RE: verb spec clarification

The verbs are not an IETF document. Under the current consensus
they will not be.

However, the security draft does assume that inbound RDMA
Read Requests do consume a resource, and that the ULP should
be tracking these resources.

In that spirit, the length of the payload for an RDMA Read
does not affect its ordering within a sequence of RDMA Reads.
Therefore it requires the same resource support as any other
RDMA Read request, and would count toward the same credit limit.
The fact that there is not payload, and no validation of the
data source STag, does not mean it is not a "real" RDMA Read.
 

> -----Original Message-----
> From: [email protected] [mailto:[email protected]] On 
> Behalf Of Patricio Kaplan
> Sent: Monday, March 28, 2005 11:07 AM
> To: [email protected]
> Subject: [rddp] verb spec clarification
> 
> Section 9.2.5.1 states that QPs have Inbound RDMA Read enable 
> and Inbound RDMA Write and inbound RDMA Read Response enable.
>  
> Does the  inbound RDMA Read Response enable check apply to a 
> zero length read response?
> 
> Thanks,
> -Patricio
> 
> _______________________________________________
> rddp mailing list
> [email protected]
> https://www1.ietf.org/mailman/listinfo/rddp
>