# export LD_LIBRARY_PATH # mpiexec -n 1 printenv | grep PATH LD_LIBRARY_PATH=/usr/lib/openmpi/lib/ PATH=/usr/lib/openmpi/bin/:/usr/lib/ccache:/usr/local/bin:/usr/bin:/bin:/usr/local/sbin:/usr/sbin:/sbin:/home/jski/.local/bin:/home/jski/bin MODULEPATH=/usr/share/Modules/modulefiles:/etc/modulefiles WINDOWPATH=1
# mpiexec -n 4 ./a.out librdmacm: couldn't read ABI version. librdmacm: assuming: 4 CMA: unable to get RDMA device list -------------------------------------------------------------------------- [[3598,1],0]: A high-performance Open MPI point-to-point messaging module was unable to find any relevant network interfaces: Module: OpenFabrics (openib) Host: elzbieta Another transport will be used instead, although this may result in lower performance. -------------------------------------------------------------------------- librdmacm: couldn't read ABI version. librdmacm: assuming: 4 librdmacm: couldn't read ABI version. CMA: unable to get RDMA device list librdmacm: assuming: 4 CMA: unable to get RDMA device list librdmacm: couldn't read ABI version. librdmacm: assuming: 4 CMA: unable to get RDMA device list [elzbieta:4145] *** An error occurred in MPI_Scatter [elzbieta:4145] *** on communicator MPI_COMM_WORLD [elzbieta:4145] *** MPI_ERR_TYPE: invalid datatype [elzbieta:4145] *** MPI_ERRORS_ARE_FATAL: your MPI job will now abort -------------------------------------------------------------------------- mpiexec has exited due to process rank 1 with PID 4145 on node elzbieta exiting improperly. There are two reasons this could occur: 1. this process did not call "init" before exiting, but others in the job did. This can cause a job to hang indefinitely while it waits for all processes to call "init". By rule, if one process calls "init", then ALL processes must call "init" prior to termination. 2. this process called "init", but exited without calling "finalize". By rule, all processes that call "init" MUST call "finalize" prior to exiting or it will be considered an "abnormal termination" This may have caused other processes in the application to be terminated by signals sent by mpiexec (as reported here). -------------------------------------------------------------------------- On Sat, Sep 15, 2012 at 2:24 PM, Ralph Castain <r...@open-mpi.org> wrote: > Ah - note that there is no LD_LIBRARY_PATH in the environment. That's the > problem > > On Sep 15, 2012, at 11:19 AM, John Chludzinski <john.chludzin...@gmail.com> > wrote: > > $ which mpiexec > /usr/lib/openmpi/bin/mpiexec > > # mpiexec -n 1 printenv | grep PATH > > PATH=/usr/lib/openmpi/bin/:/usr/lib/ccache:/usr/local/bin:/usr/bin:/bin:/usr/local/sbin:/usr/sbin:/sbin:/home/jski/.local/bin:/home/jski/bin > MODULEPATH=/usr/share/Modules/modulefiles:/etc/modulefiles > WINDOWPATH=1 > > > > On Sat, Sep 15, 2012 at 1:11 PM, Ralph Castain <r...