Quoting r. Eli cohen <[EMAIL PROTECTED]>: > Also there is a need to implement peek_cq and call it for > ib_req_notify_cq() so as to know if there is a need to call > netif_rx_schedule_prep() again.
Thanks, Eli. Implementing peek_cq is not hard, at least for mthca. I wander what we should do if peek_cq is not available in the low level driver. I guess we could just disable NAPI for this case - Roland, would that be acceptable? -- MST _______________________________________________ openib-general mailing list [email protected] http://openib.org/mailman/listinfo/openib-general To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general
