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.
|
