On Tue, Nov 25, 2014 at 5:37 PM, Ralph Castain <r...@open-mpi.org> wrote:
> So it looks like the issue isn't so much with our code as it is with the > OS stack, yes? We aren't requiring that the loopback be "up", but the stack > is in order to establish the connection, even when we are trying a non-lo > interface. Correct, as far as I can tell. It look to me as if the stack says "Hey, that is my own address" and uses the loopback interface instead of the one associated with the address. I have checked Mac OSX and Solaris and neither one exhibits this behavior. I can, if requested, check {Net,Open,Free}BSD as well. -Paul -- Paul H. Hargrove phhargr...@lbl.gov Computer Languages & Systems Software (CLaSS) Group Computer Science Department Tel: +1-510-495-2352 Lawrence Berkeley National Laboratory Fax: +1-510-486-6900