[Openib-windows] CQ event notification in user-mode

[Fab Tillier]

> From: Sean Hefty [mailto:sean.hefty at intel.com]
> Sent: Wednesday, August 17, 2005 1:32 PM
> 
> >Allowing the user to specify a key per CQ implies that each CQ has an
> >underlying
> >file object, which may impact scalability if a user has many CQs.  Having a
> >single key for all completions on the other hand allows for a single CQ
> >completion file object (likely managed in the CA object), and the I/O request
> >would have to be used to provide per-CQ context using the OVERLAPPED
> structure
> >returned by GetQueuedCompletionStatus (provided when issuing the request).
> 
> I'm not sure how Windows implements sockets, but I believe on at least Linux
> each socket is associated with a single file object.  If Windows is similar,
> then the scalability of having a key per CQ doesn't seem any worse than what
> an
> app can expect from using TCP.  If an app wants better scalability, they can
> always use the same CQ with multiple QPs.

True, but then do you apply the same logic to connection end points?  Should
each CEP have an underlying file so that the user can implement totally
different I/O completion processing on a per-connection basis?  I'm weary of
adding in useless flexibility at the cost of scalability.  I just don't quite
know where to draw the line.

- Fab