<div dir="ltr">Here is a pretty good list but it's focused on data center and carrier networking gear, not so much home networking gear:<div><br></div><div><a href="https://people.ucsc.edu/~warner/buffer.html">https://people.ucsc.edu/~warner/buffer.html</a><br></div><div><br></div><div>/Jonas</div></div><br><div class="gmail_quote"><div dir="ltr" class="gmail_attr">On Wed, Mar 9, 2022 at 6:39 PM Michael Menth <<a href="mailto:menth@uni-tuebingen.de">menth@uni-tuebingen.de</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">Hi all,<br>
<br>
I don't question the usefulness of AQMs for buffers - on the contrary. <br>
But what are up-to-date buffer sizes in networking gears, especially if <br>
AQMs are not in use? It's hard to find public and information about it. <br>
Anyone can point to a citable source?<br>
<br>
This raises also the question about the deployment of AQMs in networking <br>
infrastructure. I know it's already adopted by some OSs, but what about <br>
forwarding nodes? Any papers about it?<br>
<br>
Kind regards<br>
<br>
Michael<br>
<br>
Am 09.03.2022 um 18:24 schrieb Jesper Dangaard Brouer:<br>
> <br>
> <br>
> On 09/03/2022 17.31, Toke Høiland-Jørgensen via Bloat wrote:<br>
>> Michael Menth <<a href="mailto:menth@uni-tuebingen.de" target="_blank">menth@uni-tuebingen.de</a>> writes:<br>
>><br>
>>> Hi all,<br>
>>><br>
>>> are there up-to-date references giving evidence about typical buffer<br>
>>> sizes for various link speeds and technologies?<br>
>><br>
>> Heh. There was a whole workshop on it a couple of years ago; not sure if<br>
>> it concluded anything: <a href="http://buffer-workshop.stanford.edu/program/" rel="noreferrer" target="_blank">http://buffer-workshop.stanford.edu/program/</a><br>
>><br>
>> But really, asking about buffer sizing is missing the point; if you have<br>
>> static buffers with no other management (like AQM and FQ) you're most<br>
>> likely already doing it wrong... :)<br>
> <br>
> Exactly, I agree with Toke. The important parameter is the latency.<br>
> Or the packet sojourn time (rfc8289 + rfc8290) observed waiting in the <br>
> queue.<br>
> <br>
> The question you should be asking is:<br>
> - What is the max queue latency I'm "willing" to experience on this link?<br>
> <br>
> Hint, you can then depending on the link rate calculate the max buffer <br>
> size you should configure.<br>
> <br>
> The short solution is:<br>
> - just use fq_codel (rfc8290) as the default qdisc.<br>
> <br>
> --Jesper<br>
> <br>
> <br>
> <br>
<br>
-- <br>
Prof. Dr. habil. Michael Menth<br>
University of Tuebingen<br>
Faculty of Science<br>
Department of Computer Science<br>
Chair of Communication Networks<br>
Sand 13, 72076 Tuebingen, Germany<br>
phone: (+49)-7071/29-70505<br>
fax: (+49)-7071/29-5220<br>
mailto:<a href="mailto:menth@uni-tuebingen.de" target="_blank">menth@uni-tuebingen.de</a><br>
<a href="http://kn.inf.uni-tuebingen.de" rel="noreferrer" target="_blank">http://kn.inf.uni-tuebingen.de</a><br>
_______________________________________________<br>
Bloat mailing list<br>
<a href="mailto:Bloat@lists.bufferbloat.net" target="_blank">Bloat@lists.bufferbloat.net</a><br>
<a href="https://lists.bufferbloat.net/listinfo/bloat" rel="noreferrer" target="_blank">https://lists.bufferbloat.net/listinfo/bloat</a><br>
</blockquote></div>