Title: Efficiency of indexing database systems and optimising its implementation in NAND flash memory

Authors: Mohamed Chakraoui; Abderrafiaa Elkalay

Addresses: Faculty of Sciences and Techniques Gueliz, Cadi Ayyad University, B.P 549, Av. Abdelkarim Elkhattabi, Guéliz Marrakech, Morocco ' Faculty of Sciences and Techniques Gueliz, Cadi Ayyad University, B.P 549, Av. Abdelkarim Elkhattabi, Guéliz Marrakech, Morocco

Abstract: In this paper, we propose a model of optimisation of B+tree index in flash memory. Since the advent of multi-core computers (multi-processors) parallelism becomes an indispensable part of optimisation. Our work will focus on partitioning a table on three parts following indexing key partitioning; each processor will host a partition of the index, and the first processor that will finish its work will immediately take the first partition of the index pending according to the priority, we will implement these manipulations in flash memories storage systems. In this paper, we propose a new alterative to optimise the trade-off between B*tree or B+tree with flash memory software and avoid the data incompatibility due to crash system.

Keywords: indexing databases; tuning; flash memory; optimisation; B*tree; B+tree index; table partitioning; indexing key partitioning.

DOI: 10.1504/IJSCC.2016.077406

International Journal of Systems, Control and Communications, 2016 Vol.7 No.3, pp.221 - 239

Received: 13 Jun 2015
Accepted: 04 Jan 2016
Published online: 29 Jun 2016 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article