A Gentle Introduction to Globus Otto Sievert May 26, 1999 Parallel Computation, CSE160/CSE260, Spring 1999 Abstract As computers become better connect

Size: px
Start display at page:

Download "A Gentle Introduction to Globus Otto Sievert May 26, 1999 Parallel Computation, CSE160/CSE260, Spring 1999 Abstract As computers become better connect"

Transcription

1 A Gentle Introduction to Globus Otto Sievert May 26, 1999 Parallel Computation, CSE160/CSE260, Spring 1999 Abstract As computers become better connected across the globe, opportunities to create new programs utilizing geographically distant resources increase. New applications not possible without this computational grid include distributed supercomputing and intelligent sensing applications. However, diculties implementing this new class of applications exist: the computers on a grid are unreliably connected and not beholden to any single management policy. It is dicult to achieve performance on the grid. Users are currently requiredtohave extraordinary knowledge about every element inthe grid to make informed choices about resource allocation/management and programming paradigms. The Globus project provides infrastructure to addresses these issues. Globus is a complex entity; this document isa simple introduction to Globus and its architecture. 1 Introduction The terms computational grid and metacomputing refer to the utilization of a collection of distributed computing resources as if it were a single entity. A computational grid may include personal computers, remote instruments, workstations and MPPs, all connected via awideareanetwork. The fundamental idea of a computational grid is that the local view of all computing resources, communication, and security should be uniform. The autonomous nature of individual systems makes ecient implementation of a grid dicult. A grid attempts to unify what are, by denition, distinct systems. This tension leads directly to the most fundamental problems unique to grid computing: Dierent Administrative Domains Security and authentication methods vary from system to system. Resource Allocation Selecting the most suitable resources among a pool of simply dierent resources is a non-trivial task, even ignoring the fact that resource availability and usage may change radically in a short period of time. Resource Management Even when appropriate resources have been allocated, grid application schedulers are often in competition with local job and process schedulers. Heterogeneous Computing Resources Performance is more dicult to guarantee when individual systems have radically dierent architectures and communicate over non-uniform network connections. Communication Often, communication is relatively slow compared to clusters or other computing collections. Reliability is also an issue, as is quality of service, because grids may share communication bandwidth with others. Though dicult, it is important to address these problems because of the potential for new and exciting computing applications. For example, a grid facilitates computation on a scale never before available. Imagine connecting all the computing power of NCSA, NASA, NPACI, etc., together at one time, running one program. Imagine connecting a remote sensing device like a scanning electron microscope to a remote, highperformance visualization engine, producing real-time three-dimensional imagery of the subject and allowing better instrument control and deeper understanding. Imagine a researcher controlling this system from an of- ce computer thousands of miles away. One motivation of distributed computing is economic; if high-performance and specialized equipment were not prohibitively expensive, everyone would have 1

2 local access to these resources. Every scanning electron microscope would sit next to a graphics visualization engine; each student would sit in school with a fully interactive, educational supercomputer. But economic realities and an ever-increasing demand for computational power have created a situation where powerful or specialized resources are distributed. Computational grids are a strategy to increase eective computing capability without incurring the high cost of new equipment. 2 Globus Opportunities beckon; problems exist. The Globus project, a joint eort of the Argonne National Laboratory and the University of Southern California Information Sciences Institute, addresses some of these issues. Globus is many things; at it's core the Globus team performs basic infrastructure development for applications that integrate geographically distributed systems. Globus has developed a prototype computational grid, GUSTO, and has helped develop grid-enabled software applications to test this infrastructure. The most concrete result of the Globus project is the Globus Toolkit. This toolkit is a symbiotic set of basic grid services, including resource managers, security protocols, information services, communication services, fault tolerance services, and remote data access facilities. The Toolkit has several interesting characteristics. It adopts a \bag of services" model, which allows developers to use as few or as many of these stand-alone services as they want, and does not impose any single programming paradigm. Globus tools may replace or co-exist with mechanisms provided by commodity computing. All of this has been done with careful thought given to enabling high performance. In the rest of this paper various aspects of the Globus Toolkit are discussed in terms of how they address the fundamental grid problems mentioned above. Treatment is given to resource management, communication, security, information services, fault tolerance, and remote le access. A Globus installation, GUSTO, is then discussed, as is an example Globus application, SF- Express. 3 Resource Management Service The Globus Resource Allocation Manager (GRAM) provides a uniform interface to the wide range of local resource management tools. GRAM translates generic resource requests into commands that are specic to a particular local system. GRAM is the lowest level of Globus resource management, and interacts directly with local schedulers[4]. The user interface to GRAM is through a gatekeeper. A gatekeeperruns on every Globus machine. Globus job requests are submitted to the gatekeeper on the machine whose resources are requested. This gatekeeper authenticates the user (while the user mutually authenticates the gatekeeper), then matches the user to an account local to the machine it is necessary to have a local account on all machines whose resources are requested. After a remote user is determined, the gatekeeper starts a job manager process running under the remote user's login. The job manager is then solely responsible for that single Globus job. The job manager is responsible for communicating with the (local) user, allocating resources, executing the job, and deallocating resources after job conclusion. Another logical part of the Globus resource management system is the co-allocator. The co-allocator is responsible for coordinating resource requests to multiple machines on possibly multiple sites to synchronize program execution. Currently, all Globus co-allocation is done by the application. However, this function could be spun o into another Globus tool. Resource requests are phrased in the Globus Resource Specication Language (RSL). RSL is an extensible language used to communicate resource requests. The language is simple: a list of resource expressions logically combined with a handful of logical operators. With these operations resources may be explicitly requested or implicitly dened. For example, a concrete RSL request to run the program myprogfor 24 nodes on a specic computer at Cal Tech might look like this: &(executable=myprog) (count=24) (resourcemanager=neptune.caltech.edu:755) while an abstract resource request to execute this program on either 24 nodes of a computer with 64 MB of memory per node or 10 nodes on a computer with 128 MB of memory per node might look like: &(executable=myprog) ( (&(count=24)(memory>=64)) ((count=10)(memory>=128))) RSL allows the user to communicate intents, which paves the way for automated resource selection and allocation through the use of brokers. Automated brokers, which do not exist currently, could accept an abstract RSL request and specialize it into a concrete RSL that species exact resources. RSL parameters should be of three types: a Distinguished Name (DN) from the Metacomputing Directory Service (MDS, discussed later); a parameter specic to the local resource manager; 2

