Using NAT for best-exit routing

Mailman List Mirror (Read Only)
1

The following is a suggestion for a scalable solution to the best-exit
problem (hot-potato requests to a web farm, best-exit data return).
(This was prompted by thinking about the original problem which induced
the most-popular topic of late.)
As far as I know it's original, so if you use it, let me know how it
works, and maybe give me some credit. :slight_smile:

The idea is basically this: the web farm provider uses a NAT device
(or configures NAT on a router) for every peering point with a given peer
who wants best-exit. Separate address pools (in private address space)
are used for each such NAT (and distinct such pool sets amongst multiple
such peer networks). Ingress traffic to the web farm provider has it's
*source* address NAT'd, and internal routing points return traffic to
the *same* NAT through which the request traffic came.
Thus, return (data) traffic is best-exit.

This scales as the number of flows, not as the number of addresses announced,
so the MEDs scaling issue goes away. Performance may be an important factor,
so it is advised that anyone trying this test it in a lab first. :wink:

Pictorially
   ,-------- provider "G" -------.
  / \
  > >
NAT1 NAT2
  > >
   \ /
    `------- web farm "E" -------'

Traffic flows:
West coast, G -> NAT 1 (closest)-> web farm -> NAT1 -> west coast, G (best exit)
East coast, G -> NAT 2 (closest)-> web farm -> NAT2 -> east coast, G (best exit)

(Also works for NATs 3,4,5,...)

If the NAT can handle #flows seen, at wire speed, all is well. Limits would be
the total number of simultaneous flows, and max speed of NAT.

Side benefits are that the unique address pools allow for much easier
per-peer and per-region collection of stats, eg netflow (at some place
other than NATs).

Comments?

2

We've been doing a version of this for about a year now on a special
case basis. It works well enough, but can lead to some painful behaviours
as one attempts to scale. Paralleling NAT routers can help quite
a bit.

--Lloyd

Lloyd Taylor -- taylorl@digex.net
Vice President, Technical Operations
DIGEX Web Site Management Group
An Intermedia Company

3

"Brian Dickson" <briand@teleglobe.net> writes:

The idea is basically this: the web farm provider uses a NAT device
(or configures NAT on a router) for every peering point with a given peer
who wants best-exit. Separate address pools (in private address space)
are used for each such NAT (and distinct such pool sets amongst multiple
such peer networks). Ingress traffic to the web farm provider has it's
*source* address NAT'd, and internal routing points return traffic to
the *same* NAT through which the request traffic came.
Thus, return (data) traffic is best-exit.

Using a transparant cache for ingress traffic has the same effect as
a NAT device, and scales with the number of concurrent flows.

A cache farm is more expensive to provision and deploy than a simple NAT,
but has the advantage of allowing for logging of source/destURL pairs,
which may be important to some content providers. Caching can also can
be a significant performance improvement in many cases, such as paths
with high latency*BW links or congested long haul circuits.

-jem
     John Milburn jem@xpat.com
     Director - BoraNet jem@bora.net
     Cell +82 19-220-7035 Tel +82 2-220-7035
     Dacom Corporation, Seoul, Korea Fax +82 2-220-0751

The reasonable man adapts himself to the world; the unreasonable one
persists in trying to adapt the world to himself. Therefore all
progress depends on the unreasonable man. -- George Bernard Shaw