【24h】

An Efficient Metadata Management Method in Large Distributed Storage Systems

机译:大型分布式存储系统中的高效元数据管理方法

获取原文
获取原文并翻译 | 示例

摘要

Efficient metadata management is a critical aspect of overall system performance in large distributed storage systems. Directory subtree partitioning and traditional hashing are two common techniques used for managing metadata in such systems, but both have some shortcomings, for example, in directory subtree partitioning method, the root node easily becomes a bottleneck, and for traditional hashing, a large directory hierarchy must be maintained and traversed. In this paper, we present a new method called directory-level-based metadata management that has high efficiency while avoiding the shortcomings of traditional methods.
机译:有效的元数据管理是大型分布式存储系统中整体系统性能的关键方面。目录子树分区和传统哈希是在此类系统中用于管理元数据的两种常用技术,但是两者都有一些缺点,例如,在目录子树分区方法中,根节点很容易成为瓶颈,而对于传统哈希,则是大型目录层次结构必须维护和遍历。在本文中,我们提出了一种新方法,称为基于目录级别的元数据管理,该方法在避免传统方法的缺点的同时效率很高。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号