Introduction to Grid Computing Trends Challenges Technologies Applications

Introduction to Grid Computing: Trends, Challenges, Technologies, Applications Dr. Rajkumar Buyya Cloud Computing and Distributed Systems (CLOUDS) Laboratory Dept. of Computer Science and Software Engineering The University of Melbourne, Australia www. buyya. com www. gridbus. org

Outline n Introduction n n Defining Grids n n 2 Globus from USA and Gridbus from Australia Grid Applications n n Layered architecture Grid Technologies n n Characteristics, Security, resource management, pricing, … Grid Architecture n n What is Grid? , Types of Grid Services Global Grids and Challenges n n Utility Networks, Trends, and Grid Computing E-Science and e-Business Conclusion

4 Essential Utilities and Delivery Networks (1) Water Distribution Network (2) Electricity Power Grid (3) Gas (4) Telephone 3 Telecom Networks

(5) Computing: Grid Delivery IT services as the 5 th utility (Power Grid inspiration) 4 e. Science e. Business e. Government e. Health Multilingual e. Education …

Power Grid Inspiration: Seamlessly delivering electricity as a utility to users 5

Why Grid Computing Now? Let us look at the Evolution of ICT 6

Grid-like Vision n In 1969, Leonard Kleinrock, one of the chief scientists of the original ARPA project which seeded the Internet, wrote: n n Despite major advances in hardware and software systems over the past 40 years, we are yet to realise this vision. How far are we still from delivering computing as a utility? n 7 "As of now, computer networks are still in their infancy, but as they grow up and become sophisticated, we will probably see the spread of "computer utilities", which, like present electric and telephone utilities, will service individual homes and offices across the country“ Let us look into the ICT evolution and project the future.

COMPUTING Computing and Communication Technologies Evolution: 1960 -2010! * HTC * Mainframes * Minicomputers * PCs * Workstations * P 2 P * Grids * PC Clusters * Crays * XEROX PARC worm * PDAs * MPPs * Computing as Utility (Cloud) * WS Clusters Communication * e-Science * TCP/IP * Sputnik 1960 * Ethernet * Email 1970 1975 Centralised 8 * W 3 C * HTML * Mosaic * Internet Era * ARPANET * e-Business * IETF 1980 * WWW Era 1985 Control 1990 * Web Services * XML 1995 2000 Decentralised * Social. Net 2010

Computing is Scaling: Towards Inter-Planetary Level S E R V I C E S 2100 2100 2100 + Administrative Barriers P E R F O R M A N C E 9 • Individual • Group • Department • Campus • State • National • Globe • Inter Planet • Universe Personal Device SMPs or Super. Computers Local Cluster Enterprise Cluster/Grid Global Grid Inter Planet Grid

Outline n Introduction n n Defining Grids n n 10 Globus from USA and Gridbus from Australia Grid Applications n n Layered architecture Grid Technologies n n Characteristics, Security, resource management, pricing, … Grid Architecture n n What is Grid? , Types of Grid Services Global Grids and Challenges n n Utility Networks, Trends, and Grid Computing E-Science and e-Business Conclusion

What does Grid mean? / (It means different things to different people) n IBM n n Microsoft n n 11 Adaptive Enterprise Amazon n n Sun/Oracle Grid Engine HP n n 10 g Sun Oracle n n . NET Oracle n n On Demand Computing Elastic Compute Cloud Services United Devices and related companies: n Harvesting Unused Desktop resources

What is Grid? [Buyya et. al] n A type of parallel and distributed system that enables the sharing, exchange, selection, & aggregation of geographically distributed “autonomous” resources: n n Wide area n n n Computers – PCs, workstations, clusters, supercomputers, laptops, notebooks, mobile devices, PDA, etc; Software – e. g. , ASPs renting expensive special purpose applications on demand; Catalogued data and databases – e. g. transparent access to human genome database; Special devices/instruments – e. g. , radio telescope – SETI@Home searching for life in galaxy. People/collaborators. depending on their availability, capability, cost, and user Qo. S requirements. 12

The Grid (Foster et. al) “Resource sharing & coordinated problem solving in dynamic, multi-institutional virtual organizations” 1. 2. 3. 13 Enable integration of distributed resources Using general-purpose protocols & infrastructure To achieve better-than-best-effort service

