Managed Grids and Cloud Systems in the Asia-Pacific Research Community (eBook)

Contents 6
Program Committee 10
Contributors 12
Part I Grid Activities in Asia Pacific 16
Chapter 1 Asia Federation Report on International Symposium on Grid Computing 2009 (ISGC 2009) 17
Executive summary 17
Asia-EU 18
1. Australia 20
Physical Network 20
Australian Research Collaboration Service (ARCS) 21
Progress of HEP Grid in Australia 22
2. China 24
Progress of HEP Grid in China 24
3. India 26
ERNET 26
National and International Grid Computing Initiatives 27
Progress of HEP Grid in India 28
4. Indonesia 29
5. Japan 31
Progress of HEP Grid in Japan 32
6. Malaysia 34
7. Pakistan 37
Progress of HEP Grid in Pakistan 37
8. Philippines 39
9. Singapore 41
10. South Korea 43
11. Taiwan 46
Progress of HEP in Taiwan 49
12. Thailand 50
13. Vietnam 51
Chapter 2 Research and Deployment a Hospital Open Software Platform for e-Health on the Grid System at VAST/ IAMI 52
Abstract 52
1. Grid Computing Overview 53
1.1. Grid Computing in Vietnam and on the world 53
1.2. Introduction about Grid Computing 53
2. Components and Structure of Grid Model 55
2.1. General architecture of Middleware and gLite Technology 55
2.2. Services of gLite Grid Middleware 55
2.3. Main components of gLite [9] 56
2.4. Introduction about Metadata and AMGA on the Grid 57
2.5. Overview of AMGA (ARDA Metadata Grid Application) 58
3. A Telemedicine Platform for Information and Images Management on the Grid 59
3.1. HOPE Platform Introduction 59
3.1.1. Why to build the Hope Platform? 59
3.1.2. Obstacles and challenges 60
3.1.3. Related technologies 60
3.2. Deploy the HOPE platform 60
3.2.1. Introduction 60
3.2.2. HOPE Platform Structure 61
3.2.3. Medical data sharing 61
3.2.4. Requirements of HOPE System 62
3.2.5. Current deployment and perspectives: 63
4. HOPE Package Installation 64
4.1. HOPE’ s packages 64
4.2. The result of HOPE installation 64
5. Conclusion 66
Acknowledgments 66
References 66
Chapter 3 WLCG Node in Pakistan – Challenges & Experiences
Abstract 68
1. Introduction 68
2. Experiences Gained during Grid Infrastructure Deployment 70
2.1 Challenges Met & Adopted Solutions – Phase I
2.2 Challenges Met & Adopted Solutions – Phase II
3. Performance Statistics of NCP-LCG2 Site 72
3.1 Service Availability Monitoring (SAM) 72
3.2 APEL & R-GMA
3.3 EGEE Availability & Reliability Metrics
4. Conclusion 77
References 77
Chapter 4 In Vitro Test for Potential Inhibitors of Plasmepsin II and IV as Anti-malarial Agents 79
Abstract 79
1. Introduction 80
2. Materials and methods 81
2.1 Expression and preparation of recombinant PM 81
2.2 Sodium dodecyl sulfate-polyacrylamide gel electophoresis (SDS-PAGE) 82
2.3 Enzyme activity and kinetics 82
2.4 Chemical compounds 83
2.5 FRET substrate degradation inhibition assay 83
2.6 Assay of PM inhibition of hemoglobin degradation 84
3. Results and Discussion 84
3.1 Expression, purification and activity assay of PM 84
3.2 Biological testing 86
3.3 PM II-mediated hemoglobin degradation 89
3.4 Conclusions 91
Acknowledgements 91
References 91
Part II Grid Application 94
Chapter 5 Performance of a disk storage system at a Tier-2 site 95
Abstract 95
1. Introduction 95
2. Regional Analysis Center 96
3. Disk Storage System 97
4. Data Transfer overWAN 99
5. Data Access in LAN 101
5.1 Stand-alone Test with a single server 102
5.2 ATLAS stress test 104
6. Summary 106
Acknowledgements 106
References 107
Chapter 6 The PacCAF Grid portal for the CDF experiment 108
Abstract 108
1. Introduction 108
2. CDF Computing 109
3. The CAF portal 110
3.1 CAF modules 110
4. Glide-in to the Grid 112
4.1 The Glide CAF 112
4.2 Firewall routing and HTTP caching 113
5. Online monitoring 114
6. Summary 115
References 116
Chapter 7 Distributed Computing Model for Belle II Experiment 117
Abstract 117
1. Experimental environment 117
2. Current Belle Computing System 119
3. Belle II Computing System 120
3.1 Expected Event Rate 120
3.2 Expected Event Data size 121
3.3 Possible Computing Model for Belle II 122
4. Data Handling System for Belle II 124
5. Summary 125
Acknowledgements 125
References 126
