Hi Ralph, I tried to improve checking for mapping-too-low and fixed a minor problem in rmaps_rr.c file. Please see attached patch file.
1) Regarding mapping-too-low, in future we'll have a lager size of l1,2,3cache or other architectuers, and in that case, the needs to map by a lower object level will increase. So, it's better/exact to compare cpus_per_rank with ncpus of the mapping object in detecting it. How do you think? 2) When orte_rmaps_rr_byobj returns with ORTE_ERR_NOT_FOUND, we should change mapping policy to ORTE_MAPPING_BYSLOT so that binding direction can be exactly evaluated in rmaps_base_binding.c file. Tetsuya (See attached file: patch.rmaps)
patch.rmaps
Description: Binary data
