[ofa-general] Re: [mwg] Re: RDMA tutorial and OFA

[Andy Grover]

Todd Rimmer wrote:
> It goes beyond just a tutorial.

> In talking to customers, the consensus is that many application
> programmers struggle with sockets, RDMA is an order of magnitude
> beyond that.  It's not a cut on programmers, there are some very
> strong ones in the enterprise, but a fair percentage only have
> associate degrees or technical school training.  Even the extremely
> smart ones have 100 things to juggle (and often must write code such
> that entry level programmers can support it), so the risk/reward or
> ROI of learning RDMA has to be there.  The higher the learning cost
> the more difficult to justify the effort.

Totally agree.

Someone emailed me off-list and mentioned he had proposed an RDMA/IB
book to a few publishers and been turned down. (!?!) Don't know if that
would still be the case but it means there's a lot of work to do
increasing the technology's mindshare and perceived relevance to a lot
of developers, and the OFA and its members need to get the ball rolling
before we can expect the "... for Dummies" people to want to write a
book about RDMA :-)

> simplified APIs and easy
> migration of applications

> accessibility in scripting languages and other languages

Both of these would be great, and I think go together -- a C# RDMA API
is going to be more accessible to a C# programmer first just because
it's in the right language, but also handle many boilerplate sections of
code on behalf of the user, presenting a simpler API than the C API.

> - good simple examples of how to do it, sample programs etc

Yes I would think this could be in the Tutorial, or a Cookbook section?

> - connection establishment is still difficult in OFED.  Also many
> apps are shortcutting the process by avoiding SA queries (hence
> impacting the ability of the applications to work properly with QOS,
> LMC, complex fabrics (torus, etc), Partitioning, etc). - either the
> Base API needs to improve or "helper libraries" are needed on top of
> it.

Could go in the language wrapper libs. A helper lib for C API itself
also might be nice, yes.

> - effective tools to debug applications.

True!

Regards -- Andy