> On Oct 17, 2014, at 6:41 AM, Jed Brown <j...@jedbrown.org> wrote: > > "Jeff Squyres (jsquyres)" <jsquy...@cisco.com> writes: > >> The ompi repo only contains the master branch. Releases are not made >> from master, and therefore it doesn't make sense to tag it with >> release tags. master is therefore not (directly) related to any given >> release. > > You can have tags in the repository without the branches, though I think > it's useful for a contributor to > > git checkout -b my/bug-fix maint-1.8 > > instead of making a patch off 'master' that needs to be back-ported to > the release. The usual model is that one merges "upward" from the > maintenance branches to 'master’.
We go the other direction - all code must be committed to master so it can “soak” prior to moving to a release branch. The “upward” methodology works fine for stable situations where the master isn’t changing much relative to the releases, but that generally isn’t the case for OMPI. > > But regardless, isn't it valuable to be able to query things like this? > > git log v1.8.0..master ompi/mpi/c/iallreduce.c > > git branch -r --contains $bug_fix_commit Not really much different than we do today - the wiki explains how to make it work. > > Seems to me that most people cloning open-mpi/ompi will want to fetch > From open-mpi/ompi-release regularly so they can have this context. > >> The "dev" tag is there so that we can make nightly tarballs with a >> logical sequence (via "git describe"). The "dev" tag is basically >> there as the point at which we converted to git. We could have put it >> back at the beginning of time (i.e., equivalent to SVN r1 (i.e., the >> first CVS commit!)), but it didn't really matter, so we just opted for >> a dev that resulted in a smaller "git describe" number. > > That number will get big later and it deprives you of context when you > have no idea whether "dev-BIGNUMBER" is earlier or later than a given > release. (Does it have those features/bugs or not?) Not sure this has ever been an issue before, to be honest. > _______________________________________________ > 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/2014/10/16058.php
