On Fri, Jun 17, 2016 at 10:15:28AM +0200, Vincent Huber wrote: > Dear Mr. Joly, > > > I have tried your code on my MacBook Pro (cf. infra for details) to detail > that behavior.
Thanks for testing. > Looking at openmpi-1.10.3/ompi/mca/io/romio/romio/adio/comon/ad_fstype.c to > get the list of file system I can test, I have tried the following: > > mpirun -np 2 ./sample ufs:data.txt Works. > mpirun -np 2 ./sample nfs:data.txt Crash with SIGSEGV in ADIOI_NFS_ReadStrided() Made a quick and dirty test by replacing ADIOI_NFS_ReadStrided by ADIOI_GEN_ReadStrided() in ADIO_NFS_operations structure (ad_nfs/ad_nfs.c) ... and this fixed the problem. > mpirun -np 2 ./sample pfs:data.txt > mpirun -np 2 ./sample piofs:data.txt > mpirun -np 2 ./sample panfs:data.txt > mpirun -np 2 ./sample hfs:data.txt > mpirun -np 2 ./sample xfs:data.txt > mpirun -np 2 ./sample sfs:data.txt > mpirun -np 2 ./sample pvfs:data.txt > mpirun -np 2 ./sample zoidfs:data.txt > mpirun -np 2 ./sample ftp:data.txt > mpirun -np 2 ./sample lustre:data.txt > mpirun -np 2 ./sample bgl:data.txt > mpirun -np 2 ./sample bglockless:data.txt I don't have access to this filesystems ... The tool fails when trying to open the file, that's the corresponding assert that fire. > mpirun -np 2 ./sample testfs:data.txt This one crash with SIGSEGV but in ADIOI_Flatten(). I also tried with ompio and it seems to work. mpirun --mca io ompio -np 2 ./sample data.txt rank0 ... 000000000022222222224444444444 rank1 ... 111111111133333333335555555555 > The only one to not crash is ufs. > That is not the answer you are looking for but my two cents? Thanks. > gcc --version > Configured with: > --prefix=/Applications/Xcode.app/Contents/Developer/usr > --with-gxx-include-dir=/usr/include/c++/4.2.1 > Apple LLVM version 7.0.0 (clang-700.0.72) > Target: x86_64-apple-darwin15.5.0 > Thread model: posix > > > et > > > mpirun --version > mpirun (Open MPI) 1.10.2 > > > ? > > > 2016-06-14 17:42 GMT+02:00 Nicolas Joly <nj...@pasteur.fr>: > > > > > > Hi, > > > > At work, i do have some mpi codes that make use of custom datatypes to > > call MPI_File_read with MPI_BOTTOM ... It mostly works, except when > > the underlying filesystem is NFS where if crash with SIGSEGV. > > > > The attached sample (code + data) works just fine with 1.10.1 on my > > NetBSD/amd64 workstation using the UFS romio backend, but crash if > > switched to NFS : > > > > njoly@issan [~]> mpirun --version > > mpirun (Open MPI) 1.10.1 > > njoly@issan [~]> mpicc -g -Wall -o sample sample.c > > njoly@issan [~]> mpirun -n 2 ./sample ufs:data.txt > > rank1 ... 111111111133333333335555555555 > > rank0 ... 000000000022222222224444444444 > > njoly@issan [~]> mpirun -n 2 ./sample nfs:data.txt > > [issan:20563] *** Process received signal *** > > [issan:08879] *** Process received signal *** > > [issan:20563] Signal: Segmentation fault (11) > > [issan:20563] Signal code: Address not mapped (1) > > [issan:20563] Failing at address: 0xffffffffb1309240 > > [issan:08879] Signal: Segmentation fault (11) > > [issan:08879] Signal code: Address not mapped (1) > > [issan:08879] Failing at address: 0xffffffff881b0420 > > [issan:08879] [ 0] [issan:20563] [ 0] 0x7dafb14a52b0 > > <__sigtramp_siginfo_2> at /usr/lib/libc.so.12 > > [issan:20563] *** End of error message *** > > 0x78b9886a52b0 <__sigtramp_siginfo_2> at /usr/lib/libc.so.12 > > [issan:08879] *** End of error message *** > > -------------------------------------------------------------------------- > > mpirun noticed that process rank 0 with PID 20563 on node issan exited on > > signal 11 (Segmentation fault). > > -------------------------------------------------------------------------- > > njoly@issan [~]> gdb sample sample.core > > GNU gdb (GDB) 7.10.1 > > [...] > > Core was generated by `sample'. > > Program terminated with signal SIGSEGV, Segmentation fault. > > #0 0x000078b98871971f in memcpy () from /usr/lib/libc.so.12 > > [Current thread is 1 (LWP 1)] > > (gdb) bt > > #0 0x000078b98871971f in memcpy () from /usr/lib/libc.so.12 > > #1 0x000078b974010edf in ADIOI_NFS_ReadStrided () from > > /usr/pkg/lib/openmpi/mca_io_romio.so > > #2 0x000078b97400bacf in MPIOI_File_read () from > > /usr/pkg/lib/openmpi/mca_io_romio.so > > #3 0x000078b97400bc72 in mca_io_romio_dist_MPI_File_read () from > > /usr/pkg/lib/openmpi/mca_io_romio.so > > #4 0x000078b988e72b38 in PMPI_File_read () from /usr/pkg/lib/libmpi.so.12 > > #5 0x00000000004013a4 in main (argc=2, argv=0x7f7fff7b0f00) at sample.c:63 > > > > Thanks. > > > > -- > > Nicolas Joly > > > > Cluster & Computing Group > > Biology IT Center > > Institut Pasteur, Paris. > > > > _______________________________________________ > > users mailing list > > us...@open-mpi.org > > Subscription: https://www.open-mpi.org/mailman/listinfo.cgi/users > > Link to this post: > > http://www.open-mpi.org/community/lists/users/2016/06/29434.php > > > > > > > > > -- > Docteur Ingénieur de recherche > CeMoSiS <http://www.cemosis.fr> - vincent.hu...@cemosis.fr > Tel: +33 (0)3 68 8*5 02 06* > IRMA - 7, rue René Descartes > 67 000 Strasbourg > _______________________________________________ > users mailing list > us...@open-mpi.org > Subscription: https://www.open-mpi.org/mailman/listinfo.cgi/users > Link to this post: > http://www.open-mpi.org/community/lists/users/2016/06/29476.php -- Nicolas Joly Cluster & Computing Group Biology IT Center Institut Pasteur, Paris.
