[gmx-users] Re: GROMACS + MOSIX (fwd)

[Alan Wilter Sousa da Silva]

Oh sorry, I mean:

*You CANNOT cheat MPI.  They cannot be managed by Mosix (or OpenMosix)*

On Wed, 17 Apr 2002, David van der Spoel wrote:

> On Wed, 17 Apr 2002, Alan Wilter Sousa da Silva wrote:
>
> >1- Unfortunately you can *cheat* LAM-MPI (or MPICH).
> Or do you  mean fortunately?
> >2- MOSIX and LAM-MPI (or MPICH) can co-exist in the same cluster.
> >
> >	If run a parallel job with MPI, MOSIX gets knowing and so it try
> >balance the load although it can migrate MPI procs, so it just avoid that
> >procs that MPI is requiring.
>
> Any special tricks to get it going? It might be of interest to more
> people.
>
> Groeten, David.
> ________________________________________________________________________
> Dr. David van der Spoel, 	Biomedical center, Dept. of Biochemistry
> Husargatan 3, Box 576,  	75123 Uppsala, Sweden
> phone:	46 18 471 4205		fax: 46 18 511 755
> spoel at xray.bmc.uu.se	spoel at gromacs.org   http://zorn.bmc.uu.se/~spoel
> ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
>

-- 
-----------------------
Alan Wilter S. da Silva
-----------------------
 Laboratório de Física Biológica
  Instituto de Biofísica Carlos Chagas Filho
   Universidade do Brasil/UFRJ
    Rio de Janeiro, Brasil