Grid Computing

Presented by Wanying Zhao

Grid Computing 1 Outline ‡ Conception ‡ Basic Issues ‡ Grid Architecture ‡ Standards for Grid Environments ‡ Key Components ‡ Applications

Grid Computing 2 What Grid Computing is

‡ Allows sharing and coordinated use of diverse resources in dynamic, distributed ³virtual organizations´.

Grid Computing 3 Electrical Power Grid Analogy

Electrical power grid The Grid ‡ users (or client applications) gain ‡ users (or electrical appliances) access to computing resources get access to electricity (processors, storage, data, through wall sockets with no applications, and so on) as care or consideration for where needed with little or no or how the electricity is actually knowledge of where those generated. resources are located or what the underlying technologies, ‡ ³The power grid´ links hardware, , and together power plants of many so on are different kinds ‡ "the Grid" links together computing resources (PCs, workstations, servers, storage elements) and provides the mechanism needed to access them.

Grid Computing 4 Why need Grid Computing?

‡ Core networking technology now accelerates at a much faster rate than advances in microprocessor speeds ‡ Exploiting under utilized resources ‡ Parallel CPU capacity ‡ Virtual resources and virtual organizations for collaboration ‡ Access to additional resources

Grid Computing 5 Who needs Grid Computing?

‡ Not just computer scientists« ‡ scientists ³hit the wall´ when faced with situations: ± The amount of data they need is huge and the data is stored in different institutions. ± The amount of similar calculations the scientist has to do is huge. ‡ Other areas: ± Government ± Business ± Education ± Industrial design ± ««

Grid Computing 6 Types of resources

‡ Computation ‡ Storage ‡ Communications ‡ Software and licenses ‡ Special equipment, capacities, architectures, and policies

Grid Computing 7 Job Scheduling

Grid Computing 8 Security ‡ Access policy - What is shared? Who is allowed to share? When can sharing occur? ‡ Authentication - How do you identify a user or resource? ‡ Authorization -How do you determine whether a certain operation is consistent with the rules?

Grid Computing 9 Grid User Roles ------AA User¶s Perspective

‡ Enrolling and installing grid software ‡ Logging onto the grid ‡ Queries and submitting jobs ‡ Data configuration ‡ Monitoring progress and recovery ‡ Reserving resources

Grid Computing 10 Grid User Roles ------AnAn Administrator¶s Perspective ‡ Planning ‡ Installation ‡ Managing enrollment of donors and users ‡ Certificate authority ‡ Resource management ‡ Data sharing

Grid Computing 11 Grid Architecture

GRID Internet Application

Application Collective

Resource

Connectivity Transport Internet Fabric Link Grid Computing 12 Grid Architecture

‡ Fabric layer: Provides the resources to which shared access is mediated by Grid protocols. ‡ Connectivity layer: Defines the core communication and authentication protocols required for grid-specific network functions. ‡ Resource layer: Defines protocols, APIs, and SDKs for secure negotiations, initiation, monitoring control, accounting and payment of sharing operations on individual resources. ‡ Collective Layer: Contains protocols and services that capture interactions among a collection of resources. ‡ Application Layer: These are user applications that operate within VO environment.

Grid Computing 13 Standards for Grid Environments

‡ OGSA(Open Grid Service Architecture) ‡ OGSI(Open Grid Services Interface) ‡ OGSA-DAI(data access and integration) ‡ GridFTP ‡ WSRF(Web Services Resource Framework) ‡ Web services related standards ± XML ± WSDL(Web Services Description Language ) ± SOAP(Service Oriented Architecture Protocol ) ± UDDI

Grid Computing 14 Key Components

‡ Portal/user interface

Grid Computing 15 Key Components ‡ Security ± Grid Security Infrastructure (GSI)

Grid Computing 16 Key Components ‡ Broker ± Monitoring and Discovery Service (MDS)

Grid Computing 17 Key Components

‡ Scheduler

Grid Computing 18 Key Components ‡ Data management ± Grid Access to Secondary Storage (GASS)

Grid Computing 19 Key Components ‡ Job and resource management ± Grid Resource Allocation Manager (GRAM)

Grid Computing 20 Globus Toolkit 4

‡ An open source toolkit for building computing developed and provided by the Globus Alliance. ‡ A collection of open-source components ± Many of these are based on existing standards ± others are based on (and in some cases driving) evolving standards ‡ Globus Toolkit 4 provides components in the following five categories: ± Common runtime components ± Security ± Data management ± Information services ± Execution management

Grid Computing 21 Globus Toolkit 4

Grid Computing 22 Simple Example

‡ Application: A system that takes Scalable Vector Graphics (SVG) files and uses nodes on a grid to render a set of JPEG files representing sub-images of the complete image.