3 a language-extension parameter. Any language extension, typically created for convenience, must be distilled into one of the other two RSL parameter types before reaching the job scheduler. 4 Communication Service The Nexus communication library provides fast communication primitives to Globus. Nexus allows multi-mode communication conversations (communication over several physical networks and/or communication protocols). It supports unicast and multicast communication methods. Nexus is not designed as a user communication protocol; rather, friendly and ecient user communications are built using Nexus. Nexus abstracts ve communication objects: nodes, contexts, threads, communication links, and remote service requests[10]. A program consists of one or more address spaces or contexts, eachcontaining one or more threads of execution. Threads communicate via links between communication nodes by sending and receiving messages and executing remote service requests to other contexts. Messages contain control information, but may also contain global addresses which point to context-invariant data structures. Remote service requests allow threads to execute functions in another address space. Basic communication is constructed piece by piece. Nodes are created in two contexts[11]. One node becomes a communication start-point, the other an endpoint. One-waycommunication is then obtained by linking the start-point tothe endpoint. Two-way communication requires repeating this process with the startpoint and endpoint in the other contexts. Broadcast communication is obtained by linking one start-point to more than one endpoint. Similarly, a gather communication is obtained when more than one start-point is linked to one endpoint. 5 Security Service The Globus Security Service (GSS) provides a common interface for integrating diverse local security solutions. Features of this system include a single user sign-on, meaning that subsequent authentication requests are automatically handled by proxies. All resource use is authenticated, maintaining system security and controlling resource usage[9]. Globus security uses the ITU X.509 authentication protocol. This standard species the use of certicates, which are credentials that prove identity. Certicates are exchanged and compared to reference certicates for validity. The reference certicates are typically not identical to the oered certicate, but contain sucient information to prove the sender's identity. Certicate-based security relies exclusively on the trust of a Certicate Authority (CA). The CA is trusted by all,andprovides each entity with its own certicate. The basic rule used in certicate-based authentication is the transitive property of trust: if entity 1 trusts the CA, and entity 2hasshown that the CA trusts them, then entity 1 trusts entity 2. Each entity must initially register with the CA (and in return receive a certicate) to be able to participate in certicate-based authentication schemes. For example, assume three entities: a CA, a system administrator, and a user who wishes to use the system. By exchanging certicates, the system administrator can verify that the user is registered (trusted) by the CA and approve the access. Additionally, by obtaining the system's certicate the user can verify that they are communicating with the true system, and not an imposter. After secure authentication, Globus communication is performed using the Secure Socket Layer (SSL) protocol, which additionally encrypts communication exchanges using public/private key encryption. One additional aspect of the Globus security system is worth mentioning. A user can set up a proxy that will automatically authenticate them. Each Globus security proxy exists only for a specic time period dened by theuser. The advantage of a proxy is convenience: a user who has created a proxy does not have to authenticate himself/herself as long as the proxy is active. Additionally, proxies allow unattended batch jobs to be submitted to Globus (for example if a user wants to perform three Globus runs overnight). 6 Information Service A directory is like a database; directories hold records of information. Unlike databases, though, directories are read from more than they are written to. Globus provides the Metacomputing Directory Service (MDS) that contains resource information about grid elements[5]. System conguration information like how many processors the computer has, and what operating system is running. Usage information like the number of unallocated processors, and the system load. Management information like the name and contact information for the owning organization. Conguration info like theversion of Globus running on the machine, or the type of local resource scheduler. MDS information is automatically updated regularly but infrequently (updates occur on the order of hours) from GRAMs running on each local machine. Access to the MDS is obtained through the use of the Lightweight Directory Access Protocol (LDAP). LDAP 3

4 species the network protocols used to access directories and denes the form and character of the information as a directory information tree. This tree gives hierarchical information about specic resources[12]. The MDS is generated with and queried using LDAP. The MDS allows two kinds of directory service queries. A white pages request provides information regarding a specic directory entry. For example, the MDS may be queried to nd the IP address of a specic machine. A yellow pages request provides a list of directory entries with a specic property. For example, the MDS may be asked to provide a list of all machines with more than 48 processors. Today, the information held in the MDS allows grid users to understand the resources available and to formulate concrete resource requests. The yellow pages access mode of MDS enables future automated resource selection. 7 Fault Tolerance Service In addition to some fault tolerance integral to Nexus, Globus provides the Globus Heartbeat Monitor (HBM). The HBM performs periodic inquiry to detect process failures. The HBM does not provide system information, only process information. It additionally only provides an answer to the question "is process X still active?". To use the HBM, the user process or heartbeat client (HBC) makes a function call to register with the HBM daemon running on the local machine. This registration noties the daemon to actively probe the process, species the probing frequency, and species the data collector that receives probe data[13]. In this manner a process' health can be remotely monitored. 8 Remote Data Access Service The Global Access to Secondary Storage (GASS) provides primitive access to remote data. By accessing all les via a Universal Resource Locator (URL) the actual physical location of the le does not matter. GASS allows four types of remote le access[1]: shared read-only access to an entire le; shared write access where the last write dominates; shared append-only access to a le; unshared unrestricted read/write access. These le access modes are designed to provide commonly needed features while requiring very simple coherency rules. 9 GUSTO A prototype computational grid running Globus has been constructed. Called the Globus Ubiquitous Supercomputing Testbed (GUSTO), this system includes computing facilities from the U.S., Japan, Europe, and Australia[7]. Currently GUSTO has access to more than 3600 processors on more 300 computers at seventeen locations[8]. These machines are connected primarily via the Internet, with some connections provided by ATM networks. The aggregate peak performance of GUSTO is more than 2 Tops (2 trillion oating point operations per second)[7]. 10 SF-Express One of the most dramatic demonstrations of Globus' potential was the execution of a 55,000 entity battleeld simulation program. The U.S. Government Department of Defense maintains a virtual battleeld program to simulate wartime conditions. This application, Modular Semi-automated Forces (ModSAF), is an example of the Distributed Interactive Simulation (DIS) class of programs. In this program, troops, tanks, aircraft, and other entities interact with each other and with user input for testing and training purposes[3]. The program treats each entity uniquely and utilizes a cluster of workstations connected via a Local Area Network (LAN). Each workstation hosts a modest number of entities (30-100), and is responsible for handling interactions between entities residing on other workstations. Entity conditions and interactions are communicated in Protocol Data Unit (PDU) messages. In ModSAF, each machine broadcasts its entities' PDUs at regular intervals. All machines receive and parse all PDUs. One can see the scalability problem with this architecture as the number of entities increases: with the amount of communication scaling with the number ofentities, communication bandwidth is quickly exceeded. Barely-manageable runs of Mod- SAF involved 5400 entities. The Department of Defense, in conjunction with the Defense Advanced Research Projects Agency (DARPA) issued a challenge: they wanted to perform a ModSAF simulation with 10,000 entities. A new program, called Simulated Forces Express (SF-Express), performed the same actions as ModSAF, but was created specically for Globus. This program altered the entity communication patterns to be more scalable. Distant entities do not aect each other, allowing many communication messages to be ignored. 4

