GEC 3 - Launch www.geni.net 1
Welcome to GEC 3Global Environment for Network Innovations
GENI Engineering Conference (GEC) 3
www.geni.netClearing house for all GENI news and documents
GEC 3 - Launch www.geni.net 2
GENI Engineering ConferencesMeet every 4 months to review progress together
• GEC 1 (U. Minnesota), GEC 2 (NSF)• GEC 3 – HP Labs, Palo Alto• Meetings are open to all who fit in the room
– Held at regular 4-month periods– Geographic rotation through US (central, east, west)– Held on / near university campuses – volunteers?– Travel grants for participant diversity (US academics only)
• Current plans for future GECs– GEC 4 – Florida International University, Miami, March 17-19, 2009.– GEC 5 – University of Washington, Seattle, July 21-23, 2009.– GEC 6 – University of Utah, Salt Lake City, Nov. 16-18, 2009.– GEC 7 – RENCI, Chapel Hill, March 16-18, 2010.
GEC 3 - Launch www.geni.net 3
This Conference’s ThemeLaunching GENI Spiral 1
• GENI Spiral 1 is now starting up– 29 academic / industrial teams– Organized into 5 competing control frameworks– Goal is first integrated prototypes “up and staggering” in 6-12
months– . . . from campus wiring closets through backbones– . . . from programmable routers and compute clusters through
vehicular wireless and large-scale sensor networks– Early demos at GEC 4 in March
• GEC 3 launches Spiral 1– It aims to make it clear “where you fit” . . .– . . . and what you need to do in the next 6-12 months
GEC 3 - Launch www.geni.net 4
With many thanks to . . .
• HP Labs– Dr. Prith Banerjee, Director of HP Labs– Dr. Jack Brassil, local organizer– Dr. Rick McGeer– and many others
• National Science Foundation– Dr. Jeannette Wing and Dr. Ty Znati– Dr. Suzi Iacono and Ms. Gracie Narcho
• Many volunteers– Peter O’Neil, new chair of Substrate WG
• and behind the curtains– Larry Landweber– Henry Yeh
GEC 3 - Launch www.geni.net 5
Larry Peterson, Princeton (Chair) Tom Anderson, Washington Dan Blumenthal, UCSB Dean Casey, NGENET Research David Clark, MIT Deborah Estrin, UCLA Joe Evans, Kansas Terry Benzel, USC/ISI
Nick McKeown, Stanford Dipankar Raychaudhuri, Rutgers Mike Reiter, CMU Jennifer Rexford, Princeton Scott Shenker, Berkeley Amin Vahdat, UCSD John Wroclawski, USC/ISI CK Ong, Princeton
Peter FreemanDebbie CrawfordLarry LandweberSuzi Iacono
Guru ParulkarDarleen FisherCheryl AlbusAllison Mankin
The GENI Planning Group and Many, Many Working Group Volunteers
And Within NSF
Their hard work has created GENI’s Conceptual Design,the starting point for all our work going forward.
And “our founders”
Ty ZnatiGracie NarchoPaul Morton
GEC 3 - Launch www.geni.net 6
In memory of Jay Lepreau
GEC 3 - Launch www.geni.net 7
Conference plan
End-to-End Slices –Intro and
Selected Project Talks
Lunch (12:35 – 2 PM)
GENI Spiral 1 – Introand Control Frameworks
NetSE + Opt-in Reports
Tuesday
* International BOF lunch will meet in Bldg 20 Akita
Internet2, NLR, Quilt
Control Frameworkbreakout meetings
Control Framework WG
Lunch / posters (12:00 – 2 PM)
Opt-in WG
Substrate WG
Networking Session
ExperimentWorkflow
WG
OMIS WG
Lunch* (12:30 – 2 PM)
Asia Report
EU Report
OpenFlow Demo
Feedback to GPO
GPO Solicitation #2
Wednesday ThursdayCCC Update
GEC 3 - Launch www.geni.net 8
Conference materials
• Agenda• GENI Spiral 1 Overview• Poster board assignment• GENI Engineering Conference survey
• T-shirt and pen, courtesy of HP Labs and EDJ
• Links to draft engineering documents– System Requirements– System Overview– Control Framework Architecture
GEC 3 - Launch www.geni.net 9
Some key introductions
• Network Science and Engineering Council (NetSE)– Prof. Ellen Zegura, Chair
• GENI Working Group Chairs– Prof. Jeff Chase, Prof. Patrick Crowley, Prof. Joe Evans, Mr.
