[ofa-general] Re: [PATCH 0/2] Opensm support for external routing engines

[Ira Weiny]

Hi Sasha,

Question at the bottom.

On Tue, 23 Jun 2009 22:08:15 +0300
Sasha Khapyorsky <sashak at voltaire.com> wrote:

> Hi Nicolas,
> 
> On 07:44 Fri 19 Jun     , Nicolas Morey-Chaisemartin wrote:
> > > 
> > > Eventually it is only link list with names and callbacks. It should be
> > > easy to add new entry there.
> > > 
> > I guess it could be done but are you sure the event plugin is loaded and
> > set up before the routing engine ?
> 
> Yes.
> 
> > If it is, we could make the routing_engine list a bit more dynamic.
> > However I'm not fully satisfied of the idea of inserting new engines
> > through an "event" plugin.
> 
> This called "event" for historical reasons - now it is completely generic
> plugin interface.
> 
> > We could also make this interface a bit more generic and provides the
> > means to add new features around OpenSM more easily.
> 
> For example? Reload plugin on the fly? That is fine for me.
> 
> > 
> > >> 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.
> > > 
> > 
> > Fair enough but the cost of this plugin is quite low in terms of code
> > quantity, so it shouldn't introduce too much trouble maintaning it.  And
> > as Ira, it reduces OpenSM dependencies for external algorithm.  Some of
> > ours for example  rely on PostgreSQL drivers or libdbi, some own library
> > (which uses libibnetdisc) and much more.
> 
> I understand such arguments, but up to now I didn't see any good reason to
> have more than one plugin interface in OpenSM.
> 

Does this mean you are open to the idea now?  Or are you still not convinced?

Ira