Improving Demand Paging Performance of Compressed Filesystem with NAND Flash Memory

Sungyong Ahn, S. Hyun, K. Koh
{"title":"Improving Demand Paging Performance of Compressed Filesystem with NAND Flash Memory","authors":"Sungyong Ahn, S. Hyun, K. Koh","doi":"10.1109/ICCSA.2009.37","DOIUrl":null,"url":null,"abstract":"Demand paging with NAND flash memory is an attractive memory management technique for embedded system because of its cost efficiency. However, demand paging has the page fault handling latency. To overcome this drawback, most operating systems take advantage of kernel-level read-ahead. On the contrary, in the compressed filesystem, kernel-level read-ahead degrades performance of demand paging. The main reason is that compressed filesystem has too large read-ahead miss penalty due to decompression overhead. To solve this problem, this paper proposes the conservative read-ahead technique, which improves demand paging performance of compressed filesystem. Proposed technique improves read throughput of device by bulk read from device and reduces decompression overhead of compressed filesystem by selective decompression. We implement conservative read-ahead technique by modifying CramFS and evaluate our implementation in the Linux kernel 2.6.21. Performance evaluation results show that proposed technique reduces the average major page fault handling latency by 28%.","PeriodicalId":387286,"journal":{"name":"2009 International Conference on Computational Science and Its Applications","volume":"79 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2009-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2009 International Conference on Computational Science and Its Applications","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICCSA.2009.37","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1

Abstract

Demand paging with NAND flash memory is an attractive memory management technique for embedded system because of its cost efficiency. However, demand paging has the page fault handling latency. To overcome this drawback, most operating systems take advantage of kernel-level read-ahead. On the contrary, in the compressed filesystem, kernel-level read-ahead degrades performance of demand paging. The main reason is that compressed filesystem has too large read-ahead miss penalty due to decompression overhead. To solve this problem, this paper proposes the conservative read-ahead technique, which improves demand paging performance of compressed filesystem. Proposed technique improves read throughput of device by bulk read from device and reduces decompression overhead of compressed filesystem by selective decompression. We implement conservative read-ahead technique by modifying CramFS and evaluate our implementation in the Linux kernel 2.6.21. Performance evaluation results show that proposed technique reduces the average major page fault handling latency by 28%.
利用NAND闪存提高压缩文件系统的需求分页性能
基于NAND闪存的需求分页技术是一种极具吸引力的嵌入式系统内存管理技术。但是,需求分页具有页面错误处理延迟。为了克服这个缺点,大多数操作系统利用内核级预读。相反,在压缩的文件系统中,内核级预读会降低需求分页的性能。主要原因是由于解压缩开销,压缩文件系统有太大的预读缺失损失。为了解决这一问题,本文提出了保守预读技术,提高了压缩文件系统的需求分页性能。该技术通过从设备中批量读取来提高设备的读吞吐量,并通过选择性解压缩来减少被压缩文件系统的解压缩开销。我们通过修改CramFS来实现保守的预读技术,并在Linux内核2.6.21中评估我们的实现。性能评估结果表明,该技术将主要页面错误处理延迟平均降低了28%。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信