Peter O’Neil, Prof. Larry Peterson, Ms. Heidi Picher Dempsey, Dr. Kristin Rauschenbach, Prof. Henning Schulzrinne, Mr. John Wroclawski
• National Science Foundation – CISE– Dr. Ty Znati, Dr. Suzi Iacono, Ms. Gracie Narcho
• GENI Project Office (GPO) staff
GEC 3 - Launch www.geni.net 10
Chip Elliott (GPO)
The NetSE Council
Ellen Zegura (Chair) Tom Anderson (UW) Joe Berthold (Ciena) Charlie Catlett (Argonne) Mike Dahlin (UT Austin)
Joan Feigenbarum (Yale) Stephanie Forrest (UNM) Jim Hendler (RPI) Michael Kearns (U.Penn) Ed Lazowska (UW) Peter Lee (CMU)
Larry Peterson (Princeton) Jennifer Rexford (Princeton) Alfred Spector (Google)
And not shown . . .
Roscoe GilesHelen Nissenbaum
GEC 3 - Launch www.geni.net 11
Introductory words from
NSF CISE and HP Labs
• Dr. Suzanne IaconoGENI Program Director, NSF CISE
• Dr. Jack Brassil, HP Labs
GEC 3 - Launch www.geni.net 12
Launching
GENI Spiral 1Global Environment for Network Innovations
GENI Engineering Conference (GEC) 3
www.geni.netClearing house for all GENI news and documents
GEC 3 - Launch www.geni.net 13
The GENI Vision A national-scale suite of infrastructure for long-running,realistic experiments in Network Science and Engineering
Mobile Wireless Network Edge Site
Sensor Network
Federated International Infrastructure
Programmable & federated, with end-to-end virtualized “slices”
Heterogeneous,and evolving over time viaspiral development
Deeply programmableVirtualized
GEC 3 - Launch www.geni.net 14
Spiral DevelopmentGENI grows through a well-structured, adaptive process
GENI Prototyping Plan
Use
Planning
Design
Build outIntegration
Use
• An achievable Spiral 1Rev 1 control frameworks, federation of multiple substrates (clusters, wireless, regional / national optical net with early GENI ‘routers’, some existing testbeds),Rev 1 user interface and instrumentation.
• Envisioned ultimate goal Example: Planning Group’s desired GENI suite, probably trimmed some ways and expanded others. Incorporates large-scale distributed computing resources, high-speed backbone nodes, nationwide optical networks, wireless & sensor nets, etc.
• Spiral Development ProcessRe-evaluate goals and technologies yearly by a systematic process, decide what to prototype and build next.
GEC 3 - Launch www.geni.net 15
FederationGENI grows by “gluing together” heterogeneous infrastructure
Goals: avoid technology “lock in,” add new technologies as they mature, and potentially grow quickly by incorporating existing infrastructure into the overall “GENI ecosystem”
NSF parts of GENI
Backbone #1
Backbone #2
Wireless#1
Wireless#2
Access#1
CorporateGENI suites
Other-NationProjects
Other-NationProjects
ComputeCluster
#2
ComputeCluster
#1
My experiment runs acrossthe evolving GENI federation.
My GENI Slice
This approach looks remarkably familiar . . .