How does Grids look like? A Bird Eye View of a Global Grid Information Service Grid Resource Broker R 2 R 3 R 5 Application database R 4 RN Grid Resource Broker R 6 Grid Information Service 14 R 1 Resource Broker

How Are Grids Used? Utility computing High-performance computing Collaborative design Financial modeling E-Business High-energy physics Drug discovery Data center automation E-Science Natural language processing & Data Mining Collaborative data-sharing 15 Life sciences

Classes of Grid Services / Types of Grids Computational Services – CPU cycles n n Knowledge Grid Towards a market-based Grid computing: Leasing and delivering Grid services as ICT utilities. Interaction Grid ASP Grid Data Grid Computational Grid infrastructure The way knowledge is acquired, processed and managed—data mining. Utility Computing Services n 16 e. Learning, Virtual Tables, Group Communication (Access Grid), Gaming Knowledge Services n n Access to remote software/libraries and license management—Net. Solve Interaction Services n n Collaborative data sharing generated by instruments, sensors, persons: LHC Grid, Napster Application Services n n Utility Grid Data Services n n Pooling computing power: SETI@Home, Tera. Grid, Aus. Grid, China. Grid, India. Grid, UK Grid, … Users n

Worldwide Grid Spending: 2005 to 2010 in billion dollars n After the year 2007, business popularity of Grid computing has accelerated (especially now in the form of Cloud Computing): Especially, the financial services and ERP services is expected to take major parts in the expense Billions n Source: Insight Research Corp. 17

Outline n Introduction n n Defining Grids n n 18 Globus from USA and Gridbus from Australia Grid Applications n n Layered architecture Grid Technologies n n Characteristics, Security, resource management, pricing, … Grid Architecture n n What is Grid? , Types of Grid Services Global Grids and Challenges n n Utility Networks, Trends, and Grid Computing E-Science and e-Business Summary and Conclusion

Grid & Related Paradigms Distributed Computing • Loosely coupled • Heterogeneous • Single Administration Cluster • Tightly coupled • Homogeneous • Cooperative working Grid Computing • • Large scale Cross-organizational Geographical distribution Distributed Management Utility Computing 19 • Computing “services” • No knowledge of provider • Enabled by grid technology Hiro Kishimoto

Some Characteristics of Grids Numerous resources Owned by multiple organizations & individuals Connected by heterogeneous, multi-level networks Different security requirements & policies Unreliable resources and environments 20 Slide by Hiro Different resource management policies Resources are heterogeneous Geographically distributed

Grid Challenges Security Computational Economy Uniform Access Resource Discovery 21 Resource Allocation & Scheduling Application Construction System Management Data locality Network Management

Some Grid Initiatives Worldwide n Australia n n n n Our. Grid, Easy. Grid LNCC-Grid + many others n n UK e. Science EU Grids. . and many more. . . n n n Garuda n n Korea. . . Singapore NGP 1. 3 billion – 3 yrs IBM On Demand Computing HP Adaptive Computing Sun N 1 Microsoft -. NET Oracle 10 g Infosys – Enterprise Grid Satyam – Business Grid Storage. Tek –Grid. . and many more Public Forums n NAREGI Globus Grid. Sec Access. Grid Tera. Grid Cyberinfrasture and many more. . . Industry Initiatives n N*Grid 22 n China. Grid – Education CNGrid - application Japan 1 billion – 5 yrs n n India 1. 3 billion (Rs) n n Europe 450 million – 5 yrsn 486 million – 5 yrsn § n n n China 120 million – 5 yrs USA n n n Nimrod-G Gridbus Grange. Net. APACGrid 27 million ARC e. Research Brazil n n n Open Grid Forum Australian Grid Forum Conferences: n n CCGrid HPDC E-Science http: //www. gridcomputing. com 2? billion

mix-and-match Object-oriented Internet/partial-P 2 P Network enabled Solvers Economic-based Utility / Service-Oriented Computing Nimrod-G 23

Open-Source Grid Middleware Projects 24

Outline n Introduction n n Defining Grids n n 25 Globus from USA and Gridbus from Australia Grid Applications n n Layered architecture Grid Technologies n n Characteristics, Security, resource management, pricing, … Grid Architecture n n What is Grid? , Types of Grid Services, Global Grids and Challenges n n Utility Networks, Trends, and Grid Computing E-Science and e-Business Conclusion

Grid Realization Steps/Requirements n Step 1: n n Step 2: n n User-level middleware to support application development and aggregation of distributed resources. Step 4: n 26 Low-level middleware to provide a secure and uniform access to services provided by different resources. Step 3: n n The integration of individual s/w & h/w components into a combined networked resource (single system image cluster). The construction of Grid applications and Web portals.