‡ Three components of the system ± RenderClient: A Java application with a graphical interface for the user that drives the rendering work on the grid and displays the resulting sub-images into a final large image. ± RenderWorker: A Java application with no graphical user interface that converts one sub-image of the SVG file into a JPEG file. ± RenderSourceService: A Globus Toolkit 4 grid service, deployed into a Globus Toolkit 4 container. It is initialized by the RenderClient and hands out work instructions to RenderWorker processes on the grid.

Grid Computing 23 Simple Example

Grid Computing 24 Simple Example

Grid Computing 25 Simple Example

Grid Computing 26 Applications ‡ The Southern California Earthquake Center uses Globus software to visualize earthquake simulation data.

Grid Computing 27 Applications

‡ Scientists in the Earth System Grid (ESG) are producing, archiving, and providing access to climate data that advances our understanding of global climate change. ESG uses Globus software for security, data movement, and system monitoring.

Grid Computing 28 Applications

‡ Computational scientists at Brown University are using the Globus Toolkit and MPICH-G2 to simulate the flow of blood through human arteries.

Grid Computing 29 Applications ‡ Globus Toolkit-driven Grid computing is central to management of large datasets generated by colliders such as those at CERN. This simulation shows two colliding lead ions just after impact, with quarks in red, blue, and green and hadrons in white.

Grid Computing 30 Software implementations and middleware

‡ Advanced Resource Connector (NorduGrid's ARC) ‡ Berkeley Open Infrastructure for Network Computing (BOINC) ‡ Globus Toolkit ‡ Sun Grid Engine ‡ ProActive ‡ UNICORE ‡ SDSC Storage resource broker (data grid) ‡ gLite (EGEE) ‡ NInf GridRPC ‡ IceGrid ‡ Java CoG Kit ‡ Alchemi ‡ GridGain ‡ gridGISTICS ‡ Gridbus Middleware ‡ Vishwa ‡ UGP ‡ GRIA Grid Computing 31 Organizations & Production Grids

Alliances and organizations ‡ (Formerly Global Grid Forum) ‡ Object Management Group

Production grids ‡ Enabling Grids for E-sciencE ‡ NorduGrid ‡ Open Science Grid ‡ OurGrid ‡ Sun Grid ‡ Xgrid ‡ Distributed European Infrastructure for Supercomputing Applications DEISA ‡ FusionGrid

Grid Computing 32 Grid Projects International Grid Projects ‡ Open Middleware Infrastructure Institute Europe (OMII-Europe) - May 2006 -> May 2008 ‡ Enabling Grids for E-sciencE (EGEE) - March 2004 -> March 2006 ‡ Enabling Grids for E-sciencE II (EGEE II) - April 2006 -> April 2008 ‡ BREIN ² September 2007 ĺ August 2009 ‡ DataTAG - January 2001 -> January 2003 ‡ European DataGrid (EDG) - March 2001 -> March 2004 ‡ BalticGrid - November 2005 -> April 2008 National Grid Projects ‡ D-Grid (German) ‡ GARUDA (Indian) ‡ grid computing project at VECC (Calcutta, India) ‡ China Grid Project ‡ INFN Grid (Italian) ‡ KnowledgeGrid Malaysia ‡ NAREGI Project ‡ Singapore National Grid Project ‡ Thai National Grid Project ‡ BELNET Grid, Belgium Grid Computing 33 Prospect of Grid computing

‡ The Grid aims ultimately to turn the global network of computers into one vast computational resource. ‡ Related to many areas in computer science ‡ Being developed by hundreds of researchers and software engineers around the world. ‡ Still ³work in process´ ‡ Potentially revolutionary.

Grid Computing 34 Reference

‡ ³The Anatomy of the Grid(Enabling Scalable Virtual Organizations)´ ---by Ian Foster, Carl Kesselman, Steven Tuecke ‡ ³Physiology of the Grid (An Open Grid Services Architecture for Distributed Systems Integration )´ ---by Ian Foster, Carl Kesselman, Jeffrey M. Nick, Steven Tuecke ‡ ³Grid Computing:Past,Present, and Future´--- by Elias Kourpas, June 2006 ‡ ³Introduction to Grid Computing´ ---IBM Redbook,2005

‡ IBM Grid Computing:www-03.ibm.com/grid/index.shtml

‡ Globus website: www.globus.org

Grid Computing 35 Thank You!

³You may say I'm a dreamer But I'm not the only one I hope someday you'll join us And the world will be as one´ ---Beatles

Grid Computing 36