GEC 3 - Launch www.geni.net 16
GENI System Decomposition (simplified)Engineering analysis drives Spiral 1 integration
GENI ClearinghouseGENI Admin and Ops Org
<Register
=<View
(Aggr)CompRegistry
<Slice Create
Principal Registry
GENI ProgrammableHost Cluster A
= <Component Mgr
Research Org A
= Research
=Researcher Helper Tools
Research Org B
< Operator
< Admin
=<Ticket Broker
=<View
<Register
=<View
< Com Admin< Slice
Admin
<Authen
= PI
HelpDesk
Slice Registry
TicketLog
EU CompAA
EU Admin and Ops Org
EU Clearinghouse
(federated network example)
<Ops Portal
CompOperator
Trust
<Ops and Mgmt
<Admin and Account
Trust
Host A1
Host Ax
GENI Programmable Ntwk Routing (Switch) Node B
= <Component Mgr
< Com Admin
<Ops Portal
CompOperator
Node B
GENI Metro (Sensor) Wireless Ntwk C
= <Component Mgr
< Com Admin
<Ops Portal
CompOperator
Ntwk C
GENI Enterprise (Resident) Access Ntwk D
= <Component Mgr
< Com Admin
<Ops Portal
CompOperator
Ntwk D
GENI Regional (National) Optical Ntwk E
= <Component Mgr
< Com Admin
<Ops Portal
CompOperator
Ntwk E
PoP PoP
Measurement Plane
= Control Plane
< Ops and Mgmt Plane
Experiment Plane
Operations
OperationsNSF Clearinghouse
NSF Clearinghouse
Federations
Federations
Researchers
Researchers
GENI Aggregates
GENI Aggregates
GEC 3 - Launch www.geni.net 17
What resources can I use?
Components
Aggregate AComputer Cluster
Components
Aggregate BBackbone Net
Components
Aggregate CMetro Wireless
These
GENIClearinghouse
Researcher
Resource discoveryAggregates publish resources, schedules, etc., via clearinghouses
GEC 3 - Launch www.geni.net 18
GENIClearinghouse
Components
Aggregate AComputer Cluster
Components
Aggregate BBackbone Net
Components
Aggregate CMetro Wireless
Create my slice
Slice creationClearinghouse checks credentials & enforces policyAggregates allocate resources & create topologies
GEC 3 - Launch www.geni.net 19
Components
Aggregate AComputer Cluster
Components
Aggregate BBackbone Net
Components
Aggregate CMetro Wireless
Experiment – Install my software,debug, collect data, retry, etc.
GENIClearinghouse
ExperimentationResearcher loads software, debugs, collects measurements
GEC 3 - Launch www.geni.net 20
Components
Aggregate AComputer Cluster
Components
Aggregate BBackbone Net
Components
Aggregate CMetro Wireless
Make my slice bigger !
GENIClearinghouse
Slice growth & revisionAllows successful, long-running experiments to grow larger
GEC 3 - Launch www.geni.net 21
Components
Aggregate AComputer Cluster
Components
Aggregate BBackbone Net
Components
Aggregate CMetro Wireless
Make my slice even bigger !
GENIClearinghouse
Components
Aggregate DNon-NSF Resources
FederatedClearinghouse
Federation of ClearinghousesGrowth path to international, semi-private, and commercial GENIs
GEC 3 - Launch www.geni.net 22
Components
Aggregate AComputer Cluster
Components
Aggregate BBackbone Net
Components
Aggregate CMetro Wireless
GENIClearinghouse
FederatedClearinghouse
Components
Aggregate DNon-NSF Resources
Operations & ManagementAlways present in background for usual reasonsWill need an ‘emergency shutdown’ mechanism
Oops
Stop the experimentimmediately !
GEC 3 - Launch www.geni.net 23
GENI Spiral 1 has now begun!First results expected in 6-12 months
GENI Project Office Announces $12M forCommunity-Based GENI Prototype Development
July 22, 2008
The GENI Project Office, operated by BBN Technologies, an advanced technologies solutions firm, announced today that it has been awarded a three year grant worth approximately $4M a year from the US National Science Foundation to perform GENI design and risk-reduction prototyping.
