[Iccrg] congestion control and visability to the user

[Mikael Abrahamsson]

On Sun, 28 Mar 2010, Matt Mathis wrote:

> Yea, we are all worried about ECN.    ECN capable routers are in wide
> deployment, but nearly all have it turned off by default.

Last I checked, Cisco 12000, 7600, CRS-1 or Juniper T/M series did not do 
ECN and there was no real interest from them to start supporting it 
either.

> Your statement was true for old stacks that have fixed size receiver
> windows.   The new stacks autotune out to 4 or 8 MByte windows.
> Unless you are on a transcontinental  GigE, every connection with
> enough data will cause packet loss or queues somewhere in the network.

Yes, on the access line absolutely, but not in the core.

>  Since all networks are at least slightly oversubscribed at most
> levels, the potential exists for there to be congestion nearly
> everywhere.   Between autotuning and p2p it is no longer possible to
> avoid congestion in the core except by explicitly designing in
> bottlenecks at midlevel interconnects, the network edges or somewhere
> in between.

The customer is paying for a certain access to The Internet, congesting in 
the core basically is a breach of contract. The only congestion on a well 
behaved network is on the access line (PE-CE link).

> You are off the mark here.  The problem is that the traditional "TCP
> friendly" model does not implement anything that resembles any form of
> fairness except under completely idealistic assumptions.  TCP has been
> lame for 20+ years, such that we failed to notice that the Internet
> does not have a real capacity sharing architecture.  Now that TCP is
> mostly not lame, people are discovering that you do not want to share
> the network with a well functioning bulk TCP transfer.  This has
> actually been known in a theoretical sense for a long time (see RFC
> 2309), but was not often a problem until recently.

I guess your view of the wolrd and mine differes widely. I don't agree 
with you at all. ISPs congesting their cores are doing a bad job and 
should be punished for it.

> I didn't realize how bad it might be until I had a conversation with
> my son, who mused that he liked his new PC because it was so quick on
> the network.  However, whenever he is doing anything serious (he is a
> web designer), everybody else on his home LAN starts to complain.

That is the PE-CE link I was talking about. The PE-P-PE links should never 
go full, then they're not capacity managed correctly. The PE-CE link is 
designed to be a limiting factor (that's what you pay for) and THERE is 
where the intelligent queueing needs to be (or have really small buffers 
that saw-tooth bulk TCP performance so the smaller capacity interactive 
flows have a high probability of succeeding in getting their traffic 
thru).

-- 
Mikael Abrahamsson    email: swmike at swm.pp.se