19:51:05 <sommerfeld> n4rfblatt
20:33:07 <jbk> a bit of a random question, has there been any thought of an api (e.g. maybe setsockopt() parameter) to hint to the kernel to use a particular tx ring?
20:33:35 <jbk> or maybe to put it a bit more generic so you can just make sure a certain set of sockets are fanned out as much as you can
20:34:02 <jbk> (IIRC, right now it all ends up being how mac hashes things to a ring)
20:34:58 <jbk> so can't really control two sockets hashing to the same ring
20:36:41 <jbk> at least i'm not aware of any way to do it
21:16:00 <sommerfeld> jbk: linux has something in that space -- "transmit packet steering" aka "XPS".   Basically map CPU to TX ring. 
21:19:06 <sommerfeld> I seem to remember someone then doing a benchmark special where they selected the local port in TCP connect() such that the response traffic came back to the same CPU (they could predict the flow-hashing done in the last-hop switch and NIC).
21:20:30 <sommerfeld> otherwise for N rings you need something like N^2 flows to let things level out..
21:32:20 <kebe> Reminds me of when I launched iperf clients on sequential local-ports just to remove the entropy from everything.  (Might've been at Nexenta...)
22:05:43 <Reinhilde> :D
23:08:58 <toasterson> sommerfeld: didn't oxide implment that for illumos? I remember a repo of similar name or am I mixing it up with another linux thing starting with X?