Michael S. Tsirkin wrote: > It is somewhat unfortunate that we are duplicating the SA logic > at the endnode in kernel memory here - current sa module has > the advantage in that it just packs all data into a mad and sends it out. > Something to think about.
What alternative do you propose? The SA does reference counting on a per port basis, so joins must be handled locally. How can you avoid duplicating that logic? If a user truly only wants to query for an existing group, those requests must still go to the SA. - Sean _______________________________________________ openib-general mailing list openib-general@openib.org http://openib.org/mailman/listinfo/openib-general To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general