Home            Contact us            FAQs
    
      Journal Home      |      Aim & Scope     |     Author(s) Information      |      Editorial Board      |      MSP Download Statistics

     Research Journal of Applied Sciences, Engineering and Technology

    Abstract
2014(Vol.7, Issue:21)
Article Information:

SSD Aware File System Page Cache Algorithms Designs and Implementation to Increase Switch Merge and Reduce Full Merge

Arul Selvan Ramasamy and Porkumaran Karantharaj
Corresponding Author:  Arul Selvan Ramasamy 
Submitted: January 13, 2014
Accepted: February ‎25, ‎2014
Published: June 05, 2014
Abstract:
The NAND based SSD is a tremendous challenge for file system page cache management design as it possess inbuilt imbalance in reading and writing speeds. The present disk-based page cache management policies adopt strategies to maximize the page hit ratio and treat the cost of page read and writes are equal rather than fully exploiting the characteristics of the SSD. Therefore there exists slowness in SSD write which eventually affects the SSD endurance. In special cases like in random writes there exists a problem of augmented write amplification resulting in penalty of write performance. Therefore, a new page replacement algorithm is needed for storage systems based on NAND flash memory. The aim of this study is to propose a new page replacement algorithm for operating systems which focuses on reducing the replacement cost and I/O execution time. Trace-driven simulations show that the proposed algorithm performs better than existing algorithms in terms of the replacement cost and I/O execution time.

Key words:  Data clusters, enlarged write, full merge, random write, switch merge, write amplification, write back cache
Abstract PDF HTML
Cite this Reference:
Arul Selvan Ramasamy and Porkumaran Karantharaj, . SSD Aware File System Page Cache Algorithms Designs and Implementation to Increase Switch Merge and Reduce Full Merge. Research Journal of Applied Sciences, Engineering and Technology, (21): 4574-4583.
ISSN (Online):  2040-7467
ISSN (Print):   2040-7459
Submit Manuscript
   Information
   Sales & Services
Home   |  Contact us   |  About us   |  Privacy Policy
Copyright © 2024. MAXWELL Scientific Publication Corp., All rights reserved