Cake - FQ_codel the next generation
 help / color / mirror / Atom feed
From: Dave Taht <dave.taht@gmail.com>
To: Kevin Darbyshire-Bryant <kevin@darbyshire-bryant.me.uk>
Cc: Ryan Mounce <ryan@mounce.com.au>, Cake List <cake@lists.bufferbloat.net>
Subject: Re: [Cake] inbound cake or fq_codel shaping fails on cable on netflix reno
Date: Tue, 24 Jul 2018 08:19:38 -0700	[thread overview]
Message-ID: <CAA93jw5R1B0FexAYyDrm=9AeaS1YE7MmeVsqJiZZZfGzFo7r9w@mail.gmail.com> (raw)
In-Reply-To: <09E00B24-63DA-42B3-AC60-155AC76C0CC4@darbyshire-bryant.me.uk>


[-- Attachment #1.1.1: Type: text/plain, Size: 1919 bytes --]

cdfs help. I also try to encourage sending the flent.gz files too. :)

Outbound, to 99% or more of the rate, *with perfect framing* looks great so
far, 'cept on crappy cablemodems.

I am concerned about recommending values as high as 98% for inbound
shaping. We are engineering to
the test here (2? 3 flows? on a very short rtt), and need to leave *some*
headroom for multiple flows to enter in slow start and get kicked out of it.

I'll buy that the old 85% figure made sense in the sub 20Mbit era, and that
we only need enough headroom to allow X flows to enter based on the
characteristics of the link and typical traffic - 15 new flows per second *
per active user/10 ? and cake's response to slow start is more agressive...

try a:

flent -H flent-london.bufferbloat.net -s .02 --te=download_streams=32 -t
'98%' tcp_ndown

with htb+fq_codel and cake to see that spike more clearly.


On Tue, Jul 24, 2018 at 7:54 AM Kevin Darbyshire-Bryant <
kevin@darbyshire-bryant.me.uk> wrote:

>
>
> On 24 Jul 2018, at 14:51, Dave Taht <dave.taht@gmail.com> wrote:
>
> Now that you can join the party, I note there IS a flent server in england
> with irtt on it.
>
> flent-london.bufferbloat.net
>
>
> Ok, well if you’re desperately interested….. :-)
>
> Plot I did running to the london server, one shaped at 99% downstream, the
> other at 98%…. and I’ve decided to stick at 98% as a result - plot is a
> little bit hard to distinguish but I’d say there’s around 8ms avg less
> latency-ish between the two.  And an order of magnitude between using
> london v fremont :-)
>
> The upstream barely registers
>
> # tc -s qdisc show dev ifb4eth0
> qdisc cake 801a: root refcnt 2 bandwidth 78400Kbit diffserv3 dual-dsthost
> nat ingress split-gso rtt 100.0ms ptm overhead 26
>
>
>

-- 

Dave Täht
CEO, TekLibre, LLC
http://www.teklibre.com
Tel: 1-669-226-2619

[-- Attachment #1.1.2: Type: text/html, Size: 3015 bytes --]

[-- Attachment #1.2: ping-basingstoke-london-98v99.png --]
[-- Type: image/png, Size: 127599 bytes --]

[-- Attachment #2: ping-basingstoke-london-98v99.png --]
[-- Type: image/png, Size: 127599 bytes --]

  reply	other threads:[~2018-07-24 15:19 UTC|newest]

Thread overview: 57+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-07-21 16:09 Dave Taht
2018-07-21 17:20 ` Georgios Amanakis
2018-07-21 17:23   ` Jonathan Morton
2018-07-21 17:44     ` Georgios Amanakis
2018-07-21 17:47       ` Dave Taht
2018-07-21 18:17         ` Georgios Amanakis
2018-07-21 18:20           ` Dave Taht
2018-07-21 18:23             ` Georgios Amanakis
2018-07-21 20:01           ` Dave Taht
2018-07-21 20:24             ` Jonathan Morton
2018-07-21 20:36               ` Dave Taht
2018-07-21 21:17                 ` Arie
2018-07-21 21:37                   ` Dave Taht
2018-07-21 22:13                     ` Dave Taht
2018-07-21 22:28                       ` Dave Taht
2018-07-21 23:10                       ` Arie
2018-07-23  6:50                         ` Ryan Mounce
2018-07-23 14:56                           ` Dave Taht
2018-07-23 15:26                             ` Jonas Mårtensson
2018-07-23 15:43                               ` Dave Taht
2018-07-23 16:45                               ` Tristan Seligmann
2018-07-23 20:47                                 ` Dave Taht
2018-07-23 15:49                             ` Sebastian Moeller
2018-07-23 17:32                             ` Benjamin Cronce
     [not found]                           ` <CAA93jw7hPG5oGyKaCL69p9Sbf7BckAZzh-p8C0jU+QXF9she1A@mail.gmail.com>
2018-07-24  1:31                             ` Ryan Mounce
2018-07-24  2:17                               ` Ryan Mounce
2018-07-24  2:29                                 ` Dave Taht
2018-07-24  2:50                                   ` Ryan Mounce
2018-07-24  8:15                                     ` Kevin Darbyshire-Bryant
2018-07-24 13:51                                       ` Dave Taht
2018-07-24 14:54                                         ` Kevin Darbyshire-Bryant
2018-07-24 15:19                                           ` Dave Taht [this message]
2018-07-24 18:05                                             ` Tristan Seligmann
2018-07-24 18:08                                               ` Tristan Seligmann
2018-07-24 17:58                                           ` Sebastian Moeller
2018-07-24 19:38                                         ` Pete Heist
2018-07-24 20:44                                           ` Dave Taht
2018-07-24 22:23                                             ` Pete Heist
2018-07-24 22:29                                               ` Dave Taht
2018-07-24 22:43                                                 ` Pete Heist
2018-07-21 17:24   ` Arie
2018-07-21 17:27     ` Dave Taht
2018-07-21 17:36       ` Arie
2018-07-21 17:45         ` Dave Taht
2018-07-21 17:55           ` Arie
2018-07-21 18:02             ` Dave Taht
2018-07-21 18:23               ` Arie
     [not found]                 ` <CAA93jw64CbM9DmtHM2aRbFBb3TUepSAK2JRmcDZHZ6kUkJB1Jg@mail.gmail.com>
2018-07-21 18:38                   ` [Cake] policers, finally Dave Taht
2018-07-21 18:45                     ` Dave Taht
2018-08-04  7:53                       ` [Cake] Policers Dave Taht
2018-07-21 17:28   ` [Cake] inbound cake or fq_codel shaping fails on cable on netflix reno Georgios Amanakis
2018-07-21 17:42     ` Dave Taht
2018-07-21 19:57       ` [Cake] [Cerowrt-devel] " Toke Høiland-Jørgensen
2018-07-24  2:36   ` [Cake] " Dave Taht
2018-07-24  4:17     ` Georgios Amanakis
2018-07-22  9:57 ` Pete Heist
2018-07-22 10:29   ` Sebastian Moeller

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

  List information: https://lists.bufferbloat.net/postorius/lists/cake.lists.bufferbloat.net/

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to='CAA93jw5R1B0FexAYyDrm=9AeaS1YE7MmeVsqJiZZZfGzFo7r9w@mail.gmail.com' \
    --to=dave.taht@gmail.com \
    --cc=cake@lists.bufferbloat.net \
    --cc=kevin@darbyshire-bryant.me.uk \
    --cc=ryan@mounce.com.au \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox