Juhasz / Kacsuk / Kranzlmuller Distributed and Parallel Systems

Cluster and Grid Computing
2004
ISBN: 978-0-387-23096-2
Verlag: Springer US
Format: PDF
Kopierschutz: 1 - PDF Watermark

E-Book, Englisch, Band 777, 211 Seiten

Reihe: The Springer International Series in Engineering and Computer Science

DAPSY (Austrian-Hungarian Workshop on Distributed and Parallel Systems) is an international conference series with biannual events dedicated to all aspects of distributed and parallel computing. DAPSY started under a different name in 1992 (Sopron, Hungary) as regional meeting of Austrian and Hungarian researchers focusing on transputer-related parallel computing; a hot research topic of that time. A second workshop followed in 1994 (Budapest, Hungary). As transputers became history, the scope of the workshop widened to include parallel and distributed systems in general and the 1st DAPSYS in 1996 (Miskolc, Hungary) reflected the results of these changes. Distributed and Parallel Systems: Cluster and Grid Computing is an edited volume based on DAPSYS, 2004, the 5th Austrian-Hungarian Workshop on Distributed and Parallel Systems. The workshop was held in conjunction with EuroPVM/MPI-2004, Budapest, Hungary September 19-22, 2004.

Autoren/Hrsg.

Juhasz, Zoltan

Kacsuk, Peter

Kranzlmuller, Dieter

Inhaltsverzeichnis

1;Contents;6
2;Preface;10
3;I GRID SYSTEMS;13
3.1;GLOGIN - INTERACTIVE CONNECTIVITY FOR THE GRID*;15
3.1.1;1. Introduction;15
3.1.2;2. Overview of Approach;16
3.1.2.1;Limitations of Globus-Gatekeeper;16
3.1.2.2;Getting Interactive Connections;17
3.1.3;3. Details of the Implementation;18
3.1.3.1;Connection Establishment;18
3.1.3.2;Secure Connection Establishment;19
3.1.3.3;Getting shells and other commands;20
3.1.3.4;Traffic forwarding;20
3.1.4;4. Related Work;21
3.1.5;5. Conclusions and Future Work;22
3.1.5.1;Acknowledgments;22
3.1.5.2;Notes;22
3.1.6;References;23
3.2;PARALLEL PROGRAM EXECUTION SUPPORT IN THE JGRID SYSTEM*;25
3.2.1;1. Introduction;25
3.2.2;2. Execution Support for the Grid;26
3.2.3;3. Parallel execution support in JGrid;26
3.2.4;The Batch Execution Service;27
3.2.5;The Compute Service;30
3.2.6;4. Results;32
3.2.7;5. Conclusions and Future Work;32
3.2.8;References;32
3.3;VL-E: APPROACHES TO DESIGN A GRID-BASED VIRTUAL LABORATORY;33
3.3.1;Introduction;33
3.3.2;1. The Virtual Laboratory Architecture;34
3.3.3;2. The concept of study in VL-E;36
3.3.4;3. Resource management in VL-E;36
3.3.5;4. Related Work;38
3.3.6;5. Conclusions;39
3.3.7;References;40
3.4;SCHEDULING AND RESOURCE BROKERING WITHIN THE GRID VISUALIZATION KERNEL*;41
3.4.1;1. Introduction;41
3.4.2;2. Related Work;42
3.4.3;3. The GVK Visualization Planner;43
3.4.4;4. Visualization Task Decomposition;44
3.4.5;5. Resource Information Gathering;44
3.4.6;6. Algorithm Selection and Resource Mapping;45
3.4.7;7. Visualization Pipeline Construction;46
3.4.8;8. Conclusions and Future Work;47
3.4.9;References;47
4;II CLUSTER TECHNOLOGY;49
4.1;MESSAGE PASSING VS. VIRTUAL SHARED MEMORY A PERFORMANCE COMPARISON;51
4.1.1;1. Introduction;51
4.1.2;2. The Virtual Shared Memory Paradigm;53
4.1.3;3. Benchmarks;54
4.1.3.1;Benchmark 1: Approximation;54
4.1.3.2;Benchmark 2: Tree Structured Matrix Multiplications;55
4.1.3.3;Benchmark 3: Eigenvector Accumulation;55
4.1.4;4. Experimental Results;55
4.1.5;5. Conclusion and Future Work;57
