On Mon, 2005-10-17 at 13:01, Sean Hefty wrote: > Hal Rosenstock wrote: > > Yes, but why not ? (I think that was also part of your change). > > The agent code now allocates a buffer for the MAD by calling > ib_create_send_mad(). The input MAD buffer is copied to the send buffer, > then > transmitted. The result is that the input MAD buffer is always available for > posting on the receive queue.
What about the other resources needed ? Are they always available ? > > At least, the errors should be indicated with printk's so it can be seen > > in the log what failure occured in agent_send_response (like failed > > ib_create_ah_from_wc or ib_create_send_mad or ib_post_send_mad). > > IMO, the print statements would be better placed in agent_send_response(), > which > knows the context surrounding the failure, than by a caller. That's what I was suggesting (but I didn't see them in your updated patch). > I'm fine with having the function return a value, but the return value will > still be ignored by mad.c. I will change the function from void to int > though, > so that a caller will be aware that a failure did occur. OK. -- Hal _______________________________________________ openib-general mailing list [email protected] http://openib.org/mailman/listinfo/openib-general To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general
