[openib-general] Re: [PATCH][RFC][0/4] InfiniBand userspace verbs implementation

Roland Dreier roland at topspin.com
Mon Apr 25 16:58:03 PDT 2005


    Andrew> ug.  What stops the memory from leaking if the process
    Andrew> exits?

    Andrew> I hope this is a privileged operation?

I don't think it has to be privileged.  In my implementation, the
driver keeps a per-process list of registered memory regions and
unpins/cleans up on process exit.

    Andrew> It would be better to obtain this memory via a mmap() of
    Andrew> some special device node, so we can perform appropriate
    Andrew> permission checking and clean everything up on unclean
    Andrew> application exit.

This seems to interact poorly with how applications want to use RDMA,
ie typically through a library interface such as MPI.  People doing
HPC don't want to recode their apps to use a new allocator, they just
want to link to a new MPI library and have the app go fast.

 - R.




More information about the general mailing list