LEC-PR: Proactive Recovery Method in Erasure-Coded Storage

2022 IEEE/ACM Fifth Annual Workshop on Emerging Parallel and Distributed Runtime Systems and Middleware (IPDRM) Pub Date : 2022-11-01 DOI:10.1109/IPDRM56689.2022.00007

Ying Song, Mingjie Yang, Bo Wang

{"title":"LEC-PR: Proactive Recovery Method in Erasure-Coded Storage","authors":"Ying Song, Mingjie Yang, Bo Wang","doi":"10.1109/IPDRM56689.2022.00007","DOIUrl":null,"url":null,"abstract":"Erasure-coded storage is widely used to reduce the data redundancy and improve the reliability of the storage system compared to replication storage. The traditional approach to fault recovery research relies mostly on passive recovery, which occurs when data loss is detected. But passive recovery reduces the system's reliability. At present, machine learning methods can accurately predict soon-to-fail (STF) disks. Based on successfully predicted disk failures, we propose a method to proactively recover data in disks by using local erasure coding within nodes, called LEC-PR (Local EC Proactive Recovery). By migrating and recovering the data in advance, the reliability of the data can be improved. LEC-PR reduces cross-node recovery times and cross-node traffic during proactive data recovery by encoding part of the data blocks inside each node into parity blocks, which are placed in other nodes. As compared to the existing method, LEC-PR can reduce cross-node traffic by 35% and shorten recovery time by up to 69%.","PeriodicalId":324473,"journal":{"name":"2022 IEEE/ACM Fifth Annual Workshop on Emerging Parallel and Distributed Runtime Systems and Middleware (IPDRM)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 IEEE/ACM Fifth Annual Workshop on Emerging Parallel and Distributed Runtime Systems and Middleware (IPDRM)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IPDRM56689.2022.00007","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 0

Abstract

Erasure-coded storage is widely used to reduce the data redundancy and improve the reliability of the storage system compared to replication storage. The traditional approach to fault recovery research relies mostly on passive recovery, which occurs when data loss is detected. But passive recovery reduces the system's reliability. At present, machine learning methods can accurately predict soon-to-fail (STF) disks. Based on successfully predicted disk failures, we propose a method to proactively recover data in disks by using local erasure coding within nodes, called LEC-PR (Local EC Proactive Recovery). By migrating and recovering the data in advance, the reliability of the data can be improved. LEC-PR reduces cross-node recovery times and cross-node traffic during proactive data recovery by encoding part of the data blocks inside each node into parity blocks, which are placed in other nodes. As compared to the existing method, LEC-PR can reduce cross-node traffic by 35% and shorten recovery time by up to 69%.

查看原文本刊更多论文

LEC-PR:擦除编码存储中的主动恢复方法

相对于复制存储，Erasure-coded存储被广泛用于减少数据冗余，提高存储系统的可靠性。传统的故障恢复研究方法主要依赖于被动恢复，即在检测到数据丢失时进行被动恢复。但是被动恢复降低了系统的可靠性。目前，机器学习方法可以准确预测即将失效(STF)磁盘。在成功预测磁盘故障的基础上，我们提出了一种通过节点内的本地擦除编码来主动恢复磁盘数据的方法，称为LEC-PR (local EC Proactive Recovery)。通过对数据的提前迁移和恢复，可以提高数据的可靠性。LEC-PR通过将每个节点内的部分数据块编码为奇偶校验块，并将奇偶校验块放置在其他节点中，减少了主动数据恢复期间的跨节点恢复时间和跨节点流量。与现有方法相比，LEC-PR可以减少35%的跨节点流量，缩短69%的恢复时间。

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

2022 IEEE/ACM Fifth Annual Workshop on Emerging Parallel and Distributed Runtime Systems and Middleware (IPDRM)

自引率

0.00%

发文量