[openib-general] RE: [RFC] DAT 2.0 immediate data proposal

[Sean Hefty]

Davis, Arlin R wrote:
> *Maybe we need to just go back to one model and always deliver via the 
> event? With the post_recv_immed requirements, other transports have a 
> mechanism to emulate and create the necessary resources on the recv side 
> to place idata and copy to event when operation is completed. Would this 
> work for iWARP?*

You don't want post_recv_immed.  The receiver shouldn't have to indicate whether 
a receive will get immediate data or not.

> 12. Is your intension that post_recv_immed can ONLY except immediate 
> data and is not capable to recv any message?
> 
> *No, the intention is to extend the post_recv to handle 32bit idata 
> which may arrive with or without other send or rdma_write data.*
> 
> *Does it make more sense to add a dto_flags to the existing post_recv?*

This looks like an API designed around hardware that doesn't support immediate 
data, rather than one that actually does.  Post_recv_immed doesn't map to IB.

- Sean