[{"author": "Gorry Fairhurst", "text": "

Greetings Jana!

", "time": "2022-07-28T20:02:44Z"}, {"author": "Nick Banks", "text": "

Yes

", "time": "2022-07-28T20:04:07Z"}, {"author": "Stephen Strowes", "text": "

yes!

", "time": "2022-07-28T20:04:07Z"}, {"author": "Jonathan Lennox", "text": "

I see your screen in the room

", "time": "2022-07-28T20:04:13Z"}, {"author": "Nick Banks", "text": "

Yes, we can hear

", "time": "2022-07-28T20:04:39Z"}, {"author": "Asad Saeed", "text": "

we can hear you

", "time": "2022-07-28T20:04:46Z"}, {"author": "Neal Cardwell", "text": "

I'll take notes...

", "time": "2022-07-28T20:07:21Z"}, {"author": "Neal Cardwell", "text": "

Yep.

", "time": "2022-07-28T20:07:35Z"}, {"author": "Neal Cardwell", "text": "

Sure, you bet!

", "time": "2022-07-28T20:07:38Z"}, {"author": "Neal Cardwell", "text": "

I'm not seeing Bob's slides...

", "time": "2022-07-28T20:09:10Z"}, {"author": "Neal Cardwell", "text": "

Anyone else have this issue?

", "time": "2022-07-28T20:09:15Z"}, {"author": "Lucas Pardue", "text": "

I had to reload the tab

", "time": "2022-07-28T20:09:23Z"}, {"author": "Michael T\u00fcxen", "text": "

I can see them

", "time": "2022-07-28T20:09:24Z"}, {"author": "Anna Brunstrom", "text": "

No, I see them

", "time": "2022-07-28T20:09:26Z"}, {"author": "Richard Patterson", "text": "

yeah, no slides here either

", "time": "2022-07-28T20:09:27Z"}, {"author": "Jonathan Morton", "text": "

make sure you're in Presentation mode, leftmost of the top-right icons

", "time": "2022-07-28T20:09:47Z"}, {"author": "Jana Iyengar", "text": "

The slides are online, you can follow along in case you can't get this working

", "time": "2022-07-28T20:10:00Z"}, {"author": "Jana Iyengar", "text": "

We're on slide 3

", "time": "2022-07-28T20:10:04Z"}, {"author": "Neal Cardwell", "text": "

Yep, I'm in presentation mode and just following along in the PDF

", "time": "2022-07-28T20:11:37Z"}, {"author": "Jana Iyengar", "text": "

slide 4

", "time": "2022-07-28T20:11:47Z"}, {"author": "Hang Shi", "text": "

What is ECN-Cubic? Does Cubic react to ECN?

", "time": "2022-07-28T20:12:01Z"}, {"author": "Neal Cardwell", "text": "

Yes, it can. In Linux TCP it will.

", "time": "2022-07-28T20:12:16Z"}, {"author": "Jonathan Morton", "text": "

it's just standard Linux CUBIC with ECN enabled, I assume

", "time": "2022-07-28T20:12:28Z"}, {"author": "Neal Cardwell", "text": "

Yes, Linux CUBIC with RFC3168 ECN causing the cwnd reductions.

", "time": "2022-07-28T20:12:55Z"}, {"author": "Jonathan Morton", "text": "

it's one of those things which \"just works\" if you flip the switch

", "time": "2022-07-28T20:13:01Z"}, {"author": "Hang Shi", "text": "

Got it. Thx

", "time": "2022-07-28T20:13:12Z"}, {"author": "Hang Shi", "text": "

Brilliant idea!

", "time": "2022-07-28T20:16:38Z"}, {"author": "Jonathan Morton", "text": "

so far we've only been shown the ideal conditions; believe me things get more complicated than this

", "time": "2022-07-28T20:18:39Z"}, {"author": "Hang Shi", "text": "

Will iOS 16 ship with TCP Prague?

", "time": "2022-07-28T20:23:08Z"}, {"author": "Jonathan Morton", "text": "

I doubt it

", "time": "2022-07-28T20:23:52Z"}, {"author": "Matt Joras", "text": "

fwiw this testing is with QUIC, not TCP afaik. I don't know if they actually implemented Prague in TCP?

", "time": "2022-07-28T20:23:53Z"}, {"author": "Jana Iyengar", "text": "

Oh hm. I assumed this was TCP

", "time": "2022-07-28T20:24:16Z"}, {"author": "Jana Iyengar", "text": "

Yup, QUIC.

