Network Arcitecture (R02) Papers
This course is mainly based around reading papers
and learning how to find the positive and negative
(in that order) in those papers.
Here's some jolly good advice on
How to read a paper
by Keshav from Waterloo, plus
how to write a great paper and give a great talk about it
by Simon Peyton-Jones, from Microsoft.
We'll go through these topics at roughly one per week. There are also two guest slots from
Andrew Moore on what router algorithms can realistically be made to do
(linking to his ACS module) and by Cecilia Mascolo (on sensor nets).
One thing I'd like readers to bear in mind is that one can take an
evolutionary approach to network architecture change, or one can
try to be revolutionary. In discussing a given paper, try to see
which approach it is taking and whether this supports or undermines
the viability of the proposed idea - this notion originated with
Constantine Dovrolis and Jenifer Rexford in this nice
counterpoint discussion. An important
evolutionary refinement is
href=http://en.m.wikipedia.org/wiki/Punctuated_equilibrium>Punctuated
Equilibrium: which may be how technology (including networks) evolve
really.
A very interesting complex systems/systems bio/eco/evolutionary view
on how layered architectures evolve is this paper on
Architecture, constraints, and behavior
by John C. Doyle & Marie Cseteb.
Discussion for L1 on Oct 7
This paper by Dave Clark of MIT is the startng point for all network
architecture papers in form and content:
The Design Philosophy of the DARPA Internet Protocols
Forwarding/Addressing & IPv6 for Oct 12th
IPv6 is what is on the
table but is it too little too late?
The Simple Internet Protocol (SIP)
Paul's Internet Protocol
IETF history of IPNG
for SIP, PIP and IPv6 disaster by committee
For presentation & discussion on Oct 19
To contrast with unified view of network architecture,
(which reuse the form, but have very different conclusions from the
Clark Internet Architecture paper above),
see these two papers
Plutarch for a view of protocol plurality
Haggle
to contrast with "always on" view that IP takes.
Internet Architectural Variants: For Essay for Nov 4
Internet Indirection
IPNL (again)
New Routing and Addressing
Routing on Flat Labels
See also
Compact Routing
Multicast- Oct 21/Oct 26
Deployment Issues for Multicast IP
Pragmatic General Multicast (PGM) (transport)
Backround Reading:-
Multicast intro i
Multicast intro ii
Multicast Review
Generic Router Assist for Multicast Transport
Pragmatic General Multicast (PGM) (RFC)
CDN, including P2P and Pub/Sub - Oct 28/Nov 2
Layering as Optimization Decomposition: A Mathematical Theory of
Network Architectures
Publist/subscribe in the Net
(PSIRP) - also see, the sigcomm version of the
LIPSIN scheme
See also
Content Centric Net (CCN) +
slides
Data Oriented Net Architecture (DONA)
Debunking some myths about structured and unstructured overlays+
see also, Chord, CAN, Guntella, Bittorrent - easy to find:)
Topology - background to Nov 4 Lecture
The Flattening Internet Topology: Natural Evolution, Unsightly
Barnacles or Contrived Collapse?
Gill, Phillipa; Arlitt, Martin; Li, Zongpeng; Mahanti, Anirban
The Internet is Flat: Modeling the Transition from a Transit Hierarchy
to a Peering Mesh
Multipath + Resource Pooling - Nov 9
Key et al on multipath routing
Wischik et al on multipath congestion control
Background on
Multipath TCP
Energy and the Net (& Programming Routers) - Background for Nov 11
List of papers for
essay 2
saving akamai a
lot
A very useful survey!
Also see most the papers in the
E-Energy Conference
and
Green
Networking workshop - especially Keshav's very general paper.
Also see
google's ideas on this
packet cache
New Router Implementation Tricks - Nov 16
gpu speedups
routebricks
Names/Identifiers/Topology/Mobility - Nov 18/Nov 23
LISP
Intentional Names
IPNL A Nat Based Net
Content Centric Names
Nimrod
8+8
Data Center Protocol/Network Archtectures
Switch/Transport
TCP Impact
Applying NOX to the Datacenter:
Ripcord: A Modular Platform for Data Center Networking:
Practical declarative network management
P2
and very recently in
CACM paper 11/2009
Mobile Crowds:
Crowd
Computing
A Cost Comparison of Data Center Network Architectures
See also
Predicate
Routing and D3N
Background:-
Map/Reduce,
Dryad/linq