5 SF-Express dedicated one or more processors per machine to the task of discarding unneeded messages. SF- Express also used dedicated data servers, through which all access to secondary storage was routed. Agiven machine was decomposed into a number of simulation nodes that actually performed work, a number of interest management nodes that pruned the message stream, a number of data server nodes that managed secondary storage, and a router node that coordinated communication with other machines. Communication within a machine was handled via the Message Passing Interface (MPI), while communication between machines used sockets. These improvements, along with the raw power of GUSTO, allowed SF-Express to perform a run with more than 55,000 entities in August, This was avery successful demonstration of Globus and GUSTO. However, this display of computing power required signicant manual coordination between the six sites involved. The machines at these sites were dedicated entirely to SF-Express, and coordination of execution was painfully managed by hand[2]. 11 Conclusion The Globus Toolkit provides infrastructure supporting grid computing, enabling next-generation applications to be run on a widely distributed collection of computing resources. Globus is very much a work in progress. As new techniques addressing the fundamental grid computing problems are discovered, advances in this infrastructure ease the pain of distributed computing by increasing performance and eliminating extensive user knowledge about the underlying system. More detail can be found in the references or via the World Wide Web: 12 Review Questions 1. A telephone book is most like what Globus service? 2. What is RSL? How does Globus use it? 3. Why would you use a computational grid? Why would you not? 4. Name three fundamental problems in grid computing. 5. Does Globus provide the ability for multiple processes to simultaneously access a remote le? Under what conditions? 6. What two Globus communication primatives enable threads to communicate? References [1] Bester, J., Foster, I., Kesselman, C., Tedesco, J., and Tuecke, S. Gass: A data movement and access service for wide area computing systems. In 7 (1997), p [2] Brunett, S., Czajkowski, K., Foster, I., Fitzgerald, S., Johnson, A., Kesselman, C., Leigh, J., and Tuecke, S. Application experiences with the globus toolkit. In Proc. 7th IEEE Symp. on High Performance Distributed Computing (July 1998), IEEE Computer Society Press. To appear. [3] Brunett, S., Davis, D., Gottschalk, T., Messina, P., and Kesselman, C. Implementing distributed synthetic forces simulations in metacomputing environments. In Proceedings of the Heterogeneous Computing Workshop (Mar. 1998). [4] Czajkowski, K., Foster, I., Karonis, N., Kesselman, C., Martin, S., Smith, W., and Tuecke, S. A resource management architecture for metacomputing systems. In The 4th Workshop on Job Scheduling Strategies for Parallel Processing (Mar. 1998), IEEE-P, pp. 4{18. [5] Fitzgerald, S., Foster, I., Kesselman, C., von Laszewski, G., Smith, W., and Tuecke, S. A directory service for conguring highperformance distributed computations. In Proc. 6th IEEE Symp. on High Performance Distributed Computing (1997), IEEE Computer Society Press, pp. 365{375. [6] Foster, I., Karonis, N. T., Kesselman, C., and Tuecke, S. Managing security in highperformance distributed computations. Cluster Computing 1, 1 (1998), 95{107. [7] Foster, I., and Kesselman, C. Globus: A metacomputing infrastructure toolkit. International Journal of Supercomputer Applications 11, 2 (1997), 115{128. [8] Foster, I., and Kesselman, C. The Globus project: A progress report. In Proceedings of the Heterogeneous Computing Workshop (Mar. 1998). [9] Foster, I., Kesselman, C., and Tsudick, S. T. G. A security architecture for computational grids. In Proc. of the 5th ACM Conference on Computer and Communication Security (Nov. 1998), ACM Press. To appear. 5

6 [10] Foster, I., Kesselman, C., and Tuecke, S. The Nexus task-parallel runtime system. In Proc. 1st Intl Workshop on Parallel Processing. Tata Mc- Graw Hill, 1994, pp. 457{462. [11] Foster, I., and Tuecke, S. Nexus: Runtime support for task-parallel programming languages. Tech. rep., ANL, [12] Foster, I., and von Laszewski, G. Usage of ldap in globus. Tech. rep., ANL, [13] Stelling, P., Foster, I., Kesselman, C., Lee, C., and von Laszewski, G. A fault detection service for wide area distributed computations. In Proc. 7th IEEE Symp. on High Performance Distributed Computing (July 1998), IEEE Computer Society Press. To appear. 6

UNICORE Globus: Interoperability of Grid Infrastructures

UNICORE Globus: Interoperability of Grid Infrastructures UNICORE : Interoperability of Grid Infrastructures Michael Rambadt Philipp Wieder Central Institute for Applied Mathematics (ZAM) Research Centre Juelich D 52425 Juelich, Germany Phone: +49 2461 612057

More information

Usage of LDAP in Globus

Usage of LDAP in Globus Usage of LDAP in Globus Gregor von Laszewski and Ian Foster Mathematics and Computer Science Division Argonne National Laboratory, Argonne, IL 60439 gregor@mcs.anl.gov Abstract: This short note describes

More information

An Evaluation of Alternative Designs for a Grid Information Service

An Evaluation of Alternative Designs for a Grid Information Service An Evaluation of Alternative Designs for a Grid Information Service Warren Smith, Abdul Waheed *, David Meyers, Jerry Yan Computer Sciences Corporation * MRJ Technology Solutions Directory Research L.L.C.

More information

THE GLOBUS PROJECT. White Paper. GridFTP. Universal Data Transfer for the Grid

THE GLOBUS PROJECT. White Paper. GridFTP. Universal Data Transfer for the Grid THE GLOBUS PROJECT White Paper GridFTP Universal Data Transfer for the Grid WHITE PAPER GridFTP Universal Data Transfer for the Grid September 5, 2000 Copyright 2000, The University of Chicago and The

More information

A Resource Management Architecture. for Metacomputing Systems. fkarlcz, itf, karonis, carl, smartin, wsmith,

A Resource Management Architecture. for Metacomputing Systems. fkarlcz, itf, karonis, carl, smartin, wsmith, A Resource Management Architecture for Metacomputing Systems Karl Czajkowski 1, Ian Foster 2, Nick Karonis 2, Carl Kesselman 1, Stuart Martin 2, Warren Smith 2, and Steven Tuecke 2 fkarlcz, itf, karonis,

More information

A Survey Paper on Grid Information Systems

A Survey Paper on Grid Information Systems B 534 DISTRIBUTED SYSTEMS A Survey Paper on Grid Information Systems Anand Hegde 800 North Smith Road Bloomington Indiana 47408 aghegde@indiana.edu ABSTRACT Grid computing combines computers from various

More information

A Distributed Media Service System Based on Globus Data-Management Technologies1

A Distributed Media Service System Based on Globus Data-Management Technologies1 A Distributed Media Service System Based on Globus Data-Management Technologies1 Xiang Yu, Shoubao Yang, and Yu Hong Dept. of Computer Science, University of Science and Technology of China, Hefei 230026,

More information

Introduction to GT3. Introduction to GT3. What is a Grid? A Story of Evolution. The Globus Project

Introduction to GT3. Introduction to GT3. What is a Grid? A Story of Evolution. The Globus Project Introduction to GT3 The Globus Project Argonne National Laboratory USC Information Sciences Institute Copyright (C) 2003 University of Chicago and The University of Southern California. All Rights Reserved.