Layered Grid Architecture APPLICATIONS Applications and Portals Scientific … Prob. Solving Env. Collaboration Engineering Web enabled Apps Libraries Debuggers Monitors … Web tools Resource Management and Scheduling: CORE MIDDLEWARE Distributed Resources Coupling Services Information Security Data Process Trading … Qo. S SECURITY LAYER Local Resource Managers Operating Systems Queuing Systems FABRIC Libraries & App Kernels … Internet Protocols Networked Resources across Organizations Computers 27 Networks Storage Systems Data Sources … Scientific Instruments Adaptive Management Languages/Compilers Autonomic/ Grid Economy USER LEVEL MIDDLEWARE Application Development and Deployment Environment

Outline n Introduction n n Defining Grids n n 28 Globus from USA and Gridbus from Australia Grid Applications n n Layered architecture Grid Technologies n n Characteristics, Security, resource management, pricing, … Grid Architecture n n What is Grid? , Types of Grid Services Global Grids and Challenges n n Utility Networks, Trends, and Grid Computing E-Science and e-Business Conclusion

Grid Middleware Technologies n n 29 Globus – Argonne National Lab and ISI Gridbus – University of Melbourne Unicore – European Project (Germany…) Legion – University of Virginia

Globus Toolkit www. globus. org 30

Globus Toolkit Services n Security (GSI) n n Job submission and management (GRAM) n n n Remote Storage Access Service Remote Data Catalogue and Management Tools Recently move to: n 31 LDAP-based Information Service Remote file management (GASS) n n Uniform Job Submission Information services (MDS) n n PKI-based Security (Authentication) Service WSRF (Web Services Resource Framework)

GRAM Components MDS client API calls to locate resources Client MDS: Grid Index Info Server Site boundary MDS client API calls to get resource info GRAM client API calls to MDS: request resource allocation and process creation. GRAM client API state change callbacks Globus Security Grid Resource Info Server Query current status of resource Local Resource Manager Infrastructure Request Create Gatekeeper Job Manager Parse RSL Library 32 Monitor & control Allocate & create processes Process

Sample of High-Level Services n Resource brokers and co-allocators n n Communication & I/O libraries n n CAVERNsoft, Many. Worlds Others n 33 HPC++, CC++ Collaborative environments n n MPICH-G, RIO (MPI-IO) Parallel languages n n DUROC, Nimrod-G, Gridbus, Condor-G, App. Le. S PST Meta. NEOS, Net. Solve, LSA, Auto. Pilot, Web. Flow

The Nimrod-G Grid Resource Broker (from Monash University) n n n A resource broker for managing, steering, and executing task farming (parameter sweep/SPMD model) applications on the Grid based on deadline and computational economy. Based on users’ Qo. S requirements, our Broker dynamically leases services at runtime depending on their quality, cost, and availability. Key Features n n n n n 34 A single window to manage & control experiment Persistent and Programmable Task Farming Engine Resource Discovery Resource Trading Scheduling & Predications Generic Dispatcher & Grid Agents Transportation of data & results Steering & data management Accounting Uses Globus – MDS, GRAM, GSI, GASS

Condor-G: Condor for the Grid (from University of Wisconsin) n n Condor is a high-throughput scheduler Condor-G uses Globus Toolkit libraries for: n n Security (GSI) Managing remote jobs on Grid (GRAM) File staging & remote I/O (GSI-FTP) Grid job management interface & scheduling n Robust replacement for Globus Toolkit programs n n Supports single or high-throughput apps on Grid n 35 Globus Toolkit focus is on libraries and services, not end user vertical solutions Personal job manager which can exploit Grid resources

The Gridbus Project @ Melbourne: Enable Leasing of ICT Services on Demand WWG Gridbus Pushes Grid computing into mainstream computing 36