@open-mpi.org> wrote: > >> Couple of things worth checking: >> >> 1. verify that you executed the "mpiexec" you think you did - a simple >> "which mpiexec" should suffice >> >> 2. verify that your environment is correct by "mpiexec -n 1 printenv | >> grep PATH". Sometimes the ld_library_path doesn't carry over like you think >> it should >> >> >> On Sep 15, 2012, at 10:00 AM, John Chludzinski < >> john.chludzin...@gmail.com> wrote: >> >> I installed OpenMPI (I have a simple dual core AMD notebook with Fedora >> 16) via: >> >> # yum install openmpi >> # yum install openmpi-devel >> # mpirun --version >> mpirun (Open MPI) 1.5.4 >> >> I added: >> >> $ PATH=PATH=/usr/lib/openmpi/bin/:$PATH >> $ LD_LIBRARY_PATH=/usr/lib/openmpi/lib/ >> >> Then: >> >> $ mpif90 ex1.f95 >> $ mpiexec -n 4 ./a.out >> ./a.out: error while loading shared libraries: libmpi_f90.so.1: cannot >> open shared object file: No such file or directory >> ./a.out: error while loading shared libraries: libmpi_f90.so.1: cannot >> open shared object file: No such file or directory >> ./a.out: error while loading shared libraries: libmpi_f90.so.1: cannot >> open shared object file: No such file or directory >> ./a.out: error while loading shared libraries: libmpi_f90.so.1: cannot >> open shared object file: No such file or directory >> -------------------------------------------------------------------------- >> mpiexec noticed that the job aborted, but has no info as to the process >> that caused that situation. >> -------------------------------------------------------------------------- >> >> ls -l /usr/lib/openmpi/lib/ >> total 6788 >> lrwxrwxrwx. 1 root root 25 Sep 15 12:25 libmca_common_sm.so -> >> libmca_common_sm.so.2.0.0 >> lrwxrwxrwx. 1 root root 25 Sep 14 16:14 libmca_common_sm.so.2 -> >> libmca_common_sm.so.2.0.0 >> -rwxr-xr-x. 1 root root 8492 Jan 20 2012 libmca_common_sm.so.2.0.0 >> lrwxrwxrwx. 1 root root 19 Sep 15 12:25 libmpi_cxx.so -> >> libmpi_cxx.so.1.0.1 >> lrwxrwxrwx. 1 root root 19 Sep 14 16:14 libmpi_cxx.so.1 -> >> libmpi_cxx.so.1.0.1 >> -rwxr-xr-x. 1 root root 87604 Jan 20 2012 libmpi_cxx.so.1.0.1 >> lrwxrwxrwx. 1 root root 19 Sep 15 12:25 libmpi_f77.so -> >> libmpi_f77.so.1.0.2 >> lrwxrwxrwx. 1 root root 19 Sep 14 16:14 libmpi_f77.so.1 -> >> libmpi_f77.so.1.0.2 >> -rwxr-xr-x. 1 root root 179912 Jan 20 2012 libmpi_f77.so.1.0.2 >> lrwxrwxrwx. 1 root root 19 Sep 15 12:25 libmpi_f90.so -> >> libmpi_f90.so.1.1.0 >> lrwxrwxrwx. 1 root root 19 Sep 14 16:14 libmpi_f90.so.1 -> >> libmpi_f90.so.1.1.0 >> -rwxr-xr-x. 1 root root 10364 Jan 20 2012 libmpi_f90.so.1.1.0 >> lrwxrwxrwx. 1 root root 15 Sep 15 12:25 libmpi.so -> libmpi.so.1.0.2 >> lrwxrwxrwx. 1 root root 15 Sep 14 16:14 libmpi.so.1 -> >> libmpi.so.1.0.2 >> -rwxr-xr-x. 1 root root 1383444 Jan 20 2012 libmpi.so.1.0.2 >> lrwxrwxrwx. 1 root root 21 Sep 15 12:25 libompitrace.so -> >> libompitrace.so.0.0.0 >> lrwxrwxrwx. 