More information

AN INTRODUCTION TO THE GLOBUS TOOLKIT

AN INTRODUCTION TO THE GLOBUS TOOLKIT AN INTRODUCTION TO THE GLOBUS TOOLKIT Giovanni Aloisio UNIVERSITY OF LECCE, Lecce, Italy Massimo Cafaro UNIVERSITY OF LECCE, Lecce, Italy Abstract The Globus toolkit is a grid middleware being developed

More information

Monitoring the Usage of the ZEUS Analysis Grid

Monitoring the Usage of the ZEUS Analysis Grid Monitoring the Usage of the ZEUS Analysis Grid Stefanos Leontsinis September 9, 2006 Summer Student Programme 2006 DESY Hamburg Supervisor Dr. Hartmut Stadie National Technical

More information

Scheduling Large Parametric Modelling Experiments on a Distributed Meta-computer

Scheduling Large Parametric Modelling Experiments on a Distributed Meta-computer Scheduling Large Parametric Modelling Experiments on a Distributed Meta-computer David Abramson and Jon Giddy Department of Digital Systems, CRC for Distributed Systems Technology Monash University, Gehrmann

More information

Globus: A Metacomputing Infrastructure Toolkit. Abstract

Globus: A Metacomputing Infrastructure Toolkit.   Abstract Globus: A Metacomputing Infrastructure Toolkit Ian Foster Carl Kesselman y http://www.globus.org/ Abstract Emerging high-performance applications require the ability to exploit diverse, geographically

More information

DiPerF: automated DIstributed PERformance testing Framework

DiPerF: automated DIstributed PERformance testing Framework DiPerF: automated DIstributed PERformance testing Framework Ioan Raicu, Catalin Dumitrescu, Matei Ripeanu, Ian Foster Distributed Systems Laboratory Computer Science Department University of Chicago Introduction

More information

Introduction to Grid Computing

Introduction to Grid Computing Milestone 2 Include the names of the papers You only have a page be selective about what you include Be specific; summarize the authors contributions, not just what the paper is about. You might be able

More information

Design of Distributed Data Mining Applications on the KNOWLEDGE GRID

Design of Distributed Data Mining Applications on the KNOWLEDGE GRID Design of Distributed Data Mining Applications on the KNOWLEDGE GRID Mario Cannataro ICAR-CNR cannataro@acm.org Domenico Talia DEIS University of Calabria talia@deis.unical.it Paolo Trunfio DEIS University

More information

GridMonitor: Integration of Large Scale Facility Fabric Monitoring with Meta Data Service in Grid Environment

GridMonitor: Integration of Large Scale Facility Fabric Monitoring with Meta Data Service in Grid Environment GridMonitor: Integration of Large Scale Facility Fabric Monitoring with Meta Data Service in Grid Environment Rich Baker, Dantong Yu, Jason Smith, and Anthony Chan RHIC/USATLAS Computing Facility Department

More information

A Capabilities Based Communication Model for High-Performance Distributed Applications: The Open HPC++ Approach

A Capabilities Based Communication Model for High-Performance Distributed Applications: The Open HPC++ Approach A Capabilities Based Communication Model for High-Performance Distributed Applications: The Open HPC++ Approach Shridhar Diwan, Dennis Gannon Department of Computer Science Indiana University Bloomington,

More information

Day 1 : August (Thursday) An overview of Globus Toolkit 2.4

Day 1 : August (Thursday) An overview of Globus Toolkit 2.4 An Overview of Grid Computing Workshop Day 1 : August 05 2004 (Thursday) An overview of Globus Toolkit 2.4 By CDAC Experts Contact :vcvrao@cdacindia.com; betatest@cdacindia.com URL : http://www.cs.umn.edu/~vcvrao

More information

Grid Architectural Models

Grid Architectural Models Grid Architectural Models Computational Grids - A computational Grid aggregates the processing power from a distributed collection of systems - This type of Grid is primarily composed of low powered computers

More information

Grid Computing. MCSN - N. Tonellotto - Distributed Enabling Platforms

Grid Computing. MCSN - N. Tonellotto - Distributed Enabling Platforms Grid Computing 1 Resource sharing Elements of Grid Computing - Computers, data, storage, sensors, networks, - Sharing always conditional: issues of trust, policy, negotiation, payment, Coordinated problem

More information

Computational Mini-Grid Research at Clemson University

Computational Mini-Grid Research at Clemson University Computational Mini-Grid Research at Clemson University Parallel Architecture Research Lab November 19, 2002 Project Description The concept of grid computing is becoming a more and more important one in

More information

Grid Computing Fall 2005 Lecture 5: Grid Architecture and Globus. Gabrielle Allen

Grid Computing Fall 2005 Lecture 5: Grid Architecture and Globus. Gabrielle Allen Grid Computing 7700 Fall 2005 Lecture 5: Grid Architecture and Globus Gabrielle Allen allen@bit.csc.lsu.edu http://www.cct.lsu.edu/~gallen Concrete Example I have a source file Main.F on machine A, an

More information

Replica Selection in the Globus Data Grid

Replica Selection in the Globus Data Grid Replica Selection in the Globus Data Grid Sudharshan Vazhkudai 1, Steven Tuecke 2, and Ian Foster 2 1 Department of Computer and Information Science The University of Mississippi chucha@john.cs.olemiss.edu

More information

Attribute based query. Direct reservation. Pentium Cluster (Instruments) SGI Cluster (Gemstones) PENTIUM SCHEDULER. request 2 pentiums.

Attribute based query. Direct reservation. Pentium Cluster (Instruments) SGI Cluster (Gemstones) PENTIUM SCHEDULER. request 2 pentiums. A General Resource Reservation Framework for Scientic Computing? Ravi Ramamoorthi, Adam Rifkin, Boris Dimitrov, and K. Mani Chandy California Institute of Technology Abstract. We describe three contributions

More information

2 Application Support via Proxies Onion Routing can be used with applications that are proxy-aware, as well as several non-proxy-aware applications, w

2 Application Support via Proxies Onion Routing can be used with applications that are proxy-aware, as well as several non-proxy-aware applications, w Onion Routing for Anonymous and Private Internet Connections David Goldschlag Michael Reed y Paul Syverson y January 28, 1999 1 Introduction Preserving privacy means not only hiding the content of messages,

More information

Layered Architecture

Layered Architecture The Globus Toolkit : Introdution Dr Simon See Sun APSTC 09 June 2003 Jie Song, Grid Computing Specialist, Sun APSTC 2 Globus Toolkit TM An open source software toolkit addressing key technical problems

More information

ROCI 2: A Programming Platform for Distributed Robots based on Microsoft s.net Framework

ROCI 2: A Programming Platform for Distributed Robots based on Microsoft s.net Framework ROCI 2: A Programming Platform for Distributed Robots based on Microsoft s.net Framework Vito Sabella, Camillo J. Taylor, Scott Currie GRASP Laboratory University of Pennsylvania Philadelphia PA, 19104

More information

Web-based access to the grid using. the Grid Resource Broker Portal

Web-based access to the grid using. the Grid Resource Broker Portal Web-based access to the grid using the Grid Resource Broker Portal Giovanni Aloisio, Massimo Cafaro ISUFI High Performance Computing Center Department of Innovation Engineering University of Lecce, Italy

More information

Kenneth A. Hawick P. D. Coddington H. A. James

Kenneth A. Hawick P. D. Coddington H. A. James Student: Vidar Tulinius Email: vidarot@brandeis.edu Distributed frameworks and parallel algorithms for processing large-scale geographic data Kenneth A. Hawick P. D. Coddington H. A. James Overview Increasing

More information

Chapter 4:- Introduction to Grid and its Evolution. Prepared By:- NITIN PANDYA Assistant Professor SVBIT.

