All of lore.kernel.org
 help / color / mirror / Atom feed
From: Nickola Kolev <nikky@mnet.bg>
To: lartc@vger.kernel.org
Subject: Re: [LARTC] esfq (was cbq.init)
Date: Wed, 23 Apr 2003 19:33:22 +0000	[thread overview]
Message-ID: <marc-lartc-105112648320381@msgid-missing> (raw)

[-- Attachment #1: Type: text/plain, Size: 1382 bytes --]

On Wed, 23 Apr 2003 21:14:34 +0200
Stef Coene <stef.coene@docum.org> wrote:

[ cut ]
: Not stupid, but the wrong place.  This is not the cbq.init discussion list.
: Howerver some remarks.  I think the esfq idea came from me.  You can use if 
: you know why.  So if you are not satisfied with cbq.init, try to create your 
: own script.  
: 
: You can have the sfq "problem" if you add mutliple users in the same class.  
: With the sfq qdisc, each stream (determined by src/dst and port/ip-address)  
: has the same opportunity to send something.  The esfq qdisc can be configured 
: to only use the src address to create the streams so the each users  has his 
: own little queue.  And so they have the same chance to send something.
: 
: Or you can create 1 class for each user.
: 
: Stef
[ cut ]

In fact, Stef, 

I tried the esfq qdisc a few days ago, but I can't say
I saw satisfied. Maybe I couldn't find the right values for limit/depth/divisor,
but there were no fair links for the IPs I defined. For a 128 Kbit class,
I added the necessary filter and a esfq qdisc, but the bandwidth was not
shared equally. Two of four clients got 4 KB, and the rest got about 2,5KB
download speed. Thery wew THE ONLY users, connected to that machine.

So, I'm wondering if esfq is really working as it is supposed to do.
Maybe Alexander Atanasov could enlighten me (us)?

Regards,
Nickola

[-- Attachment #2: Type: application/pgp-signature, Size: 189 bytes --]

             reply	other threads:[~2003-04-23 19:33 UTC|newest]

Thread overview: 2+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2003-04-23 19:33 Nickola Kolev [this message]
2003-04-23 19:43 ` [LARTC] esfq (was cbq.init) Stef Coene

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

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

  git send-email \
    --in-reply-to=marc-lartc-105112648320381@msgid-missing \
    --to=nikky@mnet.bg \
    --cc=lartc@vger.kernel.org \
    /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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.