We talked off-list -- fixed this on master and just filed https://github.com/open-mpi/ompi-release/pull/33 to get this into the v1.8 branch.
On Oct 14, 2014, at 7:39 PM, Ralph Castain <r...@open-mpi.org> wrote: > > On Oct 14, 2014, at 5:32 PM, Gus Correa <g...@ldeo.columbia.edu> wrote: > >> Dear Open MPI fans and experts >> >> This is just a note in case other people run into the same problem. >> >> I just built Open MPI 1.8.3. >> As usual I put my old settings on openmpi-mca-params.conf, >> with no further thinking. >> Then I compiled the connectivity_c.c program and tried >> to run it with mpiexec. >> That is a routine that never failed before. >> >> Bummer! >> I've got a segmentation fault right away. > > Strange - it works fine from the cmd line: > > 07:27:04 (v1.8) /home/common/openmpi/ompi-release$ mpirun -n 1 -mca > rmaps_base_schedule_policy core hostname > -------------------------------------------------------------------------- > A deprecated MCA variable value was specified in the environment or > on the command line. Deprecated MCA variables should be avoided; > they may disappear in future releases. > > Deprecated variable: rmaps_base_schedule_policy > New variable: rmaps_base_mapping_policy > -------------------------------------------------------------------------- > bend001 > > HOWEVER, I can replicate that behavior when it is in the default params file! > I don't see the immediate cause of the difference, but will investigate. > >> >> After some head scratching, checking my environment, etc, >> I thought I might have configured OMPI incorrectly. >> Hence, I tried to get information from ompi_info. >> Oh well, ompi_info also segfaulted! >> >> It took me a while to realize that the runtime parameter >> configuration file was the culprit. >> >> When I inserted the runtime parameter settings one by one, >> the segfault came with this one: >> >> rmaps_base_schedule_policy = core >> >> Ompi_info (when I got it to work) told me that the parameter above >> is now a deprecated synonym of: >> >> rmaps_base_mapping_policy = core >> >> In any case, the old synonym doesn't work and makes ompi_info and >> mpiexec segfault (and I'd guess anything else that requires the OMPI runtime >> components). >> Only the new parameter name works. > > That's because the segfault is happening in the printing of the deprecation > warning. > >> >> *** >> >> I am also missing in the ompi_info output the following >> (OMPI 1.6.5) parameters (not reported by ompi_info --all --all): >> > > 1) orte_process_binding ===> hwloc_base_binding_policy > > 2) orte_report_bindings ===> hwloc_base_report_bindings > > 3) opal_paffinity_alone ===> gone, use hwloc_base_binding_policy=none if you > don't want any binding > >> >> Are they gone forever? >> >> Are there replacements for them, with approximately the same functionality? >> >> Is there a list comparing the new (1.8) vs. old (1.6) >> OMPI runtime parameters, and/or any additional documentation >> about the new style of OMPI 1.8 runtime parameters? > > Will try to add this to the web site > >> >> Since there seems to have been a major revamping of the OMPI >> runtime parameters, that would be a great help. >> >> Thank you, >> Gus Correa >> _______________________________________________ >> users mailing list >> us...@open-mpi.org >> Subscription: http://www.open-mpi.org/mailman/listinfo.cgi/users >> Link to this post: >> http://www.open-mpi.org/community/lists/users/2014/10/25497.php > > _______________________________________________ > users mailing list > us...@open-mpi.org > Subscription: http://www.open-mpi.org/mailman/listinfo.cgi/users > Link to this post: > http://www.open-mpi.org/community/lists/users/2014/10/25498.php -- Jeff Squyres jsquy...@cisco.com For corporate legal information go to: http://www.cisco.com/web/about/doing_business/legal/cri/
