Hi, I have 3 questions to ask about,


1, how does open-mpi find the faulty node?


2, if one node is dead, could the programs continue running? How about two nodes or even more nodes are dead ?


3, How to recovery faulty node (dead node) ? Is there any possibilities to recover without check-pointing, since it is time-consuming and decrease performance ?




Rui Wang


ICT, P.R. China