", "time": "2022-07-28T20:25:03Z"}, {"author": "Neal Cardwell", "text": "

what slide are we on now with Bob?

", "time": "2022-07-28T20:29:55Z"}, {"author": "Lucas Pardue", "text": "

8

", "time": "2022-07-28T20:30:03Z"}, {"author": "Jonathan Morton", "text": "

8, apparently

", "time": "2022-07-28T20:30:06Z"}, {"author": "Neal Cardwell", "text": "

thanks!

", "time": "2022-07-28T20:30:08Z"}, {"author": "Jonathan Morton", "text": "

this is a really badly labelled set of graphs

", "time": "2022-07-28T20:32:37Z"}, {"author": "Neal Cardwell", "text": "

Agreed ... :-)

", "time": "2022-07-28T20:32:53Z"}, {"author": "Jonathan Morton", "text": "

slide 9

", "time": "2022-07-28T20:33:28Z"}, {"author": "Jana Iyengar", "text": "

slide 10

", "time": "2022-07-28T20:36:01Z"}, {"author": "Neal Cardwell", "text": "

what's the metric graphed on the top row, again?

", "time": "2022-07-28T20:37:55Z"}, {"author": "Neal Cardwell", "text": "

in slide 10?

", "time": "2022-07-28T20:37:57Z"}, {"author": "Jonathan Morton", "text": "

in my experience, most of the \"long tail\" in the conventional TCPs' CDF plots is due to the startup transient

", "time": "2022-07-28T20:38:08Z"}, {"author": "Neal Cardwell", "text": "

It would be useful to see the throughputs of the long-running flows in these cases?

", "time": "2022-07-28T20:38:59Z"}, {"author": "Jonathan Morton", "text": "

I think that's the black bars at the bottom

", "time": "2022-07-28T20:39:27Z"}, {"author": "Jana Iyengar", "text": "

yup

", "time": "2022-07-28T20:39:35Z"}, {"author": "Jonathan Morton", "text": "

again, badly labelled graphs

", "time": "2022-07-28T20:39:40Z"}, {"author": "Neal Cardwell", "text": "

but that only shows total utilization

", "time": "2022-07-28T20:39:43Z"}, {"author": "Neal Cardwell", "text": "

one of the CCs could be starved?

", "time": "2022-07-28T20:39:48Z"}, {"author": "Jana Iyengar", "text": "

yeah, it doesn't show distribution

", "time": "2022-07-28T20:39:58Z"}, {"author": "Jana Iyengar", "text": "

Bob can respond when he returns to his laptop

", "time": "2022-07-28T20:40:23Z"}, {"author": "Jana Iyengar", "text": "

It would be good to show that

", "time": "2022-07-28T20:40:32Z"}, {"author": "Neal Cardwell", "text": "

Sounds great, thanks.

", "time": "2022-07-28T20:40:42Z"}, {"author": "Jonathan Morton", "text": "

the results have been \"stable since 2019\" because no substantive technical changes have been made since then, despite a lot of pushback in TSVWG

", "time": "2022-07-28T20:41:01Z"}, {"author": "Jonathan Morton", "text": "

my second question would have been to outline the requirements for the network path that can support a Prague CC

", "time": "2022-07-28T20:47:00Z"}, {"author": "Jonathan Morton", "text": "

since there was absolutely no mention of that in the presentation

", "time": "2022-07-28T20:47:16Z"}, {"author": "Jonathan Morton", "text": "

and it has been the single biggest issue in TSVWG

", "time": "2022-07-28T20:47:32Z"}, {"author": "Jonathan Morton", "text": "

@Nathalie: if you move your microphone down a little, it should pop less

", "time": "2022-07-28T20:50:59Z"}, {"author": "Jonathan Morton", "text": "

it is better now

", "time": "2022-07-28T20:51:23Z"}, {"author": "Spencer Dawkins", "text": "

The question on Nathalie's last slide is perfect ...

", "time": "2022-07-28T21:03:15Z"}, {"author": "Markus Amend", "text": "

+1

", "time": "2022-07-28T21:04:07Z"}, {"author": "Neal Cardwell", "text": "

Thanks, Jana!

", "time": "2022-07-28T21:07:23Z"}, {"author": "Jonathan Morton", "text": "

Agreed with Colin's perspective here

", "time": "2022-07-28T21:07:31Z"}, {"author": "Neal Cardwell", "text": "

Notes are at: https://notes.ietf.org/notes-ietf-114-iccrg?edit

", "time": "2022-07-28T21:07:40Z"}]