Open MPI logo

Open MPI User's Mailing List Archives

  |   Home   |   Support   |   FAQ   |   all Open MPI User's mailing list

Subject: Re: [OMPI users] Bad parallel scaling using Code Saturne with openmpi
From: Dugenoux Albert (dugenouxa_at_[hidden])
Date: 2012-07-10 11:48:24

Thanks for your answer.You are right.  I've tried upon 4 nodes with 6 processes and things are worst.   So do you suggest that unique thing to do is to order an infiniband switch or is there a possibility to enhance something by tuning mca parameters ?   ________________________________ De : Ralph Castain <rhc_at_[hidden]> À : Dugenoux Albert <dugenouxa_at_[hidden]>; Open MPI Users <users_at_[hidden]> Envoyé le : Mardi 10 juillet 2012 16h47 Objet : Re: [OMPI users] Bad parallel scaling using Code Saturne with openmpi I suspect it mostly reflects communication patterns. I don't know anything about Saturne, but shared memory is a great deal faster than TCP, so the more processes sharing a node the better. You may also be hitting some natural boundary in your model - perhaps with 8 processes/node you wind up with more processes that cross the node boundary, further increasing the communication requirement. Do things continue to get worse if you use all 4 nodes with 6 processes/node? On Jul 10, 2012, at 7:31 AM, Dugenoux Albert wrote: Hi. > >I have recently built a cluster upon a Dell PowerEdge Server with a Debian 6.0 OS. This server is composed of >4 system board of 2 processors of hexacores. So it gives 12 cores per system board. >The boards are linked with a local Gbits switch. > >In order to parallelize the software Code Saturne, which is a CFD solver, I have configured the cluster >such that there are a pbs server/mom on 1 system board and 3 mom and the 3 others cards. So this leads to >48 cores dispatched on 4 nodes of 12 CPU. Code saturne is compiled with the openmpi 1.6 version. > >When I launch a simulation using 2 nodes with 12 cores, elapse time is good and network traffic is not full. >But when I launch the same simulation using 3 nodes with 8 cores, elapse time is 5 times the previous one. >I both cases, I use 24 cores and network seems not to be satured. > >I have tested several configurations : binaries in local file system or on a NFS. But results are the same. >I have visited severals forums (in particular >and read lots of threads, but as I am not an expert at clusters, I presently do not see where it is wrong ! > >Is it a problem in the configuration of PBS (I have installed it from the deb packages), a subtile compilation options >of openMPI, or a bad network configuration ? > >Regards. > >B. S._______________________________________________ >users mailing list >users_at_[hidden] >