<div dir="ltr"><div dir="ltr"><div dir="ltr"><div dir="ltr"><div dir="ltr">On Sat, Aug 24, 2019 at 9:59 AM Sebastian Moeller <<a href="mailto:moeller0@gmx.de">moeller0@gmx.de</a>> wrote:<br></div><div class="gmail_quote"><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">Another nugget from the notes (<a href="http://yuba.stanford.edu/~bspang/buffer-sizing-meeting/notes/" rel="noreferrer" target="_blank">http://yuba.stanford.edu/~bspang/buffer-sizing-meeting/notes/</a>):<br>
<br>
This looks like an argument for fq_codel/cake's use of time instead of queue length, OR an argument for fq, because in a non-overwhelmed fq_system the local bucket's queue length should be somewhat stronger correlated with the sojurn times, than the sojurn time of a packet though a shared queue, no?<br></blockquote><div><br></div><div>I believe that using fq there are good implications in terms of buffer sizing rules.</div><div>The focus is only on backlogged flows. The sparse flow queue can be sized purely based on queue load.</div><div>Which is trivial queuing theory formulas with non-TCP traffic.</div><div><br></div><div>For backlogged flows, sizing is just like sizing a buffer for a single TCP flow. So the computation</div><div>can be done based on estimations of the number of backlogged flows and by setting the cut-off BDP based on the </div><div>largest (maximum) min RTT one want to serve optimally. So AQM is really needed to get optimality.</div><div>The number of backlogged flows could be estimated as a max value or an avg value, and this of course </div><div>changes depending on the network segment (DC, residential, campus, access, backhaul etc.).</div><div><br></div><div>Nick McKeown has done quite a lot of research on the topic (reported in the slide deck), so I find hilarious the following in his slide deck<br></div><div>"Personal confession: I have no idea what the general answer is" about sizing buffers!</div></div></div></div></div></div>