Linux Advanced Routing and Traffic Control list
 help / color / mirror / Atom feed
* [LARTC] HTB quantum for small rates
@ 2002-12-22  2:37 Hannes Ebner
  2002-12-22 11:09 ` Stef Coene
  0 siblings, 1 reply; 2+ messages in thread
From: Hannes Ebner @ 2002-12-22  2:37 UTC (permalink / raw)
  To: lartc

hi devik,

i have found the following you have written some time ago:
> It is important to know that for precise operation quantums need to 
> be as small as possible and larger than MTU. Normaly you don't need 
> to specify quantums manualy as HTB chooses precomputed values. It 
> computes classe's quantum (when you add or change it) as its rate 
> divided by r2q global parameter. Its default value is 10 and because
> typical MTU is 1500 the default is good for rates from 15 kBps (120
> kbit). For smaller minimal rates specify r2q 1 when creating qdisc -
> it is good from 12 kbit which should be enough. If you will need you
> can specify quantum manualy when adding or changing the class.

what would be the best solution for rates smaller than 120kbit? i don't
know how the higher rates are affected by scaling r2q down to 1, but
would this be a solution for rates from 12kbit?

would it be better to calculate the quantum for each rate or to set a
small quantum for all rates?

thanks in advance,
hannes

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

^ permalink raw reply	[flat|nested] 2+ messages in thread

* Re: [LARTC] HTB quantum for small rates
  2002-12-22  2:37 [LARTC] HTB quantum for small rates Hannes Ebner
@ 2002-12-22 11:09 ` Stef Coene
  0 siblings, 0 replies; 2+ messages in thread
From: Stef Coene @ 2002-12-22 11:09 UTC (permalink / raw)
  To: lartc

On Sunday 22 December 2002 03:37, Hannes Ebner wrote:
> hi devik,
>
> i have found the following you have written some time ago:
> > It is important to know that for precise operation quantums need to
> > be as small as possible and larger than MTU. Normaly you don't need
> > to specify quantums manualy as HTB chooses precomputed values. It
> > computes classe's quantum (when you add or change it) as its rate
> > divided by r2q global parameter. Its default value is 10 and because
> > typical MTU is 1500 the default is good for rates from 15 kBps (120
> > kbit). For smaller minimal rates specify r2q 1 when creating qdisc -
> > it is good from 12 kbit which should be enough. If you will need you
> > can specify quantum manualy when adding or changing the class.
>
> what would be the best solution for rates smaller than 120kbit? i don't
> know how the higher rates are affected by scaling r2q down to 1, but
> would this be a solution for rates from 12kbit?
>
> would it be better to calculate the quantum for each rate or to set a
> small quantum for all rates?
The best you can do is following this rules and choose a good r2q :
  - 1500 < rate_small / r2q
  - rate_bigg / r2q < 60.000

with
  - rate_small = smallest rate
  - rate_bigg = biggest rate

Quantum is only used if you have 2 or more class fighting for remaining 
bandwidth from the same parent.  And with remaining, I mean that each class 
already received it's rate and that the parent has some bandwidth left.

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/

^ permalink raw reply	[flat|nested] 2+ messages in thread

end of thread, other threads:[~2002-12-22 11:09 UTC | newest]

Thread overview: 2+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2002-12-22  2:37 [LARTC] HTB quantum for small rates Hannes Ebner
2002-12-22 11:09 ` Stef Coene

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox