FlashCoop: A Locality-Aware Cooperative Buffer Management for SSD-Based Storage Cluster

Q. Wei, Bozhao Gong, Suraj Pathak, Y. Tay
{"title":"FlashCoop: A Locality-Aware Cooperative Buffer Management for SSD-Based Storage Cluster","authors":"Q. Wei, Bozhao Gong, Suraj Pathak, Y. Tay","doi":"10.1109/ICPP.2010.71","DOIUrl":null,"url":null,"abstract":"Random writes significantly limit the application of flash-based Solid State Drive (SSD) in enterprise environment due to its poor latency, negative impact on SSD lifetime and high garbage collection overhead. To release above limitations, we propose a locality-aware cooperative buffer scheme referred to as FlashCoop (Flash Cooperation), which leverages free memory of neighboring storage server to buffer writes over high speed network. Both temporal and sequential localities of access pattern are exploited in the design of cooperative buffer management. Leveraging the filtering effect of the cooperative buffer, FlashCoop can efficiently shape the I/O request stream and improve the sequentiality of the write accesses passed to the SSD. FlashCoop has been extensively evaluated under various enterprise workloads. Our benchmark results conclusively demonstrate that FlashCoop can achieve 52.3% performance improvement and 56.5% garbage collection overhead reduction compared to the system without FlashCoop.","PeriodicalId":180554,"journal":{"name":"2010 39th International Conference on Parallel Processing","volume":"24 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2010-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2010 39th International Conference on Parallel Processing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICPP.2010.71","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

Random writes significantly limit the application of flash-based Solid State Drive (SSD) in enterprise environment due to its poor latency, negative impact on SSD lifetime and high garbage collection overhead. To release above limitations, we propose a locality-aware cooperative buffer scheme referred to as FlashCoop (Flash Cooperation), which leverages free memory of neighboring storage server to buffer writes over high speed network. Both temporal and sequential localities of access pattern are exploited in the design of cooperative buffer management. Leveraging the filtering effect of the cooperative buffer, FlashCoop can efficiently shape the I/O request stream and improve the sequentiality of the write accesses passed to the SSD. FlashCoop has been extensively evaluated under various enterprise workloads. Our benchmark results conclusively demonstrate that FlashCoop can achieve 52.3% performance improvement and 56.5% garbage collection overhead reduction compared to the system without FlashCoop.
FlashCoop:一种基于ssd存储集群的位置感知协同缓冲管理
随机写由于其较低的延迟、对SSD寿命的负面影响和较高的垃圾收集开销,极大地限制了基于闪存的SSD在企业环境中的应用。为了消除上述限制,我们提出了一种称为FlashCoop (Flash Cooperation)的位置感知协作缓冲方案,该方案利用相邻存储服务器的空闲内存来缓冲高速网络上的写操作。在协同缓冲区管理的设计中,同时利用了访问模式的时序定位和时序定位。利用协作缓冲区的过滤效果,FlashCoop可以有效地塑造I/O请求流,并提高传递给SSD的写访问的顺序性。FlashCoop已经在各种企业工作负载下进行了广泛的评估。我们的基准测试结果最终表明,与没有FlashCoop的系统相比,FlashCoop可以实现52.3%的性能改进和56.5%的垃圾收集开销减少。
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