Re: [OMPI devel] orted-children communication

2016-01-26 Thread Ralph Castain
As Gilles said, we actually have four pipes open to each process (one for show_help output separately from the others he mentioned). In addition, there is a Unix domain socket connection used by PMIx. The message_local_procs code path is stale - I need to prune things now that the PMIx integration

Re: [OMPI devel] orted-children communication

2016-01-26 Thread Gilles Gouaillardet
iirc, there are pipes between orted and app for IOF (I/O forwarding) (stdin, stdout and stderr) On Tuesday, January 26, 2016, Gianmario Pozzi wrote: > Thank you, Ralph. > > What about ORTE_DAEMON_MESSAGE_LOCAL_PROCS case into orte_comm.c? I see it > calls orte_odls.deliver_message() and the com

Re: [OMPI devel] orted-children communication

2016-01-26 Thread Gianmario Pozzi
Thank you, Ralph. What about ORTE_DAEMON_MESSAGE_LOCAL_PROCS case into orte_comm.c? I see it calls orte_odls.deliver_message() and the comments say something about delivering to children. Furthermore I can see a socket opened between orted and the application while it's running, what is that for?

Re: [OMPI devel] orted-children communication

2016-01-19 Thread Ralph Castain
This is on master, yes? The only orted-children communication on the master (and going forward) is via PMIx. I’ve got a branch that contains the error notification support so the orted can alert the child about changes such as migration, and Annu Dasari and Dave Solt are working on the error res