On Oct 27, 2012, at 9:47 AM, Mahmood Naderan <nt_mahm...@yahoo.com> wrote:
> > >Because communicating through shared memory when sending messages between > >processes on the same server is far faster than going through a network > >stack. > > I see... But that is not good for diskless clusters. Am I right? No, that isn't correct. Our largest clusters are diskless and use SM. They simply setup a /tmp area in memory to hold the SM region. It preserves the performance, as Jeff said. > assume processes are on a node (which has no disk). In this case, their > communication go though network (from computing node to server) then IO and > then network again (from server to computing node). > > Regards, > Mahmood > > From: Jeff Squyres <jsquy...@cisco.com> > To: Mahmood Naderan <nt_mahm...@yahoo.com>; Open MPI Users > <us...@open-mpi.org> > Sent: Saturday, October 27, 2012 6:19 PM > Subject: Re: [OMPI users] openmpi shared memory feature > > On Oct 27, 2012, at 10:49 AM, Mahmood Naderan wrote: > > > Why openmpi uses shared memory model? > > Because communicating through shared memory when sending messages between > processes on the same server is far faster than going through a network stack. > > > this can be disabled though by setting "--mca ^sm". > > It seems that by default openmpi uses such feature (shared memory backing > > files) which is strange. > > > > Regards, > > Mahmood > > _______________________________________________ > > users mailing list > > us...@open-mpi.org > > http://www.open-mpi.org/mailman/listinfo.cgi/users > > > -- > Jeff Squyres > jsquy...@cisco.com > For corporate legal information go to: > http://www.cisco.com/web/about/doing_business/legal/cri/ > > > > _______________________________________________ > users mailing list > us...@open-mpi.org > http://www.open-mpi.org/mailman/listinfo.cgi/users
