Gorlatch / Bubak / Priol Achievements in European Research on Grid Systems

CoreGRID Integration Workshop 2006 (Selected Papers)
1. Auflage 2007
ISBN: 978-0-387-72812-4
Verlag: Springer
Format: PDF
Kopierschutz: 1 - PDF Watermark

E-Book, Englisch, 238 Seiten

This volume comprises the edited proceedings of the second CoreGRID Integration Workshop, CGIW'2006, held October 2006 in Krakow, Poland. A 'Network of Excellence' funded by the European Commission's Sixth Framework Program, CoreGRID aims to strengthen and advance scientific and technological excellence in the area of Grid and Peer-to-Peer technologies by bringing together a critical mass of well-established researchers from 41 European research institutions. Designed for a professional audience of industry practitioners and researchers, the volume is also suitable for advanced-level students in computer science.

Autoren/Hrsg.

Gorlatch, Sergei

Bubak, Marian

Priol, Thierry

Inhaltsverzeichnis

1;Contents;5
2;Foreword;7
3;Contributing Authors;10
4;DIVIDE ET IMPERA: PARTITIONING UNSTRUCTURED PEER- TO- PEER SYSTEMS TO IMPROVE RESOURCE LOCATION;18
4.1;1. Introduction;19
4.2;2. RelatedWork;20
4.3;3. The Partitions Design;22
4.4;4. Experimental Results;24
4.5;5. Conclusions;28
4.6;Acknowledgments;28
4.7;References;28
5;VALIDATING DESKTOP GRID RESULTS BY COMPARING INTERMEDIATE CHECKPOINTS;30
5.1;1. Introduction;31
5.2;2. Assumptions and Definitions;33
5.3;3. Comparison of Equivalent Checkpoint Digests;34
5.3.1;3.1 Reducing the Time to Detect an Error;34
5.3.2;3.2 Theoretical Analysis;34
5.4;4. Checkpoint-based Task Replication;37
5.5;5. Experimental Results;38
5.6;6. RelatedWork;39
5.7;7. Conclusion;40
5.8;References;41
6;INTEGRATION OF THE ENANOS EXECUTION FRAMEWORK WITH GRMS*;42
6.1;1. Introduction;43
6.2;2. eNANOS Execution Environment;43
6.3;3. Grid Resource Management System (GRMS);45
6.4;4. Integration Issues;46
6.4.1;4.1 eNANOS as a new execution framework;48
6.4.2;4.2 eNANOS as a new information provider;52
6.5;5. Conclusions and Future Work;55
6.6;References;56
7;USER-TRANSPARENT SCHEDULING FOR SOFTWARE COMPONENTS ON THE GRID;57
7.1;1. Introduction;58
7.2;2. Context and Background;59
7.2.1;2.1 Environment Description;59
7.2.2;2.2 Higher-Order Components;60
7.2.3;2.3 User-Transparent Scheduling for HOCs;61
7.3;3. Implementation of the Scheduler;62
7.3.1;3.1 Integration of Existing Systems;62
7.3.2;3.2 Performance Evaluation of Scheduling;62
7.4;4. KOALA-based User-Transparent Scheduling Evaluation;64
7.4.1;4.1 Integration Feasibility;64
7.4.2;4.2 Performance Results;65
7.5;5. RelatedWork;66
7.6;6. Conclusions;67
7.7;Acknowledgments;68
7.8;References;68
8;PROBLEM SOLVING ENVIRONMENT FOR DISTRIBUTED INTERACTIVE APPLICATIONS;70
8.1;1. Introduction;71
8.2;2. PSEs for distributed interactive applications;71
8.2.1;2.1 Computational Steering Environment;72
8.2.2;2.2 CUMULVS;72
8.2.3;2.3 Cactus Problem Solving Environment;72
8.2.4;2.4 Discover;73
8.2.5;2.5 TENT;74
8.2.6;2.6 Interactive Simulation Systems Conductor;74