The funds will be used to contract with 29 university-industrial teams selected through an open, peer-reviewed process. The first year funding will be used to construct GENI Spiral 1, a set of early, functional prototypes of key elements of the GENI system.
GEC 3 - Launch www.geni.net 24
Generous Donations to GENI Prototyping
Internet2 and National Lambda Rail
40 Gbps capacity for GENI prototyping on two national footprintsto provide Layer 2 Ethernet VLANs as slices (IP or non-IP)
National Lambda RailUp to 30 Gbps nondedicated bandwidth
Internet210 Gbps dedicated bandwidth
Details at 5 PM today
Details at 5 PM today
GEC 3 - Launch www.geni.net 25
GENI’s Critical Technical RisksThese risks drive the Prototyping Goals for GENI Spiral 1
GENIClearinghouse
Components
Aggregate AComputer Cluster
Components
Aggregate BBackbone Net
Components
Aggregate CMetro Wireless
Create my slice
Critical Risk #1Clearinghouse & control framework is central but never demonstrated
Critical Risk #1Clearinghouse & control framework is central but never demonstrated
Critical Risk #2End-to-end slices across multiple technologies have never been demonstrated
Critical Risk #2End-to-end slices across multiple technologies have never been demonstrated
GEC 3 - Launch www.geni.net 26
Key Goals for GENI Spiral 1Drive down the critical technical risks in GENI’s concept
GENIClearinghouse
Components
Aggregate AComputer Cluster
Components
Aggregate BBackbone Net
Components
Aggregate CMetro Wireless
Create my slice
Goal #1Fund multiple, competing teams to develop GENI Clearinghouse technology, encourage strong competition within the first few spirals
Goal #1Fund multiple, competing teams to develop GENI Clearinghouse technology, encourage strong competition within the first few spirals
Goal #2Demonstrate end-to-end slices across representative samples of the major substrates / technologies envisioned in GENI
Goal #2Demonstrate end-to-end slices across representative samples of the major substrates / technologies envisioned in GENI
GEC 3 - Launch www.geni.net 27
Components
Aggregate AComputer
Cluster
Components
Aggregate BBackbone Net
Components
Aggregate CMetro Wireless
ReferenceDesign
Spiral 1 integration and trial operationsFive competing control frameworks, wide variety of substrates
Components
Aggregate A1
Computer Cluster
Components
Aggregate A2
Optical Network
Components
Aggregate A3
Metro Wireless
Cluster A
Components
Aggregate B1
Optical Network
Components
Aggregate B2
Sensor Network
Cluster B
Components
Aggregate C1
Computer Cluster
Components
Aggregate C2
Programmable Switches
Cluster C
Components
Aggregate D1
Optical Network
Components
Aggregate D2
Sensor Network
Cluster D
Components
Aggregate E1
Computer Cluster
Components
Aggregate E2
Optical Network
Components
Aggregate E3
Sensor Network
Cluster E
Components
Aggregate E4
Programmable Switches
GEC 3 - Launch www.geni.net 28
What do you need to do?
Key goals for Spiral 1 teams
• Integrate “vertically”into your control framework
• Integrate “horizontally”to create end-to-end slices
• Demonstrate (early) integrated prototypesin 6-12 months
• . . . and design GENI as you go!
Components
Aggregate AComputer
Cluster
Components
Aggregate BBackbone Net
Components
Aggregate CMetro Wireless
ReferenceDesign
GEC 3 - Launch www.geni.net 29
“Large project” challenges
• Engineering teams must work together– Each must rely on others– If one group changes its plans without agreement, other groups are
liable to get annoyed
• Meeting your schedules and deliverables is important– Very hard to integrate if schedules are hazy– Or if teams deliver something different from what they promised
• We expect some attrition of teams that fail to progress . . .– Their options will not be exercised for Years 2 or 3– The resultant $$$ will be given to teams that perform well– (But no DARPA-style “sudden death” downselects)
Can we really do it?Yes! This is roughly how our community built the early Internet.
