Ralph Castain 8b6d117541 Per the OMPI devel conference that changed our default behaviors: ... * default to bind-to core * map-by slot if np=2 * map-by socket (balance across sockets on each node) if np > 2 * map-by <obj> will imply rank-by <obj> by default (leave default binding as above) Fix a bug in the map-by <obj> mapper where we incorrectly compute the #procs to assign if the #slots > #procs cmr=v1.7.4:reviewer=jsquyres:subject=Update default binding and mapping values This commit was SVN r29919.		2013-12-15 17:25:54 +00:00
..
dfs	As per the RFC, bring in the ORTE async progress code and the rewrite of OOB:	2013-08-22 16:37:40 +00:00
errmgr	This patch fixes	2013-12-06 14:40:10 +00:00
ess	Fix headers when building with ft enabled. Thanks to Adrian Reber for the patch!	2013-11-23 22:58:32 +00:00
filem	Per patch from Jeff, treat the case where someone transfers an archived file of an unknown type. This can't actually happen as this is on the receive end, and the error would have been treated and rejected on the send side. Still, practice defensive programming.	2013-11-13 23:49:26 +00:00
grpcomm	****************************************************************	2013-10-14 16:52:58 +00:00
iof	orte_iof_base.output_limit is an unsigned type; just initialize it to INT_MAX	2013-11-13 19:36:43 +00:00
odls	Singletons currently start out by spawning an HNP - this is required solely in the cases where the singleton subsequently calls MPI_Comm_spawn or publishes port info without support from an external orte-server. In all other cases, the HNP is of no value and can actually be a detriment by creating additional overhead on the node. This is particularly concerning for async operations where processes may begin as singletons and then dynamically wireup to perform pt2pt communications.	2013-10-04 02:58:26 +00:00
oob	Add missing argv.h includes.	2013-12-13 21:17:36 +00:00
plm	Fix some minor memory leaks in error code paths.	2013-12-14 00:41:21 +00:00
ras	Once again, the Slurm folks have decided to redefine their envars, reversing what they had previously told us to do. So cleanup the Slurm allocation code, and also adjust to a change in srun behavior that now aborts a job if the ntasks-per-node doesn't get specified when ORTE calls it, but the user specified it when getting an allocation. Sigh.	2013-12-09 17:58:46 +00:00
rmaps	Per the OMPI devel conference that changed our default behaviors:	2013-12-15 17:25:54 +00:00
rml	Cleanup merge conflict that was incorrectly committed	2013-12-09 20:20:14 +00:00
routed	Cleanup the radix MCA params - the max connections has no relationship to the max fd's on a node. It solely is used to improve the performance of small jobs by avoiding unnecessary inter-daemon routing.	2013-11-14 04:19:06 +00:00
sensor	As per the RFC, bring in the ORTE async progress code and the rewrite of OOB:	2013-08-22 16:37:40 +00:00
snapc	This patch fixes	2013-12-06 14:40:10 +00:00
sstore	This patch fixes	2013-12-06 14:40:10 +00:00
state	Per request from Dave Goodell, add support for MPIEXEC_TIMEOUT - if set in the environment, terminate the job after the specified number of seconds has passed. Equivalent to MPICH functionality.	2013-12-07 01:58:32 +00:00