I did try that but still got the same thing: > [[email protected]] HYDU_sock_is_local (utils/sock/sock.c:532): gethostbyname error on MacBook-Pro.local: Unknown host > [[email protected]] main (ui/mpich/mpiexec.c:291): unable to check if localhost is local /Users/markadams/Codes/petsc/src/ksp/ksp/examples/tutorials
On Thu, Feb 26, 2015 at 5:27 PM, Matthew Knepley <[email protected]> wrote: > On Thu, Feb 26, 2015 at 4:26 PM, Mark Adams <[email protected]> wrote: > >> >> runex55: >> -@${MPIEXEC} -n 4 ./ex55 -ne 29 -alpha 1.e-3 -pc_type gamg -pc_gamg_type >> agg -pc_gamg_agg_nsmooths 1 -use_coordinates -ksp_monitor_short >> -mg_coarse_ksp_type preonly > ex55.tmp 2>&1; \ >> > > You need ${MPIEXEC} -n 4 -host localhost,localhost,localhost,localhost > ./ex55 ... > > Matt > > >> ${DIFF} output/ex55_sa.out ex55.tmp || printf "${PWD}\nPossible >> problem with ex55, diffs >> above\n=========================================\n"; \ >> ${RM} -f ex55.tmp >> >> >> and MPIEXEC=/Users/markadams/homebrew/Cellar/mpich2/3.1.2/bin/mpiexec >> >> >> On Thu, Feb 26, 2015 at 5:23 PM, Matthew Knepley <[email protected]> >> wrote: >> >>> On Thu, Feb 26, 2015 at 4:20 PM, Mark Adams <[email protected]> wrote: >>> >>>> Humm, this did not seem to work: >>>> >>> >>> Show me the actual command executed. >>> >>> Matt >>> >>> >>>> 17:15 mark/gamg-remove-eig-est >>>> ~/Codes/petsc/src/ksp/ksp/examples/tutorials$ make runex55 >>>> 1,8c1,2 >>>> < 0 KSP Residual norm 162.78 >>>> < 1 KSP Residual norm 25.4723 >>>> < 2 KSP Residual norm 2.96171 >>>> < 3 KSP Residual norm 0.460234 >>>> < 4 KSP Residual norm 0.0651141 >>>> < 5 KSP Residual norm 0.00705928 >>>> < 6 KSP Residual norm 0.0016868 >>>> < 7 KSP Residual norm 0.000213352 >>>> --- >>>> > [[email protected]] HYDU_sock_is_local >>>> (utils/sock/sock.c:532): gethostbyname error on MacBook-Pro.local: Unknown >>>> host >>>> > [[email protected]] main (ui/mpich/mpiexec.c:291): unable to >>>> check if localhost is local >>>> /Users/markadams/Codes/petsc/src/ksp/ksp/examples/tutorials >>>> Possible problem with ex55, diffs above >>>> ========================================= >>>> >>>> >>>> On Thu, Feb 26, 2015 at 4:25 PM, Matthew Knepley <[email protected]> >>>> wrote: >>>> >>>>> It can't run gethostbyname(), so maybe you are not connected to a >>>>> network? >>>>> If you want to remain disconnected, use mpirun -n 2 -host >>>>> localhost,localhost >>>>> which is how I run my tests. >>>>> >>>>> >>>>> Matt >>>>> >>>>> On Thu, Feb 26, 2015 at 3:16 PM, Mark Adams <[email protected]> wrote: >>>>> >>>>>> I started getting this error on master. I have no threads as far as >>>>>> I can see. >>>>>> Mark >>>>>> >>>>>> 16:14 mark/gamg-remove-eig-est >>>>>> ~/Codes/petsc/src/ksp/ksp/examples/tutorials$ make runex55 >>>>>> 1,8c1,40 >>>>>> < 0 KSP Residual norm 162.78 >>>>>> < 1 KSP Residual norm 25.4723 >>>>>> < 2 KSP Residual norm 2.96171 >>>>>> < 3 KSP Residual norm 0.460234 >>>>>> < 4 KSP Residual norm 0.0651141 >>>>>> < 5 KSP Residual norm 0.00705928 >>>>>> < 6 KSP Residual norm 0.0016868 >>>>>> < 7 KSP Residual norm 0.000213352 >>>>>> --- >>>>>> > Fatal error in