4.1.6;References;58
4.2;MPI-I/O WITH A SHARED FILE POINTER USING A PARALLEL VIRTUAL FILE SYSTEM IN REMOTE I/ O OPERATIONS;59
4.2.1;1. Introduction;59
4.2.2;2. Implementation of PVFS in Stampi;60
4.2.3;3. Performance measurement;62
4.2.3.1;Inter-machine data transfer;63
4.2.3.2;Local I/O operations;63
4.2.4;Remote MPI-I/O operations;64
4.2.5;4. Summary;65
4.2.5.1;Acknowledgments;66
4.2.6;References;66
4.3;AN APPROACH TOWARD MPI APPLICATIONS IN;67
4.4;WIRELESS NETWORKS;67
4.4.1;1. Introduction;67
4.4.2;2. Reviewing the Fault Detection Mechanism;68
4.4.3;3. Unconstrained Global Optimization for n-Dimensional Functions;69
4.4.3.1;Parallel Program Without Wireless Channel State Detection;69
4.4.3.2;Parallel Program With Wireless Channel State Detection;71
4.4.3.3;Experimental Results;72
4.4.4;4. Conclusions and Future Work;73
4.4.5;References;74
4.5;DEPLOYING APPLICATIONS IN MULTI- SAN SMP CLUSTERS;75
4.5.1;1. Introduction;75
4.5.2;2. Our Approach;76
4.5.3;3. Representation of Resources;76
4.5.3.1;Basic Organization;77
4.5.3.2;Virtual Views;78
4.5.4;4. Application Modelling;78
4.5.4.1;Entities for Application Design;78
4.5.4.2;A Modelling Example;79
4.5.5;5. Mapping Logical into Physical Resources;80
4.5.5.1;Laying Out Logical Resources;80
4.5.5.2;Dynamic Creation of Resources;81
4.5.6;6. Discussion;82
4.5.6.1;Notes;82
4.5.7;References;82
5;III PROGRAMMING TOOLS;83
5.1;EXAMPLES OF MONITORING AND PROGRAM ANALYSIS ACTIVITIES WITH DEWIZ;85
5.1.1;1. Introduction;85
5.1.2;2. Overview of;86
5.1.3;3. Analysis of OpenMP and PVM Pograms with DEWIZ;87
5.1.4;4. User-defined Visualization of Event-Graphs using the Client;89
5.1.5;5. Conclusions and Future Work;92
5.1.6;References;93
5.2;INTEGRATION OF FORMAL VERIFICATION AND DEBUGGING METHODS IN P- GRADE ENVIRONMENT*;95
5.2.1;1. Introduction to P- GRADE and DIWIDE;95
5.2.2;2. Coloured Petri- net and Occurrence Graph;98
5.2.3;3. Transformation steps from GRAPNEL to CPN;98
5.2.4;4. Steering the macrostep debugger based on simulation;100
5.2.5;5. Related works;103
5.2.6;6. Summary, future goals;103
5.2.7;References;104
5.3;TOOLS FOR SCALABLE PARALLEL PROGRAM ANALYSIS - VAMPIR NG AND DEWIZ;105
5.3.1;1. Introduction;105
5.3.2;2. Tools for Parallel Program Analysis;106
5.3.3;3. High- Performance Program Analysis with VNG;108
5.3.4;4. Distributed Program Analysis with DeWiz;109
5.3.5;5. Comparison and Insights;110
5.3.6;6. Summary and Future Work;112
5.3.7;Acknowledgments;113
5.3.8;Notes;113
5.3.9;References;113
5.4;PROCESS MIGRATION IN CLUSTERS AND CLUSTER GRIDS *;115
5.4.1;1. Introduction;115
5.4.2;2. The Hungarian ClusterGrid Project;116
5.4.3;3. The P-GRADE software development tool;117
5.4.4;4. Migration in the 1st generation ClusterGrid;118
5.4.5;5. Migration in the 2nd generation ClusterGrid;120
5.4.6;6. Performance and Related Work;121
5.4.7;7. Conclusion;121
5.4.8;References;122
6;IV P-GRADE;123
6.1;GRAPHICAL DESIGN OF PARALLEL PROGRAMS WITH CONTROL BASED ON GLOBAL APPLICATION STATES USING AN EXTENDED P- GRADE SYSTEM;125
6.1.1;1. INTRODUCTION;125
6.1.2;2. PS-GRADE - SYNCHRONIZATION -ORIENTED P-GRADE SYSTEM;126
6.1.3;3. EXAMPLE: A TSP SOLVED BY B&B METHOD;127
6.1.4;4. CONCLUSIONS;131
6.1.5;5. BIBLIOGRAPHY;132
6.2;PARALLELIZATION OF A QUANTUM SCATTERING CODE USING P- GRADE: A CASE STUDY;133
6.2.1;1. Introduction;133
6.2.2;2. Re-structuring of the FORTRAN code;134