Chapter 4:- Introduction to Grid and its Evolution. Prepared By:- NITIN PANDYA Assistant Professor SVBIT. Chapter 4:- Introduction to Grid and its Evolution Prepared By:- Assistant Professor SVBIT. Overview Background: What is the Grid? Related technologies Grid applications Communities Grid Tools Case Studies

More information

Wide-area Cluster System

Wide-area Cluster System Performance Evaluation of a Firewall-compliant Globus-based Wide-area Cluster System Yoshio Tanaka 3, Mitsuhisa Sato Real World Computing Partnership Mitsui bldg. 14F, 1-6-1 Takezono Tsukuba Ibaraki 305-0032,

More information

Grid Computing Middleware. Definitions & functions Middleware components Globus glite

Grid Computing Middleware. Definitions & functions Middleware components Globus glite Seminar Review 1 Topics Grid Computing Middleware Grid Resource Management Grid Computing Security Applications of SOA and Web Services Semantic Grid Grid & E-Science Grid Economics Cloud Computing 2 Grid

More information

MONITORING OF GRID RESOURCES

MONITORING OF GRID RESOURCES MONITORING OF GRID RESOURCES Nikhil Khandelwal School of Computer Engineering Nanyang Technological University Nanyang Avenue, Singapore 639798 e-mail:a8156178@ntu.edu.sg Lee Bu Sung School of Computer

More information

PARALLEL PROGRAM EXECUTION SUPPORT IN THE JGRID SYSTEM

PARALLEL PROGRAM EXECUTION SUPPORT IN THE JGRID SYSTEM PARALLEL PROGRAM EXECUTION SUPPORT IN THE JGRID SYSTEM Szabolcs Pota 1, Gergely Sipos 2, Zoltan Juhasz 1,3 and Peter Kacsuk 2 1 Department of Information Systems, University of Veszprem, Hungary 2 Laboratory

More information

A RESOURCE MANAGEMENT FRAMEWORK FOR INTERACTIVE GRIDS

A RESOURCE MANAGEMENT FRAMEWORK FOR INTERACTIVE GRIDS A RESOURCE MANAGEMENT FRAMEWORK FOR INTERACTIVE GRIDS Raj Kumar, Vanish Talwar, Sujoy Basu Hewlett-Packard Labs 1501 Page Mill Road, MS 1181 Palo Alto, CA 94304 USA { raj.kumar,vanish.talwar,sujoy.basu}@hp.com

More information

Introduction to Networking

Introduction to Networking Introduction to Networking The fundamental purpose of data communications is to exchange information between user's computers, terminals and applications programs. Simplified Communications System Block

More information

THE VEGA PERSONAL GRID: A LIGHTWEIGHT GRID ARCHITECTURE

THE VEGA PERSONAL GRID: A LIGHTWEIGHT GRID ARCHITECTURE THE VEGA PERSONAL GRID: A LIGHTWEIGHT GRID ARCHITECTURE Wei Li, Zhiwei Xu, Bingchen Li, Yili Gong Institute of Computing Technology of Chinese Academy of Sciences Beijing China, 100080 {zxu, liwei, libingchen,

More information

IMAGE: An approach to building standards-based enterprise Grids

IMAGE: An approach to building standards-based enterprise Grids IMAGE: An approach to building standards-based enterprise Grids Gabriel Mateescu 1 and Masha Sosonkina 2 1 Research Computing Support Group 2 Scalable Computing Laboratory National Research Council USDOE

More information

Globus Toolkit Firewall Requirements. Abstract

Globus Toolkit Firewall Requirements. Abstract Globus Toolkit Firewall Requirements v0.3 8/30/2002 Von Welch Software Architect, Globus Project welch@mcs.anl.gov Abstract This document provides requirements and guidance to firewall administrators at

More information

Managing CAE Simulation Workloads in Cluster Environments

Managing CAE Simulation Workloads in Cluster Environments Managing CAE Simulation Workloads in Cluster Environments Michael Humphrey V.P. Enterprise Computing Altair Engineering humphrey@altair.com June 2003 Copyright 2003 Altair Engineering, Inc. All rights

More information

High Performance Computing Course Notes Grid Computing I

High Performance Computing Course Notes Grid Computing I High Performance Computing Course Notes 2008-2009 2009 Grid Computing I Resource Demands Even as computer power, data storage, and communication continue to improve exponentially, resource capacities are

More information

Knowledge Discovery Services and Tools on Grids

Knowledge Discovery Services and Tools on Grids Knowledge Discovery Services and Tools on Grids DOMENICO TALIA DEIS University of Calabria ITALY talia@deis.unical.it Symposium ISMIS 2003, Maebashi City, Japan, Oct. 29, 2003 OUTLINE Introduction Grid

More information

W H I T E P A P E R : O P E N. V P N C L O U D. Implementing A Secure OpenVPN Cloud

W H I T E P A P E R : O P E N. V P N C L O U D. Implementing A Secure OpenVPN Cloud W H I T E P A P E R : O P E N. V P N C L O U D Implementing A Secure OpenVPN Cloud Platform White Paper: OpenVPN Cloud Platform Implementing OpenVPN Cloud Platform Content Introduction... 3 The Problems...

More information

Architecture Proposal

Architecture Proposal Nordic Testbed for Wide Area Computing and Data Handling NORDUGRID-TECH-1 19/02/2002 Architecture Proposal M.Ellert, A.Konstantinov, B.Kónya, O.Smirnova, A.Wäänänen Introduction The document describes

More information

CSF4:A WSRF Compliant Meta-Scheduler

CSF4:A WSRF Compliant Meta-Scheduler CSF4:A WSRF Compliant Meta-Scheduler Wei Xiaohui 1, Ding Zhaohui 1, Yuan Shutao 2, Hou Chang 1, LI Huizhen 1 (1: The College of Computer Science & Technology, Jilin University, China 2:Platform Computing,

More information

Grid-Based Data Mining and the KNOWLEDGE GRID Framework

Grid-Based Data Mining and the KNOWLEDGE GRID Framework Grid-Based Data Mining and the KNOWLEDGE GRID Framework DOMENICO TALIA (joint work with M. Cannataro, A. Congiusta, P. Trunfio) DEIS University of Calabria ITALY talia@deis.unical.it Minneapolis, September

More information

Credentials Management for Authentication in a Grid-Based E-Learning Platform

Credentials Management for Authentication in a Grid-Based E-Learning Platform Credentials Management for Authentication in a Grid-Based E-Learning Platform Felicia Ionescu, Vlad Nae, Alexandru Gherega University Politehnica of Bucharest {fionescu, vnae, agherega}@tech.pub.ro Abstract

More information

UNIT IV PROGRAMMING MODEL. Open source grid middleware packages - Globus Toolkit (GT4) Architecture, Configuration - Usage of Globus

