WPCB-Tree: A Novel Flash-Aware B-Tree Index Using a Write Pattern Converter
AbstractFor the past few years, flash memory has been widely used because of its prominent advantages such as fast access speed, nonvolatility, high reliability, and low power consumption. However, flash memory still has several drawbacks that need to be overcome, e.g., the erase-before-write characteristic and a limited life cycle. Among these drawbacks, the erase-before-write characteristic causes the B-tree implementation on flash memory to be inefficient because it generates many erase operations. This study introduces a novel B-tree index structure using a write pattern converter (WPCB-tree) for flash memory. A WPCB-tree can minimize the risk of data loss and can improve the performance of the B-tree on flash memory. This WPCB-tree uses some blocks of flash memory as a buffer that temporarily stores all updated nodes. When the buffer is full, a buffer block is selected by a greedy algorithm, then the node pages in the block are converted into a sequential write pattern, and finally they are written into flash memory. In addition, in the case that all key values of a leaf node are continuously inserted, the WPCB-tree does not split the leaf node. As a result, this mechanism helps the WPCB-tree reduce the number of write operations on the flash memory. The experimental results show that the proposed B-tree variant on flash memory yields a better performance than that of other existing variants of the B-tree. View Full-Text
Share & Cite This Article
Ho, V.P.; Park, D.-J. WPCB-Tree: A Novel Flash-Aware B-Tree Index Using a Write Pattern Converter. Symmetry 2018, 10, 18.
Ho VP, Park D-J. WPCB-Tree: A Novel Flash-Aware B-Tree Index Using a Write Pattern Converter. Symmetry. 2018; 10(1):18.Chicago/Turabian Style
Ho, Van P.; Park, Dong-Joo. 2018. "WPCB-Tree: A Novel Flash-Aware B-Tree Index Using a Write Pattern Converter." Symmetry 10, no. 1: 18.
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.