>can't anyone get async modify QP today on any platform by just doing the >operation in another thread (or thread pool)? It seems that the >operations themselves are heavy enough that thread dispatch, locking etc >is going to be significant overhead.
On WinOF this is basically how things are implemented anyway. The lower level drivers are ports of the Linux drivers and do everything synchronously. The kernel uverbs equivalent just queues the modify calls to a kernel thread pool. It's not as efficient as it could be, since it ends up adding two context switches, but works. I could try adding threads to the librdmacm, move the modify calls to those threads, and see if there's any difference. - Sean _______________________________________________ ewg mailing list ewg@lists.openfabrics.org http://lists.openfabrics.org/cgi-bin/mailman/listinfo/ewg