On Thu, 2006-05-04 at 13:54, Sean Hefty wrote:
> Hal Rosenstock wrote:
> >>To me, this feature seems most useful for all-to-all type connections, but 
> >>would 
> >>require some sort of coordination between connecting end-points in order to 
> >>have 
> >>fault independent connections between different nodes.  E.g. the connection 
> >>from 
> >>A to B is independent from the connection between C and D.
> > 
> > I don't understand what end node coordination you are referring to here
> > in terms of this.
> 
> Today, connections are established from the local node to some given 
> destination 
> without considering what other connections may exist between other nodes.  
> For 
> example, an app may select a path to connect A to B based on the connection 
> from 
> C to D.

So each node needs to know the entire connection mesh (and traffic
pattern) to help it choose a path ? I'm not sure how MPR v. PR relates
to this exactly other than there is a current difference in how the half
world paths would be obtained using MPR v. PR.

> I'm just trying to determine how an implementation can make use of MPR to 
> understand the best way to expose it.  The use of MPR over just path records 
> seems complex.

In terms of what ?

-- Hal

> - Sean

_______________________________________________
openib-general mailing list
[email protected]
http://openib.org/mailman/listinfo/openib-general

To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general

Reply via email to