37

Gridbus Architecture Layer Adaptive Management 38

On Demand Assembly of Services: Putting Them All Together Application Code Explore data 1 Visual Application Composer + ults fo s e R t In Cos 2 Data Catalogue 5 6 Grid Resource Broker Grid Info Service 3 ASP Catalogue lts Grid Market Directory 7 Alchemi Bill GS CPU or PE 39 GSP (e. g. , IBM) 12 Resu Job 9 8 Grid Service (GS) (Globus) 4 10 Cluster Scheduler PE GSP (e. g. , Uof. M) PE GTS GSP (e. g. , VPAC) 11 Gridbus Grid. Bank GSP (Accounting Service)

40

Alchemi: . NET-based Enterprise Grid Platform & Web Services Alchemi Manager Web Services Internet Alchemi Users Internet 41 • SETI@Home like Model • General Purpose • Dedicated/Non-dedicate workers • Role-based Security • . NET and Web Services • C# Implementation • Grid. Thread and Job Model Programming • Easy to setup and use • Widely in use! Alchemi Worker Agents

Some Users of Alchemi Tier Technologies, USA Large scale document processing using Alchemi framework Satyam Computers Applied Research Laboratory, India Micro-array data processing using Alchemi framework CSIRO, Australia Natural Resource Modeling The University of Sao Paulo, Brazil The Alchemi Executor as a Windows Service stochastix Gmb. H, Germany Serving clients in International Banking/Finance sector The Friedrich Miescher Institute (FMI) for Biomedical Research, Switzerland Patterns of transcription factors in mammalian genes 42 Many users in Universities: See next for an example.

Gridbus Broker and Remote Service Access Enablers Portlets Home Node/Portal Gridbus Broker Credential Repository My. Proxy batch() fork() -PBS -Condor -SGE -Alchemi -XGrid Data Catalog Alchemi Globus Data Store Job manager Unicore Access Technology fork() batch() -PBS -Condor -SGE 43 Gridbus agent Grid FTP SRB Gateway SSH fork() batch() -PBS -Condor -SGE -XGridbus agent

44

Comparison of Middleware Technologies Middleware Property UNICORE Globus Legion Gridbus Focus High level Programming models Low level services High level Programming models Abstractions and market models Category Mainly uniform job submission and monitoring Generic computational Architecture Vertical multi tiered system Layered and modular toolkit Vertically integrated system Layered component and utility model Implementation Model Abstract Job Object Hourglass model at system level Object-oriented metasystem Hourglass model at user level Implementation Technologies Java C and Java C++ C, Java, C# and Perl Runtime Platform Unix and Windows with. NET Programming Environment Workflow environment Replacement libraries for Unix & C libraries. Special MPI library (MPICH – G), Co. G (Commodity Grid) kits in Java, Python, CORBA, Matlab, Java Server Pages, Perl and Web Services Legion Application Programming Interfaces (API). Command line utilities Broker Java API XML-based parameter-sweep language Grid Thread model via Alchemi. Some Users and Applications Euro. Grid], Grid Interoperability Project, Open. Mol. Grid and Japanese NAREGI. App. Le. S, Ninf], Nimrod-G, NASA IPG, Condor-G, Gridbus Broker, UK e. Science Project], Gri. Phy. N], and EU Data Grid. NPACI Testbed, Nimrod-L, and NCBio. Grid. Additionally, it has been used in the study of axially symmetric steady flow and protein folding applications. e. Physics, Belle Analysis Data Grid], Neuro. Grid], Natural Language Engineering, Hydro. Grid, and Amsterdam Private Grid]. 45

Outline n Introduction n n Defining Grids n n 46 Globus from USA and Gridbus from Australia Grid Applications n n Layered architecture Grid Technologies n n Characteristics, Security, resource management, pricing, … Grid Architecture n n What is Grid? , Types of Grid Services Global Grids and Challenges n n Utility Networks, Trends, and Grid Computing E-Science and e-Business Conclusion

Collaborative Science and Global Grid E-Scientist Peers sharing ideas and collaborative interpretation of data/results Distributed data Global Grid Remote Visualization 2100 Distributed computation 2100 47 Data & Compute Service Distributed instruments

Some e-Science Grid Applications Bioinformatics: Drug Design / Protein Modelling Sensitivity experiments on smog formation Natural Language Engineering Computer Graphics: Ray Tracing High Energy Physics: Searching for Rare Events Electronic CAD: Field Programmable Gate Arrays VLSI Design: Finance: SPICE Simulations Investment Risk Analysis Civil Engineering: Building Design Automobile: Crash Simulation 48 Ecological Modelling: Control Strategies for Cattle Tick Data Mining Network Simulation Aerospace: Wing Design astrophysics

