Found it! A trivial error (missing a break in a switch statement) that only impacts things if multiple sockets are specified in the slot_list. CMR filed to include the fix in 1.6.4
Thanks for your patience Ralph On Jan 24, 2013, at 7:50 PM, Ralph Castain <r...@open-mpi.org> wrote: > I built the current 1.6 branch (which hasn't seen any changes that would > impact this function) and was able to execute it just fine on a single socket > machine. I then gave it your slot-list, which of course failed as I don't > have two active sockets (one is empty), but it appeared to parse the list > just fine. > > From what I can tell, it looks like your linpc1 is unable to detect a second > socket for some reason when given the slot_list argument. I'll have to try > again tomorrow when I have access to a dual-socket machine. > > On Jan 19, 2013, at 1:45 AM, Siegmar Gross > <siegmar.gr...@informatik.hs-fulda.de> wrote: > >> Hi >> >> I have installed openmpi-1.6.4rc2 and have still a problem with my >> rankfile. >> >> linpc1 rankfiles 113 ompi_info | grep "Open MPI:" >> Open MPI: 1.6.4rc2r27861 >> >> linpc1 rankfiles 114 cat rf_linpc1 >> rank 0=linpc1 slot=0:0-1,1:0-1 >> >> linpc1 rankfiles 115 mpiexec -report-bindings -np 1 \ >> -rf rf_linpc1 hostname >> -------------------------------------------------------------------- >> We were unable to successfully process/set the requested processor >> affinity settings: >> >> Specified slot list: 0:0-1,1:0-1 >> Error: Error >> >> This could mean that a non-existent processor was specified, or >> that the specification had improper syntax. >> -------------------------------------------------------------------- >> -------------------------------------------------------------------- >> mpiexec was unable to start the specified application as it >> encountered an error: >> >> Error name: Error >> Node: linpc1 >> >> when attempting to start process rank 0. >> -------------------------------------------------------------------- >> >> >> Everything works fine with the following command. >> >> linpc1 rankfiles 116 mpiexec -report-bindings -np 1 -cpus-per-proc 4 \ >> -bycore -bind-to-core hostname >> [linpc1:20140] MCW rank 0 bound to socket 0[core 0-1] >> socket 1[core 0-1]: [B B][B B] >> linpc1 >> >> >> I would be grateful if somebody could fix the problem. Thank you very >> much for any help in advance. >> >> >> Kind regards >> >> Siegmar >> >> _______________________________________________ >> users mailing list >> us...@open-mpi.org >> http://www.open-mpi.org/mailman/listinfo.cgi/users >