MPI_Init_thread: Other MPI error, error stack: >>>>>> > MPIR_Init_thread(498)..............: >>>>>> > MPID_Init(177).....................: channel initialization failed >>>>>> > MPIDI_CH3_Init(89).................: >>>>>> > MPID_nem_init(320).................: >>>>>> > MPID_nem_tcp_init(171).............: >>>>>> > MPID_nem_tcp_get_business_card(418): >>>>>> > MPID_nem_tcp_init(377).............: gethostbyname failed, >>>>>> MacBook-Pro.local (errno 1) >>>>>> > Fatal error in MPI_Init_thread: Other MPI error, error stack: >>>>>> > MPIR_Init_thread(498)..............: >>>>>> > MPID_Init(177).....................: channel initialization failed >>>>>> > MPIDI_CH3_Init(89).................: >>>>>> > MPID_nem_init(320).................: >>>>>> > MPID_nem_tcp_init(171).............: >>>>>> > MPID_nem_tcp_get_business_card(418): >>>>>> > MPID_nem_tcp_init(377).............: gethostbyname failed, >>>>>> MacBook-Pro.local (errno 1) >>>>>> > Fatal error in MPI_Init_thread: Other MPI error, error stack: >>>>>> > MPIR_Init_thread(498)..............: >>>>>> > MPID_Init(177).....................: channel initialization failed >>>>>> > MPIDI_CH3_Init(89).................: >>>>>> > MPID_nem_init(320).................: >>>>>> > MPID_nem_tcp_init(171).............: >>>>>> > MPID_nem_tcp_get_business_card(418): >>>>>> > MPID_nem_tcp_init(377).............: gethostbyname failed, >>>>>> MacBook-Pro.local (errno 1) >>>>>> > Fatal error in MPI_Init_thread: Other MPI error, error stack: >>>>>> > MPIR_Init_thread(498)..............: >>>>>> > MPID_Init(177).....................: channel initialization failed >>>>>> > MPIDI_CH3_Init(89).................: >>>>>> > MPID_nem_init(320).................: >>>>>> > MPID_nem_tcp_init(171).............: >>>>>> > MPID_nem_tcp_get_business_card(418): >>>>>> > MPID_nem_tcp_init(377).............: gethostbyname failed, >>>>>> MacBook-Pro.local (errno 1) >>>>>> > >>>>>> > >>>>>> =================================================================================== >>>>>> > = BAD TERMINATION OF ONE OF YOUR APPLICATION PROCESSES >>>>>> > = PID 78010 RUNNING AT MacBook-Pro.local >>>>>> > = EXIT CODE: 1 >>>>>> > = CLEANING UP REMAINING PROCESSES >>>>>> > = YOU CAN IGNORE THE BELOW CLEANUP MESSAGES >>>>>> > >>>>>> =================================================================================== >>>>>> /Users/markadams/Codes/petsc/src/ksp/ksp/examples/tutorials >>>>>> Possible problem with ex55, diffs above >>>>>> >>>>>> >>>>> >>>>> >>>>> -- >>>>> What most experimenters take for granted before they begin their >>>>> experiments is infinitely more interesting than any results to which their >>>>> experiments lead. >>>>> -- Norbert Wiener >>>>> >>>> >>>> >>> >>> >>> -- >>> What most experimenters take for granted before they begin their >>> experiments is infinitely more interesting than any results to which their >>> experiments lead. >>> -- Norbert Wiener >>> >> >> > > > -- > What most experimenters take for granted before they begin their > experiments is infinitely more interesting than any results to which their > experiments lead. > -- Norbert Wiener >
