Jake’s ECN Position=Blue (+Yellow Stripes)

I think of myself as BLUE, with big yellow racing stripes.

I think ECN has a lot of important potential for improving the way the internet operates.

In general, I think the sender can do great things with rate tuning when it has just a little more information about the state of the network than “there might have been some loss, I’m not quite sure”.

(I worked on FastTCP for years and saw it there, and I’m seeing it again from more of a distance in BBR.)

I mean, it’s complicated. No argument here. The response depends on the RTT in uncomfortable ways, and analyzing the performance characteristics of competing flows with different parameters gets you out into the weeds of insanity really fast, and that’s before you try to worry about the possibility of corner case issues in the details of different implementations.

But the advantages of getting an explicit signal out of the network are huge, compared to trying to infer guesses about the network out of the ack patterns. Night vs. day. Forensics vs. surveillance cameras. Just because today’s congestion controls don’t nail the optimal response yet doesn’t mean the information isn’t worth its weight in bitcoins.

I think that to the extent we can get better at this, we can have a better internet. I’d love to see it out there and working. I’m glad Apple and Linux have done their parts to get deployment closer to a real possibility, and I’m glad this list is here and the people on it are digging into the issues. I hope other groups working on middle boxes are doing so as well.

With a little luck and a lot more work, maybe we’ll end up with a more efficient internet one day. My biggest fear is getting it unfixably wrong. But I have a pretty strong belief there’s a good answer in there somewhere.

Mailing list post for reference.

To edit this page, submit a pull request to the Github repository.
RSS feed

Recent News & Articles

Mar 21, 2019 Wiki page
Dave Taht's Take on TCP
Mar 17, 2019 Wiki page
Jake Holland's Stance on ECN
Sep 6, 2018 Wiki page
Pete Heist's Thoughts on ECN
Sep 5, 2018 Wiki page
Dave Taht's Stance on ECN
Sep 4, 2018 Wiki page
Jonathan Morton's Take on ECN

Find us elsewhere

Bufferbloat Mailing Lists
#bufferbloat on Twitter
Google+ group
Archived Bufferbloat pages from the Wayback Machine

Sponsors

Comcast Research Innovation Fund
Nlnet Foundation
Shuttleworth Foundation
GoFundMe

Bufferbloat Related Projects

Congestion Control Blog
Lede Project (OpenWrt)
Flent Network Test Suite
Sqm-Scripts
The Cake shaper
AQMs in BSD
IETF AQM WG

Network Performance Related Resources


Jim Gettys' Blog - The chairman of the Fjord
Toke's Blog - Karlstad University's work on bloat
Voip Users Conference - Weekly Videoconference mostly about voip
Candelatech - A wifi testing company that "gets it".