pNFS-Based Software-Defined Storage for Information Lifecycle Management

The data explosion brings several difficult challenges. One of critical and fundamental challenges is to have a storage infrastructure that can store and manage such voluminous information to meet business goals, such as cost, performance, reliability, and availability. To reduce the storage cost an...

Full description

Saved in:
Bibliographic Details
Published in2015 International Conference on Cloud Computing and Big Data (CCBD) pp. 89 - 92
Main Authors Kuo Sheng Deng, Chin Feng Lee, Chou, Jerry, Yi Chen Shih, Shang Hao Chuang, Po Hsuan Wu
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.11.2015
Subjects
Online AccessGet full text

Cover

Loading…
More Information
Summary:The data explosion brings several difficult challenges. One of critical and fundamental challenges is to have a storage infrastructure that can store and manage such voluminous information to meet business goals, such as cost, performance, reliability, and availability. To reduce the storage cost and improve data access performance, it is typically required a storage management solution based on Information Lifecycle Management (ILM). In this work, we propose a design of ILM system for managing a tiered storage using pNFS(Parallel NFS) file system. pNFS is an emerging NFSv4 extension that bypasses the server bottleneck by enabling direct access to storage by NFSv4 clients. Furthermore, because pNFS separates control and data flows, it enables a software-defined storage architecture. This paper describes our system design and shows the preliminary performance results in this work as a future roadmap to achieve our goal.
DOI:10.1109/CCBD.2015.13