[16369] in North American Network Operators' Group

home help back first fref pref prev next nref lref last post

Re: MAE-East snafu redux

daemon@ATHENA.MIT.EDU (Mikael Abrahamsson)
Wed Apr 22 11:34:04 1998

Date: Wed, 22 Apr 1998 09:06:23 +0200 (MET DST)
From: Mikael Abrahamsson <swmike@swm.pp.se>
To: Jeremiah Kristal <jeremiah@fs.IConNet.NET>
cc: nanog@merit.edu
In-Reply-To: <Pine.GSO.3.92.980421175450.18518M-100000@fs.IConNet.NET>

On Tue, 21 Apr 1998, Jeremiah Kristal wrote:

> Has everyone just become so used to terrible performace at MAE-East, or am
> I the only one seeing problems?  I'm seeing perfect performance to
> networks connected to Gigaswitch 1 (excluding overloaded ports), but
> 15-20% packet loss to anyone connected to any other Gigaswitch.  In the
> past MFS would jump on these tickets, find a frozen card on Gigaswitch 6,
> reset it, and clear the trouble.  It has been over 24 hours since I opened
> a ticket, I've spoken with MFS Datanet Engineering, and I still don't
> think I've spoken to anyone at MFS who is aware that all traffic between
> Gigaswitches goes through Giga6.
> If anyone has time tonight, could they check performance to other
> providers on the same Gigaswitch and on other Gigas.  If you need to know
> which provider is on which switch, go to
> http://www.mfsdatanet.com:80/MAE/east.map.html
> Thanks, and hopefully this is on topic, even if it doesn't contain actual
> router commands.  :)

http://208.234.102.97/MAE/east.aggr.overlay.html

The past two years it has been a pretty much smoothe curve in the traffic
graph, but the past months (as soon as it started hitting 1500mbit/s) the
graph started to get rugged the way it is now. I interpret that as
trouble... It used to spike a few times a week max, nowadays it seems to
do that hourly. 

I interpret that as overload.

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


home help back first fref pref prev next nref lref last post