On Mon, Oct 31, 2005 at 10:24:05AM -0700, Galen M. Shipman wrote:
> Gleb
>
> Yes, yes it is.. This was causing RNR NAK problems!
>
RNR problem is exactly how I found this :)
> Thanks,
>
> Galen
>
>
> On Oct 31, 2005, at 9:57 AM, Gleb Natapov wrote:
>
> >
> > Index: ompi/mca/btl/openib/btl_openib_component.c
> > ===================================================================
> > --- ompi/mca/btl/openib/btl_openib_component.c (revision 7935)
> > +++ ompi/mca/btl/openib/btl_openib_component.c (working copy)
> > @@ -165,7 +165,7 @@
> > mca_btl_openib_param_register_int("ib_retry_count", "IB
> > transmit retry count",
> > 7, (int*)
> > &mca_btl_openib_component.ib_retry_count);
> > mca_btl_openib_param_register_int("ib_rnr_retry", "IB rnr retry",
> > - 7, (int*)
> > mca_btl_openib_component.ib_rnr_retry);
> > + 7, (int*)
> > &mca_btl_openib_component.ib_rnr_retry);
> > mca_btl_openib_param_register_int("ib_max_rdma_dst_ops", "IB
> > max rdma destination operations",
> > 16, (int*)
> > &mca_btl_openib_component.ib_max_rdma_dst_ops);
> > mca_btl_openib_param_register_int("ib_service_level", "IB
> > service level",
> > --
> > Gleb.
> > _______________________________________________
> > devel mailing list
> > de...@open-mpi.org
> > http://www.open-mpi.org/mailman/listinfo.cgi/devel
> >
>
> _______________________________________________
> devel mailing list
> de...@open-mpi.org
> http://www.open-mpi.org/mailman/listinfo.cgi/devel
--
Gleb.
