1 On the Design & Evolution of an Architecture for Testbed Federation Stephen Soltesz, David Eisenstat, Marc Fiuczynski, Larry Peterson.

Slides:



Advertisements
Similar presentations
A Usage-based Authorization Framework for Collaborative Computing Systems Xinwen Zhang George Mason University Masayuki Nakae NEC Corporation Michael J.
Advertisements

News in XACML 3.0 and application to the cloud Erik Rissanen, Axiomatics
NRL Security Architecture: A Web Services-Based Solution
1 The Challenges of Creating an Identity Management Infrastructure for the University of California David Walker Karl Heins Office of the President University.
PlanetLab V3 and beyond Steve Muir Princeton University September 17, 2004.
PlanetLab: Evolution vs Intelligent Design in Global Network Infrastructure Larry Peterson Princeton University.
1 Planetary Network Testbed Larry Peterson Princeton University.
PlanetLab Architecture Larry Peterson Princeton University.
Sponsored by the National Science Foundation 1 Activities this trimester 0.5 revision of Operational Security Plan Independently (from GPO) developing.
High Performance Computing Course Notes Grid Computing.
PlanetLab: Evolution vs Intelligent Design in Global Network Infrastructure Larry Peterson Princeton University.
PlanetLab: Present and Future Steve Muir 3rd August, 2005 (slides taken from Larry Peterson)
Global Overlay Network : PlanetLab Claudio E.Righetti 6 October, 2005 (some slides taken from Larry Peterson)
PlanetLab: Catalyzing Network Innovation October 2, 2007 Larry Peterson Princeton University Timothy Roscoe Intel Research at Berkeley.
Xen , Linux Vserver , Planet Lab
OneLab: Federating Testbeds Timur Friedman Laboratoire LIP6-CNRS Université Pierre et Marie Curie TERENA Networking Conference 2007 Lyngby, Denmark, 22.
PlanetLab Federation Development Aaron Klingaman Princeton University.
PlanetLab: An open platform for developing, deploying, and accessing planetary-scale services Overview Adapted from Peterson.
CoreGRID Workpackage 5 Virtual Institute on Grid Information and Monitoring Services Authorizing Grid Resource Access and Consumption Erik Elmroth, Michał.
NanoHUB.org online simulations and more Network for Computational Nanotechnology 1 Autonomic Live Adaptation of Virtual Computational Environments in a.
DISTRIBUTED CONSISTENCY MANAGEMENT IN A SINGLE ADDRESS SPACE DISTRIBUTED OPERATING SYSTEM Sombrero.
Global Overlay Network : PlanetLab Claudio E.Righetti October, 2006 (some slides taken from Larry Peterson)
Deconstructing PLC PlanetLab Developer’s Meeting May 13-14, 2008 Larry Peterson.
Exokernel: An Operating System Architecture for Application-Level Resource Management Dawson R. Engler, M. Frans Kaashoek, and James O’Toole Jr. M.I.T.
Container-based OS Virtualization A Scalable, High-performance Alternative to Hypervisors Stephen Soltesz, Herbert Pötzl, Marc Fiuczynski, Andy Bavier.
Dienst Distributed Networked Publishing Carl Lagoze Digital Library Scientist Cornell University.
Report from Breakout Session 1.2 Secure Consumerization: the Genuine Trustworthiness Revolution Chair: Craig Lee Rapporteur: Paolo Mazzetti.
Secure Web Applications via Automatic Partitioning Stephen Chong, Jed Liu, Andrew C. Meyers, Xin Qi, K. Vikram, Lantian Zheng, Xin Zheng. Cornell University.
PlanetLab: A Distributed Test Lab for Planetary Scale Network Services Opportunities Emerging “Killer Apps”: –CDNs and P2P networks are first examples.
GENI: Catalyzing Network Research May 31, 2007 Larry Peterson Princeton University.
Federation Strategy Robert Ricci GENI-FIRE Workshop September 2015.
Grid Security Issues Shelestov Andrii Space Research Institute NASU-NSAU, Ukraine.
