230 likes | 396 Views
Software-defined Networks October 2009. With Martin Casado and Scott Shenker And contributions from many others. Outline. Trends Towards “Software-defined Network” Towards “Slicing” of network infrastructure Government role. Million of lines of source code. 500M gates 10Gbytes RAM.
E N D
Software-defined NetworksOctober 2009 With Martin Casado and Scott Shenker And contributions from many others
Outline Trends • Towards “Software-defined Network” • Towards “Slicing” of network infrastructure • Government role
Million of linesof source code 500M gates 10Gbytes RAM We have lost our way Routing, management, mobility management, access control, VPNs, … App App App 5400 RFCs Barrier to entry Operating System Specialized Packet Forwarding Hardware Bloated Power Hungry Many complex functions baked into the infrastructure • OSPF, BGP, multicast, differentiated services,Traffic Engineering, NAT, firewalls, MPLS, redundant layers, … • An industry with a “mainframe-mentality”
Reality App App App App App App Operating System Operating System Specialized Packet Forwarding Hardware Specialized Packet Forwarding Hardware • Lack of competition means glacial innovation • Closed architecture means blurry, closed interfaces
Glacial process of innovation made worse by captive standards process Deployment Idea Standardize Wait 10 years • Driven by vendors • Consumers largely locked out • Lowest common denominator features • Glacial innovation
Change is happening in non-traditional markets App App App Network Operating System App App App App App App Operating System Specialized Packet Forwarding Hardware Operating System App App App App App App Specialized Packet Forwarding Hardware Operating System Specialized Packet Forwarding Hardware Operating System Specialized Packet Forwarding Hardware App App App Operating System Specialized Packet Forwarding Hardware
3. Well-defined open API The “Software-defined Network” 2. At least one good operating system Extensible, possibly open-source App App App 1. Open interface to hardware Network Operating System Simple Packet Forwarding Hardware Simple Packet Forwarding Hardware Simple Packet Forwarding Hardware Simple Packet Forwarding Hardware Simple Packet Forwarding Hardware
Isolated “slices” Many operating systems, or Many versions App App App App App App App App Network Operating System 1 Network Operating System 2 Network Operating System 3 Network Operating System 4 Open interface to hardware Open interface to hardware Virtualization or “Slicing” Layer Simple Packet Forwarding Hardware Simple Packet Forwarding Hardware Simple Packet Forwarding Hardware Simple Packet Forwarding Hardware Simple Packet Forwarding Hardware
Consequences More innovation in network services • Owners, operators, 3rd party developers, researchers can improve the network • E.g. energy management, data center management, policy routing, access control, denial of service, mobility Lower barrier to entry for competition • Healthier market place, new players
The change has already started In a nutshell • Driven by cost and control • Started in data centers…. and may spread • Trend is towards an open-source, software-defined network • Growing interest for cellular and telecom networks
Example: New Data Center Cost 200,000 servers Fanout of 20 a 10,000 switches $5k commercial switch a $50M $1k custom-built switch a $10M Savings in 10 data centers = $400M Control Optimize for features needed Customize for services & apps Quickly improve and innovate Large data center operators are moving towards defining their own network in software.
Trend App App App App App App Controller 1 Controller 2 Controller 1 Controller 2 NOX (Network OS) Network OS Windows (OS) Linux Mac OS Windows (OS) Linux Mac OS Windows (OS) Linux Mac OS Virtualization or “Slicing” Virtualization layer OpenFlow x86 (Computer) Computer Industry Network Industry
What NSF is supportingTrials of “Software-defined Network” & OpenFlow US College Campus Trials • UW, Georgia Tech, Princeton, Rutgers, UW-Madison, Clemson, Indiana, Stanford • Vendors with prototype OpenFlow: Cisco, Juniper, HP, NEC, Ciena, Arista, Quanta, …. National College Backbone Trials Data Center Clusters (with Google, Yahoo!, HP, etc.)
Nationwide OpenFlow Trials UW UnivWisconsin Princeton IndianaUniv Rutgers Stanford NLR Internet2 Clemson GeorgiaTech Production deployments before end of 2010
The role of government When funding new infrastructure • Mandate open interface to equipment (OpenFlow) • Recommend trials of “software-defined networks” Risk Invest in the wrong equipment, and we are stuck with “same old” equipment for 10 years
Software-defined Wireless NetworksApplies equally to wireless networks Mobility manager, AAA, billing, MVNO, Wireless service provider, … App App App Network Operating System Simple Packet Forwarding Hardware Simple Packet Forwarding Hardware Simple Packet Forwarding Hardware WiFi, WiMAX, LTE Simple Packet Forwarding Hardware Simple Packet Forwarding Hardware
Outline Trends • Towards “Software-defined Network” • Towards “Slicing” of network infrastructure • Government role Dream • Making available the abundant wireless capacity around us • Technical trend • Business hurdles
Observations • We are not short of wireless capacity: It is abundant, but off limits • Cell phone today = 6 radios • Cell phone in 2020 = 20 radios? Can we: • Decouple service providers from physical networks? • Allow user to decide to connect to any or many wireless networks simultaneously?
Service Providers and Infrastructure Services Services Services App App App App App App “Newco” OS “Vodafone” OS “AT&T” OS Service providers in cloud Open flow-based interface My Employer Slicing Slicing Slicing Nationwide infrastructure owners A home WiMAX WiFi AP LTE WiFi AP Slicing LTE WiMAX WiFi AP WiFi AP LTE