[openib-general] Re: [PATCH] [CMA] RDMA CM abstraction module

[Sean Hefty]

Michael S. Tsirkin wrote:
> Yes, fine, but names like rdma_event_type probably do need the prefix,
> dont they?

I'll fix this.

> Maybe rdma_connection (these things encapsulate connectin state)?
> Or, rdma_sock or rdma_socket, since people are used to the fact that connections
> are sockets?

Any objection to rdma_socket?

>>>>+int rdma_resolve_route(struct rdma_id *id, int timeout_ms);
> 
> I was trying to say, why doesnt rdma_connect just do this
> transparently? Why do we need a separate call?

Eventually rdma_connect will call this for the user if a route hasn't been 
resolved.  At some point though, the API will likely need to be expanded to 
specify some sort of quality of service.

> What happends on the passive side?
> May we need more than one qp per rdma_id?
> Or is a new id created each time a connection request arrives?

A new identifier is created each time a connection request arrives.  The goal is 
to support a single listen across multiple devices, so listen id's will not 
necessarily be bound to an ib_device.  The new id will be bound to the device 
that the connection request was received on.

- Sean