> -----Original Message----- > From: Tillier, Fabian > Sent: Thursday, January 06, 2005 4:36 PM > To: 'Roland Dreier'; 'Hal Rosenstock' > Cc: [email protected] > Subject: RE: [openib-general] Re: IPoIB Path Static Rate > > > > From: Roland Dreier [mailto:[EMAIL PROTECTED] > > Sent: Saturday, December 18, 2004 7:47 AM > > > > I don't object in principle to doing this right, it just > seems like a > > fair bit of work to write code to retrieve the local PortInfo to get > > the active link speed and link width so that we can calculate our > > local rate and get the right IPD. > > > > To solve this, do you think it makes sense to add the active link > > speed and link width to struct ib_port_attr so that it's > easy for ULPs > > to get them? Otherwise ULPs would have to do their own > PortInfo queries. > > > > Why not just let clients specify the static rate in the AV, > rather than the > IPD, and have the HCA driver figure out the right IPD based > on information > it can easily cache? > > - Fab Yes, that would better align with the information the CM and the applications would have available to them from the SA (both CM and SA packets use Static Rate, not IPD). Also IPD can be hardware dependent, for example mt23108 silicon uses a single bit rather than a IPD value. So it would be most efficient to translate only once (eg. from Static rate available in Path Record or CM REQ to what ever format the hardware used for Static Rate/IPD).
Todd R. > > _______________________________________________ > openib-general mailing list > [email protected] > http://openib.org/mailman/listinfo/openib-general > > To unsubscribe, please visit > http://openib.org/mailman/listinfo/openib-general > _______________________________________________ openib-general mailing list [email protected] http://openib.org/mailman/listinfo/openib-general To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general
