Have you tried a typical benchmark (e.g., NetPipe or OMB) to ensure the problem isn't in your program? Outside of that, you might want to explicitly tell it to --bind-to core just to be sure it does so - it's supposed to do that by default, but might as well be sure. You can check by adding --report-binding to the cmd line.


On Apr 14, 2014, at 11:10 PM, Muhammad Ansar Javed <muhammad.ansar@seecs.edu.pk> wrote:

Hi,
I am trying to benchmark Open MPI performance on 10G Ethernet network between two hosts. The performance numbers of benchmarks are less than expected. The maximum bandwidth achieved by OMPI-C is 5678 Mbps and I was expecting around 9000+ Mbps. Moreover latency is also quite higher than expected, ranging from 37 to 59 us. Here is complete set of numbers.

Latency
Open MPI C   
Size    Time (us)

1         37.76
2         37.75
4         37.78
8         55.17
16       37.89
32       39.08
64       37.78
128     59.46
256     39.37
512     40.39
1024   47.18
2048   47.84
   

Bandwidth
Open MPI C   
Size (Bytes)    Bandwidth (Mbps)

2048               412.22
4096               539.59
8192               827.73
16384             1655.35
32768             3274.3
65536             1995.22
131072           3270.84
262144           4316.22
524288           5019.46
1048576         5236.17
2097152         5362.61
4194304         5495.2
8388608         5565.32
16777216       5678.32


My environments consists of two hosts having point-to-point (switch-less) 10Gbps Ethernet connection.  Environment (OS, user, directory structure etc) on both hosts is exactly same. There is no NAS or shared file system between both hosts. Following are configuration and job launching commands that I am using. Moreover, I have attached output of script ompi_info --all.

Configuration commmand: ./configure --enable-mpi-java --prefix=/home/mpj/installed/openmpi_installed CC=/usr/bin/gcc --disable-mpi-fortran

Job launching command: mpirun -np 2 -hostfile machines -npernode 1 ./latency.out

Are these numbers okay? If not then please suggest performance tuning steps...

Thanks

--
Ansar Javed
HPC Lab
SEECS NUST
Contact: +92 334 438 9394
Email: muhammad.ansar@seecs.edu.pk
<ompi_info.tar.bz2>_______________________________________________
users mailing list
users@open-mpi.org
http://www.open-mpi.org/mailman/listinfo.cgi/users