[ofa-general] Re: [PATCHv4 RFC] Scalable Reliable Connection: API and documentation

[Michael S. Tsirkin]

> Quoting Roland Dreier <rdreier at cisco.com>:
> Subject: Re: [PATCHv4 RFC] Scalable Reliable Connection: API and documentation
> 
>  > +++ b/SRC.txt
>  > @@ -0,0 +1,138 @@
>  > +Here's some documentation on Scalable Reliable Connections.
> 
> I think this would be more useful in the man page for
> ibv_open_src_domain() (which needs to be written ;).
> 
> You know, reading over the patch, it strikes me that "src" is a very
> confusing acronym, since it really looks like an abbreviation for
> "source."  I don't know what would be better off the top of my head
> but ideas would be appreciated.

No idea.

>  > --- a/src/libibverbs.map
>  > +++ b/src/libibverbs.map
>  > @@ -24,6 +24,7 @@ IBVERBS_1.0 {
>  >  		ibv_get_cq_event;
>  >  		ibv_ack_cq_events;
>  >  		ibv_create_srq;
>  > +		ibv_create_src_srq;
>  >  		ibv_modify_srq;
>  >  		ibv_query_srq;
>  >  		ibv_destroy_srq;
>  > @@ -35,6 +36,8 @@ IBVERBS_1.0 {
>  >  		ibv_destroy_ah;
>  >  		ibv_attach_mcast;
>  >  		ibv_detach_mcast;
>  > +		ibv_open_src_domain;
>  > +		ibv_close_src_domain;
>  >  		ibv_cmd_get_context;
>  >  		ibv_cmd_query_device;
>  >  		ibv_cmd_query_port;
> 
> These new symbols definitely don't belong in the IBVERBS_1.0 ABI.  In
> fact since this all changes structure layout I think we need to create
> an IBVERBS_1.2 ABI and create compat-1_1.c to deal with it.

I actually took pains to avoid breaking the ABI, so I think we won't
need to change the version and/or create compat wrappers. No?

> Also, if we're going to change the signature of the create_srq method:
> 
>  >  	struct ibv_srq *	(*create_srq)(struct ibv_pd *pd,
>  > +					      struct ibv_src_domain *src_domain,
>  > +					      struct ibv_cq *src_cq,
>  >  					      struct ibv_srq_init_attr *srq_init_attr);
> 
> then I think we need something like
> 
> #define IBV_CREATE_SRQ_METHOD_HAS_SRC_PARAMS
> 
> so that driver libraries can still work with both old and new
> libibverbs.  I'm not sure the gain of avoiding a new entry point is
> worth forcing every driver library (even the ones that don't do SRC)
> to change -- it might be better to mimic the consumer API and just
> have a new create_srq_srq method.  That way driver libraries that
> don't do SRC would stay source compatible (I think).

Right. OK, let's do it this way.

-- 
MST