Three fun things to work on in your spare time

1
Three fun things to work on in your spare time

• John Wroclawski
• USC/ISI

2
The mostly theoreticalReconceiving the
intellectual basis of Network Dist. System
Architecture

• Electricity Today
• (Architecture ???)

Electricity 1800 (Architecture Today)
3
Theoretically Derived Architectures

• MANET resource allocation formulated as global
  optimization problem
• Primal-dual decomposition generates a set of dual
  problems/algorithms/modules
• Local (except scheduling)
• Tied together through congestion prices
• System Architecture traceable to theoretically
  provable optimality..
• Framework to reason rigorously about tradeoffs..

Utility function U_sx_s (strictly concave
function of the sending rates)
Cross-layer interaction in form of congestion
prices (cost per unit flow of sending data
along a link to a destination)
Optimal Cross-Layer Congestion Control, Routing,
and Scheduling Design in Ad Hoc Wireless
Networks. Lijun Chen, Steven H. Low, Mung
Chiang, John C. Doyle (Caltech and Princeton)
4
Language-Defined Architecture

• Role Based Architecture imagined flexible,
  customizable location and composition of
  architectural functions
• But just a data path mechanism. Where do
  semantics come from?
• One possible idea Architecture Composition
  Languages
• Explicit description may give
• Introspection
• Run-time Validation

• ?(defmethod (flow check-security-policy)
• ((port protocol)
• (cond ((eq port 'smtp)
• ())))
• (defwrapper (flow check-security-policy)
• ((port protocol) . wrapped-body)
• (cond ((eq port 'smtp)
• (format t
• "s no mail for you, monkey-boy"
• self))
• (t
• ,_at_wrapped-body
• (format t
• "s pass traffic for s onward"
• self port))))

From Protocol Stack to Protocol Heap - Role
Based Architecture. Robert Braden, Ted Faber, and
Mark Handley. Proc. Hotnets-1, ACM SIGCOMM CCR,
v33 1, Jan 2003
5
The possibly practicalNetworks that know what
theyre doing

• Network Management is a poster child challenge
  for the next few years
• Highly skilled humans
• managing a critical infrastructure of society
• by hand. Oops.
• Todays network management is very low level
• Glossy interfaces often just make the problem
  harder

6
The alternative networks that know what theyre
trying to do

• Model based and similar techniques allow the
  system to understand its goals
• Separating model and actual implementation..
• Allows introspection, consistency evaluation,
  similar actions..
• To be performed by reasoning agents at high level.

I think therefore I am. Yikes!
7
Problem 1The lack of Domain-Appropriate
Algorithms

• Some limitations of current fault diagnosis
  algorithms
• Multi-layer fault isolation
• Temporal correlation among events
• Distributed fault localization techniques
• Fault localization in service-oriented
  environments
• Fault localization in dynamic networks
• Obtaining fault localization models

• Distributed Fault Diagnosis across multiple
  administrative domains
• Partition problem hierarchically, following
  routing
• If failure cannot be diagnosed (probabilistically)
  within local domain
• delegate to higher level manager with
  interdomain routing expertise
• HL manager calls multiple local managers..
• Which report back so HL manager can synthesize
  result

A survey of fault localization techniques in
computer networks. M. Steinder and A. Sethi,
Science of Computer Programming 53 (2004)
Multi-domain diagnosis of end to end service
failures in hierarchically routed networks. M.
Steinder and A. Sethi, Unpublished.
8
Problem 2Shared, Common Structure
High level problem assertion Fixit!
High level specs Goals and constraints
High level specs Goals and constraints
High level operationalcharacterization Success
story!
Designspecs
Problemresolver
Network (re)builder
Network observer
Region composer
Negotiation
Yourregion composer
Networkexplainer
Networkregion
Networkregion
Details
Status
Networkregion
Networkregion
Networkregion
Networkregion
Networkregion
A Knowledge Plane for the Internet. D. D. Clark,
C. Partridge, J. C. Ramming, and J. Wroclawski,
Proc. ACM SIGCOMM 2003.
9
The nearly impossibleBuilding a realistic
experimental research facility

• GENI is an open, large-scale, realistic
  experimental facility that will revolutionize
  research in global communication networks.

Goal Seamless conception-to-deployment process
10
Modeling the Real World

• Real users
• User opt-in
• Real user workloads
• Long lived services
• Economics
• virtual costs assigned to system elements..
• Failures
• Modeled or arbitrary hw failures and sw bugs..
• Administrative environment
• Multiple players with competing interests..