PlanetLab and OneLab Presentation at the GRID 5000 School 9 March 2006 Timur Friedman Université Pierre et Marie Curie Laboratoire LIP6-CNRS PlanetLab.
GEC5 Security Summary Stephen Schwab Cobham Analytical Services July 21, 2009.
HEPKI-PAG Policy Activities Group David L. Wasley University of California.
An Overview of the PlanetLab SeungHo Lee.
Sponsored by the National Science Foundation GENI Integration of Clouds and Cyberinfrastructure Chip Elliott GENI Project Director
1 A Blueprint for Introducing Disruptive Technology into the Internet Larry Peterson Princeton University / Intel Research.
Sponsored by the National Science Foundation GENI Exploring Networks of the Future
PlanetLab: A Platform for Planetary-Scale Services Mic Bowman
Access Control for Federation of Emulab-based Network Testbeds Ted Faber, John Wroclawski 28 July 2008
Privacy Preserving Delegated Access Control in Public Clouds.
PlanetLab Architecture Larry Peterson Princeton University.
Sponsored by the National Science Foundation GENI Security Architecture What’s Up Next? GENI Engineering Conference 7 Durham, NC Stephen Schwab SPARTA/Cobham.
The RISE Internet Architecture Nick Feamster (Georgia Tech) Brighten Godfrey (UIUC) Nick McKeown (Stanford) Guru Parulkar (Stanford) Jennifer Rexford (Princeton)
Marc Fiuczynski Princeton University Marco Yuen University of Victoria PlanetLab & Clusters.
PlanetLab: Evolution vs Intelligent Design in Global Network Infrastructure Larry Peterson Princeton University.
SDN Management Layer DESIGN REQUIREMENTS AND FUTURE DIRECTION NO OF SLIDES : 26 1.
Globus and PlanetLab Resource Management Solutions Compared M. Ripeanu, M. Bowman, J. Chase, I. Foster, M. Milenkovic Presented by Dionysis Logothetis.
WLCG Authentication & Authorisation LHCOPN/LHCONE Rome, 29 April 2014 David Kelsey STFC/RAL.
Distributed Data Access Control Mechanisms and the SRM Peter Kunszt Manager Swiss Grid Initiative Swiss National Supercomputing Centre CSCS GGF Grid Data.
MagicNET: XACML Authorization Policies for Mobile Agents Mr. Awais Shibli.
Hosting Wide-Area Network Testbeds: Policy Considerations Larry Peterson Princeton University.
1 A Blueprint for Introducing Disruptive Technology into the Internet Larry Peterson Princeton University / Intel Research.
Clearing house for all GENI news and documents GENI Architecture Concepts Global Environment for Network Innovations The GENI Project Office.
May 7-8, 2007ICVCI 2007 RTP Autonomic Approach to IT Infrastructure Management in a Virtual Computing Lab Environment H. Abdel SalamK. Maly R. MukkamalaM.
PlanetLab-Based Control Framework for GENI Larry Peterson Princeton University.
01/27/10 What is PlanetLab? A planet-wide testbed for the R & D of network applications and distributed computing Over 1068 nodes at 493 sites, primarily.
Designing a Federated Testbed as a Distributed System Robert Ricci, Jonathon Duerig, Gary Wong, Leigh Stoller, Srikanth Chikkulapelly, Woojin Seok 1.
Hardware-rooted Trust for Secure Key Management & Transient Trust
OneLab - PlanetLab Europe Presentation for Rescom 2007
Container-based Operating System Virtualization: A scalable, High-performance Alternative to Hypervisors Stephen Soltesz, Herbert Potzl, Marc E. Fiuczynski,
Session 11 Other Assurance Services
THE STEPS TO MANAGE THE GRID
PlanetLab: a foundation on which the next Internet can emerge
PlanetLab: Evolution vs Intelligent Design in Global Network Infrastructure Larry Peterson Princeton University.
GENI Integration of Clouds and Cyberinfrastructure
Mix & Match: Resource Federation
Example Use Case for Attribute Authorities and Token Translation Services - the case for eduGAIN Andrea Biancini.
Presentation transcript:

