Ralph Castain 75684dc260 Resolve a race condition for setting our working directory when fork/exec'ing application procs. We have to ensure we do it after the fork occurs since we want to use multiple threads in the odls. Otherwise, the different threads are bouncing the entire process around. ...

Signed-off-by: Ralph Castain <rhc@open-mpi.org>

2017-03-21 13:54:03 -07:00

..

alps

Resolve a race condition for setting our working directory when fork/exec'ing application procs. We have to ensure we do it after the fork occurs since we want to use multiple threads in the odls. Otherwise, the different threads are bouncing the entire process around.

2017-03-21 13:54:03 -07:00

base

Resolve a race condition for setting our working directory when fork/exec'ing application procs. We have to ensure we do it after the fork occurs since we want to use multiple threads in the odls. Otherwise, the different threads are bouncing the entire process around.

2017-03-21 13:54:03 -07:00

default

Resolve a race condition for setting our working directory when fork/exec'ing application procs. We have to ensure we do it after the fork occurs since we want to use multiple threads in the odls. Otherwise, the different threads are bouncing the entire process around.

2017-03-21 13:54:03 -07:00

Makefile.am

Purge whitespace from the repo

2015-06-23 20:59:57 -07:00

odls_types.h

Revert e9bc293 and try a different approach for scalably dealing with hetero clusters. Have each orted send back its topo "signature". If mpirun detects that this signature has not been seen before, then ask for that daemon to send back its full topology description. This allows the system to only get the topology once for each unique topo in the cluster.

2017-01-18 10:22:15 -08:00

odls.h

Refactor the ORTE DVM code so that external codes can submit multiple jobs using only a single connection to the HNP.

2016-02-13 08:10:44 -08:00