1. [Grid Use in Science] Online Medical Instrumentation and Neuroscience Osaka Univ. Hospital DV transfer Analysis Results Data Generation Virtual Laboratory for medicine and brain science sharing Data • Knowledge Analysis • MEG sharing? Analysis Results Cybermedia Center • Data Sharing Life-electronics laborat AIST • Provision of MEG • Provision of expertise in the analysis of brain fun A 49

2: [Grid in Data Sharing] Physics Collaboration (fundamental investigation on the origin of mass) 50

LHC Grid Computing Model ~PBytes/sec Online System ~100 MBytes/sec ~20 TIPS There are 100 “triggers” per second Each triggered event is ~1 MByte in size Tier 0 ~622 Mbits/sec Italy Regional Centre US Regional Centre Tier 1 ~100 MBytes/sec CERN Computer Centre Asia Pacific Centre ~4 TIPS ~622 Mbits/sec Tier 2 ~622 Mbits/sec Melbourne Institute ~0. 25 TIPS Physics data cache 51 Spec. Int 95 equivalents Offline Processor Farm There is a “bunch crossing” every 25 nsecs. France Regional Centre 1 TIPS is approximately 25, 000 Physicist desktop computers Tier 2 Centre Australian Centre Tier 2 Centre ~1 TIPS ~1 TIPS Institute Tier 3 ~10 to 100 Mbits/sec Tier 4

3. [Grid Use in Business] Enterprise Computing Application n Traditional Model n Grid-based Model Service Virtualization Layer & Load Balancing Email server 52 Web server Database server Apps server Upgrade to a new server to handle more users Utilise IT infrastructure effectively

Outline n Introduction n n Defining Grids n n 53 Globus from USA and Gridbus from Australia Grid Applications n n Layered architecture Grid Technologies n n Characteristics, Security, resource management, pricing, … Grid Architecture n n What is Grid? , Types of Grid Services Global Grids and Challenges n n Utility Networks, Trends, and Grid Computing E-Science and e-Business Conclusion

Conclude with a comparison to the Electrical Grid………. . Where we are ? ? Courtesy: Domenico Laforenza

Alessandro Volta in Paris in 1801 inside French National Institute shows the battery while in the presence of Napoleon I Fresco by N. Cianfanelli (1841) (Zoological Section "La Specula" of National History Museum of Florence University)

What ? !? ! Oh, mon Dieu ! This is a mad man… 56 …. and in the future, I imagine a Worldwide Power (Electrical) Grid …. . .

2012 - 1801 = 211 Years (Recent R&D: Delivering Internet services via Electric cables). 57

Summary and Conclusion n n Grid computing is our greatest hope for delivering computing as utility to homes and offices. Grids exploit synergies that result from cooperation of autonomous entities: n n n Several open source middleware technologies such as Gridbus exist demonstrating Grid potential. Grid computing offers enormous opportunities for realizing e-Science and e-Business at global level. n 58 Resource sharing, dynamic provisioning, and aggregation at global level Great Science and Great Business! Use our Gridbus technology to realise this and make money!

Some References n n n Mark Baker, Rajkumar Buyya, and Domenico Laforenza, Grids and Grid Technologies for Wide-Area Distributed Computing, International Journal of Software: Practice and Experience, Volume 32, Issue 15, Wiley Press, USA, Nov. 2002. Madhu Chetty and Rajkumar Buyya, Weaving Computational Grids: How Analogous Are They with Electrical Grids? , Computing in Science and Engineering (Ci. SE), Vol. 4, Issue 4, IEEE CS Press, USA, July-August 2002. Ian Foster, Carl Kesselman, Steve Tuecke, The Anatomy of the Grid: Enabling Scalable Virtual Organizations, International J. Supercomputer Applications, 15(3), 2001. Parvin Asadzadeh, Rajkumar Buyya, Chun Ling Kei, Deepa Nayar, and Srikumar Venugopal, Global Grids and Software Toolkits: A Study of Four Grid Middleware Technologies, High Performance Computing: Paradigm and Infrastructure, Wiley Press, New Jersey, USA, June 2005. Grid Computing Course Material from the University Melbourne: n 59 http: //www. cs. mu. oz. au/678/