An efficient hash index structure for solid state disks

Hongchan Roh, Sanghyun Park

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

An SSD is a data storage device which has excellent features such as fast access time, shock-resistance, and power-efficiency. However, the SSD is vulnerable to small-size random writes. Therefore, a good index structure is needed in order to completely utilize these superior features and address the drawback. This paper proposes an efficient hash index structure using a write buffer and log-based flushing policy, based on linear hashing and deferred splitting. A write buffer accumulates index records, and logs them to index buckets when flushing them. Through a simple performance analysis, the proposed index confirmed that it significantly reduces the number of small-size random writes.

Original languageEnglish
Title of host publicationProceedings of the 2008 International Conference on Information and Knowledge Engineering, IKE 2008
Pages256-261
Number of pages6
Publication statusPublished - 2008
Event2008 International Conference on Information and Knowledge Engineering, IKE 2008 - Las Vegas, NV, United States
Duration: 2008 Jul 142008 Jul 17

Publication series

NameProceedings of the 2008 International Conference on Information and Knowledge Engineering, IKE 2008

Other

Other2008 International Conference on Information and Knowledge Engineering, IKE 2008
CountryUnited States
CityLas Vegas, NV
Period08/7/1408/7/17

All Science Journal Classification (ASJC) codes

  • Software
  • Artificial Intelligence
  • Computer Science Applications
  • Information Systems

Cite this

Roh, H., & Park, S. (2008). An efficient hash index structure for solid state disks. In Proceedings of the 2008 International Conference on Information and Knowledge Engineering, IKE 2008 (pp. 256-261). (Proceedings of the 2008 International Conference on Information and Knowledge Engineering, IKE 2008).