1 root root 21 Sep 14 16:14 libompitrace.so.0 -> >> libompitrace.so.0.0.0 >> -rwxr-xr-x. 1 root root 13572 Jan 20 2012 libompitrace.so.0.0.0 >> lrwxrwxrwx. 1 root root 20 Sep 15 12:25 libopen-pal.so -> >> libopen-pal.so.3.0.0 >> lrwxrwxrwx. 1 root root 20 Sep 14 16:14 libopen-pal.so.3 -> >> libopen-pal.so.3.0.0 >> -rwxr-xr-x. 1 root root 386324 Jan 20 2012 libopen-pal.so.3.0.0 >> lrwxrwxrwx. 1 root root 20 Sep 15 12:25 libopen-rte.so -> >> libopen-rte.so.3.0.0 >> lrwxrwxrwx. 1 root root 20 Sep 14 16:14 libopen-rte.so.3 -> >> libopen-rte.so.3.0.0 >> -rwxr-xr-x. 1 root root 790052 Jan 20 2012 libopen-rte.so.3.0.0 >> -rw-r--r--. 1 root root 301520 Jan 20 2012 libotf.a >> lrwxrwxrwx. 1 root root 15 Sep 15 12:25 libotf.so -> libotf.so.0.0.1 >> lrwxrwxrwx. 1 root root 15 Sep 14 16:14 libotf.so.0 -> >> libotf.so.0.0.1 >> -rwxr-xr-x. 1 root root 206384 Jan 20 2012 libotf.so.0.0.1 >> -rw-r--r--. 1 root root 337970 Jan 20 2012 libvt.a >> -rw-r--r--. 1 root root 591070 Jan 20 2012 libvt-hyb.a >> lrwxrwxrwx. 1 root root 18 Sep 15 12:25 libvt-hyb.so -> >> libvt-hyb.so.0.0.0 >> lrwxrwxrwx. 1 root root 18 Sep 14 16:14 libvt-hyb.so.0 -> >> libvt-hyb.so.0.0.0 >> -rwxr-xr-x. 1 root root 428844 Jan 20 2012 libvt-hyb.so.0.0.0 >> -rw-r--r--. 1 root root 541004 Jan 20 2012 libvt-mpi.a >> lrwxrwxrwx. 1 root root 18 Sep 15 12:25 libvt-mpi.so -> >> libvt-mpi.so.0.0.0 >> lrwxrwxrwx. 1 root root 18 Sep 14 16:14 libvt-mpi.so.0 -> >> libvt-mpi.so.0.0.0 >> -rwxr-xr-x. 1 root root 396352 Jan 20 2012 libvt-mpi.so.0.0.0 >> -rw-r--r--. 1 root root 372352 Jan 20 2012 libvt-mt.a >> lrwxrwxrwx. 1 root root 17 Sep 15 12:25 libvt-mt.so -> >> libvt-mt.so.0.0.0 >> lrwxrwxrwx. 1 root root 17 Sep 14 16:14 libvt-mt.so.0 -> >> libvt-mt.so.0.0.0 >> -rwxr-xr-x. 1 root root 266104 Jan 20 2012 libvt-mt.so.0.0.0 >> -rw-r--r--. 1 root root 60390 Jan 20 2012 libvt-pomp.a >> lrwxrwxrwx. 1 root root 14 Sep 15 12:25 libvt.so -> libvt.so.0.0.0 >> lrwxrwxrwx. 1 root root 14 Sep 14 16:14 libvt.so.0 -> libvt.so.0.0.0 >> -rwxr-xr-x. 1 root root 242604 Jan 20 2012 libvt.so.0.0.0 >> -rwxr-xr-x. 1 root root 303591 Jan 20 2012 mpi.mod >> drwxr-xr-x. 2 root root 4096 Sep 14 16:14 openmpi >> >> >> The file (actually, a link) it claims it can't find: libmpi_f90.so.1, is >> clearly there. And LD_LIBRARY_PATH=/usr/lib/openmpi/lib/. >> >> What's the problem? >> >> ---John >> _______________________________________________ >> users mailing list >> us...@open-mpi.org >> http://www.open-mpi.org/mailman/listinfo.cgi/users >> >> >> >> _______________________________________________ >> users mailing list >> us...@open-mpi.org >> http://www.open-mpi.org/mailman/listinfo.cgi/users >> > > _______________________________________________ > users mailing list > us...@open-mpi.org > http://www.open-mpi.org/mailman/listinfo.cgi/users > > > > _______________________________________________ > users mailing list > us...@open-mpi.org > http://www.open-mpi.org/mailman/listinfo.cgi/users >
