From mboxrd@z Thu Jan 1 00:00:00 1970 From: jamal Subject: RE: FW: Submission for S2io 10GbE driver Date: 25 Jan 2004 14:14:42 -0500 Sender: netdev-bounce@oss.sgi.com Message-ID: <1075058082.1746.85.camel@jzny.localdomain> References: <002501c3e2b5$543c45e0$0400a8c0@S2IOtech.com> Reply-To: hadi@cyberus.ca Mime-Version: 1.0 Content-Type: text/plain Content-Transfer-Encoding: 7bit Cc: netdev@oss.sgi.com Return-path: To: Leonid Grossman In-Reply-To: <002501c3e2b5$543c45e0$0400a8c0@S2IOtech.com> Errors-to: netdev-bounce@oss.sgi.com List-Id: netdev.vger.kernel.org On Sat, 2004-01-24 at 15:04, Leonid Grossman wrote: > These schemes could be complimentary, right now we do see that different > thresholds need to be programmed for regular and Jumbo traffic. > > One thing I did not mention is that our ASIC supports several > utilization thresholds on per interrupt basis (up to 64 MSI-X > interrupts). There are also independent tx and rx queues, and each can > have it's own interrupt. There is a pretty large number of parameters > that traffic could be steered upon, packet size is one of them. > Would be interesting to see what these queue selection parameters are. For example, an extremely important thing to avoid is reordering of packets. You reorder packets on a TCP flow and you perfomance goes beserk. > So, if you want to have different interrupt moderation schemes for > different packet sizes, you just need to steer packets to separate > queues based upon size, and then assign a separate MSI interrupt to > these queues and set different utilization thresholds for different > interrupts. At any given workload, you will be getting interrupts at > different rate for small and for big packets. Does sound interesting, but i am suspcious about reordering; i.e you dont want a 64 byte packet from one flow to be in a different queue than another which is 1500 bytes. The 2 packet must be processed strictly in FIFO manner. > Anyway, you are right there are many interrupt moderation schemes that > host driver can deploy, our goal was to provide a flexible hardware > assist. So is it possible to program it such that if a threshold interupt rate is crossed it adjusts its mitigation values? actually i should say its the second order effect that is of interest to the threshold i.e the integral of the interupt arrival rate. cheers, jamal