8.2.7;2.7 Comparision of existing PSEÌs;74
8.3;3. PSE for HLA-based simulations ;76
8.3.1;3.1 Need for a Grid for HLA-based applications;76
8.3.2;3.2 Grid HLA Management System;77
8.4;4. Application of G-HLAM to vascular reconctruction;78
8.5;5. Summary and future work;79
8.6;Acknowledgments;80
8.7;References;80
9;FAULT-TOLERANT DATA SHARING FOR HIGH- LEVEL GRID PROGRAMMING: A HIERARCHICAL STORAGE ARCHITECTURE;82
9.1;1. Introduction;83
9.2;2. Analysis: using JuxMem to enable grid-level, fault-tolerant storage in ASSIST;84
9.2.1;2.1 Data sharing in ASSIST;84
9.2.2;2.2 Existing building blocks: ad-HOC and JuxMem;85
9.3;3. Proposal: an integrated 2-tier architecture;88
9.4;4. ASSIST and fault-tolerance: a sample scenario;90
9.5;5. Design and Implementation;91
9.5.1;5.1 Preliminary Experiments;92
9.6;6. Conclusion;94
9.7;References;95
10;PAL: EXPLOITING JAVA ANNOTATIONS FOR PARALLELISM;97
10.1;1. Introduction;98
10.2;2. Parallel Abstraction Layer (PAL);99
10.3;3. A PAL prototype;102
10.4;4. Experimental results;104
10.5;5. Related work;106
10.6;6. Conclusion and future work;107
10.7;References;109
11;A NEW APPROACH ON NETWORK RESOURCES MANAGEMENT IN GRIDS*;111
11.1;1. Introduction;112
11.2;2. Grid Resource Broker;113
11.3;3. Network Resource Manager and Information Services;114
11.3.1;3.1 Network Resource Management System;115
11.3.2;3.2 Network Configuration Management System;116
11.3.3;3.3 GNRB and Multi-Point Real-Time Network Monitoring System;116
11.4;4. Network-aware Grid Resource Broker;116
11.5;5. Experimental Evaluation;119
11.6;6. Conclusion;121
11.7;References;121
12;COMPONENTISING A SCIENTIFIC APPLICATION FOR THE GRID*;123
12.1;1. Introduction;124
12.2;2. Background on Jem3D;124
12.2.1;2.1 The ProActive library;124
12.2.2;2.2 Jem3D overview;125
12.3;3. Approach;126
12.3.1;3.1 Componentisation process;127
12.3.2;3.2 Fractal/ProActive component model;129
12.4;4. Componentising Jem3D;130
12.5;5. Performance results;132
12.6;6. Related work;133
12.7;7. Conclusion;134
12.8;References;135
13;A PEER-TO-PEER FRAMEWORK FOR RESOURCE DISCOVERY IN LARGE- SCALE GRIDS;137
13.1;1. Introduction;138
13.2;2. Related work;139
13.3;3. Resources and query types;141
13.4;4. System architecture;144
13.4.1;4.1 Local components;144
13.4.2;4.2 Static attribute discovery;145
13.4.3;4.3 Dynamic attribute discovery;146
13.5;5. Conclusions;149
13.6;Acknowledgements;150
13.7;References;150
14;GRID SUPERSCALAR AND GRICOL: INTEGRATING DIFFERENT PROGRAMMING APPROACHES;152
14.1;1. Introduction;153
14.2;2. GriCoL;154
14.3;3. GRID superscalar;157
14.4;4. Studying the integration possibilities;160
14.4.1;4.1 Control-flow level integration;160
14.4.2;4.2 Data-flow level integration;161
14.4.3;4.3 General integrations;162
14.5;5. Conclusions and future work;163
14.6;Acknowledgments;163
14.7;References;163
15;DERIVING POLICIES FROM GRID SECURITY REQUIREMENTS MODEL*;164
15.1;1. Introduction;165
15.2;2. Security Requirements Model;165
15.2.1;2.1 Problem Statement;165
15.2.2;2.2 Goal Model;166
