The Grid: Past, Present, and Future Tom DeFanti University of Illinois at Chicago as Ian Foster Mathematics and Computer Science Division Argonne National.

Slides:



Advertisements
Similar presentations
Electronic Visualization Laboratory University of Illinois at Chicago EVL Optical Networking Research Oliver Yu Electronic Visualization Laboratory University.
Advertisements

University of Illinois at Chicago The Future of STAR TAP: Enabling e-Science Research Thomas A. DeFanti Principal Investigator, STAR TAP Director, Electronic.
The Anatomy of the Grid: An Integrated View of Grid Architecture Carl Kesselman USC/Information Sciences Institute Ian Foster, Steve Tuecke Argonne National.
ASCR Data Science Centers Infrastructure Demonstration S. Canon, N. Desai, M. Ernst, K. Kleese-Van Dam, G. Shipman, B. Tierney.
High Performance Computing Course Notes Grid Computing.
Foundations for an LHC Data Grid Stu Loken Berkeley Lab.
1 Software & Grid Middleware for Tier 2 Centers Rob Gardner Indiana University DOE/NSF Review of U.S. ATLAS and CMS Computing Projects Brookhaven National.
Computational Grids and the Globus Project Ian Foster Argonne National Laboratory The University of Chicago Globus Co-PI: Carl Kesselman, USC/ISI.
USING THE GLOBUS TOOLKIT This summary by: Asad Samar / CALTECH/CMS Ben Segal / CERN-IT FULL INFO AT:
The DOE Science Grid Computing and Data Infrastructure for Large-Scale Science William Johnston, Lawrence Berkeley National Lab Ray Bair, Pacific Northwest.
Presented by Scalable Systems Software Project Al Geist Computer Science Research Group Computer Science and Mathematics Division Research supported by.
Workload Management Workpackage Massimo Sgaravatto INFN Padova.
Computer Science Department 1 Load Balancing and Grid Computing David Finkel Computer Science Department Worcester Polytechnic Institute.
Milos Kobliha Alejandro Cimadevilla Luis de Alba Parallel Computing Seminar GROUP 12.
Grids and Grid Technologies for Wide-Area Distributed Computing Mark Baker, Rajkumar Buyya and Domenico Laforenza.
Workload Management Massimo Sgaravatto INFN Padova.
1 GRID D. Royo, O. Ardaiz, L. Díaz de Cerio, R. Meseguer, A. Gallardo, K. Sanjeevan Computer Architecture Department Universitat Politècnica de Catalunya.
Simo Niskala Teemu Pasanen
Grid Computing Net 535.
Introduction to Grid Computing Ann Chervenak Carl Kesselman And the members of the Globus Team.
The Globus Toolkit: Description and Applications Review Steve Tuecke & Ian Foster Argonne National Laboratory The University of Chicago Globus Co-PI: Carl.
Nimrod/G GRID Resource Broker and Computational Economy David Abramson, Rajkumar Buyya, Jon Giddy School of Computer Science and Software Engineering Monash.
DISTRIBUTED COMPUTING
ARGONNE  CHICAGO Ian Foster Discussion Points l Maintaining the right balance between research and development l Maintaining focus vs. accepting broader.
CoG Kit Overview Gregor von Laszewski Keith Jackson.
GT Components. Globus Toolkit A “toolkit” of services and packages for creating the basic grid computing infrastructure Higher level tools added to this.
An Integrated Instrumentation Architecture for NGI Applications Ian Foster, Darcy Quesnel, Steven Tuecke Argonne National Laboratory The University of.
Grid Workload Management & Condor Massimo Sgaravatto INFN Padova.
Grid Technologies  Slide text. What is Grid?  The World Wide Web provides seamless access to information that is stored in many millions of different.
The Anatomy of the Grid: An Integrated View of Grid Architecture Ian Foster, Steve Tuecke Argonne National Laboratory The University of Chicago Carl Kesselman.
National Computational Science Alliance Tele-Immersion - The Killer Application for High Performance Networks Panel Talk at a Vanguard Meeting in San Francisco,
The Globus Project: A Status Report Ian Foster Carl Kesselman
