Are you asking about a *node* joining the universe, or a *process*
joining a computation? Or both?
For a node to join, you need to use the lamgrow command.
For a process to join, yes, you can to use the OPEN_PORT,
COMM_ACCEPT/CONNECT calls. Check the MPI-2 standard in the dynamic
chapter; there are code examples in there.
On Aug 8, 2005, at 10:58 AM, Jim Lasc wrote:
> Hi, I searched a lot on node insertion for dynamic clusters.
> All I could find was this post from this mailinglist:
> ------
>
> This only "sorta" supported. Note that lamgrow / lamshrink really only
> expand / shrink the LAM *univerise*, not a running application. You'll
> need to add special stuff into an application to make it aware that
> the
> universe has grown or shunk.
>
> For example, you may want to have one "master" process that
> MPI_COMM_SPAWN's a bunch of workers and dynamically gives them work to
> do. As a new worker becomes available, the master can be notified
> somehow (perhaps via some mechanism outside of MPI, such as a socket,
> pipe, file, or other IPC mechanism) and it can spawn a new worker
> there. Similarly, when a node becomes unavailable, the master can be
> told, and it can send a "please shut yourself down" message to the
> worker.
> -----
> I have some questions about this:
> Can someone give me example code for a node which joins the cluster
> and starts calculating. I tried to make it myself, but apparently it's
> too hard for me to do so.
>
> I guess I should use MPI_Open_Port , MPI_Comm_accept and
> MPI_Comm_spawn, but didn't managed into getting something to work
> (and my attempts are to pathetic to post)...
>
> Any help is really appreciated.
> Jim Lascov.
> _______________________________________________
> This list is archived at http://www.lam-mpi.org/MailArchives/lam/
--
{+} Jeff Squyres
{+} jsquyres_at_[hidden]
{+} http://www.lam-mpi.org/
|
