Maybe not relevant, but... In the GASNet and Berkeley UPC projects we include our analogue of autogen.sh in tarballs, too. Because of this our analogue of MTT is able to exercise it across many versions of the autotools. This *has* actually allowed us to learn of problems in our configury before developers had updated their own autotools.
Not that I get a vote, but I think leaving it out of the tarball is the "safer" choice. Anyone who needs to run autogen.pl should be capable of using git. -Paul On Tue, Oct 27, 2015 at 1:21 PM, Jeff Squyres (jsquyres) <jsquy...@cisco.com > wrote: > Yo Brian Barrett: cast your brain into the WayBack(tm) machine... > > Do you remember why we include autogen.pl in distribution tarballs? > > My recollection is: > > 1. It was handy for OMPI developers to "make dist" in a SVN checkout to > take a tarball over to back-end machine where you couldn't do an SVN > checkout. In short: including autogen.* in the tarball (and all of its > machinery) makes "make dist" tarballs that are functional for an OMPI > developer. > > 2. We wanted to be friendly to 3rd-party vendors who have their own > out-of-tree plugins. They can take an official release tarball, add their > components into the source tree, run autogen, and be good to go. > > 3. It seemed like the Right Thing to do. > > ---- > > The question came up today on the weekly call for obscure reasons... not > worth describing here. But it raised the question, "Is there a reason we > include autogen.pl in the tarball?" > > I dug in history, and I see that autogen.sh was added here: > > https://svn.open-mpi.org/trac/ompi/changeset/17505 > > It cited the wrong Trac ticket, but I found that, too: > > https://svn.open-mpi.org/trac/ompi/ticket/1205 > > Neither of them really talks much about *why* we added autogen.sh to the > tarball. > > FWIW: > > The switch from SVN ti Git may obviate #1. > > #2 hasn't really ever occurred. Although it could happen in the future, > 3rd-party vendors can just grab from github at the right Git tag, too. > > #3 ...shrug. > > Do you have a memory of a stronger reason than #3 to keep autogen.pl in > the tarball? > > (I don't have a super strong opinion either way, I think -- perhaps 51% in > favor of removing it from the tarball, simply because we do occasionally > get the user on us...@open-mpi.org who runs autogen.pl for no reason, and > then runs into problems because they've got old Autotools) > > -- > Jeff Squyres > jsquy...@cisco.com > For corporate legal information go to: > http://www.cisco.com/web/about/doing_business/legal/cri/ > > _______________________________________________ > 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/2015/10/18289.php > -- 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