Chapter 8 INFN, IT the GENIUS grid portal and the robot certificates to perform phylogenetic analysis on large scale: a success story from the International LIBI project 127
Abstract 127
1. Introduction 128
2. Structure and Components of a Public Key Infrastructure in a Nutshell 130
3. The Robot Certificates 132
3.1 Access Grid Infrastructure with robot certificates and the GENIUS Grid portal 132
4. The Bioinformatics Use Case 134
4.1 Bayesian Phylogenetic Inference on large scale 134
5. Conclusions 137
Acknowledgments 137
References 137
Chapter 9 Developing a Philippine Cancer Grid. Part 1: Building a Prototype for a Data Retrieval System for Breast Cancer Research Using Medical Ontologies 139
Abstract 139
1. Introduction 139
1.1 Computational Ontology 139
1.2 Ontologies and Information Systems 140
1.3 Ontology Development for the Medical Domain 141
2. Project Objective, Significance and Scope 142
3. Review of Related Literature 144
4. Methodology, Framework and Features of the Prototype 146
4.1 Use Case Categories 147
4.2 Actors 147
4.3 Identified Features 148
4.4 Use Case Diagram Framework of Prototype 148
4.5 Programming Development Flow 149
4.6 Overview Model for Grid Integration 150
5 Conclusion and Future Work 151
Acknowledgements 152
References 152
Chapter 10 The ASTRA (Ancient instruments Sound/Timbre Reconstruction Application) Project brings history to life! 153
Abstract 153
1. Introduction 154
2. The Technique 155
2.1 The modeling of ancient instruments 155
2.2 The GILDA t-Infrastructure 157
2.3 GÉANT and GÉANT2 157
2.4 EUMEDCONNECT and EUMEDCONNECT2 158
3. Running ASTRA in Grid 158
3.1 The GENIUS architecture and the EnginFrame framework 159
4. Astra Results 160
5. The Orchestra 162
6. Conclusions 162
Acknowledgments 163
References 163
Chapter 11 GRASS GIS in Grid Environment 165
Abstract 165
1. UNOSAT and CERN Grid Computing 165
2. GRASS GIS Sample application in the Grid Environment 166
3. Conclusion 170
References 171
Chapter 12 Academia Sinica, TW E-science to Assistant Seismic Observations for Earthquake Research, Monitor and Hazard Reduction Surrounding the South China Sea 172
Abstract 172
1. Introduction 173
2. Deployment and data processing 175
3. Applications of recorded data 177
4. The necessary to upgrade for earthquake monitoring and early warning 180
5. Implementation of Grid Infrastructure for the SCS network and hazard reduction 183
6. Summary 184
Acknowledgements 184
References 184
Chapter 13 A Data Research Infrastructure for the Arts and Humanities 186
Abstract 186
1. Introduction - Changing Data Perspectives in Humanities 186
2. The interoperability challenge 188
3. Grid-enabling Humanities Data 189
4. Case Study: Linking and Querying Ancient Texts 190
5. Implementation 193
6. Conclusion and Future Work 196
References 198
Part III Security & Networking
Chapter 14 Review on Concurrent Data Transfer in Grid Computing 200
Abstract 200
1. Introduction 200
2. Challenges in Concurrent Data Transfer over Grid Computing 201
2.1 Typical Network Topology 202
3. Approach to Improve the Performance 203
3.1 MuniSocket 203
3.2 MuniCluster 204
3.3 Concurrent Multipath Transfer 205
3.4 Channel Bonding 205
3.5 Other Solutions 205
4. Conclusion 206
References 206
Chapter 15 SVOPME: A Scalable Virtual Organization Privileges Management Environment 208
Abstract 208
Acknowledgments 208
1. Introduction 209
1.1 Challenges in Reconciling VO and Site Policies 210
1.2 The Need for Managing VO User Privileges 211
2. Related Work 211
3. VO Policies and Grid Sites 212
4. The SVOPME Architecture 214
4.1 VO Components 216
4.2 Site Components 217
4.2.1 Grid Probe 217
4.2.2 Policy Advisor 218
4.2.3 Policy Comparer 219
5. Discussion 219
6. Current Progress 219
7. Conclusions 220
References 220
Part IV Grid Computing and Cloud Computing 222
Chapter 16 Elastic Cloud Computing Infrastructures in the Open Cirrus Testbed Implemented via Eucalyptus 223
Abstract 223
1. Cloud Computing – An upcoming trend in IT 223
1.1 Everything as a service 224
2. OpenCirrus™ 225
2.1 OpenCirrus™ Blueprint 226
3. Cloud application services in OpenCirrus™ 228
3.1 Hadoop 228
3.2 Eucalyptus 228
3.2.1 Storage Performance of Eucalyptus. 230
3.3 AppScale 232
4. Further Steps 232
