[ofa-general] Re: [PATCH 0/2] Opensm support for external routing engines
chu11 at llnl.gov
Thu Jun 18 13:38:36 PDT 2009
On Thu, 2009-06-18 at 17:36 +0300, Sasha Khapyorsky wrote:
> On 15:54 Thu 18 Jun , Vincent Ficet wrote:
> > The idea is to include non-open source routing algorithms into opensm on
> > demand, which is permitted by the BSD license.
> It is permitted, but I don't think that we as open source community
> need to support such efforts.
I agree with this on principle, however, we already support a plugin
system that allows users to develop proprietary perfmgr plugins. So I
feel that we already are down this path.
Is the primary issue that this module "imports" new behavior into
opensm? I don't know the perfmgr plugin code that well, but my
understanding is that you can "import new behavior" into opensm via the
perfmgr plugin code too? So what is really different??
> I'm not a lawyer and cannot say for sure, but maybe in the case of dual
> GPL/BSD license choice you will need anyway to relicense and to
> redistribute OpenSM for doing this.
> > It also enables to try a new algorithm on the fly without having to
> > reinstall opensm, which can prove useful on a running cluster.
> Even with your patches you will need to restart OpenSM, so it should not
> be a big deal to build and run OpenSM even on a running cluster
> especially if you are going to experiment with new routing engines.
> Alternatively you can load routing tables from file.
> > The event-based perfmgr plugin does not make it easy to integrate a new
> > routing algorithm because the list of available routing algorithms is
> > statically declared.
> Eventually it is only link list with names and callbacks. It should be
> easy to add new entry there.
> > AFAIK, the latest Voltaire UFM also includes or will include proprietary
> > routing algorithms (mesh + fat tree), so it could also be useful for
> > Voltaire.
> I don't know about this, but even if it is so. It is not our charter as
> open source project to care about such practices and they (UFM) will need
> to support their stuff by themselves.
> general mailing list
> general at lists.openfabrics.org
> http:// lists.openfabrics.org/cgi-bin/mailman/listinfo/general
> To unsubscribe, please visit http:// openib.org/mailman/listinfo/openib-general
chu11 at llnl.gov
High Performance Systems Division
Lawrence Livermore National Laboratory
More information about the general