计算机应用 ›› 2010, Vol. 30 ›› Issue (3): 813-817.

• 数据库与数据挖掘 • 上一篇    下一篇

P级文件系统搜索概述

张妤芝1,刘海涛2   

  1. 1. 上海交通大学
    2.
  • 收稿日期:2009-09-15 修回日期:2009-11-02 发布日期:2010-03-14 出版日期:2010-03-01
  • 通讯作者: 张妤芝

Survey on search of file system with petascale size

  • Received:2009-09-15 Revised:2009-11-02 Online:2010-03-14 Published:2010-03-01

摘要: 当文件系统规模达到P级时,管理和查找这数以百万甚至千万计的文件将会变得越来越困难,高效的文件系统搜索成为必不可少的工具。综述了P级文件系统搜索的总体研究情况,包括面临的挑战,P级文件系统搜索中的关键问题,介绍了一些P级文件系统搜索研究项目及其所用到的索引技术,特别指出了它们的局限性。最后,结合当前搜索技术的发展,指出了P级文件系统搜索面临的一些新的发展方向。

关键词: P级文件系统搜索, 桌面搜索, 全文搜索, 倒排索引, 语义, 索引层级划分

Abstract: As file systems grow to petabytes, managing and retrieving the billions of files become increasingly difficult. Efficient file system search becomes more and more important and necessary. The authors gave an overview on the current state of petascale file system search and the challenges, discussed the key points, existing projects in petascale file system search and the index technology. At the end, the authors proposed some new research prospects in petascale file system search.

Key words: petascale file system search, desktop search, full-text search, inverted index, semantic, hierarchical partitioning