ICANN/GNSO GNSO Email List Archives

[ga]


<<< Chronological Index >>>    <<< Thread Index >>>

Re: [ga] Re: No more FUD -- what is the current size of the .com database?


At 03:10 AM 9/27/2006, Stephane Bortzmeyer wrote:
On Wed, Sep 27, 2006 at 02:07:40AM -0400,
 Martin Hannigan <hannigan@xxxxxxxxxxx> wrote
 a message of 40 lines which said:

> Then why is there not consistency across the globe on root server
> query performance?

1) Geographical/provider closeness (there is a root name server at an
exchange point connected to the network of my Internet access provider
so, obviously, this root name server replies faster).

2) Speed of the software (nsd, used by K-root, is much, much faster
than BIND)

% qtest 'SOA .' `dig +short NS .`
3 202.12.27.33#53(202.12.27.33)

(202.12.27.33 is M-root, qtest is attached.)



Thanks. I'm using smokeping+dig across the root. Geo/provider closeness seems to be more the answer than anything, most beg for peering instead of buying transit. J, K, and the USG have the most consistency of all from my views.

-M<








--
Martin Hannigan (c) 617-388-2663
Renesys Corporation (w) 617-395-8574
Member of Technical Staff Network Operations
hannigan@xxxxxxxxxxx





<<< Chronological Index >>>    <<< Thread Index >>>