On Mon, Jul 20, 2009 at 12:24 PM, Sasha Khapyorsky<[email protected]> wrote: > On 09:32 Mon 20 Jul , Hal Rosenstock wrote: >> >> > Wouldn't it be better instead of allocating extra memory for "disabled" >> > (0 - lash_vl_start) VLs range and tracking 'max_vl' in many places just >> > to setup lash->vl_min at end of discover_network_properties() as vl_min - >> > lash_vl_start and to increase routing_table[i].lane value by >> > lash_vl_start at end of lash cycle? >> >> Something like that could be done. Does it save significant memory >> (haven't looked yet to see exactly) ? > > Not sure about memory saving significance, but guess that this will > simplify (actually leave "as is") the flows and will keep lash core > unaffected by this addition.
Are you sure about the simplification ? It might leave lash_core flows as is but I think that the start VL pops up and complicates things elsewhere. This seemed like a pretty straightforward change to me. -- Hal >> OK as a subsequent patch to this >> change ? > > I don't think - this seems like a different approach for me. > > Sasha > _______________________________________________ general mailing list [email protected] http://lists.openfabrics.org/cgi-bin/mailman/listinfo/general To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general
