[mpich-discuss] MPI_File_read_shared on NFS seems to be slow on multi-node

[Aboorva Devarajan]

MPI_File_read_shared / MPI_File_write_shared on NFS seems to be very slow
when running on multi-node environment compared to a single node run.
originally detected with the mpich test case (*writeshf90*)

Here is a minimal reproducer with MPI_File_read_shared,
https://gist.github.com/AboorvaDevarajan/db4797e02ac71f60384a8254ae2862c8


[aboorvad at c712f6n06 io]$ cat hostfile_mpich
c712f6n06:2
c712f6n07:2
[aboorvad at c712f6n06 io]$ time mpirun -np 4 --hostfile hostfile_mpich
./read_shared
*real    0m14.709s*
user    0m27.703s
sys    0m1.438s

[aboorvad at c712f6n06 io]$ time mpirun -np 4 ./read_shared

*real    0m0.247s*
user    0m0.153s
sys    0m0.616s

Is it an expected behaviour? If yes, why?


Thanks.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.mpich.org/pipermail/discuss/attachments/20171220/1b64c4a7/attachment.html>
-------------- next part --------------
_______________________________________________
discuss mailing list     discuss at mpich.org
To manage subscription options or unsubscribe:
https://lists.mpich.org/mailman/listinfo/discuss