LineFS:高效的SmartNIC卸载分布式文件系统与流水线并行

Q3 Computer Science Operating Systems Review (ACM) Pub Date : 2021-10-26 DOI:10.1145/3477132.3483565
Jongyul Kim, Insu Jang, Waleed Reda, Jaeseong Im, M. Canini, Dejan Kostic, Youngjin Kwon, Simon Peter, E. Witchel
{"title":"LineFS:高效的SmartNIC卸载分布式文件系统与流水线并行","authors":"Jongyul Kim, Insu Jang, Waleed Reda, Jaeseong Im, M. Canini, Dejan Kostic, Youngjin Kwon, Simon Peter, E. Witchel","doi":"10.1145/3477132.3483565","DOIUrl":null,"url":null,"abstract":"In multi-tenant systems, the CPU overhead of distributed file systems (DFSes) is increasingly a burden to application performance. CPU and memory interference cause degraded and unstable application and storage performance, in particular for operation latency. Recent client-local DFSes for persistent memory (PM) accelerate this trend. DFS offload to SmartNICs is a promising solution to these problems, but it is challenging to fit the complex demands of a DFS onto simple SmartNIC processors located across PCIe. We present LineFS, a SmartNIC-offloaded, high-performance DFS with support for client-local PM. To fully leverage the SmartNIC architecture, we decompose DFS operations into execution stages that can be offloaded to a parallel datapath execution pipeline on the SmartNIC. LineFS offloads CPU-intensive DFS tasks, like replication, compression, data publication, index and consistency management to a Smart-NIC. We implement LineFS on the Mellanox BlueField Smart-NIC and compare it to Assise, a state-of-the-art PM DFS. LineFS improves latency in LevelDB up to 80% and throughput in Filebench up to 79%, while providing extended DFS availability during host system failures.","PeriodicalId":38935,"journal":{"name":"Operating Systems Review (ACM)","volume":"32 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2021-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"47","resultStr":"{\"title\":\"LineFS: Efficient SmartNIC Offload of a Distributed File System with Pipeline Parallelism\",\"authors\":\"Jongyul Kim, Insu Jang, Waleed Reda, Jaeseong Im, M. Canini, Dejan Kostic, Youngjin Kwon, Simon Peter, E. Witchel\",\"doi\":\"10.1145/3477132.3483565\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In multi-tenant systems, the CPU overhead of distributed file systems (DFSes) is increasingly a burden to application performance. CPU and memory interference cause degraded and unstable application and storage performance, in particular for operation latency. Recent client-local DFSes for persistent memory (PM) accelerate this trend. DFS offload to SmartNICs is a promising solution to these problems, but it is challenging to fit the complex demands of a DFS onto simple SmartNIC processors located across PCIe. We present LineFS, a SmartNIC-offloaded, high-performance DFS with support for client-local PM. To fully leverage the SmartNIC architecture, we decompose DFS operations into execution stages that can be offloaded to a parallel datapath execution pipeline on the SmartNIC. LineFS offloads CPU-intensive DFS tasks, like replication, compression, data publication, index and consistency management to a Smart-NIC. We implement LineFS on the Mellanox BlueField Smart-NIC and compare it to Assise, a state-of-the-art PM DFS. LineFS improves latency in LevelDB up to 80% and throughput in Filebench up to 79%, while providing extended DFS availability during host system failures.\",\"PeriodicalId\":38935,\"journal\":{\"name\":\"Operating Systems Review (ACM)\",\"volume\":\"32 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2021-10-26\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"47\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Operating Systems Review (ACM)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1145/3477132.3483565\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"Computer Science\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Operating Systems Review (ACM)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3477132.3483565","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"Computer Science","Score":null,"Total":0}
引用次数: 47

摘要

在多租户系统中,分布式文件系统(dfs)的CPU开销日益成为应用程序性能的负担。CPU和内存干扰会导致应用程序和存储性能下降和不稳定,特别是操作延迟。最近用于持久内存(PM)的客户端本地dfse加速了这一趋势。DFS卸载到SmartNIC是解决这些问题的一个很有前途的解决方案,但是将DFS的复杂需求适应到位于PCIe上的简单SmartNIC处理器上是一个挑战。我们介绍了LineFS,这是一个卸载smartnic的高性能DFS,支持客户端本地PM。为了充分利用SmartNIC架构,我们将DFS操作分解为执行阶段,这些执行阶段可以卸载到SmartNIC上的并行数据路径执行管道上。LineFS将cpu密集型DFS任务(如复制、压缩、数据发布、索引和一致性管理)卸载到Smart-NIC。我们在Mellanox BlueField智能网卡上实现LineFS,并将其与Assise进行比较,Assise是最先进的PM DFS。LineFS将LevelDB中的延迟提高到80%,将Filebench中的吞吐量提高到79%,同时在主机系统故障期间提供扩展的DFS可用性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
LineFS: Efficient SmartNIC Offload of a Distributed File System with Pipeline Parallelism
In multi-tenant systems, the CPU overhead of distributed file systems (DFSes) is increasingly a burden to application performance. CPU and memory interference cause degraded and unstable application and storage performance, in particular for operation latency. Recent client-local DFSes for persistent memory (PM) accelerate this trend. DFS offload to SmartNICs is a promising solution to these problems, but it is challenging to fit the complex demands of a DFS onto simple SmartNIC processors located across PCIe. We present LineFS, a SmartNIC-offloaded, high-performance DFS with support for client-local PM. To fully leverage the SmartNIC architecture, we decompose DFS operations into execution stages that can be offloaded to a parallel datapath execution pipeline on the SmartNIC. LineFS offloads CPU-intensive DFS tasks, like replication, compression, data publication, index and consistency management to a Smart-NIC. We implement LineFS on the Mellanox BlueField Smart-NIC and compare it to Assise, a state-of-the-art PM DFS. LineFS improves latency in LevelDB up to 80% and throughput in Filebench up to 79%, while providing extended DFS availability during host system failures.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Operating Systems Review (ACM)
Operating Systems Review (ACM) Computer Science-Computer Networks and Communications
CiteScore
2.80
自引率
0.00%
发文量
10
期刊介绍: Operating Systems Review (OSR) is a publication of the ACM Special Interest Group on Operating Systems (SIGOPS), whose scope of interest includes: computer operating systems and architecture for multiprogramming, multiprocessing, and time sharing; resource management; evaluation and simulation; reliability, integrity, and security of data; communications among computing processors; and computer system modeling and analysis.
期刊最新文献
Disaggregated GPU Acceleration for Serverless Applications Navigating Performance-Efficiency Tradeoffs in Serverless Computing: Deduplication to the Rescue! Using Local Cache Coherence for Disaggregated Memory Systems Make It Real: An End-to-End Implementation of A Physically Disaggregated Data Center Memory disaggregation: why now and what are the challenges
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1