[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [RRG] Geoff Huston's article on BGP stability, update statistics and damping



On Jun 21, 2007, at 3:23 PM, Geoff Huston wrote:


Actually Noel, I'm not sure that I agree with either of your assertions, and the basic reason is a lack of an analysis of this over a long term over a number of years (the data is there, but someone has to set up the computational run across it). My intuition says that as the degree of interconnection in the inter- AS cloud increases, then the BGP "amplification" of underlying events increases, and the same set of underlying events could be the cause of 26%, 27%,... etc of all updates in the future. i.e. the querstion in my mind is: are the dynamics we've been seeing in update load an artifact of the increasing size of the internet, the increasing interconnection of the Internet, the increasing level of policy diversity within the Internet or all three - or do all three growth elements tend to interact with the rather chatty way in which BGP undertakes convergence to create a long term traffic trend? If this is the case and if we understand that we really cannot change the dynamics of the first three elements, then what precisely is the nature of the interaction with BGP, and is it possible that by altering BGP update propagation behaviors is it possible to shift the BGP load onto a different trajectory?


I know I've said this a few times but figured it's worth stating here
again..  In addition to external BGP and inter-AS cloud interconnection
comments, the intra-domain BGP topologies imposed by the protocol
are considerable (iBGP advertisement rules, network topologies, etc..)
and will likely find considerable benefit in this and related stability work.

This amplification we're speaking of is quite obvious where BGP's
route advertisement is most strict and policy capabilities of BGP are
of less utility - in the "core" of the iBGP core internal to an AS. While
the FIB/RIB sizes in this "DFZ" remain on fixed trajectory, the external
interconnection denseness forces a much steeper growth curve
in RIB size (and all the underlying update oscillation, instability and
other properties) internal to the BGP network (as does a whole
additional array of path attributes).

The number of BGP paths in internal BGP core is very often 5-15x or
more than that of the AS border routers, and it's where things will break
first.  Keeping this in mind when considering both short and long-term
solutions is paramount.

-danny


--
to unsubscribe send a message to rrg-request@psg.com with the
word 'unsubscribe' in a single line as the message text body.
archive: <http://psg.com/lists/rrg/> & ftp://psg.com/pub/lists/rrg