Abstract

Replication is a useful technique for distributed database systems and has been implemented in EU data grid and HEP in CERN for handling huge data access. Replica selection in their prototypes still can be enhanced to provide high availability, fault tolerant and low in communication cost. This paper introduces a new replica control protocol, named Diagonal Replication in 2D Mesh (DR2M) for grid environment and compares its performance with the previous protocols. The performance in this paper is data availability for read and write operation, which are compared to the Read-One Write-All (ROWA), Voting (VT), Tree Quorum (TQ), Grid Configuration (GC), Three Dimensional Grid Structure (TDGS), and Diagonal Replication on Grid (DRG). This paper discusses the protocol of replicating data for grid environment, putting the protocol in a logical 2D mesh structure by employing the quorums and voting techniques. The data file is copied in a selected replica from the diagonal sites in each quorum. The selection of a replica depends on the diagonal location of the structured 2D mesh network where the middle replica is selected because it is the shortest path to get a copy of the data from most of the direction in the quorum. The algorithm in this paper also calculates the optimized number of nodes to be grouped in each quorum and how many quorums are needed for the number of nodes, N in a network. DR2M protocol also ensures that the data for read and write operations are consistent, by ensuring the quorum must not have a nonempty intersection quorum. To evaluate the DR2M protocol, we developed a simulation model in Java. Our results prove that our protocol improves the performance of data availability compared to the previous data replication protocol, namely Read-One Write-All (ROWA), Voting (VT), Tree Quorum (TQ), Grid Configuration (GC), Three Dimensional Grid Structure (TDGS), and Diagonal Replication on Grid (DRG).

Highlights

  • A grid is a distributed network computing system, a virtual computer formed by a networked set of heterogeneous machines that agree to share their local resources with each other

  • We investigate on the replica selection for optimizing and improving data accessing by using replica control protocol in distributed database to the grid environment

  • Diagonal Replication in 2D Mesh (DR2M) protocol is compared to the results of read and write availability of the previous protocols, namely: Read-One Write-All (ROWA), VT, Tree Quorum (TQ), Grid Configuration (GC), Three Dimensional Grid Structure (TDGS), and Diagonal Replication on Grid (DRG)

Read more

Summary

Introduction

A grid is a distributed network computing system, a virtual computer formed by a networked set of heterogeneous machines that agree to share their local resources with each other. We investigate on the replica selection for optimizing and improving data accessing by using replica control protocol in distributed database to the grid environment. Quorums reduce the number of copies for reading or writing data. DR2M replicates data on the middle node of a quorum of read or write in the logical structured of 2D mesh topology network. This section includes the formulation for read/write availability for the previous protocols in distributed database and grid computing. Quorum is grouping the nodes or databases into small cluster to manage the replica for read or write operations. The number of nodes grouped in quorum, R must be odd so that only one middle node from the diagonal sites can be selected such as the black circle, which reduces the communication cost. S(3,3) in Figure 2 is selected to have the copy of data

The correctness
Related Work
Results and Discussion
Conclusions
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call