5. Conclusion 233
References 233
Chapter 17 Belle Monte-Carlo Production on the Amazon EC2 Cloud 235
Abstract 235
1. Introduction 235
2. Concepts 236
2.1 Belle Monte Carlo 236
2.2 Cloud 237
2.3 Traditional Solution 238
2.3.1 Generalising 239
2.4 Value Weighted Output 239
3. Architecture 240
3.1 Data Flow 241
3.2 Control Flow 241
4. Results 242
4.1 Identifying bottlenecks 243
4.2 Scheduling 244
4.3 Comparison with Traditional Solution 245
4.4 Other providers 245
5. Future Work 246
5.1 Scale 246
5.2 Bandwidth 246
5.3 Accounting, Access and Authorization 246
5.4 Grid Integration 247
6. Conclusion 247
References 247
7. A Scientific Linux Amazon Machine Image 248
7.1 Working with image files 248
7.2 Preparing for installation 249
7.3 Installation and configuration 250
7.4 Adding the Belle libraries 252
7.5 Cleaning up 253
8. Further Information 253
Chapter 18 Impact of Advanced Virtualization Technologies on Grid Computing Centres 254
Abstract 254
1. Introduction 254
2. Virtualization 255
2.1 Network Virtualization 255
2.2 Storage Virtualization 256
2.3 I/O Virtualization 258
2.4 Platform Virtualization 259
3. Grid Computing 260
4. Existing Work 260
5. Impact of Virtualization on Grid Computing 261
5.1 Grid Middleware Level 261
5.2 LRMS Level 262
5.3 Flexible Creation of Virtual Appliances 263
6. Conclusion and Outlook 264
References 265
Part V Operation & Management
Chapter 19 Usage of the Open Science Grid 268
Abstract 268
1. Introduction 268
2. Terminology and Measurements 269
3. Resource Measurement and Usage on the OSG 270
4. Resource Value 274
5. Approaches for Resource Estimation 276
6. Conclusions 280
References 281
Chapter 20 Karlsruhe Institute of Technology, DE Grid Support Beyond the Project Life Cycle 282
Abstract. 282
1. Introduction 282
2. GGUS management 283
3. USAG 284
4. Shopping list 285
5. Release cycle 285
6. GGUS Standard workflow 286
7. TPM 287
8. Services support 287
9. Expert support 288
10. Special workflows and tools 288
11. Direct user ticket notification to resource centres 288
12. Team tickets 289
13. VOMS integration 290
14. Ticket timeline tool 290
15. Report generator 291
16. Summary 292
References 292
Chapter 21 Plans for a German Grid Operations and Support Centre 293
Abstract 293
1. Grid activities in Germany 293
2. Achievements at KIT 295
3. User Support 295
4. Operations Support 296
5. Reference Installation 296
6. Monitoring 297
7. Plans for the future 297
References 298
Chapter 22 Catch-All Virtual Organizations - Solution for Heterogeneous and Disperse Grid Users Communities 299
Abstract. 299
1. Introduction 299
2. Enabling Grids in E-SciencE 301
3. Virtual Organizations 301
4. VOCE Use Case 304
5. EUAsia Virtual Organization 306
6. Conclusions and Future Prospective 308
Acknowledgements 308
References 309
Chapter 23 GILDA Status and Recent Activities in Grid Training 310
Abstract 310
1. Introduction 310
2. GILDA and the t-Infrastructure 313
2.1 The infrastructure 314
3. Services 315
3.1 Infrastructure services 315
3.2 User oriented services 317
4. Activities 318
5. Conclusion 320
References 321
Part VI Grid Middleware & Interoperability
Chapter 24 GridMate – The Grid Matlab Extension 323
Abstract 323
1. Introduction 323
2. Related Work 324
2.1 The Parallel Computing Toolbox and the Distributed Computing Server 324
2.2 The Matlab Compiler 325
3 GridMate – The Grid Matlab Extension 326
3.1 The Service Oriented Grid Architecture 326
3.2 The Matlab Builder for Java 328
3.3 Integration into Matlab 328
3.4 The GridMate Service 329
3.4.1 Asynchronous Mode (Non–Blocking) 331
3.4.2 Synchronous Mode (Blocking) 332
4 Performance Measurements 332
4.1 Application 1: 3D Volume Reconstruction 333
4.2 Application 2: Digital Image Correlation 334
5 Conclusions and Future Work 336
References 336
Chapter 25 An Interoperable GridWorkflow Management System 338
Abstract 338
1. Introduction 338
2. Interoperability among Grid middleware 340
3. The ProGenGridWorkFlow Management System 342
3.1 Architecture 343
3.2 The GMS operation schema 345
4. Testbed domain: Bioinformatics 349
5. Related Work 350
6. Conclusions and Future Work 352
Acknowledgements 352
References 352