Hi Gabriele, On Wed, 14 Dec 2011 23:43:28 +0100 Gabriele Svelto <[email protected]> wrote:
> Hello all, > I was considering contributing native support for InfiniBand and other > RDMA-enabled technologies to 0MQ and wished to know if there was some > interest in it first. I have played a little bit with the project and > found it very interesting, and I think that native support for > RDMA-enabled technologies would be a nice addition to it. When you say "other RDMA-enabled technologies", does that mean there are more interconnect technologies which have adopted the IB verbs API? There appears to be some confusion / overloading of terms at least in the IB world, what I've seen is that a lot of people refer to RDMA, when what they actually mean is the native IB verbs API. If I understand it correctly RDMA in the strict sense (CPU bypass of writes to foreign memory) does not gain you much for small messages, so for example SDP will use normal packets for small transfers and RDMA for large transfers. I may have misunderstood, am still coming to grips with the technology. > [...] > So my question is: before I start working on it, is there any interest > for this? I would do it mostly for fun and because I find RDMA > networking technologies very powerful tools that are unfortunately > fairly hard to use for the non-initiated and I feel that adding > support in 0MQ would make them more accessible to a wider public. Yes, definitely. One question; at least for IB, would it not be easier and get us the same functionality if we were to add explicit AF_SDP support, by which I mean building libzmq with --with-sdp and explicit SDP addressing, e.g. sdp://<GUID>. This would allow people to use ZeroMQ without dealing with the somewhat messy details of configuring libsdp in wrapper (LD_PRELOAD) mode. Cheers, -mato -- Martin Lucina <[email protected]> _______________________________________________ zeromq-dev mailing list [email protected] http://lists.zeromq.org/mailman/listinfo/zeromq-dev
