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 Bosilca <bosi...@icl.utk.edu> wrote: > > 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 <r...@open-mpi.org > <mailto:r...@open-mpi.org>> wrote: > 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 <gil...@rist.or.jp > > <mailto:gil...@rist.or.jp>> wrote: > > > > Folks, > > > > this RFC is a follow-up of > > * issue 585 https://github.com/open-mpi/ompi/issues/585 > > <https://github.com/open-mpi/ompi/issues/585> > > * related PR 591 https://github.com/open-mpi/ompi/pull/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 root cause is IPv6 link-local addresses are not (yet) correctly handled. > > > > Wikipedia has a good pages about link-locak addresses at > > http://en.wikipedia.org/wiki/Link-local_address > > <http://en.wikipedia.org/wiki/Link-local_address> > > > > basically, in IPv4, link-local addresses are 169.254.0.0/16 > > <http://169.254.0.0/16> and should be used only when zeroconf'ing the IP > > stack. > > on the other hand, IPv6 are fe80::/10, are also used when zeroconf'ing, but > > must always be present, in addition of a non link-local address. > > > > Currently, these addresses are considered as regular addresses, but the tcp > > btl (and probably oob tcp too) do not know how to handle them, and that > > causes OpenMPI crash. > > > > I can think of three options : > > 1) it is very unlikely a user wants Open MPI use a link-local address, so > > link-local addresses should be simply skipped > > 2) each module should decide if/how to handle link-local addresses > > 3) all modules should correctly handle link-local addresses (that requires > > some extra devel) > > > > as far as i am concerned, i am fine with 1) because i think it is very > > unlikely an user ever wants to use link-local addresses. > > > > Thanks in advance for your feedback so we can move forward. > > > > Cheers, > > > > Gilles > > > > > > _______________________________________________ > > devel mailing list > > de...@open-mpi.org <mailto:de...@open-mpi.org> > > Subscription: http://www.open-mpi.org/mailman/listinfo.cgi/devel > > <http://www.open-mpi.org/mailman/listinfo.cgi/devel> > > Link to this post: > > http://www.open-mpi.org/community/lists/devel/2015/05/17442.php > > <http://www.open-mpi.org/community/lists/devel/2015/05/17442.php> > > _______________________________________________ > devel mailing list > de...@open-mpi.org <mailto:de...@open-mpi.org> > Subscription: http://www.open-mpi.org/mailman/listinfo.cgi/devel > <http://www.open-mpi.org/mailman/listinfo.cgi/devel> > Link to this post: > http://www.open-mpi.org/community/lists/devel/2015/05/17443.php > <http://www.open-mpi.org/community/lists/devel/2015/05/17443.php> > _______________________________________________ > devel mailing list > de...@open-mpi.org > Subscription: http://www.open-mpi.org/mailman/listinfo.cgi/devel > Link to this post: > http://www.open-mpi.org/community/lists/devel/2015/05/17444.php
