Re: [PCN] Concensus questions from Thursday's PCN meeting

Hi Gengyu,

Can you clarify please?

If you have 5x congestion overall on a link, (which means you have 5
times more traffic than your link can carry),  would you not expect to
lose 4/5 of your traffic?

You may have misunderstood that in this example the IEA in question
itself only has K amount of traffic arriving to this link, not 16K. I am
assuming then that approximately 4/5 of k will be lost. This clearly
assumes that the loss is proportionally spread among all IEAs, which is
indeed not always the case - but seems like a fair approximation for
this level of discussion.

If I am missing something fundamental, can you explain? 

Anna 

> -----Original Message-----
> From: Wei Gengyu [mailto:weigengyu@vip.sina.com] 
> Sent: Thursday, March 20, 2008 2:05 AM
> To: Anna Charny (acharny); Georgios Karagiannis; 
> philip.eardley@bt.com; steven.blake@ericsson.com
> Cc: pcn@ietf.org
> Subject: Re: [PCN] Concensus questions from Thursday's PCN meeting
> 
> Hi, all,
> 
> No matter what you want to express,
> the explanation of your assumed model is incorrect.
> 
> Also, see comments inline.
> 
> Gengyu
> 
> ----- Original Message -----
> From: "Anna Charny (acharny)" <acharny@cisco.com>
> To: "Georgios Karagiannis" <karagian@cs.utwente.nl>; 
> <philip.eardley@bt.com>; <steven.blake@ericsson.com>
> Cc: <pcn@ietf.org>
> Sent: Thursday, March 20, 2008 4:33 AM
> Subject: Re: [PCN] Concensus questions from Thursday's PCN meeting
> 
> 
> > Hi Georgios,
> >
> 
> >  Assume now that the link in question has a very high overload.  I 
> > would assume is 5X overload is quite large (Rudiger I am sure will 
> > agree :)), so let us just take 5.  That means that 
> approximately 80% 
> > of traffic of this IEA is dropped at the input, so we end up having 
> > only 0.2K actually leaving this link.
> 
> It is wrong.
> You can not get 0.2K ACTUALLY!
> And because of this, the following calculation is inredible.
> 
> 
> >
> > Now assume that the admission threshold is set to 80% of your link 
> > (picking a high value to make things worse). And assume we 
> are running 
> > SM - or LC-PCN (or whatever other alg that uses excess 
> marking).  Now 
> > that means that ~20% of our remaining traffic of the IEA aggregate 
> > gets marked. The egress now sees:  0.2*0.2K=0.04K of marked traffic 
> > and (M-1)K+0.2*0.8K unmarked traffic.  The CLE now is now 
> ~0.04K/15K~0.002.
> > If you need a larger CLE than that, then neither SM, nor, for that 
> > matter, LC-PCN, would trigger admission stop on that aggregate 
> > (without probing added).
> >
> >
> > Anna
> >
> 
> Strongly suggest people refer to textbook about throughput 
> performance of congested node.
> The throughput of the congested will be different in case the 
> input is 5*X and 16*X.
> 
> Gengyu 
> 
> 
_______________________________________________
PCN mailing list
PCN@ietf.org
https://www.ietf.org/mailman/listinfo/pcn