[ofa-general] IB credit-based flow control

[Andy Grover]

Sean Hefty wrote:
>> So, why is it necessary for a ULP like RDS to implement its own flow
>> control? It looks like IB's flow control should result in no RNR
>> retries, yet without protocol-level FC, we see RNR retries.
> 
> If you're using a shared receive queue, end to end flow control is disabled.
> Also, see 9.7.7.2.5 C9-162 - an HCA is allowed to send up to one packet for a
> send request even if it doesn't have any credits available.

Good point, but just looking at the non-SRQ case:

I'm reading C9-162 and still not seeing why (according to the spec 
anyways) there should ever be RNR retries on a connection. I would think 
the receiving HCA would not credit its last WQE to the sender, and thus 
retries should never happen?

The whole point of this feature is to eliminate RNR retries, no?

Thanks -- Regards -- Andy