On Sat, 2004-01-31 at 15:53, Vladimir B. Savkin wrote:
> On Sat, Jan 31, 2004 at 03:26:53PM -0500, jamal wrote:
[..]
> > Note that Areas A and B are shared between many clients and is here to
> > serve as an example just to show how you can do the following:
> > a) a client gets a fair share i.e Guaranteed rate in a long period of
> > time.
>
> No, that's not what I mean by fairness!
> No problem to give everyone their guaranteed rate.
>
> > b) many clients coming from one device like eth1 share some excess
> > bandwidth allocated for eth1 if it is available.
> > c) Many clients share bandwidth allocated for the system (i.e
> > fre-for-all for eth1 and eth2).
>
> Yes, they will share it. But in what proportion?
Excess b/width is shared in FIFO mode in what i described whoever comes
first grabs whats excess.
Thanks for clarifying this point.
[..]
> With your solution, if every client open some number of TCP connections
[..]
> See, my bandwidth limit is artificial and defined by political reasons.
> And that's the only restriction that is defined, and the goal
> is the maximal fairness. Minimal guaranteed rate for each client is
> not enough.
> With your proposal, there's just no place to put this aggregate
> restriction, except a policer, which doesn't give fairness.
>
Ok, i think i have understood you finally;->
The challenge is in this one direction whose characteristics can be
described as follows:
a) Incoming pipe (from internet) is smaller than outgoing pipe (to
clients).
b) Desire is to have excess bwidth with max fairness to all flows
instead of free-for-all scheme.
[This can only be achieved by a non-work conserving scheduler].
Is the above correct?
cheers,
jamal
|