Transcript The Stanford Clean Slate Program: An Overview

A Case for Rethinking the
Internet Architecture:
Some Promising Approaches
Guru Parulkar
http://cleanslate.stanford.edu
Executive Summary

Internet has been a great success
– Has emerged to be a great platform for innovations

It is time to reinvent Internet infrastructure
– Being subject to uses and abuses it is not designed for
– Can be a even bigger platform for innovations

Many promising approaches being put forward
– Infrastructure virtualization and programmability key

CIO organizations have a big role to play
– Active collaboration with “infrastructure” researchers important
The Stanford Clean Slate Program
http://cleanslate.stanford.edu
Internet Has Been A
Transformative Infrastructure
Top 20 Engineering
Innovations of 20th Century
A Century of Innovations
(National Academy of Engineering)
Internet Ossification
Kazaa VoIP Mail
Applications
Everything
Newson Video
WEB Audio
IM
YouTube
HTTP
Ossification
Transport protocols
TCP
SIP
UDP
RTP
Continued
Innovations
IP
Ethernet 802.11
on
Power lines IP
ATM
The Stanford Clean Slate Program
everything
Optical
Satellite Bluetooth
http://cleanslate.stanford.edu
State of Internet
“… in the thirty-odd years since its invention, new uses
and abuses, …, are pushing the Internet into realms
that its original design neither anticipated nor easily
accommodates.”
“Freezing forevermore the current architecture would
be bad enough, but in fact the situation is
deteriorating.”
Overcoming Barriers to Disruptive Innovation in Networking, NSF Workshp Report, 05.
The Stanford Clean Slate Program
http://cleanslate.stanford.edu
Internet Architecture Limitations

Security & robustness - to support other critical infrastructures

Control and management

Addressing, naming & (inter-domain) routing

Mobility of hosts and networks

Economic viability of different stakeholders

Scaling of service innovations
The Stanford Clean Slate Program
http://cleanslate.stanford.edu
IP Narrow Waist Not Designed to
Absorb Innovations

IP narrow waist architecture very successful

The IP narrow waist decides Internet
architecture and thus its behavior
– Trust and security
IP
– QoS
– Mobility
– …

IP narrow waist difficult to change and evolve
– Not designed for evolution
– Does not “absorb” innovations to the narrow waist
The Stanford Clean Slate Program
http://cleanslate.stanford.edu
Internet Architecture Does Not
Support Scaling of Services
Applications
Service innovation
starts at the edges
Network Substrate
New service providers have to build and deploy
their own infrastructure -- tremendous barrier
Scaling successful services requires
migrating into the infrastructure
The Stanford Clean Slate Program
http://cleanslate.stanford.edu
Future Internet Research Agenda

GENI Research Plan
– Compelling & comprehensive case for rethinking Internet
– 100+ page with two years of work
– http://www.geni.net/GDD/GDD-06-28.pdf

Not universally admired
– One group -- too broad
– Another group -- not broad enough
– “Classic science” missing -- maybe it should??
More a reflection of how CS community doesn’t still know
how to champion multiple big agendas
The Stanford Clean Slate Program
http://cleanslate.stanford.edu
Momentum Building: Funding

NSF: GENI Initiative
– FIND and other research programs
– GENI as a facility for experimentation

US multi-agency study on advanced networking

Europe
– FIRE and other complementary programs

Japan, Korea, …
The Stanford Clean Slate Program
http://cleanslate.stanford.edu
Momentum Building: Research

NSF FIND projects: http://www.nets-find.net/

European FIRE awards

Many ideas from the past few years

Stanford Clean Slate Internet Design Program
The Stanford Clean Slate Program
http://cleanslate.stanford.edu
Executive Summary

Internet has been a great success
– Has emerged to be a great platform for innovations

It is time to reinvent Internet infrastructure
– Being subject to uses and abuses it is not designed for
– Can be a even bigger platform for innovations

Many promising approaches being put forward
– Infrastructure virtualization and programmability key

