Software is increasingly powering technological innovation and disrupting traditional industries as more aspects become software-defined. Mobile data usage continues rising rapidly, driven mainly by video. The internet economy is advancing towards a service-centric model. Software-defined networking aims to make networks more programmable through logical abstractions, enabling new capabilities like traffic engineering and dynamic configuration. However, distributed systems and concurrency present challenges to scaling that require ongoing research.

1. Software is Eating
the World
Gary Berger
Technical Leader, Cisco Systems Inc.
gaberger@cisco.com
Image: http://www.crunchzilla.com/code-monster

2. Mobile computing continues to dominate
capacity
0
2
4
6
8
10
12
2011 2012 2013 2014 2015 2016
Mobile Data Traffic
(Exabytes/Month)
0%
20%
40%
60%
80%
100%
Mobile Data Transfer
Distribution
Other
Web
Video
Source: Cisco VNI Mobile 2012 Source: ByteMobile Mobile Analytics Report 2012

3. Internet Economy
Advancing towards Services
• Time shared
system
• Explicit
control
• Restricted
scope
• Tightly
Coupled
• Vertically
Integrated
Database CentricClient Centric Service CentricHost Centric
• Desktop
applications
• Centralized
File & Print
• Many
dependencies
• Low network
utilization
• Evolution of
Client/Server
• 4GL
Programming
• Stored
Procedures
• Vertically
Integrated
• Proprietary
“Technical Debt”
• Loosely
coupled
components
• Web based
interactions
• Activities
across
multiple hosts
• Global scope
• Data driven
constraints
Web Centric
• Normalized
Presentation
Layer
• Activities
scheduled off
isolated hosts
• Self-Described
Data
“New Economy”
Sparse to Dense

4. Software Defined Everything?
Software Defined Networking
Software Defined Storage
Software Defined Security
Etc..

5. Open Network Foundation
“The physical separation of the network control plane from the
forwarding plane, and where a control plane controls several
devices”[1]
Software Defined Networking?
1. https://www.opennetworking.org/sdn-resources/sdn-definition

6. “A software-defined network can be flexible enough to
avoid the application assumptions of designers of
previous kinds of networks”.
Derived from Staple, Werbach “The End Of Spectrum
Scarcity”
Software Defined Networking

7. Adoption

8. The “Power Wall”, 2004
Herb Sutter “Free Lunch is Over”, 2005
Economic crash, 2008
Data, Data, Data..
Many Contributing Factors

9. 1. Managing the network at scale!
2. Control access to network resources through declarative
(policy) and compositional (predicate) based
programming paradigms
3. Leverage the increasing network node degree (higher bi-
sectional bandwidth) for performance and availability
4. Static -> dynamic configuration and reconfiguration
5. Enabling an architecture for Ubiquitous Computing
6. Everything and Anything at the moment!
What is it about!
What its mostly about:
Leveraging Global Information to
optimize for:
• Traffic Engineering
• Admission control
• Isolation
• Filtering and
• Forwarding

10. OpenDayLight

11. Known problems have gone back 40 years.
Quite possibly vendors have been listening to the wrong
people?
Many attempts at programming the network but the
consumer demanded a weak and confusing interface
(i.e. CLI, SNMP, NetCONF) which have polluted the
design space
We still don’t have a formal way of thinking about
network architecture
The Network Disruption

12. 5 Oct 201112
RINA Architecture
As many layers as you need
“Layers contain distributed state of a specific scope”

13. Geomorphic View of Classic Internet
Application 1
Application 2
1 2 3 4
Gateway Gateway
Internet Core
LAN 1 LAN 2 LAN 3

14. NetAPI
Programmatic Forwarding
Secure communications
Policy Driven Inter-domain routing (i.e. Pathlets)
Framework for Internet Innovation

15. But really distributed computing is
hard!!
Concurrency
Contention
Coherency

16. Universal Scalability Law
C(N) =
N
1+a(N -1)+ bN(N -1)
Contention
(e.g. serialization, locking)
Coherency
(i.e. penalty incurred for
maintaining consistency of shared
writeable data)
Source: A General Theory of Computational Scalability Based on Rational Functions, Gunther 2008
Concurrency

17. SDN Scaling still under active
research
How many
controllers?
Devices per
controller?
Partitioning
strategy?

18. Controller Clusters
Connectivity
CA B

19. Deeper analysis shows we cannot
just throw away peer communication
• Data
dissemination
• Discovery
• Availability

20. The cost of deadlock free consensus
1+(N-1)+[N*(N-1)]+N+1
0
50
100
150
200
250
300
2 3 4 5 6 7 8 9 10 11 12 13 14 15
Messages
Messages
N = # of Acceptors
Acceptors/Learners
Note: Classic Multi-Paxos without optimization

21. SDN Continuum
A spectrum which encompasses
in-network state distribution at
one extreme and complete
separation of control and
dataplane as the other extreme
The purpose of which can result in
either a discovery of an invariant
protocol architecture which
provides the foundation for the
next generation Internet or paves
the way for complete protocol
customization.

