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}
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.
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.