPI_INIT

2007-01-29 22:01:28 +00:00

ompi_mpi_finalize.c

Rewriting much of the errorcode and errorclass code, since

2006-12-05 19:07:02 +00:00

ompi_mpi_init.c

More sm startup time reduction

2007-02-01 18:47:43 +00:00

ompi_mpi_io.c

Bring over the update to terminate orteds that are generated by a dynamic spawn such as comm_spawn. This introduces the concept of a job "family" - i.e., jobs that have a parent/child relationship. Comm_spawn'ed jobs have a parent (the one that spawned them). We track that relationship throughout the lineage - i.e., if a comm_spawned job in turn calls comm_spawn, then it has a parent (the one that spawned it) and a "root" job (the original job that started things).

2006-11-14 19:34:59 +00:00

ompi_mpi_params.c

The mpi_leave_pinned and mpi_leave_pinned_pipeline MCA parameters were

2007-01-21 14:02:06 +00:00

ompi_mpi_preconnect.c

modify preconnect to use a rotating ring algorithm, OOB connections are

2006-12-21 01:36:57 +00:00

params.h

The mpi_leave_pinned and mpi_leave_pinned_pipeline MCA parameters were

2007-01-21 14:02:06 +00:00