[openib-general] Question

[Hal Rosenstock]

On Mon, 2005-02-28 at 17:40, Ronald G. Minnich wrote:
> On Mon, 28 Feb 2005, Hal Rosenstock wrote:
> 
> > What is the definition of "opensm won't work at all ?" I am presuming
> > that somehow the ports are not brought to active. Is that it or
> > something else ?
> 
> [1109361464:000221781][411FF970] -> umad_receiver: send completed with 
> error(method=1 attr=11) -- dropping.
> 
> I got to 13482 of these and gave up.

That's a Get NodeInfo. So much for my theory. Wonder which node it is
going after that was not responding. What's failing is that this code is
matching the response with the request so either the request does not
make it there or the response does not make it back. This is all with
direct routed MADs.

Also, wasn't that the same failure as a while ago when one of those 96
port switches kept forwarding but didn't terminate MADs ? (Yes, I know
you recycled everything which would seem to be inconsistent with this).

> > Can you provide the salient part of the logs ? How was OpenSM invoked ?
> > Was it with -V ?
> 
> opensm -v

I'm not sure we will see anything more from the logs than the error. Is
there anything before the first error ? Can you also rerun with -V and
look for the same ?

I think I will need the output from ibnetdiscover and the failing direct
route header from the request. (I work on generating a patch for this).

-- Hal

> > The difference is that ibnetdiscover only performs gets whereas OpenSM
> > does both gets and sets.
> 
> ah!
> 
> ron