[Openib-windows] RE: IB Diagnositic Tools

Hal Rosenstock halr at voltaire.com
Tue Jun 28 06:10:34 PDT 2005


On Tue, 2005-06-28 at 07:30, Eitan Zahavi wrote: 
> > > [EZ] How would you define the internal structure of a 288port
> switch
> > > in the existing topology file?
> > > Would it support writing code that is able to report something
> like
> > > "board spine2 of system mySwitch is missing"?
> > 
> > I think it could.
> [EZ] Anyway this capability already exists in IBDM. So why re-develop
> it again?

IBDM is not available for OpenIB as yet and the OpenIB diagnostics have
been in place for a while now. 

Also, as far as I know, no one outside of Mellanox has looked at this.
So that would be a next step. 

Is there any documentation on IBDM ?

Also, are there updates to this or is the version in the tree what
should be looked at (and commented on) ?

> Also you did not answer the first question.

By using the comment fields appropriately with semantics for logical
hierarchy. 

> Is the implementation open to support definition of hierarchical
> internal IB network like the one embedded in a 288port switch?

Yes.

> > > The code that supports all that is part of the simulator code I
> have
> > > posted long ago.
> > > Please give it a look. Especially the Fabric.h, SysDef.h,
> > > ibnl_parser.yy in
> > > https://openib.org/svn/gen2/utils/src/linux-user/ibdm/datamodel
> > 
> > Why part of the simulator ? Will these be part of the to be released
> > diagnostics ?
> [EZ] It was uploaded with the simulator. It is a separate library:
> IBDM.
> The simulator uses it to define the topology that is simulated.

OK.

> > > > This brings in more things that are not currently ported to
> OpenIB
> > > and
> > > > also there are some issues with some of these tools.
> > > [EZ] Never heard of any specific issue. Can you describe these
> issues?
> > 
> > I'm pretty sure they were discussed on this list before perhaps
> quite a
> > while ago.
> [EZ] If nobody remembers what they were maybe they are not so subtle
> and critical?

IMO that was not the case. I don't have the time to go dig these back
out right now.

-- Hal




More information about the ofw mailing list