Cake - FQ_codel the next generation
 help / color / mirror / Atom feed
From: Sebastian Moeller <moeller0@gmx.de>
To: Alec Robertson <alecrobertson13@gmail.com>
Cc: Cake@lists.bufferbloat.net
Subject: Re: [Cake] How to test Cake on TP-Link WDR3600
Date: Sat, 25 Jul 2015 21:19:28 +0200	[thread overview]
Message-ID: <2BE70C89-86F7-43F8-8AFE-FFA524189408@gmx.de> (raw)
In-Reply-To: <CAGwEnGz9oB1G475fU_oRJ1is4Mo7oR3=ipOvKoGYkhnnNamkqA@mail.gmail.com>

Hi Alec,


On Jul 25, 2015, at 20:57 , Alec Robertson <alecrobertson13@gmail.com> wrote:

> That's it, it's all showing up now.
> 
> I will try it out right away. What should I be testing and looking out for?

1) test whether using cake as link layer adaptation mechanism works: put in a number for overhead and run “tc -d qdisc” and post the output of:
	a) cat /etc/config/sqm
	b) /etc/init.d/sqm stop ; tc -d qdisc
	c) /etc/init.d/sqm start ; tc -d qdisc

2) test whether you like the performance under load, http://www.dslreports.com/speedtest is a good start, registered (for free) users can change the configuration, I like to use 16 streams for upstream and downstream each and I like the “Hi-Res BufferBloat:	 (10hz check)” option.

3) test even more, have a loo at flent (https://flent.org), especially the rrul test has been a real help in understanding link behavior under load.
Please note, piece_of_cake will only use 1 priority for all packets (so effectively no priority), layer_cake.qos will by default, use 4 different priority layers, so expect some difference between layer_cake and piece_of_cake in the rrul results...


Best Regards
	Sebastian


> _______________________________________________
> Cake mailing list
> Cake@lists.bufferbloat.net
> https://lists.bufferbloat.net/listinfo/cake


  reply	other threads:[~2015-07-25 19:19 UTC|newest]

Thread overview: 26+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-07-25 15:45 Alec Robertson
2015-07-25 16:27 ` Sebastian Moeller
2015-07-25 16:40   ` Alec Robertson
2015-07-25 16:49   ` Alec Robertson
2015-07-25 17:15     ` Sebastian Moeller
2015-07-25 17:38       ` Alec Robertson
2015-07-25 18:12         ` Dave Taht
2015-07-25 18:21           ` Alec Robertson
2015-07-25 18:49             ` Sebastian Moeller
2015-07-25 18:47         ` Sebastian Moeller
2015-07-25 18:57           ` Alec Robertson
2015-07-25 19:19             ` Sebastian Moeller [this message]
2015-07-25 20:58               ` Alec Robertson
2015-07-26  7:01                 ` Sebastian Moeller
2015-07-26  9:11                   ` Alan Jenkins
2015-07-26 12:32                     ` Alec Robertson
2015-07-26 12:35                       ` Jonathan Morton
2015-07-26 20:09                         ` Alec Robertson
2015-07-26 21:05                           ` Alan Jenkins
2015-07-26 21:20                             ` Jonathan Morton
2015-07-26 21:38                               ` Alan Jenkins
2015-07-27  7:17                               ` Sebastian Moeller
2015-08-02 19:04                             ` Benjamin Cronce
2015-08-02 20:07                               ` Dave Taht
2015-07-27  7:13                           ` Sebastian Moeller
2015-07-27  7:10                       ` 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=2BE70C89-86F7-43F8-8AFE-FFA524189408@gmx.de \
    --to=moeller0@gmx.de \
    --cc=Cake@lists.bufferbloat.net \
    --cc=alecrobertson13@gmail.com \
    /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