Dynamic replica placement and selection strategies in data grids— A comprehensive survey
Section snippets
Introduction: replica placement and replica selection
A computational grid [22] is a combination of both hardware and software that provides reliable and consistent resources to execute a job in distributed environment. Data grid is a distributed collection of storage and computational resources located in different geographical locations. [1], [18], [23] describe grid is a flexible, secure and co-ordinated resource sharing environment for individuals, institutions and resources. Computationally intensive applications need large amount of data,
Dynamic replica placement techniques
Both centralized and distributed dynamic replica placement strategies are further classified according to the type of network used for implementation.
Dynamic replica selection techniques
Replica selection is one of the key components of data management in data intensive application. It decides which replica location is the best place to access the data for users. If several replicas are available for a file, the optimization algorithm determines which replica should be selected to execute the job. The optimal replica is selected based on the following parameters: access cost, access latency, bandwidth consumption, balanced workload, maintenance cost, job execution time,
Summary of replica placement and selection strategies
In this paper, the summary of various replica placement and selection strategies is done based on the following aspects:
- •
parameters that are used to evaluate the grid performance;
- •
architectural models;
- •
assumptions that are made during replication;
- •
simulation tools used.
The grid replication and selection strategies are evaluated based on certain performance parameters. Any replica placement and selection strategy tries to improve one or more of the following parameters: makespan, quality assurance,
Conclusion
This paper presents a survey on replica placement and selection strategies for dynamic data grid environment. Different replica placement and selection strategies are proposed by researchers. In dynamic grid configuration, the user can join and leave the network at any point of time. Therefore, there is no specific grid topology used for the dynamic data grid. Most of the work done in replica placement and selection is based on the hierarchical and modified hierarchical architecture. The graph
R. Kingsy Grace graduated with B.E. Computer Science and Engineering in 2003 from Noorul Islam College of Engineering, India and completed M.E. Computer Science and Engineering in 2005 from Karunya Institute of Technology, Coimbatore, India. She is currently pursuing her Ph.D. at Anna University, Chennai, India. Her area of interest includes Grid Computing and her current research focus is on Dynamic replica placement and selection in data grids. She has about 10 years of teaching experience.
References (54)
- et al.
A survey of dynamic replication strategies for improving data availability in data grids
Future Gener. Comput. Syst.
(2012) - et al.
Dynamic QoS- aware data replication in grid environments based on data importance
Future Gener. Comput. Syst.
(2012) - et al.
Job scheduling and data replication on data grids
Future Gener. Comput. Syst.
(2007) - et al.
Methods for replica creation in data grids using complex network
J. China Univ. Posts Telecommun.
(2010) - et al.
The complexity of static data replication in data grids
Parallel Comput.
(2005) - et al.
A dynamic replica management strategy in data grid
J. Netw. Comput. Appl.
(2012) - et al.
Branch replica scheme: a new model for data replication in large scale
Future Gener. Comput. Syst.
(2010) - et al.
Using OptorSim to efficiently simulate replica placement strategies
J. China Univ. Posts Telecommun.
(2010) Antony selvadoss thanamani, dynamic replication in a data grid using modified BHR region based algorithm
Future Gener. Comput. Syst.
(2011)- et al.
Dynamic replication algorithm for the multi-tier data grid
Future Gener. Comput. Syst.
(2005)
Optimal replica placement in hierarchical data grids with locality assurance
J. Parallel Distrib. Comput.
Data management and transfer in high performance computational grid environments
Parallel Comput. J.
Secure, efficient data transport and replica management for high-performance data-intensive computing
OptorSim: a grid simulator for studying dynamic data replication strategies
Int. J. High Perform. Comput. Appl.
Evaluation of an economy based file replication strategy for a data grid
The data grid: towards architecture for the distributed management and analysis of large scientific datasets
J. Netw. Comput. Appl.
Cited by (69)
A multi-objective optimized replication using fuzzy based self-defense algorithm for cloud computing
2020, Journal of Network and Computer ApplicationsKeeping up with storage: Decentralized, write-enabled dynamic geo-replication
2018, Future Generation Computer SystemsCitation Excerpt :In this paper, we focus on allowing a geo-distributed application to access a geo-distributed data source with the lowest possible latency. Kingsy Grace et al. [7] provide an extensive survey of replica placement and selection algorithms available in the literature. Among these, Chen et al. [8] propose a dissemination-tree based replication algorithm leveraging a peer-to-peer location service.
Data Replication and Placement Strategies in Distributed Systems: A State of the Art Survey
2023, Wireless Personal CommunicationsA Fuzzy Logic-Based Method for Replica Placement in the Peer to Peer Cloud Using an Optimization Algorithm
2022, Wireless Personal CommunicationsAccess strategies for network caching
2021, IEEE/ACM Transactions on Networking
R. Kingsy Grace graduated with B.E. Computer Science and Engineering in 2003 from Noorul Islam College of Engineering, India and completed M.E. Computer Science and Engineering in 2005 from Karunya Institute of Technology, Coimbatore, India. She is currently pursuing her Ph.D. at Anna University, Chennai, India. Her area of interest includes Grid Computing and her current research focus is on Dynamic replica placement and selection in data grids. She has about 10 years of teaching experience. She is currently working as an Assistant Professor (Sr. Grade) in the Department of Computer Science and Engineering, Sri Ramakrishna Engineering College, Coimbatore, India.
R. Manimegalai is presently working as a Professor and Director–Research, Department of Computer Science and Engineering, Park College Engineering and Technology, Coimbatore, India. She has published many papers in international/national journals and conferences. Her area of interest includes Reconfigurable Computing and Distributed Systems. She has to her credit 19 years of teaching, research and industry experience.