<div dir="ltr">and C) you can implement any packet scheduler using a timing wheel using virtual times.</div><br><div class="gmail_quote"><div dir="ltr">On Fri, Jul 20, 2018 at 4:09 PM Dave Taht <<a href="mailto:dave.taht@gmail.com">dave.taht@gmail.com</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><a href="https://www.files.netdevconf.org/d/46def75c2ef345809bbe/files/?p=/Evolving%20from%20AFAP%20%E2%80%93%20Teaching%20NICs%20about%20time.pdf" rel="noreferrer" target="_blank">https://www.files.netdevconf.org/d/46def75c2ef345809bbe/files/?p=/Evolving%20from%20AFAP%20%E2%80%93%20Teaching%20NICs%20about%20time.pdf</a><br>
<br>
Talking about replacing queues with timing wheels.<br>
<br>
I will refrain from commenting other than noting A) I like it. We<br>
essentially have limits in the OS on packet scheduling that make it<br>
harder and harder to have sub 2ms, much less sub 10usec, queues with<br>
the existing qdiscs and pacing systems B) that NIC support seems<br>
needed. I can think of a lot of things I'd like to have in a NIC<br>
(which certainly include default timestamping on rx and multiple kinds<br>
of X-tuple hash) - but hadn't thought about replacing queues entirely!<br>
<br>
I haven't read up on carousel yet either.<br>
<br>
Look forward to seeing the video when it comes out.<br>
<br>
-- <br>
<br>
Dave Täht<br>
CEO, TekLibre, LLC<br>
<a href="http://www.teklibre.com" rel="noreferrer" target="_blank">http://www.teklibre.com</a><br>
Tel: 1-669-226-2619<br>
_______________________________________________<br>
Make-wifi-fast mailing list<br>
<a href="mailto:Make-wifi-fast@lists.bufferbloat.net" target="_blank">Make-wifi-fast@lists.bufferbloat.net</a><br>
<a href="https://lists.bufferbloat.net/listinfo/make-wifi-fast" rel="noreferrer" target="_blank">https://lists.bufferbloat.net/listinfo/make-wifi-fast</a></blockquote></div>