Re: [ofw] Re: [ewg] RE: SC'09 BOF - Meeting notes and Final Slides

2009-11-23 Thread Roland Dreier
> Why should clients have to emulate asynchronous behavior when the > (Mellanox) HCA command interface is already asynchronous? That's one HCA command model... others may not be (eg I believe ehca makes synchronous hypercalls to do things like modify QP, and ipath is pure software with no other

RE: [ofw] RE: [ewg] RE: SC'09 BOF - Meeting notes and Final Slides

2009-11-19 Thread Sean Hefty
>> I could try adding threads to the librdmacm, move the modify calls to >> those threads, and see if there's any difference. > >You'll still need to have the kernel thread pool to support WinVerbs (at least >on Windows.) I was only referring to Linux, and only for testing to see how much differen

RE: [ofw] RE: [ewg] RE: SC'09 BOF - Meeting notes and Final Slides

2009-11-19 Thread Fab Tillier
Hi Sean Sean Hefty wrote on Thu, 19 Nov 2009 at 11:53:56 >> 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 si

RE: [ofw] Re: [ewg] RE: SC'09 BOF - Meeting notes and Final Slides

2009-11-19 Thread Fab Tillier
Hi Roland Roland Dreier wrote on Thu, 19 Nov 2009 at 11:19:02 > >> WinOF has asynchronous interfaces for modify QP, and limited testing >> has shown that it can improve connection times. QP transitions are >> probably the second largest component of connection setup after the SA. >> Since the