The Anatomy of the Grid Mahdi Hamzeh Fall 2005 Class Presentation for the Parallel Processing Course. All figures and data are copyrights of their respective.
Major Grid Computing Initatives Ian Foster Mathematics and Computer Science Division Argonne National Laboratory and Department of Computer Science The.
Virtual Data Grid Architecture Ewa Deelman, Ian Foster, Carl Kesselman, Miron Livny.
1 4/23/2007 Introduction to Grid computing Sunil Avutu Graduate Student Dept.of Computer Science.
Perspectives on Grid Technology Ian Foster Argonne National Laboratory The University of Chicago.
Grid Architecture William E. Johnston Lawrence Berkeley National Lab and NASA Ames Research Center (These slides are available at grid.lbl.gov/~wej/Grids)
Ames Research CenterDivision 1 Information Power Grid (IPG) Overview Anthony Lisotta Computer Sciences Corporation NASA Ames May 2,
Grid Computing & Semantic Web. Grid Computing Proposed with the idea of electric power grid; Aims at integrating large-scale (global scale) computing.
Commodity Grid Kits Gregor von Laszewski (ANL), Keith Jackson (LBL) Many state-of-the-art scientific applications, such as climate modeling, astrophysics,
The Grid the united computing power Jian He Amit Karnik.
GRID ARCHITECTURE Chintan O.Patel. CS 551 Fall 2002 Workshop 1 Software Architectures 2 What is Grid ? "...a flexible, secure, coordinated resource- sharing.
Authors: Ronnie Julio Cole David
Grid Technologies Research and Development Ian Foster Argonne National Laboratory The University of Chicago.
Globus Toolkit Massimo Sgaravatto INFN Padova. Massimo Sgaravatto Introduction Grid Services: LHC regional centres need distributed computing Analyze.
GRIDS Center Middleware Overview Sandra Redman Information Technology and Systems Center and Information Technology Research Center National Space Science.
GRID Overview Internet2 Member Meeting Spring 2003 Sandra Redman Information Technology and Systems Center and Information Technology Research Center National.
CEOS Working Group on Information Systems and Services - 1 Data Services Task Team Discussions on GRID and GRIDftp Stuart Doescher, USGS WGISS-15 May 2003.
Introduction to Grids By: Fetahi Z. Wuhib [CSD2004-Team19]
University of Illinois at Chicago StarLight: Applications-Oriented Optical Wavelength Switching for the Global Grid at STAR TAP Tom DeFanti, Maxine Brown.
1 Observations on Architecture, Protocols, Services, APIs, SDKs, and the Role of the Grid Forum Ian Foster Carl Kesselman Steven Tuecke.
7. Grid Computing Systems and Resource Management
Globus and PlanetLab Resource Management Solutions Compared M. Ripeanu, M. Bowman, J. Chase, I. Foster, M. Milenkovic Presented by Dionysis Logothetis.
Securing the Grid & other Middleware Challenges Ian Foster Mathematics and Computer Science Division Argonne National Laboratory and Department of Computer.
GraDS MacroGrid Carl Kesselman USC/Information Sciences Institute.
GRID ANATOMY Advanced Computing Concepts – Dr. Emmanuel Pilli.
Globus: A Report. Introduction What is Globus? Need for Globus. Goal of Globus Approach used by Globus: –Develop High level tools and basic technologies.
The Globus Toolkit The Globus project was started by Ian Foster and Carl Kesselman from Argonne National Labs and USC respectively. The Globus toolkit.
PARALLEL AND DISTRIBUTED PROGRAMMING MODELS U. Jhashuva 1 Asst. Prof Dept. of CSE om.
Towards a High Performance Extensible Grid Architecture Klaus Krauter Muthucumaru Maheswaran {krauter,
Clouds , Grids and Clusters
Globus —— Toolkits for Grid Computing
Collaborations and Interactions with other Projects
University of Technology
Grid Computing B.Ramamurthy 9/22/2018 B.Ramamurthy.
The Globus Toolkit™: Information Services
The Anatomy and The Physiology of the Grid
The Anatomy and The Physiology of the Grid
Presentation transcript:

