[75585] in North American Network Operators' Group
Re: anycast roots
daemon@ATHENA.MIT.EDU (Stephane Bortzmeyer)
Wed Nov 17 11:05:53 2004
Date: Wed, 17 Nov 2004 17:05:26 +0100
From: Stephane Bortzmeyer <bortzmeyer@nic.fr>
To: Joe Abley <jabley@isc.org>
Cc: "Elmar K. Bins" <elmi@4ever.de>,
Stephane Bortzmeyer <bortzmeyer@nic.fr>, nanog@merit.edu
In-Reply-To: <192F2CCB-38AA-11D9-B89F-000D93B24C7A@isc.org>
Errors-To: owner-nanog-outgoing@merit.edu
On Wed, Nov 17, 2004 at 10:05:20AM -0500,
Joe Abley <jabley@isc.org> wrote
a message of 36 lines which said:
> I have no idea about Verisign's scheme, but in case anybody notices
> similar distribution of queries across F root servers, it may help to
> know that:
>
> xxxNa.f.root-servers.org
> xxxNb.f.root-servers.org
> xxxNc.f.root-servers.org
> etc
>
> are hosts all located at the same site "xxxN".
OK, I understand. So, like Elmar Bins, I was seeing "intra-site"
jitter, which is normal (it is only seen with UDP queries, probably
because the Verisign load balancer is stateful and remembers the
binding for TCP) and no "inter-site" jitter, which would be more
serious. But I'm quite at this edge of the Internet, so let's wait for
more reports with Peter Boothe's tool. And just be sure to "sanitize"
the results before jumping to the wrong conclusion, like I did.