CIO organizations have a big role to play
– Active collaboration with “infrastructure” researchers important
The Stanford Clean Slate Program
http://cleanslate.stanford.edu
The Stanford Clean Slate Program
Bring together Stanford’s breadth and depth:
Networking, optical communications, wireless, access networks, theory,
economics, security, applications, multimedia, operating systems, hardware
and VLSI, system architecture, …
Research for long term impact on the practice of
networking
Two pronged approach: “innovations in the small” and “innovations in the large”
Funding
Industry Collaborators & Sponsors: Cisco, DT, DoCoMo, NEC, Xilinx
Government Agencies: NSF, DARPA, …
Clean slate as a research process, not necessarily as a
deployment strategy
The Stanford Clean Slate Program
http://cleanslate.stanford.edu
Broad Interdisciplinary Focus
Heterogeneous
Applications
Security
Robustness
Network
Architectures
Economics
Policies
Heterogeneous
PHY Technologies
The Stanford Clean Slate Program
http://cleanslate.stanford.edu
Example Projects
Architectural
Blueprint of Future Internet?
E2E Secured
Network
Backbone
(Lightflow)
Flow
Theory
The Stanford Clean Slate Program
Open Prog
Mobile Internet
2020
Security
(Ethane)
Wireless
(Spectrum)
EASI:
Enable & Scale
Innovations
Backbone
(VLB)
Congestion
Control
(RCP)
http://cleanslate.stanford.edu
EASI: Goals
Enhancing the Internet to make it an even more
powerful engine for innovation.
Two Motivating Cases
 Architectural innovations
– enabling fundamental changes to the Internet
architecture

Service-level innovations
– lowering barrier-to-entry for scalable service
deployment
Joint project between Stanford and Princeton University
The Stanford Clean Slate Program
http://cleanslate.stanford.edu
Future Infrastructure: Key Concepts
Slicing, Virtualization, Programmability
The Stanford Clean Slate Program
http://cleanslate.stanford.edu
Future Infrastructure: Key Concepts
Slicing, Virtualization, Programmability
The Stanford Clean Slate Program
http://cleanslate.stanford.edu
Future Infrastructure: Key Concepts
Slicing, Virtualization, Programmability
The Stanford Clean Slate Program
http://cleanslate.stanford.edu
EASI Infrastructure Observations

Infrastructure includes
– Computing, storage, packet/circuit switching resources

Slicing, virtualization, programmability
– Across layers: layer 1 and up
– Across resource types: computing, storage, net
– End-to-end: end nodes, enterprise, regional, backbone,
…

Functionality and performance both important
The Stanford Clean Slate Program
http://cleanslate.stanford.edu
Potential for Innovation

Allow network providers to support value-added services

Empower end-user innovation

Allow user-centric innovations to migrate into the network

Allow network architectures to evolve seamlessly

Provide economic viability to different stakeholders
Democratization of Innovations
Eric von Hippel
The Stanford Clean Slate Program
http://cleanslate.stanford.edu
EASI in Enterprise
Controller
To Internet
The Stanford Clean Slate Program
http://cleanslate.stanford.edu
EASI OpenFlow Network: Goals

A way for researchers to run experiments in the
networks they use everyday.

Ease the deployment of GENI in college
campuses.

A “pragmatic” compromise
– Allow researchers to run experimental architectures in
their network…
– …without requiring vendors to expose internal
workings.
The Stanford Clean Slate Program
http://cleanslate.stanford.edu
No obvious way

Commercial vendor won’t open software and
hardware development environment
– Complexity of support
– Market protection and barrier to entry

Hard to build my own
– Prototypes are flakey
– Software only: Too slow
– Hardware/software: Fanout too small (need >100 for
wiring closet)
The Stanford Clean Slate Program
http://cleanslate.stanford.edu
Furthermore, we want…





Isolation: Regular production traffic untouched
Virtualized and programmable: Different flows processed in
different ways
Equipment we can trust in our wiring closet
Open development environment for all researchers (e.g.
Linux, Verilog, etc).
Flexible definitions of a flow
–
–
–
–
Individual application traffic
Aggregated flows
Alternatives to IP running side-by-side
…
“Flow” is a useful granularity for virtualization
The Stanford Clean Slate Program
http://cleanslate.stanford.edu
Network Slicing and Virtualization:
OpenFlow Switch
Flow Switch
sw Secure
Channel
hw Flow
Table
e.g. 48-ports of 1GE, or
wireless access point.
The Stanford Clean Slate Program
Open API
Linux PC
1. Decides which flows to allow
2. Programs flow-table
Packet processing:
If flow in table, forward packet
Else, send to controller
http://cleanslate.stanford.edu
Customized Flow Processing
Commercial
Switch
sw
Normal
Software
hw
Normal
datapath
Line-rate packet processing
Open API
Secure
Channel
Linux PC
Flow
Table
Office
1.
2.
3.
4.
5.
6.
Hardware virtualization
Congestion Control
Measurement
Packet inspection
New protocols
…?
Laboratory
Ivo
NetFPGA
The Stanford Clean Slate Program
http://cleanslate.stanford.edu
Server room
controller
OpenFlow-enabled
sw
hw
PC
SC
FT
OpenFlow-enabled
sw
hw
OpenFlow-enabled
sw
hw
sw
hw
SC
FT
OpenFlow-enabled
Commercial Switch
SC
FT
sw Normal
Software
hw Normal
Datapath
The Stanford Clean Slate Program
OpenFlow-enabled
SC
FT
OpenFlow-enabled
sw
hw
SC
FT
Secure
Channel
Flow
Table
http://cleanslate.stanford.edu
Deployment at Stanford
Stanford Computer Science Department
Gates Building
~1,000 network users
Current network
– Catalyst 4k in 22 wiring closets
• 100M Ethernet to desktops
• 2 x 1GE uplinks to basement
– 2 x Catalyst 6500 in basement
• 2 x 10GE uplinks to campus
– Cat 4k coming to end of life
Expect to announce building-wide OpenFlow shortly
The Stanford Clean Slate Program
http://cleanslate.stanford.edu
The EASI/GENI Big Picture
Experimenter
OpenFlow Network Aggregate
Enterprise GENI
Clearinghouse
Other Enterprise GENI Components
Controller: Aggregate
Component Manager
(ACM) on NOX
OpenFlow switches,
NetFPGA
The Stanford Clean Slate Program
Desktop, Clusters,
Storage, etc.
http://cleanslate.stanford.edu
Nationwide EASI Network
Over Internet2 Backbone
EASI
Enterprise
The Stanford Clean Slate Program
http://cleanslate.stanford.edu
Virtual World (VW) Environment

