Exploiting Flat Namespace to Improve File System Metadata Performance on Ultra-Fast, Byte-Addressable NVMs

Author:

Cai Miao1ORCID,Shen Junru2ORCID,Tang Bin1ORCID,Huang Hao3ORCID,Ye Baoliu4ORCID

Affiliation:

1. Key Laboratory of Water Big Data Technology of Ministry of Water Resources, School of Computer and Information, Hohai University, China

2. School of Computer and Information, Hohai University, China

3. State Key Laboratory for Novel Software Technology, Nanjing University, China

4. State Key Laboratory for Novel Software Technology, Nanjing University; Key Laboratory of Water Big Data Technology of Ministry of Water Resources, School of Computer and Information, Hohai University, China

Abstract

The conventional file system provides a hierarchical namespace by structuring it as a directory tree. Tree-based namespace structure leads to inefficient file path walk and expensive namespace tree traversal, underutilizing ultra-low access latency and superior sequential performance provided by non-volatile memories (NVMs). This article proposes FlatFS+, an NVM file system that features a flat namespace architecture while providing a compatible hierarchical namespace view. FlatFS+ incorporates three novel techniques: the direct file path walk model, range-optimized B r tree, and compressed index key design with scan and write dual optimization, to fully exploit flat namespace to improve file system metadata performance on ultra-fast, byte-addressable NVMs. Evaluation results demonstrate that FlatFS+ achieves significant performance improvements for metadata-intensive benchmarks and real-world applications compared to other file systems.

Funder

Fundamental Research Funds for the Central Universities

National Natural Science Foundation of China

Natural Science Foundation of Jiangsu Province

CCF-Huawei Innovation Research Plan

Future Network Scientific Research Fund Project

China Postdoctoral Science Foundation

Jiangsu Planned Projects for Postdoctoral Research Funds

Publisher

Association for Computing Machinery (ACM)

Subject

Hardware and Architecture

Reference77 articles.

1. Intel. 2015. Intel and Micron Produce Breakthrough Memory Technology. Retrieved September 16 2023 from https://newsroom.intel.com/news-releases/intel-and-micron-produce-breakthrough-memory-technology/

2. GitHub. 2018. Google LevelDB. Retrieved September 16 2023 from https://github.com/google/leveldb

3. Tom’s Hardware. 2019. Samsung 983 ZET SSD Review: Z-NAND Takes on Optane. Retrieved September 16 2023 from https://www.tomshardware.com/reviews/samsung-983-zet-z-nand-optane-ssd 6036.html

4. Percona. 2021. Percona TokuDB. Retrieved September 16 2023 from https://docs.percona.com/percona-server/8.0/tokudb/tokudb_intro.html

5. Apache Hadoop. 2022. Download. Retrieved September 16 2023 from https://hadoop.apache.org/releases.html

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3