The Grid: Past, Present, and Future Tom DeFanti University of Illinois at Chicago as Ian Foster Mathematics and Computer Science Division Argonne National Laboratory and Department of Computer Science The University of Chicago

ARGONNE CHICAGO On-demand creation of powerful virtual computing systems The Grid: The Web on Steroids Web: Uniform access to HTML documents Grid: Flexible, high-perf access to all significant resources Sensor nets Data archives Computers Software catalogs Colleagues

ARGONNE CHICAGO Why Now? l The Internet as infrastructure –Increasing bandwidth, advanced services l Advances in storage capacity –You can buy a Terabyte for < $15,000 l Increased availability of compute resources –Clusters, supercomputers, etc. l Advances in application concepts –Simulation-based design, advanced scientific instruments, collaborative engineering,...

ARGONNE CHICAGO Talk in a Nutshell … l Where this all started –Special purpose networks, stunts l Where we are –Grid services as unifying concept –Limited but growing application set –Persistent testbeds l Where were going –Production grids –New user communities and applications –Convergence of Grid and Info Infrastructure –High-level services and development tools

ARGONNE CHICAGO Disclaimers l Describing work of many people –ANL, ISI, NCSA, CIT, SDSC, NASA, EVL, etc. –In particular, Carl Kesselman, Globus Co-PI –In U.S., Europe, Asia, Australia l Much important work by others is left out –I have picked just a representative sample

Where This All Started

ARGONNE CHICAGO High-Performance Networks: E.g., CASA Gigabit Testbed l One of four U.S. testbeds in early 90s l Dedicated network –HIPPI over SONET, custom hardware –Caltech, SDSC, LANL l Focus on distributed supercomputing applications –Large distributed memory & vector supercomputers CASA: Paul Messina et al.

ARGONNE CHICAGO The SC95 Conference l Focus on application demonstrations –60+ groups l OC-3 backbone l Large-scale use of immersive displays –CAVE and I-Desk l I-Soft programming environment –Pioneered security, scheduling ideas I-WAY leaders: Tom DeFanti, Tim Kuhfuss, Rick Stevens, Maxine Brown

ARGONNE CHICAGO The I-Soft Software Environment l Kerberos authentication –I-POP initiated rsh to local resources l Andrew File System to distribute software & state l Central scheduler –Dedicated I-WAY nodes on resource –Interface to local scheduler l Nexus-based comm libraries –MPI, CAVEcomm, CC++ I-Soft development: Warren Smith, Jonathon Geisler, Steve Tuecke I-POP AFSKerberosScheduler ATM Switch Resource 1 Resource N Possible Firewall ATM Internet

ARGONNE CHICAGO Combustion System Modeling l A shared collaborative space –Link people at multiple locations –Share and steer scientific simulations on supercomputer l Prototypical of new applns –Traditional HPC an element of a more complex whole l Substantial development effort –Yet insecure, no QoS Chicago San Diego Lori Freitag et al., Argonne National Laboratory and NALCO DC

Where We Are Now

ARGONNE CHICAGO The Need for Grid Services Remote access Remote monitor Information services Fault detection... Resource mgmt Collaboration Tools Data Mgmt Tools Distributed simulation... net

ARGONNE CHICAGO A Defining Framework: Grid Services Architecture Grid-enabled archives, networks, computers, display devices, etc.; associated local services Protocols, authentication, policy, resource management, instrumentation, discovery, etc., etc. Grid Fabric Grid Services Appln Toolkits Applns... … a rich variety of applications... Remote viz toolkit Remote comp. toolkit Remote data toolkit Remote sensors toolkit Async. collab. toolkit

ARGONNE CHICAGO The Grid Services Concept l Standard services that –Provide uniform, high-level access to a wide range of resources (including networks) –Address interdomain issues: security, policy –Permit application-level management and monitoring of end-to-end performance l Broadly deployed, like Internet Protocols l Enabler of application-specific tools as well as applications themselves l Integrate across domains to support the creation of scalable virtual organizations

ARGONNE CHICAGO The Globus Project: Developing a Grid Services Architecture l Developed as a key enabling mechanism the Grid Security Infrastructure –Uniform authentication & authorization mechanisms in multi-institutional setting –Single sign-on, delegation, identity mapping –Public key technology, SSL, X.509, GSS-API l Used to construct Grid resource managers that provide secure remote access to –Computers: GRAM server (HTTP), secure shell –Storage: storage resource managers, GSIFTP –Networks: differentiated service mechanisms Globus project Co-PI: Carl Kesselman

ARGONNE CHICAGO Developing a Grid Services Architecture l Developed as a 2nd key enabling mechanism the Grid Information Service (aka MDS) –Lightweight Directory Access Protocol (LDAP) used to access info about specific resources –Index servers provide for flexible indexing –Uniform resource discovery & characterization mechanisms in highly distributed systems –A basis for resource brokering, adaptation, autoconfiguration l Other services include fault detection and communication GIS: Steve Tuecke, Steve Fitzgerald, Gregor von Laszewski