15.2.3;2.3 Responsibility Model;166
15.2.4;2.4 Object Model;167
15.2.5;2.5 Operation Model;168
15.2.6;2.6 Dealing with Obstacles;168
15.3;3. Derivation of Policies from Security Requirements Model;169
15.3.1;3.1 Refinement of Requirements Model;171
15.3.2;3.2 Policy Templates;172
15.3.3;3.3 Population of Policy Templates;173
15.3.4;3.4 Refinement of Policies;173
15.3.5;3.5 Implementation of Policies;174
15.4;4. RelatedWork and Discussions;175
15.5;5. Conclusions and Future Directions;175
15.6;References;176
16;DOMAIN-SPECIFIC METADATA FOR MODEL VALIDATION AND PERFORMANCE OPTIMISATION;177
16.1;1. Introduction;178
16.2;2. GENIE Application ;180
16.2.1;2.1 Overview;180
16.2.2;2.2 The Past, the Present and the Future;181
16.3;3. Motivation;181
16.4;4. Metadata for Legacy Components;182
16.5;5. Staging the Metadata;183
16.5.1;5.1 Model Validation;183
16.5.2;5.2 Performance Optimisation;184
16.6;6. RelatedWork;185
16.7;7. Conclusions;186
16.8;References;188
17;A SERVICE FOR RELIABLE EXECUTION OF GRID APPLICATIONS;190
17.1;1. Introduction;191
17.2;2. Failures in Grid Environments;191
17.2.1;2.1 Related Work;192
17.3;3. A Service for Reliable Application Execution;193
17.3.1;3.1 Design objectives;193
17.3.2;3.2 Service design;195
17.3.3;3.3 Application wrapping;196
17.3.4;3.4 Failures detected by the service;197
17.3.5;3.5 Recovery techniques;198
17.3.6;3.6 Evaluation;199
17.4;4. Case Study: Reliable Execution for GRID superscalar;200
17.5;5. Conclusions;202
17.6;Acknowledgments;202
17.7;References;202
18;PERFORMANCE MONITORING OF GRID SUPERSCALAR WITH OCM- G/ G- PM: INTEGRATION ISSUES;204
18.1;1. Introduction;205
18.2;2. Monitoring requirements for and from the GS environment;206
18.3;3. Current status of research;207
18.4;4. The G-PM performance tool and its enhancements;209
18.5;5. Other integration issues;210
18.6;6. Case Study;211
18.7;7. Visualization of GS applications with GSM;213
18.8;8. Summary;214
18.9;References;215
19;IMPROVING WORKFLOWEXECUTION THROUGH SLA- BASED ADVANCE RESERVATION;217
19.1;1. Introduction;218
19.1.1;1.1 Related work;218
19.1.2;1.2 Remainder of the Paper;219
19.2;2. Service Level Agreements - State of the art ;220
19.2.1;2.1 Technology Overview;220
19.2.2;2.2 Defining Service Level Objectives and Penalties;221
19.2.3;2.3 WS-Agreement;222
19.3;3. SLA based service provisioning for workflows;223
19.3.1;3.1 The workflow resource problem;223
19.3.2;3.2 Negotiating resource usage;224
19.3.3;3.3 MSS Implementation;225
19.4;4. Results;226
19.5;5. Future Perspectives;228
19.6;Acknowledgments;229
19.7;References;229
20;DEPENDABILITY EVALUATION OF THE OGSA- DAI MIDDLEWARE;232
20.1;1. Introduction;233
20.2;2. RelatedWorks;233
20.3;3. OGSA-DAI Overview;234
20.4;4. QUAKE: A Benchmarking Tool for Grid Services;236
20.5;5. Experimental Results;237
20.5.1;5.1 Performance Overhead;237
20.5.2;5.2 Benchmarking Tomcat+Axis;238
20.5.3;5.3 Benchmarking OGSA-DAI;239
20.6;6. Conclusions;243
20.7;Acknowledgements;244
20.8;References;244
21;Author Index;246