[openib-general] problems with lustre o2ib module & ofed

[Thierry Delaitre]

On Mon, 25 Sep 2006, Jack Morgenstein wrote:

> On Monday 25 September 2006 09:58, Or Gerlitz wrote:
> > Jack Morgenstein wrote:
> > > Did you recompile Lustre following the installation of ofed-1.1?
> > > I'm not familiar with the Lustre installation procedure (i.e., if it
> > > gets compiled on the current host).  If yes, you probably merely need
> > > to uninstall and reinstall Lustre o2ib.
> >
> > OK, can we state clearly what's the user needs to do with modules
> > directly dependent on ofed symbols (eg Lustre's o2ib, NFSoRDMA, RDS and
> > hopefully more to come).
> >
> > Is it recompile / uninstall / install ???
>
> If possible:
>  - recompile (make) and reinstall to kernel (make install) Lustre o2ib
>
> Otherwise:
>  - uninstall and reinstall onto the host Lustre o2ib (assuming that
> 	the Lustre installation compiles its modules on that host
> 	during the installation process and then installs them,
> 	rather than just copying over pre-compiled modules to
> 	/lib/modules/<kernel version>/drivers/kernel/infiniband
> >
> > > On Sunday 24 September 2006 12:57, Thierry Delaitre wrote:
> > >> I get the following when loading lustre o2ib module. I'm using ofed-1.1
> > >> rc6 on sles10 and i'm sure the ib modules are the ones recompiled for the
> > >> kernel i'm using and lustre too. I don't understand why i get the
> > >> following as i only have one version of the ib modules ?
>
> This is a bit unclear.  Was Lustre installed AFTER the OFED installation?

1) patch kernel with lustre patches and recompile/install kernel
2) boot with new kernel
3) make + install ofed-1.1-rc6
4) depmod -a
5) compile + install lustre (lustre was installed after ofed installation)
6) depmod -a
7) modprobe lnet
8) lctl network up.

in step (5), lustre was configured as follows:
./configure --with-o2ib=/usr/local/ofed/src/openib-1.1/

Thierry.