Fundamentals of grid computing: theory, algorithms and technologies / edited by Frédéric Magoulès.

"A Chapman & Hall book."

Grid computing overview
Frederic Magoules, Thi-Mai-Huong Nguyen, and Lei Yu
1.1 Introduction
1.2 Definitions
1.3 Classifying grid systems
1.4 Grid applications
1.5 Grid architecture
1.6 Grid computing projects
1.6.1 Grid middleware (core services)
1.6.2 Grid resource brokers and schedulers
1.6.3 Grid systems
1.6.4 Grid programming environments
1.6.5 Grid portals
1.7 Grid evolution
1.8 Concluding remarks
1.9 References
Synchronization protocols for sharing resources in grid envi
ronments
Julien Sopena, Luciana Arantes, Fabrice Legend-Aubry, and Pierre Sens
2.1 Introduction
2.2 Token-based mutual exclusion algorithms
2.2.1 Martin's algorithm
2.2.2 Naimi-Trehel's algorithm
2.2.3 Suzuki-Kasami's algorithm
2.3 Mutual exclusion algorithms for large configurations
2.3.1 Priority-based approach
2.3.2 Composition-based approach
2.4 Composition approach to mutual exclusion algorithms
2.4.1 Coordinator processes
2.5 Composition properties and its natural effects
2.5.1 Filtering and aggregation
2.5.2 Preemption and structural effects
2.5.3 Natural effects of composition
2.6 Performance evaluation
2.6.1 Experiment parameters
2.6.2 Performance results: composition study
2.6.3 The impact of the grid architecture
2.7 Concluding remarks
2.8 References
Data replication in grid environments
Thi-Mai-Huong Nguyen and Frederic Magoules
3.1 Introduction
3.2 Data replication
3.2.1 Replication in databases
3.2.2 Replication in peer-to-peer systems
3.2.3 Replication in web environments .
3.2.4 Replication in data grids
3.3 System architecture
3.4 Selective-rank model for a replication system .
3.4.1 Model assumptions
3.4.2 Estimating the availability of files
3.4.3 Problem definition
3.5 Selective-rank replication algorithm
3.5.1 Popularity of files .
3.5.2 Correlation of files
3.5.3 MaxDAR optimizer algorithm
3.6 Evaluation
3.6.1 Grid configuration
3.6.2 Experimental results
3.7 Concluding remarks
3.8 References
Data management in grids
Jean-Marc Pierson
4.1 Introduction
4.2 Prom data sources to databases ... to data sources
4.3 Positioning the data management in grids within distributed
systems
4.4 Links with the other services of the middleware
4.5 Problems and some solutions
4.5.1 Data identification, indexing, metadata
4.5.2 Data access, interoperability, query processing, transac
tions ,
4.5.3 Transport
4.5.4 Placement, replication, caching
4.5.5 Security: transport, authentication, access control, en
cryption
4.5.6 Consistency
4.6 Toward pervasive, autonomic and on-demand data manage
ment
4.7 Concluding remarks
4.8 References
5 Future of grids resources management
Fei Teng and Frederic Magoules
5.1 Introduction
5.2 Several computing paradigms
5.2.1 Utility computing
5.2.2 Grid computing
5.2.3 Autonomic computing
5.2.4 Cloud computing
5.3 Definition of cloud computing
5.3.1 One definition
5.3.2 Architecture
5.4 -Cloud services
5.4.1 Three-level services . .
5.4.2 Service characters . .
5.5 Cloud resource management
5.5.1 Comparison with grid systems
5.5.2 Resource model .
5.5.3 Economy-oriented model
5.6 Future direction of resource scheduling
5.6.1 Scalable and dynamic
5.6.2 Secure and trustable .
5.6.3 Virtual machines-based
5.7 Concluding remarks
5.8 References
6 Fault-tolerance and availability awareness in computational
grids 143
Xavier Besseron, Mohamed'Slim Bouguerra, Thierry Gautier, Erik Saule,
and Denis Trystram