1 On the Design & Evolution of an Architecture for Testbed Federation Stephen Soltesz, David Eisenstat, Marc Fiuczynski, Larry Peterson

2/17 The Original Problem Give User access to an Owner’s Nodes

3/17 Contribution of PLC princeton_codeen nyu_d cornell_beehive att_mcash cmu_esm harvard_ice hplabs_donutlab idsl_psepr irb_phi paris6_landmarks mit_dht mcgill_card huji_ender arizona_stork ucb_bamboo ucsd_share umd_scriptroute … N x N Trusted Intermediary (PLC) Users Princeton Berkeley Washington MIT Brown CMU NYU EPFL Harvard HP Labs Intel NEC Labs Purdue UCSD SICS Cambridge Cornell … Owners

4/17 Trust in PLC Owner PLC User ) PLC expresses trust in a user by issuing it credentials to access a slice 2) Users trust PLC to create slices on their behalf and respect credentials 3) Owner trusts PLC to vet users and map network activity to right user 4) PLC trusts owner to keep nodes physically secure and running

5/17 The New Problem Owners Testbed 1 Users Owners Testbed 2 Users Owners Testbed 3 Users ? ?

6/17 Outline Federation Design Tension in a Central Implementation Two Authorities Federation between Authorities Evolution during the last year Delegation of Slice Creation Federation With OneLab How to address Scale and Isolation

7/17 PLC is Centralized princeton_codeen nyu_d cornell_beehive att_mcash cmu_esm harvard_ice hplabs_donutlab idsl_psepr irb_phi paris6_landmarks mit_dht mcgill_card huji_ender arizona_stork ucb_bamboo ucsd_share umd_scriptroute … Trusted Intermediary (PLC) Users Princeton Berkeley Washington MIT Brown CMU NYU EPFL Harvard HP Labs Intel NEC Labs Purdue UCSD SICS Cambridge Cornell … Owners

8/17 Two Authorities of PLC SA = Slice Authority Represents Users Names Slices MA = Management Authority Represents Owners Creates Slices on Nodes User SA Owner MA PLC

9/17 Narrow Waist The New Narrow Waist SA exports Slices MA exports Nodes The Simplest form of Federation Between Users and Node owners SAMA Slices Nodes User Node

10/17 Federation with a Management Authority SA users benefit, access to more nodes MAs control policy on its nodes

11/17 Federation with a Slice Authority MA has a single infrastructure SAs represent different user groups Shared namespace Agreement between SA1 & SA2

12/17 Federation In Combination Slice & Management Federation This is the goal with Onelab

13/17 Outline Federation Design Tension in a Central Design Two Authorities Federation between Authorities Evolution during the last year Delegation of Slice Creation Federation With OneLab How to address Scale and Isolation

14/17 Delegation as a Slice User PLC is default Slice Creation Service (SCS) User A delegates Slice Creation User B calls Node Manager to create slice User B could be a Slice Authority

15/17 Federation with OneLab PLC1 caches PLC2, and vice versa Concerns How to limit slices, or nodes? Where to place policy? How many peers can we maintain? Who enforces namespaces?

16/17 Addressing Scale & Isolation What if… The SA exports one slice to the MA SA 1MA MA - Node Manager SA1_fooSA1_bar Node SA2_one SA2_one_aSA2_one_b SA 2 SA2_one

17/17 Conclusion PLC addresses disparate concerns Pulls at the centralized implementation Proposed a general approach Decouples PLC design into MA & SA Development efforts during the last year Delegation and Federation

18/17

19/17 PLC Today

20/17 PLC with MA and SA Recursive MA and SA User privilege from position in tree Any MA or SA may be autonomous

21/17

22/17

23/17 User to VM MA and SA cache Owner and User info SA is an authority for Slice names MA is an authority for Node software

24/17 PLC with State on Nodes Node Owner Management Hard state in a volatile environment PLC state conflicts with Owner preference Solve by central policy management

25/17 Four Scenarios | Users | >> Size(node) O(N 2 ) O(N)