UNIT IV PROGRAMMING MODEL. Open source grid middleware packages - Globus Toolkit (GT4) Architecture, Configuration - Usage of Globus UNIT IV PROGRAMMING MODEL Open source grid middleware packages - Globus Toolkit (GT4) Architecture, Configuration - Usage of Globus Globus: One of the most influential Grid middleware projects is the Globus

More information

DISTRIBUTED SYSTEMS Principles and Paradigms Second Edition ANDREW S. TANENBAUM MAARTEN VAN STEEN. Chapter 1. Introduction

DISTRIBUTED SYSTEMS Principles and Paradigms Second Edition ANDREW S. TANENBAUM MAARTEN VAN STEEN. Chapter 1. Introduction DISTRIBUTED SYSTEMS Principles and Paradigms Second Edition ANDREW S. TANENBAUM MAARTEN VAN STEEN Chapter 1 Introduction Modified by: Dr. Ramzi Saifan Definition of a Distributed System (1) A distributed

More information

Benchmarking the CGNS I/O performance

Benchmarking the CGNS I/O performance 46th AIAA Aerospace Sciences Meeting and Exhibit 7-10 January 2008, Reno, Nevada AIAA 2008-479 Benchmarking the CGNS I/O performance Thomas Hauser I. Introduction Linux clusters can provide a viable and

More information

06-Dec-17. Credits:4. Notes by Pritee Parwekar,ANITS 06-Dec-17 1

06-Dec-17. Credits:4. Notes by Pritee Parwekar,ANITS 06-Dec-17 1 Credits:4 1 Understand the Distributed Systems and the challenges involved in Design of the Distributed Systems. Understand how communication is created and synchronized in Distributed systems Design and

More information

Distributed Computing: PVM, MPI, and MOSIX. Multiple Processor Systems. Dr. Shaaban. Judd E.N. Jenne

Distributed Computing: PVM, MPI, and MOSIX. Multiple Processor Systems. Dr. Shaaban. Judd E.N. Jenne Distributed Computing: PVM, MPI, and MOSIX Multiple Processor Systems Dr. Shaaban Judd E.N. Jenne May 21, 1999 Abstract: Distributed computing is emerging as the preferred means of supporting parallel

More information

A CORBA Commodity Grid Kit

A CORBA Commodity Grid Kit A CORBA Commodity Grid Kit Snigdha Verma 2, Jarek Gawor 1, Gregor von Laszewski 1, and Manish Parashar 2 1 Mathematics and Computer Science Division Argonne National Laboratory, 9700 S. Cass Ave, Argonne,

More information

Functional Requirements for Grid Oriented Optical Networks

Functional Requirements for Grid Oriented Optical Networks Functional Requirements for Grid Oriented Optical s Luca Valcarenghi Internal Workshop 4 on Photonic s and Technologies Scuola Superiore Sant Anna Pisa June 3-4, 2003 1 Motivations Grid networking connection

More information

Web site Image database. Web site Video database. Web server. Meta-server Meta-search Agent. Meta-DB. Video query. Text query. Web client.

Web site Image database. Web site Video database. Web server. Meta-server Meta-search Agent. Meta-DB. Video query. Text query. Web client. (Published in WebNet 97: World Conference of the WWW, Internet and Intranet, Toronto, Canada, Octobor, 1997) WebView: A Multimedia Database Resource Integration and Search System over Web Deepak Murthy

More information

A Comparison of Conventional Distributed Computing Environments and Computational Grids

A Comparison of Conventional Distributed Computing Environments and Computational Grids A Comparison of Conventional Distributed Computing Environments and Computational Grids Zsolt Németh 1, Vaidy Sunderam 2 1 MTA SZTAKI, Computer and Automation Research Institute, Hungarian Academy of Sciences,

More information

INTERNATIONAL JOURNAL OF COMPUTER ENGINEERING & TECHNOLOGY (IJCET)

INTERNATIONAL JOURNAL OF COMPUTER ENGINEERING & TECHNOLOGY (IJCET) INTERNATIONAL JOURNAL OF COMPUTER ENGINEERING & TECHNOLOGY (IJCET) International Journal of Computer Engineering and Technology (IJCET), ISSN 0976-6367(Print), ISSN 0976 6367(Print) ISSN 0976 6375(Online)

More information

The Beta Grid: A National Infrastructure for Computer Systems Research

The Beta Grid: A National Infrastructure for Computer Systems Research The Beta Grid: A National Infrastructure for Computer Systems Research Ian Foster Argonne National Laboratory and The University of Chicago 1 Introduction In future information infrastructures, boundaries

More information

The Grid Authentication System for Mobile Grid Environment

The Grid Authentication System for Mobile Grid Environment IJSRD - International Journal for Scientific Research & Development Vol. 2, Issue 02, 2014 ISSN (online): 2321-0613 The Grid Authentication System for Mobile Grid Environment A.Sudha 1 S.M.Karpagavalli

More information

Outline. Definition of a Distributed System Goals of a Distributed System Types of Distributed Systems

Outline. Definition of a Distributed System Goals of a Distributed System Types of Distributed Systems Distributed Systems Outline Definition of a Distributed System Goals of a Distributed System Types of Distributed Systems What Is A Distributed System? A collection of independent computers that appears

More information

Attribute based query. Direct reservation. Pentium Cluster (Instruments) SGI Cluster (Gemstones) PENTIUM SCHEDULER. request 2 pentiums.

Attribute based query. Direct reservation. Pentium Cluster (Instruments) SGI Cluster (Gemstones) PENTIUM SCHEDULER. request 2 pentiums. A General Resource Reservation Framework for Scientic Computing K. Mani Chandy, Boris Dimitrov, Ravi Ramamoorthi, and Adam Rifkin Caltech Department of Computer Science 256-80, Pasadena, CA 91125 fmani,boris,ravir,adamg@cs.caltech.edu

More information

Lecture 9: MIMD Architectures

Lecture 9: MIMD Architectures Lecture 9: MIMD Architectures Introduction and classification Symmetric multiprocessors NUMA architecture Clusters Zebo Peng, IDA, LiTH 1 Introduction A set of general purpose processors is connected together.

More information

Service Mesh and Microservices Networking

Service Mesh and Microservices Networking Service Mesh and Microservices Networking WHITEPAPER Service mesh and microservice networking As organizations adopt cloud infrastructure, there is a concurrent change in application architectures towards

More information

Kevin Skadron. 18 April Abstract. higher rate of failure requires eective fault-tolerance. Asynchronous consistent checkpointing oers a

Kevin Skadron. 18 April Abstract. higher rate of failure requires eective fault-tolerance. Asynchronous consistent checkpointing oers a Asynchronous Checkpointing for PVM Requires Message-Logging Kevin Skadron 18 April 1994 Abstract Distributed computing using networked workstations oers cost-ecient parallel computing, but the higher rate

More information

An Engineering Computation Oriented Visual Grid Framework

An Engineering Computation Oriented Visual Grid Framework An Engineering Computation Oriented Visual Grid Framework Guiyi Wei 1,2,3, Yao Zheng 1,2, Jifa Zhang 1,2, and Guanghua Song 1,2 1 College of Computer Science, Zhejiang University, Hangzhou, 310027, P.