ARGONNE CHICAGO Status of Grid Services l Core Grid services & others (e.g., Network Weather Service) have been deployed in large-scale testbeds l Availability of these services is enabling tool & application development projects l Major challenges certainly remain: e.g. –Advance reservation, policy, accounting –End-to-end application adaptation (events?) –Integration with commodity technology l Grid Forum:

ARGONNE CHICAGO Examples of Grid-Enabled Tools l Message Passing –MPICH-G2 l Distributed collaboration –CAVERNsoft, Access Grid l High-throughput computing –Condor-G, Nimrod-G l Distributed data management & analysis –Data Grid toolkits l Desktop access to Grid resources –Commodity Grid Toolkits (CoG Kits)

ARGONNE CHICAGO tomographic reconstruction real-time collection wide-area dissemination desktop & VR clients with shared controls Advanced Photon Source Online Instrumentation archival storage DOE X-ray grand challenge: ANL, USC/ISI, NIST, U.Chicago

ARGONNE CHICAGO Distributed Supercomputing SF-Express Distributed Interactive Simulation: Caltech, USC/ISI l Starting point: SF-Express parallel simulation code l Globus mechanisms for –Resource allocation –Distributed startup –I/O and configuration –Fault detection l 100K vehicles using 13 computers, 1386 nodes, 9 sites (5 years early!) NCSA Origin Caltech Exemplar CEWES SP Maui SP

ARGONNE CHICAGO l Problem solving environment for comp. chemistry l Globus services used for authentication, remote job submission, monitoring, and control l Future: distributed data archive, resource discovery, charging Problem Solving Environments ECCE: Pacific Northwest National Laboratory

Where We Are Going

ARGONNE CHICAGO Emerging Production Grids NASA Information Power Grid NSF National Technology Grid

ARGONNE CHICAGO Emerging User Communities l NSF Network for Earthquake Engineering Simulation (NEES) –Integrated instrumentation, collaboration, simulation l Grid Physics Network (GriPhyN) –ATLAS, CMS, LIGO, SDSS –World-wide distributed analysis of Petascale data l Access Grid: supporting group based collaboration

ARGONNE CHICAGO Todays Information Infrastructure l Network-centric: simple, fixed end systems; few embedded capabilities; few services; no user-level quality of service O(10 6 ) nodes

ARGONNE CHICAGO Tomorrows Information Infrastructure: Not Just Faster and More Reliable l Application-centric: heterogeneous, mobile end-systems; many embedded capabilities; rich services; user-level quality of service QoS Resource Discovery Caching O(10 9 ) nodes

ARGONNE CHICAGO Optical MREN (OM) ANL 3 pr 1 pr (2) OC-3 3 pr OC-3 2 pr Bell Nexxia to CA*net4 I-WIRE OC-3 ? Optical STAR TAP (AUP free) AADS switch 6 pr Franklin CO Central Office UIUC UIC UCIIT MREN NU Chicago BN NU Evanston GigE IU Bloom- ington UIPUI Purdue STAR LIGHT

ARGONNE CHICAGO I-WIRE: Computing Urbana ArgonneChicago Topology Research Areas Latency-Tolerant Algorithms Interaction of SAN/LAN/WAN technologies Cluster Architectures

ARGONNE CHICAGO Scalable Global Services: The InterGrid l Do for the Grid what routers do for the network l Wide variety of services –Resource trading –Policy enforcement –Agent based scheduling –Agent based monitoring –Virtual data l Exploit emerging network services, e.g. QoS Data Caching Schedulin g Fault Recover y Routing

ARGONNE CHICAGO l Megacomputing (Larry Smarr) –Very large numbers of computers –Opportunistic, dynamic behaviors –Bandwidths variable, ultimately to Gb/s l distributed.net, entropia.com

ARGONNE CHICAGO The Emergence of the Application Service Provider l ASP model: rent access to applications that execute on remote computers l Decouples interface, application, computing, hardware –Each can be optimized & sold separately l Highly disruptive impact on all aspects of the computer industry l May also be key to a dramatic increase in the penetration of HPC –E.g., see NetSolve (U.Tenn), PUNCH (Purdue)

ARGONNE CHICAGO Summary l Grids will change the way we do science and engineering l Key services and concepts have been identified, although major challenges remain l Transition of services and applications to production use is starting to occur l Future will see increased sophistication and scope of services, tools, and applications l Potentially disruptive trends: ASPs, megacomputing

ARGONNE CHICAGO For More Information l Book published by Morgan Kaufman – l Globus – l Grid Forum –

ARGONNE CHICAGO We are Hungry for the Grid