Cake - FQ_codel the next generation
 help / color / mirror / Atom feed
From: Noah Causin <n0manletter@gmail.com>
To: cake@lists.bufferbloat.net
Subject: Re: [Cake] WAN ingress rate with concurrent downloads
Date: Thu, 27 Oct 2016 12:42:15 -0400	[thread overview]
Message-ID: <c925c50d-f599-e886-1a65-4b04cadd186b@gmail.com> (raw)
In-Reply-To: <C9ECCBD8-915F-4916-942B-5AB09B6DFCBC@gmx.de>

[-- Attachment #1: Type: text/plain, Size: 1772 bytes --]

I notice this behavior as well.  I believe it is the fact that SQM is 
not the true bottleneck.  Senders continue to increase their transfer 
rate until active queue management on your router causes them to slow down.

If I watch LEDE's built-in realtime traffic graphs, I do see incoming 
rates higher than the set limit.


On 10/27/2016 2:41 AM, Sebastian Moeller wrote:
> Could you set the ingress shaper to 50% of you true ingress rate and 
> try again, please?
> Also could you post the results of 'tc -d qdisc' with your current 
> settings and with the 50% settings (I will probably ask for more 
> data...)? And finally I believe you are on an ADSL link, what are the 
> sync rates reported by the modem, and which ISP are you with (I ask, 
> as some ISPs actually employ a shaper at their BRAS, so the modem sync 
> rate might not be the actual bottleneck bandwidth). That said, with 
> wrong shaper settings I would rather expect increased latency under 
> load, but not bandwidth violations.
>
> Best Regards
> Sebastian
>
> On October 27, 2016 2:16:06 AM GMT+02:00, "G. Amanakis" 
> <g_amanakis@yahoo.com> wrote:
>
>     I mean that the ingress limit on WAN (or egress limit on LAN)
>     seems to be ignored, and the rate bmon and bwm-ng report is the
>     maximum achievable. I.e. on 450kbyte/s ingress with the limit set
>     at 400kbyte/s, when bittorrent is in use bmon reports 450kbyte/s
>     after 10-20 seconds.
>
>     ------------------------------------------------------------------------
>
>     Cake mailing list
>     Cake@lists.bufferbloat.net
>     https://lists.bufferbloat.net/listinfo/cake
>
> _______________________________________________
> Cake mailing list
> Cake@lists.bufferbloat.net
> https://lists.bufferbloat.net/listinfo/cake

[-- Attachment #2: Type: text/html, Size: 2844 bytes --]

  reply	other threads:[~2016-10-27 16:42 UTC|newest]

Thread overview: 10+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <mailman.5.1477497601.28053.cake@lists.bufferbloat.net>
2016-10-27  0:10 ` G. Amanakis
2016-10-27  0:16   ` G. Amanakis
2016-10-27  6:41     ` Sebastian Moeller
2016-10-27 16:42       ` Noah Causin [this message]
2016-10-28  1:34     ` Georgios Amanakis
2016-10-28  7:45       ` Sebastian Moeller
     [not found] <mailman.1.1477670401.20617.cake@lists.bufferbloat.net>
2016-10-30 16:43 ` Georgios Amanakis
2016-10-30 19:27   ` Sebastian Moeller
     [not found] <1462124589.1190968.1481310707746.ref@mail.yahoo.com>
2016-12-09 19:11 ` George Amanakis
2016-12-10 19:33   ` Benjamin Cronce

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=c925c50d-f599-e886-1a65-4b04cadd186b@gmail.com \
    --to=n0manletter@gmail.com \
    --cc=cake@lists.bufferbloat.net \
    /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