22. Standards

23. IETF Bottleneck
Count by Publication Status
Total
BEST CURRENT PRACTICE 213
DRAFT STANDARD 145
EXPERIMENTAL 417
HISTORIC 267
INFORMATIONAL 2164
INTERNET STANDARD 96
PROPOSED STANDARD 2597
UNKNOWN 906
Grand Total 6805

24. RFC By Year
0
50
100
150
200
250
300
350
400
450
500 1968
1971
1974
1977
1980
1983
1986
1989
1992
1995
1998
2001
2004
2007
2010
2013
Average of 265/yr
over past decade

25. Gap is widening
0
50
100
150
200
250
300
1968
1971
1974
1977
1980
1983
1986
1989
1992
1995
1998
2001
2004
2007
2010
2013
BEST CURRENT PRACTICE
DRAFT STANDARD
EXPERIMENTAL
HISTORIC
INFORMATIONAL
INTERNET STANDARD
PROPOSED STANDARD
UNKNOWN

26. Getting To Internet Standard?
1. There are at least two independent interoperating implementations with
widespread deployment and successful operational experience.
2. There are no errata against the specification that would cause a new
implementation to fail to interoperate with deployed ones.
3. There are no unused features in the specification that greatly increase
implementation complexity.
4. If the technology required to implement the specification
requires patented or otherwise controlled technology, then the
set of implementations must demonstrate at least two independent,
separate and successful uses of the licensing process.
RFC 6410

27. “Network Virtualization is the abstraction of the control
plane into layers”.. Scott Shenker
Abstract the invariants from the set of complex
control plane protocols
Vertex
Edge
Property (tenant, vlan, min bw, min
latency, open, closed, etc.)
Network Virtualization

28. Address Virtualization
Policy Virtualization
Topology Virtualization
Virtualization Profile

29. Address Coupling
Application
Node
L2 (MAC)
L3 (IP)
Socket
(local)
Route Path
Application
Node
L2 (MAC)
L3 (IP)
Socket
(local)
L2 and L3 address
point to the
interface not the
node

30. Strict dependencies of identity and address force coupling of
policy, telemetry and state..
Programming models still being thought about
(Languages, Compilers, Runtimes)
Virtualization provides the illusion of infinite resources but we must
have “Mechanical Sympathy” (i.e. TCAM Space, SRAM, CPU Cycles)
Encapsulation provides a means to decouple identity from location
by adding a logical name space over a location dependent address
space (i.e. TRILL, FabricPath, LISP, STT, VXLAN, NVGRE, etc..)
Proper abstractions provide the invariant interfaces but do we have
the right ones?
Centralizing control provides a global view. Are we willing to throw
away the local view (BFD, LAG, etc..)?
Conclusion

31. Innovation at the Server
NFV Enablement

32. L3 Performance
Source: http://www.intel.com/content/dam/www/public/us/en/documents/solution-briefs/communications-packet-processing-brief.pdf

33. Application Budgets
BYOS (Bring Your Own Stack)
1400
881
341
69
3000
1962
881
338
4920
3259
1530
661
10Mpps 14.8Mpps(1x10GE) 29.6Mpps(2x10GE) 59.5Mpps(1x40GE)
Intel E5-2600
@200 Cycles
8Core@2Ghz 16Core@2Ghz 16Core@3.2GHz Optimizations
DPDK
NETMAP
PF_RING/LI
BZERO

34. "The only way to get increased performance for new
applications is for developers to be aware of new
features in these chips. They have to be aware of what’s
inside to make their code more efficient.”
Krste Asanovic, UC Berkley
Systems Driven Networking

35. SDN is a manifestation of over 20 years of technical debt
which can no longer be swept under the rug
IETF process is antiquated
Crowd Sourcing + Parallel Programming + CMP allows for
rapid prototyping
Things are going to change..
“Network innovation is stifled by applying a limited set of
design principals along with craft-like patching in a rigid
architecture”
Conclusion