Suchen und Finden
Preface
5
Contents
8
List of Contributors
10
XtreemOS: a Sound Foundation for Cloud Infrastructure and Federations
14
1 XtreemOS
14
Scalability.
15
Transparency.
15
Towards a Grid File System Based on a Large-Scale BLOB Management Service
20
1 Introduction
20
2 The building blocks: Gfarm and BlobSeer
23
2.1 The Gfarm grid file system
23
2.1.1 Overview of Gfarm’s architecture
23
2.2 The BlobSeer BLOB management service
24
2.2.1 BlobSeer at a glance
24
2.2.2 Overview of BlobSeer’s architecture
24
2.3 Why combine Gfarm and BlobSeer?
25
3 Towards an object-based file system based on Gfarm and BlobSeer
26
3.1 How to couple Gfarm and BlobSeer?
26
3.2 The Gfarm/BlobSeer file system design
27
4 Experimental evaluation
29
5 Conclusion
30
References
32
Improving the Dependability of Grids via Short-Term Failure Predictions
34
1 Introduction
34
2 Analyzing Grid Tomography Data
36
2.1 The Anatomy of a Grid
36
2.2 The FailBase repository
36
2.3 Types of monitoring data
37
2.4 Preprocessing
38
2.5 Modeling methodology
38
3 Experimental Results
39
3.1 Evaluation metrics: recall and precision
40
3.2 Analysis of prediction accuracy
41
3.2.1 Selecting the target attributes
41
3.2.2 Data characteristics and accuracy
42
3.2.3 Effects of different classification algorithms
43
4 Conclusions
43
Acknowledgements
44
References
44
Distributed Data Mining using a Public Resource Computing Framework
46
1 Introduction
47
2 A Distributed Framework for Public Computing with Caching Capabilities
48
2.1 Parallel Mining of Closed Frequent Itemset
51
3 Performance Evaluation
53
4 Conclusions
56
References
56
Integration of the ProActive Suite and the semantic-oriented monitoring tool SemMon
58
1 Introduction
58
2 Related work
60
3 Extending SemMon’s support for specific platforms
60
4 ProActive integration strategy
61
4.1 Features of the systems to be integrated
61
4.2 ProActive requirements for monitoring vs. SemMon
62
4.3 Concept of architecture
63
4.4 Extensions introduced into the integrated system
64
5 Sample monitoring session
67
5.1 SemMon’s impact on monitored system
67
6 Conclusions and Future work
69
References
70
An Experimental Evaluation of the DQ-DHT Algorithm in a Grid Information Service
72
1 Introduction
73
2 Background on DQ-DHT
74
2.1 Broadcast over a Chord DHT
74
2.2 The DQ-DHT algorithm
76
3 Experimental evaluation
78
3.1 System prototype
78
3.2 Experimental results
80
4 Related work
83
5 Conclusions
84
Acknowledgement
85
References
85
Reducing traffic in DHT-based discovery protocols for dynamic resources
86
1 Introduction
87
2 Related Work
88
2.1 MAAN Range Query Implementation
89
3 REMED
89
3.1 Reducing the Routing Overhead
90
3.2 Skipping Publication
92
4 Cost model
93
4.1 The Standard MAAN Model
93
4.2 The REMED Optimized Model
93
5 Simulations
94
5.1 Tools and Implementation
94
5.2 Data Analysis
95
5.3 Cache Evaluation
96
5.4 Churn Evaluation
96
5.5 Model Evaluation
98
6 Conclusion and Future Work
99
References
99
Autonomic management of multiple non-functional concerns in behavioural skeletons
102
1 Introduction
102
2 Parallel framework
103
3 Autonomic management of multiple concerns in structured parallel computations
104
3.1 Centralized vs. distributed autonomic management of multiple concerns
105
3.2 Shared knowledge among different autonomic managers
106
3.3 Impact of local decisions on global application management
108
3.3.1 Consensus building
108
3.3.2 Consensus results
109
3.4 Initialization of theAM hierarchy
110
3.5 Rule-based multi-concern autonomic manager implementation
111
4 Sample case study
112
5 Related work
114
6 Conclusions
115
References
115
Decision Models for Resource Aggregation in Peer-to-Peer Architectures
118
1 Introduction
118
2 Related Work
119
3 The resource aggregation setup
120
4 Decision Models for Resource Aggregation
122
4.1 Onicescu
122
4.2 Promethee
123
4.3 The Multi-Attribute Utility Theory
125
5 Experiments and results
126
6 Conclusion
128
References
129
MappingWorkflows on Grid Resources: Experiments with the MontageWorkflow
132
1 Introduction
132
2 Background
134
3 A Motivating Example
136
4 Experimental Evaluation
138
4.1 The Simulator and Settings
138
4.2 Results and Discussion
140
4.2.1 All tasks at each level have a similar (estimated) execution time
141
4.2.2 All tasks at each level, except the rightmost task, have an (estimated) execution time which is twice the (estimated) exec
141
4.2.3 The leftmost task at each level has an (estimated) execution time, which is 10 times the (estimated) execution time of the
142
4.2.4 Summary
142
5 Conclusion
143
References
144
A Proposal on Enhancing XACML with Continuous Usage Control Features*
146
1 Introduction
147
2 Background
148
2.1 UCON
148
2.2 XACML
149
3 U-XACML policy syntax and semantics
150
4 U-XACML architecture
153
5 A case study
157
6 Conclusions
158
References
159
Self-* and Adaptive Mechanisms for Large Scale Distributed Systems
160
1 Introduction
161
2 Elastic management of computational Grid resources
162
3 Bio-inspired algorithms for self-organizing distributed systems
163
4 Non-intrusive monitoring and healing of complex applications
165
5 Self-management in desktop Grids
166
6 Conclusions
167
Acknowledgements
168
Network Monitoring in the age of the Cloud
170
1 Introduction
170
2 LAN virtualization
172
2.1 The IEEE802.1Q protocol
173
3 The VLAN-cloud connection
175
3.1 Amazon EC2
175
3.2 VMware
176
4 Network Monitoring in the age of the Cloud
177
4.1 Network monitoring on the user side
178
4.2 Network monitoring on the service provider side
179
5 Conclusions
181
5.1 Looking ahead
181
References
182
Acronyms
182
Recent Advances and Research Challenges in Desktop Grid and Volunteer Computing
184
1 Introduction
184
2 History and Classification of Desktop Grid Systems
185
3 Towards Data Desktop Grid
189
4 Integrating Desktop Grids into Cyber-Science Infrastructures
192
5 Conclusion
195
References
196
Research Challenges in Managing and Using Service Level Agreements
200
1 Introduction
200
2 SLA Research Landscape
202
3 Electronic Markets
204
4 Smart Licencing
205
5 WS-Agreement
207
5.1 Initialisation of the negotiation process
208
5.2 Negotiation of the template
209
5.3 Post-processing of the templates
210
6 Future Directions and Research Challenges
211
6.1 Conclusions and Research Directions
211
References
213
Alle Preise verstehen sich inklusive der gesetzlichen MwSt.