You are right, during the reading of the configuration file we are bailing
out if a rule doesn't start with a zero-length. While the selection logic
(where I was looking) doesn't have such a restriction (it automatically
selects the first rule), I consider that forcing the communicator-based
rules
Folks,
this RFC is a follow-up of
* issue 585 https://github.com/open-mpi/ompi/issues/585
* related PR 591 https://github.com/open-mpi/ompi/pull/591
As some of you might have already noticed, Open MPI fails if configure'd
with --enable-ipv6 and ipv6 interfaces are found on the system.
The r
I can’t speak for the BTL, but the OOB has no need for link-local addresses
> On May 21, 2015, at 1:24 AM, Gilles Gouaillardet wrote:
>
> Folks,
>
> this RFC is a follow-up of
> * issue 585 https://github.com/open-mpi/ompi/issues/585
> * related PR 591 https://github.com/open-mpi/ompi/pull/591
As I indicated in the ticket, these are sometimes useful for identifying
issues with the internals of the MPI stack. I'll go with 2, but having them
by default in the tcp_exclude list.
George.
On Thu, May 21, 2015 at 10:28 AM, Ralph Castain wrote:
> I can’t speak for the BTL, but the OOB has
I can live with that - the OOB currently looks for loopback and ignores them if
any other option is available. Easy enough to extend that logic to link-local.
So I guess we should leave link-local addrs in the opal IF list, and let the
modules deal with it
> On May 21, 2015, at 8:08 AM, George
