[ofa-general] MPI IB Errors

[John Leidel]

Yeah, I'm sure the OFED release is the same.  I'm running ROCKS 4.2.1, so
all the node images are identical regarding the package selection.  There
could possibly be [well, probably] a difference in the firmware releases of
the HCAs and switches from the older machines and the latest delivery.

On 8/22/07, Jeff Squyres <jsquyres at cisco.com> wrote:
>
> This typically means that the IB kernel drivers are not loaded.  Are
> you running the same version of OFED on all of your blades?
>
>
> On Aug 22, 2007, at 4:02 PM, John Leidel wrote:
>
> > All, in adding two new blade centers full of machines to my
> > existing cluster install, I'm getting the following errors in
> > trying to run MPI jobs over MVAPICH ::
> >
> > libibverbs: Fatal: no infiniband class devices found.
> > No IB device found
> >
> > All machines are essentially the same archticture... 2.8Ghz
> > opterons.  All are running TopSpin/Cisco IB gear.  The blade
> > centers both has internal IB switches, to which I have connected to
> > our existing TopSpin core switch.  I disabled the subnet managers
> > on both blade chassis IB switches as I'm running the subnet manager
> > from the IB core switch.
> >
> >
> > Any thoughts on what is going on?
> > _______________________________________________
> > general mailing list
> > general at lists.openfabrics.org
> > http://lists.openfabrics.org/cgi-bin/mailman/listinfo/general
> >
> > To unsubscribe, please visit http://openib.org/mailman/listinfo/
> > openib-general
>
>
> --
> Jeff Squyres
> Cisco Systems
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.openfabrics.org/pipermail/general/attachments/20070822/e9168761/attachment.html>