VW emerging to be another interesting application class

VW is very demanding and will push Internet to its limits
– 3D graphics, multimedia streaming and scalability critical
– Scalable to 1M+ concurrent users & 50M registered users spread over
world
– A single VW environment to support many VW applications

Two big components of the environment
– Massive content dissemination and large scale simulation
– Neither one supported well on the current Internet
The Stanford Clean Slate Program
http://cleanslate.stanford.edu
VW Environment: High Level Structure
Content
Dissemination

Simulation
“Simulation” models the VW for potentially 1M+ users
– Increasingly better fidelity and responsiveness are key requirements

Content provided by providers and 50M+ participants
– Higher quality multimedia and graphics content is a must

Content dissemination provides content to render relevant VW for 1M+
users
The Stanford Clean Slate Program
http://cleanslate.stanford.edu
VW Simulation
A simple model: map the world being simulated on a
2D grid and assign each square of the grid to a
processor
The Stanford Clean Slate Program
http://cleanslate.stanford.edu
VW Simulation on a Slice
Data Center A
Data Center B
Data Center C
Data Center D
VW Simulation on a PVI that is customized for
high
end
computing
with dynamic
topologies
The Stanford
Clean Slate
Program
http://cleanslate.stanford.edu
VW CDN on another Slice
VW CDN on a slice that is customized for
caching at the edges
The Stanford Clean Slate Program
http://cleanslate.stanford.edu
Research Scope
Virtual worlds, gaming, ubiquitous computing,
content dissemination, distributed storage,
sensor integration, …
Security, mobility,
robustness,
manageability,
scalability
Resource acquisition
and configuration,
programming models
and tools
Architecture for a
Virtualizable & Programmable
Network Substrate
Diverse node configurations:
data centers, backbone PoPs,
enterprise networks, wireless APs
The Stanford Clean Slate Program
http://cleanslate.stanford.edu
Networking Research and CIO Org

1970-80s
– Close collaboration between research groups and CIO org
– PhD students worked for CIO and produced some of the best research

1990s and beyond
– CIO orgs focused on providing service and keeping the infrastructure up
– Research becoming too sterile -- not benefiting from CIO orgs insights,
infrastructure, relationships with vendors
– CIO orgs missing the fun and excitement of research and innovations
Everyone loses, rate of innovations slows, vendors dominate.
[There are of course exceptions: Google and Stanford]
The Stanford Clean Slate Program
http://cleanslate.stanford.edu
New Opportunities

Infrastructure virtualization
– Multiple virtual infrastructures on same physical infra
– Isolation between production & experimental traffic/infra
– Production applications can opt-in into experimental
infrastructure to exploit new capabilities

Stanford and Princeton want to bring this to your
campus on commercial equipment
– With EASI and OpenFlow
This is just beginning -- lots of innovations to come
 Are you ready? Do you want to enable this?

The Stanford Clean Slate Program
http://cleanslate.stanford.edu
Executive Summary

Internet has been a great success
– Has emerged to be a critical infrastructure for society

It is time to reinvent Internet infrastructure
– Being subject to uses and abuses it is not designed for
– Can be a even bigger platform for innovations

Many promising approaches being put forward
– E.g., EASI and OpenFlow by Stanford and Princeton

CIO organizations have a big role to play
– Infrastructure virtualization and OpenFlow can be key enablers
The Stanford Clean Slate Program
http://cleanslate.stanford.edu