Highly scalable metadata distribution algorithm in mass storage system

Distribution of metadata in a metadata server cluster is important in mass storage system. A good distribution algorithm has a significant influence on the system performance, availability and scalability. Subtree partition and hash are two traditional metadata distribution algorithms used in distri...

Full description

Saved in:
Bibliographic Details
Published inJournal of Shanghai University Vol. 12; no. 5; pp. 419 - 425
Main Author 吴伟 谢长生 黄建忠 张成峰
Format Journal Article
LanguageEnglish
Published Heidelberg Shanghai University Press 01.10.2008
Subjects
Classical Mechanics
Engineering
Environment
Life Sciences
Materials Science
Mathematical and Computational Engineering
Mechatronics
分布算法
海量存储系统
研究分析
高扩展性元数据
metadata server cluster
mass storage system
high scalability
directory hash (DH)
Online AccessGet full text
ISSN1007-6417
1863-236X
DOI10.1007/s11741-008-0509-1

Cover

More Information
Summary:Distribution of metadata in a metadata server cluster is important in mass storage system. A good distribution algorithm has a significant influence on the system performance, availability and scalability. Subtree partition and hash are two traditional metadata distribution algorithms used in distributed file systems. They both have a defect in system scalability. This paper proposes a new directory hash （DH） algorithm. By treating directory as the key value of hash function, implementing concentrated storage of metadata, pipelining operations and prefetching technology, DH algorithm can enhance the system scalability on the premise without sacrificing system performance.
Bibliography:31-1735/N
TP30
mass storage system, metadata server cluster, high scalability, directory hash （DH）
ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 23
ISSN:1007-6417
1863-236X
DOI:10.1007/s11741-008-0509-1