All of lore.kernel.org
 help / color / mirror / Atom feed
From: Stef Coene <stef.coene@docum.org>
To: lartc@vger.kernel.org
Subject: Re: [LARTC] CBQ Rate
Date: Thu, 04 Sep 2003 17:49:41 +0000	[thread overview]
Message-ID: <marc-lartc-106269785907476@msgid-missing> (raw)
In-Reply-To: <marc-lartc-106269010029191@msgid-missing>

On Thursday 04 September 2003 19:07, Emmanuel SIMON wrote:
> It is me again.
> is there nos a trouble in my script :
> " ... rate 5Mbit weight 0.3 ..." --> is it compatible ??
Yes.  But take weight = rate / 10 as a general rule.
And your bandwidth parameter should be the real NIC bandwidth.  So 10mbit.
And it's also better to create a "parent" class attached to the root qdisc.
And different prio's in the filter statement will not change much.  It only 
determines the order the filters are checked.

> Thanks again
>
> > -----Message d'origine-----
> > De : lartc-admin@mailman.ds9a.nl
> > [mailto:lartc-admin@mailman.ds9a.nl]De
> > la part de Emmanuel SIMON
> > Envoyé : jeudi 4 septembre 2003 17:40
> > À : 'LARTC'
> > Objet : [LARTC] CBQ Rate
> >
> >
> > Hi everyone,
> >
> > This is on a linux box, ingress (eth1) at 100Mb/s and egress (eth0) at
> > 10Mb/s. The purpose is to test CBQ
> > Here is my script
> >
> > -------------------------------------------------------------------
> > # Root qdisc
> > tc qdisc add dev eth0 root handle 1:0 cbq bandwidth 9Mbit \
> >   avpkt 1000 cell 8
> >
> > # Classes
> > tc class add dev eth0 parent 1:0 classid 1:1 cbq bandwidth 9Mbit \
> >   rate 5Mbit weight 0.3 allot 1514 avpkt 1000 bounded prio 1
> > tc class add dev eth0 parent 1:0 classid 1:2 cbq bandwidth 9Mbit \
> >   rate 5Mbit weight 0.3 allot 1514 avpkt 1000 bounded prio 2
> > tc class add dev eth0 parent 1:0 classid 1:3 cbq bandwidth 9Mbit \
> >   rate 5Mbit weight 0.3 allot 1514 avpkt 1000 bounded prio 3
> >
> > # Leaf qdiscs
> > tc qdisc add dev eth0 parent 1:1 handle 10:0 sfq perturb 10
> > tc qdisc add dev eth0 parent 1:2 handle 20:0 sfq perturb 10
> > tc qdisc add dev eth0 parent 1:3 handle 30:0 sfq perturb 10
> >
> > # Filters
> > tc filter add dev eth0 parent 1:0 proto ip prio 0 u32 \
> >   match ip tos 0x10 0xff flowid 1:1
> > tc filter add dev eth0 parent 1:0 proto ip prio 1 u32 \
> >   match ip tos 0x04 0xff flowid 1:2
> > tc filter add dev eth0 parent 1:0 proto ip prio 2 u32 \
> >   match ip tos 0x08 0xff flowid 1:3
> > -------------------------------------------------------------------
> >
> > I send some traffic at different rate : 3Mb/s, 3.5Mb/s,
> > 4Mb/s, 4.5Mb/s,
> > 5Mb/s, 6Mb/s
> >
> > 1st in only one class at a time
> >    => the result is always 2.35Mb/s
> >
> > then in the 3 classes at the same time with the same rates.
> >    => the result rate is close from wanted rate
> >
> > Can someone explain to me why we I send data in only one
> > class the rate is
> > so low ?
> >
> > Thank you
> > Emmanuel

Stef

-- 

stef.coene@docum.org
 "Using Linux as bandwidth manager"
     http://www.docum.org/
     #lartc @ irc.oftc.net

_______________________________________________
LARTC mailing list / LARTC@mailman.ds9a.nl
http://mailman.ds9a.nl/mailman/listinfo/lartc HOWTO: http://lartc.org/

  parent reply	other threads:[~2003-09-04 17:49 UTC|newest]

Thread overview: 4+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2003-09-04 15:39 [LARTC] CBQ Rate Emmanuel SIMON
2003-09-04 17:07 ` Emmanuel SIMON
2003-09-04 17:49 ` Stef Coene [this message]
2003-09-05 14:31 ` Damjan

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-106269785907476@msgid-missing \
    --to=stef.coene@docum.org \
    --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.