6.1 Introduction
6.2 Background and definitions
6.2.1 Grid architecture and execution model
6.2.2 Faults models
6.2.3 Consistent system states
6.3 Multi-objective scheduling for safety
6.3.1 Generalities . .
6.3.2 No duplication
6.3.3 Using duplication
6.4 Stable memory-based protocols
6.4.1 Log-based rollback recovery
6.4.2 Checkpoint-based rollback recovery .
6.5 Stochastic checkpoint model analysis issues
6.5.1 Completion time without fault tolerance
6.5.2 Impact of checkpointing on the completion time
6.6 Implementations
6.6.1 Single process snapshot
6.6.2 Fault-tolerance protocol implementations
6.6.3 Implementation comparison
6.7 Concluding remarks
6.8 References
7 Fault tolerance for distributed scheduling in grids
Lei Yu and Frederic Magoules
7.1 Introduction
7.2 Fault tolerance in distributed systems
7.3 Distributed scheduling model
7.3.1 MMS fault tolerance .
7.3.2 LMS/SMS fault tolerance
7.3.3 CR fault tolerance
7.4 Fault detection and repairing in the tree structure
7.4.1 Notations
7.4.2 Algorithms description
7.4.3 Messages treatment analysis
7.5 Distributed scheduling algorithm
7.5.1 Distributed dynamic scheduling algorithm with fault
tolerance (DDFT)
7.5.2 Algorithm fault tolerance issues
7.6 SimGrid and simulation design
7.7 Evaluation
7.7.1 Simulation setup
7.7.2 Comparison with centralized scheduling
7.7.3 Fault tolerance experiments
7.7.4 Workload analysis
7.8 Related work
7.9 Concluding remarks
7.10 References
8 Broadcasting for grids
Christophe Cerin, Luiz-Angelo Steffenel, and Hazem Fkaier
8.1 Introduction .
8.2 Broadcastings
8.3 Heuristics for broadcasting
8.3.1 Basic approaches for broadcasting in homogeneous en
vironments
8.3.2 Advanced approaches for heterogeneous clusters
8.3.3 Grid aware heuristics .
8.3.4 New approach for broadcasting in clusters and hyper
clusters
8.4 Related work and related methods
8.4.1 Broadcasting and dynamic programming
8.4.2 Multi-criteria approach
8.4.3 Broadcast for clusters
8.4.4 Broadcast and heterogeneous systems .
8.5 Concluding remarks
8.6 References
9 Load balancing algorithms for dynamic networks
Jacques M. Bahiy Raphael Couturier, and Abderrahmane Sider
9.1 Introduction
9.2 A taxonomy for load balancing
9.3 Distributed load balancing algorithms for static networks
9.3.1 Network model and performance measures
9.3.2 Diffusion
9.3.3 Dimension exchange . .
9.3.4 ODE
9.3.5 Second order algorithms
9.4 Distributed load balancing algorithms for dynamic networks
9.4.1 Adaption to dynamic networks
9.4.2 Generalized adaptive exchange (CAE)
9.4.3 Illustrating the generalized adaptive exchange most to
least loaded policy on a dynamic network
9.5 Implementation
9.5.1 On synchronous and asynchronous approaches
9.5.2 How to define the load for some applications .
9.5.3 Implementation of static algorithms
9.5.4 Implementation of dynamic algorithms
9.6 A practical example: the advection diffusion application
9.6.1 Load balancing and the application
9.6.2 Load balancing in a dynamic network
9.7 Concluding remarks
9.8 References
Implementation of the replication strategies in OptorSim
Thi-Mai-Huong Nguyen and FYediric Magoules
A.l Introduction
A.2 Download
A.3 Implementation
A.3.1 OptorSim implementation
A.3.2 MaxDAR implementation
A.4 How to execute the simulation
Implementation of the simulator for the distributed schedul
ing model
Lei Yu and Frederic Magoules
B.l Introduction
B.2 Download
B.3 Implementation
B.3.1 Data structures .
B.3.2 Functions
B.4 How to execute the simulation