[openib-general] Re: Re: ibv_get_async_event

[Michael S. Tsirkin]

Quoting r. Sean Hefty <mshefty at ichips.intel.com>:
> Subject: Re: Re: ibv_get_async_event
> 
> Sean Hefty wrote:
> >I think that this would work well.  I will update the uCM put event to 
> >match.
> 
> After looking at the uCM more, changing from it's current model of 
> put_event to ack_events would require changes to the get_event, which 
> requires changes to the ib_cm_event structure.  I think that having 
> matching event models across IB interfaces is ideal, but it requires 
> re-working a fair portion of the uCM event processing.  How important do 
> others feel that this is?

I dont think its too important: I think Roland added multiple events as
a performance optimization for completion events.
CM speed isnt that critical a data path IMO to really need
such an optimization.

-- 
MST