[OMPI devel] RFC: standardize verbosity values

2015-05-29 Thread Nathan Hjelm
At the moment we have a loosely enforced standard for verbosity values. In general frameworks accept anything in the range 0 - 100 with few exceptions. I am thinking about adding an enumerator for verbosities that will accept values in this range and certain named constants which will match with s

Re: [OMPI devel] v1.8.6 release

2015-05-29 Thread Gilles Gouaillardet
i do not know :-( all I can tell is I did not run into any issue involving the oob tcp that being said, I am not sure link-local addresses are considered as local addresses by oob/tcp since these IPv6 are part of the orted command line Cheers, Gilles On Saturday, May 30, 2015, Ralph Castain w

Re: [OMPI devel] v1.8.6 release

2015-05-29 Thread Ralph Castain
Thanks Gilles! Looking at your patch, do we have a remaining issue in the OOB TCP component? I believe the answer is “no” because we already ignore all local addresses there unless nothing else is available, but can you please confirm? Ralph > On May 29, 2015, at 8:11 AM, Gilles Gouaillardet

Re: [OMPI devel] v1.8.6 release

2015-05-29 Thread Gilles Gouaillardet
Ralph, this is being discussed at https://github.com/open-mpi/ompi/pull/605 my latest solution is available at https://github.com/ggouaillardet/ompi/commit/2a8ef01bad02b6c833c642d17d9a1140ea9292a4 the pr is a simple but temporary solution in which I introduced a new mca param, so if we decide th

[OMPI devel] v1.8.6 release

2015-05-29 Thread Ralph Castain
Hi folks The 1.8.6 branch is nearing the planned closure date - the only known outstanding issue is the IPv6 support, which remains broken for the TCP BTL. I know a solution has been proposed and/or committed to the master, but we need something resolved for 1.8.6 so we can release. Can someon