GEC 3 - Launch www.geni.net 30
Suggestions for “how to”
• How do I know what to do?– Discuss within your control framework– Ask questions within the working groups– Ask GPO system engineers– Write simple, clear documents to help others– Communicate early and often
• How do I successfully integrate my prototype and manage dependencies?– Determine exactly who you need to integrate with– Communicate early and often within your framework– Pick simple, realistic goals with clear deadlines, and meet them– Ask GPO system engineers to help with documents and planning– Integrate early and often
• What if my cluster is not working out?– Don’t wait until the last second!– Talk with your GPO system engineer– We will be sympathetic and do our best to help– But all prototypes have to be in some cluster!
GEC 3 - Launch www.geni.net 31
Currently in the works
Regional Networks and RF Spectrum
• Regional networks– Key GENI participants– Potential for very interesting
new topologies– Perhaps GENI colo sites– Perhaps good networks for
advanced optical networking experiments
• National RF Research Spectrum– Try for good experimental
spectrum from FCC– Suitable for wideband
cognitive radios– Talk to Dave Farber, Srini
Seshan (CMU), Doug Sicker (CU)
Speaker at 5 PM: Jen Leasure, Program Manager
GEC 3 - Launch www.geni.net 32
Currently in the works
Prototyping GENI through campuses• August Meeting at O’Hare
– Thanks to EduCause (Mark Luker, Garret Sern)– Stimulated by Larry Landweber
• CIOs from 11 major research universities– Berkeley, Clemson, GA Tech, Indiana, MIT, Penn State, Rice, U.
Alaska, UIUC, UT Austin, U. Wisconsin
• Discussions of representative GENI prototypes– Nick McKeown, Stanford (OpenFlow)– Arvind Krishnamurthy, UW (Million Node GENI)– GPO Staff
• Near-term GENI / CIO activities– How to “GENI-enable” campus IT infrastructure– Coordinated policy for handling side-effects of network research
(Larry Peterson, Helen Nissenbaum)
GEC 3 - Launch www.geni.net 33
A look ahead . . .
GENI Workshops currently being contemplated
• Instrumentation and Measurement– Prof. Paul Barford, Wisconsin– Prof. Jim Griffioen, UKY
• Security– Prof. Matt Bishop, UC Davis
GEC 3 - Launch www.geni.net 34
A look ahead . . .
GENI Solicitation 2
• Current plans (tentative)– Solicitation issues ~ December 2008– Proposals due ~ February 2009– Total funds ~ $3.5 M / yr for 3 years,
as always subject to availability of funds
– Existing / new GENI participants both welcome
• Strong preference given to . . .– Joint Academic / Industrial teams– Active participation of campus /
regional infrastructure providers(e.g., letter from campus CIO)
• Current thoughts on what will be solicited
– Security design and analysis for GENI– Experimental workflow prototypes– Instrumentation and measurement
prototypes– Early tries at international federation– Other good ideas
• Discussion on Thursday afternoon
GEC 3 - Launch www.geni.net 35
Some thoughts as we begin . . .
• Move fast– A new world is unfolding very quickly
• Think big– We have enormous opportunities
• Work together– GENI prototyping is very much a positive-sum game
• Be yourself– We value your creativity and insights
GEC 3 - Launch www.geni.net 36
GENI Spiral 1
• Provides the very first, national-scale prototype of an interoperable infrastructure suite for Network Science and Engineering experiments
• Creates an end-to-end GENI prototype in 6-12 months with broad academic and industrial participation, while encouraging strong competition in the design and implementation of GENI’s control framework and clearinghouse
• Includes multiple national backbones and regional optical networks, campuses, compute and storage clusters, metropolitan wireless and sensor networks, instrumentation and measurement, and user opt-in
• Because the GENI control framework software presents very high technical and programmatic risk, the GPO has funded multiple, competing teams to integrate and demonstrate competing versions of the control software in Spiral 1
Nothing like GENI has ever existed; the integrated, end-to-end, virtualized,and sliceable infrastructure suite created in Spiral 1 will be entirely novel.