More information

By Ian Foster. Zhifeng Yun

By Ian Foster. Zhifeng Yun By Ian Foster Zhifeng Yun Outline Introduction Globus Architecture Globus Software Details Dev.Globus Community Summary Future Readings Introduction Globus Toolkit v4 is the work of many Globus Alliance

More information

NUSGRID a computational grid at NUS

NUSGRID a computational grid at NUS NUSGRID a computational grid at NUS Grace Foo (SVU/Academic Computing, Computer Centre) SVU is leading an initiative to set up a campus wide computational grid prototype at NUS. The initiative arose out

More information

Reporting Interface. network link sensor machine machine machine. memory sensor. CPU sensor. 2.1 Sensory Subsystem. Sensor Data. Forecasting Subsystem

Reporting Interface. network link sensor machine machine machine. memory sensor. CPU sensor. 2.1 Sensory Subsystem. Sensor Data. Forecasting Subsystem Implementing a Performance Forecasting System for Metacomputing: The Network Weather Service (Extended Abstract) submitted to SC97 UCSD Technical Report TR-CS97-540 Rich Wolski Neil Spring Chris Peterson

More information

CSE 5306 Distributed Systems. Course Introduction

CSE 5306 Distributed Systems. Course Introduction CSE 5306 Distributed Systems Course Introduction 1 Instructor and TA Dr. Donggang Liu @ CSE Web: http://ranger.uta.edu/~dliu Email: dliu@uta.edu Phone: 817-2720741 Office: ERB 555 Office hours: Tus/Ths

More information

A Parallel Programming Environment on Grid

A Parallel Programming Environment on Grid A Parallel Programming Environment on Grid Weiqin Tong, Jingbo Ding, and Lizhi Cai School of Computer Engineering and Science, Shanghai University, Shanghai 200072, China wqtong@mail.shu.edu.cn Abstract.

More information

A Resource Discovery Algorithm in Mobile Grid Computing Based on IP-Paging Scheme

A Resource Discovery Algorithm in Mobile Grid Computing Based on IP-Paging Scheme A Resource Discovery Algorithm in Mobile Grid Computing Based on IP-Paging Scheme Yue Zhang 1 and Yunxia Pei 2 1 Department of Math and Computer Science Center of Network, Henan Police College, Zhengzhou,

More information

A Grid Web Portal for Aerospace

A Grid Web Portal for Aerospace A Grid Web Portal for Aerospace Sang Boem Lim*, Joobum Kim*, Nam Gyu Kim*, June H. Lee*, Chongam Kim, Yoonhee Kim * Supercomputing Application Technology Department, Korea Institute of Science and Technology

More information

Introduction to Cluster Computing

Introduction to Cluster Computing Introduction to Cluster Computing Prabhaker Mateti Wright State University Dayton, Ohio, USA Overview High performance computing High throughput computing NOW, HPC, and HTC Parallel algorithms Software

More information

Network. Department of Statistics. University of California, Berkeley. January, Abstract

Network. Department of Statistics. University of California, Berkeley. January, Abstract Parallelizing CART Using a Workstation Network Phil Spector Leo Breiman Department of Statistics University of California, Berkeley January, 1995 Abstract The CART (Classication and Regression Trees) program,

More information

THEBES: THE GRID MIDDLEWARE PROJECT Project Overview, Status Report and Roadmap

THEBES: THE GRID MIDDLEWARE PROJECT Project Overview, Status Report and Roadmap THEBES: THE GRID MIDDLEWARE PROJECT Project Overview, Status Report and Roadmap Arnie Miles Georgetown University adm35@georgetown.edu http://thebes.arc.georgetown.edu The Thebes middleware project was

More information

Introduction to Networking

Introduction to Networking Introduction to Networking Chapters 1 and 2 Outline Computer Network Fundamentals Defining a Network Networks Defined by Geography Networks Defined by Topology Networks Defined by Resource Location OSI

More information

Cluster Abstraction: towards Uniform Resource Description and Access in Multicluster Grid

Cluster Abstraction: towards Uniform Resource Description and Access in Multicluster Grid Cluster Abstraction: towards Uniform Resource Description and Access in Multicluster Grid Maoyuan Xie, Zhifeng Yun, Zhou Lei, Gabrielle Allen Center for Computation & Technology, Louisiana State University,

More information

WebFlow - High-Level Programming Environment and Visual Authoring Toolkit for High Performance Distributed Computing

WebFlow - High-Level Programming Environment and Visual Authoring Toolkit for High Performance Distributed Computing WebFlow - High-Level Programming Environment and Visual Authoring Toolkit for High Performance Distributed Computing Erol Akarsu Northeast Parallel Architectures Center at Syracuse University Syracuse,

More information

An OGSI CredentialManager Service Jim Basney a, Shiva Shankar Chetan a, Feng Qin a, Sumin Song a, Xiao Tu a, and Marty Humphrey b

An OGSI CredentialManager Service Jim Basney a, Shiva Shankar Chetan a, Feng Qin a, Sumin Song a, Xiao Tu a, and Marty Humphrey b UK Workshop on Grid Security Experiences, Oxford 8th and 9th July 2004 An OGSI CredentialManager Service Jim Basney a, Shiva Shankar Chetan a, Feng Qin a, Sumin Song a, Xiao Tu a, and Marty Humphrey b

More information

submission and collaborative spaces. Science portals are a continuation of the successfully implemented scientic workbenches [4]. Unfortunately, the c

submission and collaborative spaces. Science portals are a continuation of the successfully implemented scientic workbenches [4]. Unfortunately, the c grid infrastructure to support science portals for large scale instruments gregor von laszewski and ian foster Mathematics and Computer Science Division Argonne National Laboratory 9700 S. Cass Avenue

More information

M. Roehrig, Sandia National Laboratories. Philipp Wieder, Research Centre Jülich Nov 2002

M. Roehrig, Sandia National Laboratories. Philipp Wieder, Research Centre Jülich Nov 2002 Category: INFORMATIONAL Grid Scheduling Dictionary WG (SD-WG) M. Roehrig, Sandia National Laboratories Wolfgang Ziegler, Fraunhofer-Institute for Algorithms and Scientific Computing Philipp Wieder, Research

More information

Cluster quality 15. Running time 0.7. Distance between estimated and true means Running time [s]

Cluster quality 15. Running time 0.7. Distance between estimated and true means Running time [s] Fast, single-pass K-means algorithms Fredrik Farnstrom Computer Science and Engineering Lund Institute of Technology, Sweden arnstrom@ucsd.edu James Lewis Computer Science and Engineering University of

More information

Grid Programming: Concepts and Challenges. Michael Rokitka CSE510B 10/2007

Grid Programming: Concepts and Challenges. Michael Rokitka CSE510B 10/2007 Grid Programming: Concepts and Challenges Michael Rokitka SUNY@Buffalo CSE510B 10/2007 Issues Due to Heterogeneous Hardware level Environment Different architectures, chipsets, execution speeds Software

