面向高性能计算的分布式可靠软件定义存储控制平面

2023 IEEE/ACM 23rd International Symposium on Cluster, Cloud and Internet Computing Workshops (CCGridW) Pub Date : 2023-05-01 DOI:10.1109/CCGridW59191.2023.00071

Mariana Miranda

{"title":"面向高性能计算的分布式可靠软件定义存储控制平面","authors":"Mariana Miranda","doi":"10.1109/CCGridW59191.2023.00071","DOIUrl":null,"url":null,"abstract":"The Software-Defined Storage (SDS) paradigm has emerged as a way to ease the orchestration and management complexities of storage systems. This work aims to mitigate the storage performance issues that large-scale HPC infrastructures are currently facing by developing a scalable and dependable control plane that can be integrated into an SDS design to take full advantage of the tools this paradigm offers. The proposed solution will enable system administrators to define storage policies (e.g., I/O prioritization, rate limiting) and, based on them, the control plane will orchestrate the storage system to provide better QoS for data-centric applications.","PeriodicalId":341115,"journal":{"name":"2023 IEEE/ACM 23rd International Symposium on Cluster, Cloud and Internet Computing Workshops (CCGridW)","volume":"217 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Distributed and Dependable Software-Defined Storage Control Plane for HPC\",\"authors\":\"Mariana Miranda\",\"doi\":\"10.1109/CCGridW59191.2023.00071\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The Software-Defined Storage (SDS) paradigm has emerged as a way to ease the orchestration and management complexities of storage systems. This work aims to mitigate the storage performance issues that large-scale HPC infrastructures are currently facing by developing a scalable and dependable control plane that can be integrated into an SDS design to take full advantage of the tools this paradigm offers. The proposed solution will enable system administrators to define storage policies (e.g., I/O prioritization, rate limiting) and, based on them, the control plane will orchestrate the storage system to provide better QoS for data-centric applications.\",\"PeriodicalId\":341115,\"journal\":{\"name\":\"2023 IEEE/ACM 23rd International Symposium on Cluster, Cloud and Internet Computing Workshops (CCGridW)\",\"volume\":\"217 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-05-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2023 IEEE/ACM 23rd International Symposium on Cluster, Cloud and Internet Computing Workshops (CCGridW)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/CCGridW59191.2023.00071\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2023 IEEE/ACM 23rd International Symposium on Cluster, Cloud and Internet Computing Workshops (CCGridW)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CCGridW59191.2023.00071","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 0

摘要

软件定义存储(SDS)范式作为一种简化存储系统编排和管理复杂性的方法而出现。这项工作旨在通过开发可扩展且可靠的控制平面来缓解大规模HPC基础设施目前面临的存储性能问题，该控制平面可以集成到SDS设计中，以充分利用该范例提供的工具。提出的解决方案将使系统管理员能够定义存储策略(例如，I/O优先级，速率限制)，并在此基础上，控制平面将编排存储系统，为以数据为中心的应用程序提供更好的QoS。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Distributed and Dependable Software-Defined Storage Control Plane for HPC

The Software-Defined Storage (SDS) paradigm has emerged as a way to ease the orchestration and management complexities of storage systems. This work aims to mitigate the storage performance issues that large-scale HPC infrastructures are currently facing by developing a scalable and dependable control plane that can be integrated into an SDS design to take full advantage of the tools this paradigm offers. The proposed solution will enable system administrators to define storage policies (e.g., I/O prioritization, rate limiting) and, based on them, the control plane will orchestrate the storage system to provide better QoS for data-centric applications.

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

2023 IEEE/ACM 23rd International Symposium on Cluster, Cloud and Internet Computing Workshops (CCGridW)

自引率

0.00%

发文量