6.2.3;3. Setting up the parallel code using P-GRADE;136
6.2.4;4. Program performance analysis;137
6.2.5;5. Summary;139
6.2.5.1;Acknowledgments;139
6.2.6;References;140
6.3;TRAFFIC SIMULATION IN P-GRADE AS A GRID SERVICE;141
6.3.1;1. Introduction;141
6.3.2;2. Traffic simulation using P-Grade;142
6.3.3;3. Grid Execution Management for Legacy Code Architecture;143
6.3.4;4. Integrating GEMLCA with the P-Grade portal;145
6.3.5;5. Conclusion;146
6.3.6;Acknowledgments;147
6.3.7;References;148
6.4;DEVELOPMENT OF A GRID ENABLED CHEMISTRY APPLICATION;149
6.4.1;1. Introduction;149
6.4.2;2. Reaction-diffusion equations;150
6.4.3;3. Parallel implementation in P-GRADE;151
6.4.4;4. Performance results on non-dedicated cluster;152
6.4.5;5. Performance results in the Grid;154
6.4.6;6. Related works;155
6.4.7;7. Summary;155
6.4.8;References;156
7;V APPLICATIONS;157
7.1;SUPPORTING NATIVE APPLICATIONS IN WEBCOM- G;159
7.1.1;1. Introduction;159
7.1.1.1;Program Execution in WebCom-G 2.;161
7.1.1.2;Extraction;161
7.1.1.3;Annotation;164
7.1.2;3. Automatic Parallelization;164
7.1.3;4. Conclusions and Future Work;165
7.1.3.1;Acknowledgments;165
7.1.4;References;165
7.2;GRID SOLUTION FOR E-MARKETPLACES INTEGRATED WITH LOGISTICS;167
7.2.1;1. INTRODUCTION;167
7.2.2;2. INTEGRATING LOGISTICS INTO EMARKETPLACES;168
7.2.3;3. ROLE OF GRID COMPUTING IN EMARKETPLACES;171
7.2.4;4. GRID EXECUTION MANAGEMENT FOR LEGACY CODE ARCHITECTURE;172
7.2.5;5. GRID SERVICES BASED E-MARKETPLACE MODEL WITH GEMLCA;173
7.2.6;6. SUMMARY;174
7.2.7;7. ACKNOWLEDGEMENTS;175
7.2.8;8. REFERENCES;175
7.3;INCREMENTAL PLACEMENT OF NODES IN A LARGE- SCALE ADAPTIVE DISTRIBUTED MULTIMEDIA SERVER;177
7.3.1;1. Introduction;177
7.3.2;2. Related Work;178
7.3.3;3. The problem model;178
7.3.4;4. Incremental algorithm;180
7.3.5;5. Results;181
7.3.6;6. Conclusions and Further Work;183
7.3.7;References;183
7.4;COMPONENT BASED FLIGHT SIMULATION IN DIS SYSTEMS;185
7.4.1;Introduction;185
7.4.2;1. DIS system architecture;186
7.4.3;2. Component interaction model;187
7.4.3.1;Simulation object;188
7.4.3.2;Remote object interaction;191
7.4.3.3;Human operator;192
7.4.4;3. Summary;193
7.4.4.1;Notes;193
7.4.5;References;193
8;VI ALGORITHMS;195
8.1;MANAGEMENT OF COMMUNICATION ENVIRONMENTS FOR MINIMALLY SYNCHRONOUS PARALLEL ML;197
8.1.1;1. Introduction;197
8.1.2;2. Minimally Synchronous Parallel ML;198
8.1.3;3. Management of Communication Environments;200
8.1.4;4. Comparison to Related Work;202
8.1.5;5. Conclusions and Future Work;203
8.1.6;References;204
8.2;ANALYSIS OF THE MULTI-PHASE COPYING GARBAGE COLLECTION ALGORITHM;205
8.2.1;Introduction;205
8.2.2;1. Multi-Phase Copying Garbage Collection Algorithm;206
8.2.3;2. Analysis of the algorithm;207
8.2.3.1;Number of phases in the MC-GC algorithm;209
8.2.4;3. Conclusion;212
8.2.5;References;212
8.3;A CONCURRENT IMPLEMENTATION OF SIMULATED ANNEALING AND ITS APPLICATION TO THE VRPTW OPTIMIZATION PROBLEM;213
8.3.1;1. INTRODUCTION;213
8.3.2;2. SIMULATED ANNEALING;214
8.3.3;3. COMMUNICATION SCHEME OF CONCURRENT SIMULATED ANNEALING;215
8.3.3.1;3.1 Implementation of communication with synchronization at solution acceptance events;216
8.3.3.2;3.2 Tuning of the algorithm;217
8.3.4;4. EXPERIMENTAL RESULTS;219
8.3.4.1;4.1 VRPTW;219
8.3.5;5. IMPLEMENTATION;219
8.3.6;6. CONCLUSIONS;220
8.3.7;REFERENCES;221
9;Author Index;222