More information

A Guide to Transparency in Five Research Metasystems

A Guide to Transparency in Five Research Metasystems A Guide to Transparency in Five Research Metasystems Allen Chu, Marsha Eng, Kevin D. Munroe, and Shava Smallen Abstract Metasystems are geographically distributed networks of heterogeneous computers on

More information

A Directory Service for Configuring High-Performance Distributed Computations

A Directory Service for Configuring High-Performance Distributed Computations A Directory Service for Configuring High-Performance Distributed Computations Steven Fitzgerald, 1 Ian Foster, 2 Carl Kesselman, 1 Gregor von Laszewski, 2 Warren Smith, 2 Steven Tuecke 2 1 Information

More information

Language-Based Parallel Program Interaction: The Breezy Approach. Darryl I. Brown Allen D. Malony. Bernd Mohr. University of Oregon

Language-Based Parallel Program Interaction: The Breezy Approach. Darryl I. Brown Allen D. Malony. Bernd Mohr. University of Oregon Language-Based Parallel Program Interaction: The Breezy Approach Darryl I. Brown Allen D. Malony Bernd Mohr Department of Computer And Information Science University of Oregon Eugene, Oregon 97403 fdarrylb,

More information

Gregor von Laszewski, Ian Foster, Jarek Gawor, Warren Smith, Steven Tuecke. 1 Introduction 1. 2 Grids and Grid Technologies 2

Gregor von Laszewski, Ian Foster, Jarek Gawor, Warren Smith, Steven Tuecke. 1 Introduction 1. 2 Grids and Grid Technologies 2 Title: CoG Kits: A Bridge between Commodity Distributed-Computing and High- Performance Grids Authors: Address: e-mail: Gregor von Laszewski, Ian Foster, Jarek Gawor, Warren Smith, Steven Tuecke Argonne

More information

An Introduction to the Grid

An Introduction to the Grid 1 An Introduction to the Grid 1.1 INTRODUCTION The Grid concepts and technologies are all very new, first expressed by Foster and Kesselman in 1998 [1]. Before this, efforts to orchestrate wide-area distributed

More information

Adaptive Cluster Computing using JavaSpaces

Adaptive Cluster Computing using JavaSpaces Adaptive Cluster Computing using JavaSpaces Jyoti Batheja and Manish Parashar The Applied Software Systems Lab. ECE Department, Rutgers University Outline Background Introduction Related Work Summary of

More information

Toward Scalable Monitoring on Large-Scale Storage for Software Defined Cyberinfrastructure

Toward Scalable Monitoring on Large-Scale Storage for Software Defined Cyberinfrastructure Toward Scalable Monitoring on Large-Scale Storage for Software Defined Cyberinfrastructure Arnab K. Paul, Ryan Chard, Kyle Chard, Steven Tuecke, Ali R. Butt, Ian Foster Virginia Tech, Argonne National

More information

Grid Computing Security: A Survey

Grid Computing Security: A Survey Grid Computing Security: A Survey Basappa B. Kodada, Shiva Kumar K. M Dept. of CSE Canara Engineering College, Mangalore basappabk@gmail.com, shivakumarforu@rediffmail.com Abstract - This paper provides

More information

THE IMPACT OF E-COMMERCE ON DEVELOPING A COURSE IN OPERATING SYSTEMS: AN INTERPRETIVE STUDY

THE IMPACT OF E-COMMERCE ON DEVELOPING A COURSE IN OPERATING SYSTEMS: AN INTERPRETIVE STUDY THE IMPACT OF E-COMMERCE ON DEVELOPING A COURSE IN OPERATING SYSTEMS: AN INTERPRETIVE STUDY Reggie Davidrajuh, Stavanger University College, Norway, reggie.davidrajuh@tn.his.no ABSTRACT This paper presents

More information

Advanced School in High Performance and GRID Computing November Introduction to Grid computing.

Advanced School in High Performance and GRID Computing November Introduction to Grid computing. 1967-14 Advanced School in High Performance and GRID Computing 3-14 November 2008 Introduction to Grid computing. TAFFONI Giuliano Osservatorio Astronomico di Trieste/INAF Via G.B. Tiepolo 11 34131 Trieste

More information

30 Nov Dec Advanced School in High Performance and GRID Computing Concepts and Applications, ICTP, Trieste, Italy

30 Nov Dec Advanced School in High Performance and GRID Computing Concepts and Applications, ICTP, Trieste, Italy Advanced School in High Performance and GRID Computing Concepts and Applications, ICTP, Trieste, Italy Why the Grid? Science is becoming increasingly digital and needs to deal with increasing amounts of

More information

How does Internet (Big-I) routing work? The Internet is broken up into Autonomous Systems (AS) An AS is an administrative boundary. Each ISP has 1 or

How does Internet (Big-I) routing work? The Internet is broken up into Autonomous Systems (AS) An AS is an administrative boundary. Each ISP has 1 or Internet Routing Robustness Improving ftp://engr.ans.net/pub/slides/ndss/feb-1999/ Curtis Villamizar How does Internet routing work? How noticeable are routing related outages? Why have

More information

Enterprise SOA Experience Workshop. Module 8: Operating an enterprise SOA Landscape

Enterprise SOA Experience Workshop. Module 8: Operating an enterprise SOA Landscape Enterprise SOA Experience Workshop Module 8: Operating an enterprise SOA Landscape Agenda 1. Authentication and Authorization 2. Web Services and Security 3. Web Services and Change Management 4. Summary

More information

OmniRPC: a Grid RPC facility for Cluster and Global Computing in OpenMP

OmniRPC: a Grid RPC facility for Cluster and Global Computing in OpenMP OmniRPC: a Grid RPC facility for Cluster and Global Computing in OpenMP (extended abstract) Mitsuhisa Sato 1, Motonari Hirano 2, Yoshio Tanaka 2 and Satoshi Sekiguchi 2 1 Real World Computing Partnership,

More information

OPERATING SYSTEMS UNIT - 1

OPERATING SYSTEMS UNIT - 1 OPERATING SYSTEMS UNIT - 1 Syllabus UNIT I FUNDAMENTALS Introduction: Mainframe systems Desktop Systems Multiprocessor Systems Distributed Systems Clustered Systems Real Time Systems Handheld Systems -

More information

Chapter 4. Fundamental Concepts and Models

Chapter 4. Fundamental Concepts and Models Chapter 4. Fundamental Concepts and Models 4.1 Roles and Boundaries 4.2 Cloud Characteristics 4.3 Cloud Delivery Models 4.4 Cloud Deployment Models The upcoming sections cover introductory topic areas

More information

Designing Grid-based Problem Solving Environments and Portals

Designing Grid-based Problem Solving Environments and Portals Designing Grid-based Problem Solving Environments and Portals Gregor von Laszewski, Ian Foster, Jarek Gawor, Peter Lane, Nell Rehn, Mike Russell Argonne National Laboratory, 9700 South Cass Avenue, Argonne,

More information