Hi Joachim,
> Is there a formula to calculate the number of socket connections per
> node (S) that an OpenMPI application needs for running (via sockets) on
> N nodes with P processes each? I guess something like
>
> S = P * (N-1)*P
I would say that S=(N-1)*P (why do you assume that S=O(P^2)?) is an
upper bound for the MPI layer (each rank connects to all other ranks
besides the ones on its node (connect via sm) and there is no connection
'aggregation' on a single node yet). However, the connection
establishment is lazy (each connection is established with the first
send - see btl_tcp_endpoint.c:495). So you'll have the fully-connected
case after an MPI_Alltoall with a sufficient size or a similar send/recv
pattern :).
You could try to use the hierarch collective component to minimize the
number of active connections (open sockets) per node.
> but what about the daemons etc.? Let's assume only a single interface is
> used.
Ralph answered on this. They use own sockets, so these could be simply
added to S.
Regards,
Torsten
--
bash$ :(){ :|:&};: ----- pgp: http://www.unixer.de/htor-key.asc -----
"A designer knows he has arrived at perfection not when there is no
longer anything to add, but when there is no longer anything to take
away." - Antoine de Saint-Exupery