Leseproben

GRID SOLUTION FOR E-MARKETPLACES INTEGRATED WITH LOGISTICS (p. 155-156)

Abstract:  Electronic marketplaces are important facilitators of today’s e-business activities. Besides substantial advantages offered by these exchange sites, e-marketplaces do not work up to their full potential at the moment. This paper describes both a new business model and its technical implementation using Grid technology. A new, three-sided e-commerce model is suggested that integrates buyers, sellers and logistics service providers who all participate in the same negotiation process. To solve computation intensive optimisation tasks and to integrate back-office and marketplace applications, a Grid services based marketplace implementation model is outlined.

Key words: e-business, logistics, e-marketplace, Grid service, legacy code


1. INTRODUCTION

The evolution of business models and technological solutions advance together like intertwining spirals motivating and supporting each other. Business requirements drive information technology (IT) to find new tools and techniques that make businesses develop new needs again. Early electronic commerce – Electronic Data Interchange (EDI) - was started because telecommunication between computers facilitated a new relationship between businesses.

The rise of new business needs resulted in new communication standards and protocols. Real ecommerce was born out of the opportunity offered by the World Wide Web and triggered new IT researches again. After the unrealistic hype of the 90’s and the crises around 2000 e-commerce by now has entered the reality phase where efficiency drives the businesses, Internet usage adds value and increases the profitability of the companies. (Plankett Research 2004) A main target area of seeking business efficiency is supply chain management (SCM). Today a substantial part of supply chains are managed across the Internet still they contain a surprisingly high amount of inefficiencies. (Oliver at al. 2002) Both business and technology sides should be revised to find ways of improvement.

New e-commerce models might be considered and the latest information technology tools searched for to support them. The Grid concept has been created for solving computation intensive scientific problems, but the possibility of business applications was soon discovered. The convergence between Web services and Grid computing, that was triggered by the specification of OGSA (Open Grid Services Architecture) (Foster et al., 2002), resulted in even more intensive interest from large industry players towards Grid-based solutions. OGSA defines a Grid architecture that is based on Web service standards and protocols. As Web services are becoming more and more common in business applications, a Grid architecture based on SOAP (Simple Object Access Protocol) communication and WSDL (Web Services Description Language) service descriptions is the natural model to adopt in a business environment.

This paper would like to provide a step forward both in the fields of business and technology. As an answer to SCM problems a new, threesided e-commerce model is suggested that integrates buyers, sellers and logistics service providers in the same negotiation process. This marketplace helps trading partners to minimise their costs and increase their profit. The online optimisation requires large amounts of computation without any delay, which has focused attention on Grid technology. Following the direction set by Kacsukné (2004) and using the Grid-based e-marketplace architecture introduced by Kiss at al. (2004) this article gives a complex picture of the new e-marketplace model and its planned implementation.