[openib-general] IPoIB broadcast MC group membership

[Hal Rosenstock]

On Tue, 2006-02-21 at 12:08, Fabian Tillier wrote:
> On 21 Feb 2006 11:23:45 -0500, Hal Rosenstock <halr at voltaire.com> wrote:
> > Hi Fab,
> >
> > On Tue, 2006-02-21 at 11:15, Fabian Tillier wrote:
> > > On 21 Feb 2006 09:42:10 -0500, Hal Rosenstock <halr at voltaire.com> wrote:
> > > > On Tue, 2006-02-21 at 01:10, Fabian Tillier wrote:
> > > > > The lack of detailed error reporting in SA queries could stand to be
> > > > > improved, and something as simple as the SA returning a component mask
> > > > > indicating which components caused conflicts would be extremely useful
> > > > > in determining the next course of action.
> >
> > Or at least 1 component mask bit of a conflict...
> >
> > Interesting idea :-)
> 
> If I were to write something up as an enhancement to the spec, which
> working group would it be submitted to,

MgtWG

>  and do you want to help?

Sure. I'd be happy to help improve the spec :-)

> I don't know if SMs today clear the component mask in responses or
> just leave it as the component mask of the request, but it would be
> great to find a way that is backward compatible.

I think I see where you are headed with this.

The CM header description for SA header only indicates SA operations and
does not appear to distinguish between queries and responses and most
importantly errors. There is some additional informative text on p.925
on its use during read, set, or delete operations but not event
forwarding. Based on that, I suspect it technically is not backward
compatible as there is no statement on CM in error cases.

-- Hal

> - Fab