From owner-freebsd-hackers  Wed Nov 22 11:15:48 1995
Return-Path: owner-hackers
Received: (from root@localhost)
          by freefall.freebsd.org (8.6.12/8.6.6) id LAA03519
          for hackers-outgoing; Wed, 22 Nov 1995 11:15:48 -0800
Received: from labinfo.iet.unipi.it (labinfo.iet.unipi.it [131.114.9.5])
          by freefall.freebsd.org (8.6.12/8.6.6) with ESMTP id LAA03510
          for <hackers@freebsd.org>; Wed, 22 Nov 1995 11:15:41 -0800
Received: from localhost (luigi@localhost) by labinfo.iet.unipi.it (8.6.5/8.6.5) id UAA14961; Wed, 22 Nov 1995 20:17:50 +0100
From: Luigi Rizzo <luigi@labinfo.iet.unipi.it>
Message-Id: <199511221917.UAA14961@labinfo.iet.unipi.it>
Subject: connectivity problems...
To: grog@lemis.de
Date: Wed, 22 Nov 1995 20:17:49 +0100 (MET)
Cc: jmb@kryten.atinc.com, hackers@freebsd.org
In-Reply-To: <199511211255.NAA13591@allegro.lemis.de> from "Greg Lehey" at Nov 21, 95 01:54:46 pm
X-Mailer: ELM [version 2.4 PL23]
Content-Type: text
Content-Length: 1655      
Sender: owner-hackers@freebsd.org
Precedence: bulk

> Jonathan M. Bresler writes:
> > 
> > i have heard horror stories about non-us 
> > connectivity--several nets in one country reach each other by way of the 
> > usa.  is this really teh case ??
> 
> 'fraid so.  This is how I get to Joerg, who's only about 150 miles
> down the road:

... traceroute output omitted

> > 	if so regional majordomo's need to reflect the net topology more 
> > closely than a simple divison along political boundaries.
> 
> There's also a question of net load.  If you look at the figures
> above, you'll notice that the time from me to ipgate2.win-ip.dfn.de
> was under .5 second.  From there to sax.sax.de (all inside Germany, in
> the DFN), things rapidly go to hell.  I'm told that this is a normal
> state of affairs.

same here. The nice thing is, you ping the remote side (the US in
our case) and get up to 70% of packet losses, practically independent
of the size of the packet, and often also of the sending rate (tried
with ping -s xxx -f).  For those packets which pass through the
RTT has a surprisingly low variance (considering the loss rate),
and the bandwidth is equally high (>100Kbit/s).

I am wondering how big are the receive queues on these routers, and if
they have configuration or software problems!

	Luigi
====================================================================
Luigi Rizzo                     Dip. di Ingegneria dell'Informazione
email: luigi@iet.unipi.it       Universita' di Pisa
tel: +39-50-568533              via Diotisalvi 2, 56126 PISA (Italy)
fax: +39-50-568522              http://www.iet.unipi.it/~luigi/
====================================================================