General list for discussing Bufferbloat
 help / color / mirror / Atom feed
From: Simon Barber <simon@superduper.net>
To: Eric Dumazet <eric.dumazet@gmail.com>
Cc: bloat <bloat@lists.bufferbloat.net>,
	Juliusz Chroboczek <jch@pps.univ-paris-diderot.fr>
Subject: Re: [Bloat] AQM and PPP on Linux
Date: Tue, 28 Jul 2015 07:31:36 -0700	[thread overview]
Message-ID: <14ed5136170.27f7.e972a4f4d859b00521b2b659602cb2f9@superduper.net> (raw)
In-Reply-To: <1438093312.20182.49.camel@edumazet-glaptop2.roam.corp.google.com>

The issue is that Codel tries to keep the delay low, and will start 
dropping when sojourn time grows above 5ms for 100ms. For longer RTT links 
more delay is necessary to avoid underutilizing the link. This is due to 
the multiplicative decrease - it's worst with Reno, where the halving of 
cWind means that you need to have a full BDP of data in the buffer to avoid 
the link going idle when cWind is halved. With longer RTTs this means more 
delay than Codel allows is required to avoid a throughput hit. The worst 
case happens when a single flow is controlled, but that can be a common 
situation. My proposal is to sense and have the target value in Codel 
automatically adjust when this worst case scenario happens - which would 
mitigate most of the downside.

Simon

Sent with AquaMail for Android
http://www.aqua-mail.com


On July 28, 2015 7:21:56 AM Eric Dumazet <eric.dumazet@gmail.com> wrote:

> On Tue, 2015-07-28 at 07:11 -0700, Simon Barber wrote:
> > The main danger is the negative effects on performance of using Codel. You
> > may experience low throughput on high RTT links.
>
> Really ? I've never seen this, unless you mess with codel qdisc
> attributes maybe.
>
> (Some guys seem to not really understand whole concept of a queue, and
> set very low values for 'limit' attribute for example)
>
>
>
>



  reply	other threads:[~2015-07-28 14:31 UTC|newest]

Thread overview: 25+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-07-28 13:09 Juliusz Chroboczek
2015-07-28 13:33 ` Toke Høiland-Jørgensen
2015-07-28 13:50   ` Juliusz Chroboczek
2015-07-28 14:05     ` Toke Høiland-Jørgensen
2015-07-28 14:11       ` Simon Barber
2015-07-28 14:21         ` Eric Dumazet
2015-07-28 14:31           ` Simon Barber [this message]
2015-07-28 14:43             ` Jonathan Morton
2015-07-28 14:49             ` Eric Dumazet
2015-07-28 14:55               ` Eric Dumazet
2015-07-28 16:02               ` Alan Jenkins
2015-07-28 16:22             ` Sebastian Moeller
2015-07-28 17:11               ` Michael Welzl
2015-07-29  7:19         ` David Lang
2015-07-28 19:20       ` Juliusz Chroboczek
2015-07-28 19:29         ` Alan Jenkins
2015-07-28 14:18     ` Eric Dumazet
2015-07-28 14:44 ` Dave Taht
2015-07-28 14:52   ` Eric Dumazet
2015-07-28 19:24   ` Juliusz Chroboczek
2015-07-28 19:31     ` Bill Ver Steeg (versteb)
2015-07-28 20:10     ` Alan Jenkins
2015-07-28 20:45       ` Alan Jenkins
2015-07-29 13:15   ` Stefan Alfredsson
2015-07-29 13:41     ` Dave Taht

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/bloat.lists.bufferbloat.net/

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

  git send-email \
    --in-reply-to=14ed5136170.27f7.e972a4f4d859b00521b2b659602cb2f9@superduper.net \
    --to=simon@superduper.net \
    --cc=bloat@lists.bufferbloat.net \
    --cc=eric.dumazet@gmail.com \
    --cc=jch@pps.univ-paris-diderot.fr \
    /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