基于ssd存储系统中擦除码的持久性研究

Saeideh Alinezhad Chamazcoti, S. Miremadi, H. Asadi
{"title":"基于ssd存储系统中擦除码的持久性研究","authors":"Saeideh Alinezhad Chamazcoti, S. Miremadi, H. Asadi","doi":"10.1109/CADS.2013.6714239","DOIUrl":null,"url":null,"abstract":"The wear-out of flash-based Solid-State Drives (SSDs) is a main concern that significantly affects their reliability. One major parameter that accelerates SSD wear-out is the number of write-cycles committed to flash chips. The number of write-cycles in SSD-based disk subsystem is highly dependent on the erasure code implemented in Redundant Array of Independent Disks (RAIDs). In this paper, we investigate the impact of erasure codes and the configuration of storage subsystems (i.e., the number of disks participated in the RAID array and stripe unit size) on the endurance of storage systems. The number of write-cycles is considered as a metric to evaluate the endurance of storage system. We evaluate the endurance of four different well-known erasure codes, i.e., Reed-Solomon, EVENODD, RDP, and X-Code, employed in SSD-based RAID systems. In the evaluation, the number of write-cycles is measured with respect to the number of disks, stripe unit size, and request size using trace-driven simulation. The simulation results show that Reed-Solomon provides the lowest number of write-cycles due to the optimal dependency between data and parities in its coding. The results also demonstrate that EVENODD and RDP impose the highest number of write-cycles when using the high number of disks with large stripe unit size. These results recommend designing erasure codes with minimum dependency between data and parities as this minimum dependency provides optimal number of write-cycles.","PeriodicalId":379673,"journal":{"name":"The 17th CSI International Symposium on Computer Architecture & Digital Systems (CADS 2013)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":"{\"title\":\"On endurance of erasure codes in SSD-based storage systems\",\"authors\":\"Saeideh Alinezhad Chamazcoti, S. Miremadi, H. Asadi\",\"doi\":\"10.1109/CADS.2013.6714239\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The wear-out of flash-based Solid-State Drives (SSDs) is a main concern that significantly affects their reliability. One major parameter that accelerates SSD wear-out is the number of write-cycles committed to flash chips. The number of write-cycles in SSD-based disk subsystem is highly dependent on the erasure code implemented in Redundant Array of Independent Disks (RAIDs). In this paper, we investigate the impact of erasure codes and the configuration of storage subsystems (i.e., the number of disks participated in the RAID array and stripe unit size) on the endurance of storage systems. The number of write-cycles is considered as a metric to evaluate the endurance of storage system. We evaluate the endurance of four different well-known erasure codes, i.e., Reed-Solomon, EVENODD, RDP, and X-Code, employed in SSD-based RAID systems. In the evaluation, the number of write-cycles is measured with respect to the number of disks, stripe unit size, and request size using trace-driven simulation. The simulation results show that Reed-Solomon provides the lowest number of write-cycles due to the optimal dependency between data and parities in its coding. The results also demonstrate that EVENODD and RDP impose the highest number of write-cycles when using the high number of disks with large stripe unit size. These results recommend designing erasure codes with minimum dependency between data and parities as this minimum dependency provides optimal number of write-cycles.\",\"PeriodicalId\":379673,\"journal\":{\"name\":\"The 17th CSI International Symposium on Computer Architecture & Digital Systems (CADS 2013)\",\"volume\":\"9 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2013-10-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"3\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"The 17th CSI International Symposium on Computer Architecture & Digital Systems (CADS 2013)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/CADS.2013.6714239\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"The 17th CSI International Symposium on Computer Architecture & Digital Systems (CADS 2013)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CADS.2013.6714239","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 3

摘要

基于闪存的固态硬盘(ssd)的损耗是影响其可靠性的主要问题。加速SSD损耗的一个主要参数是用于闪存芯片的写周期数量。基于ssd的磁盘子系统的写周期数高度依赖于raid (Redundant Array of Independent Disks)中实现的擦除码。在本文中,我们研究了擦除码和存储子系统的配置(即参与RAID阵列的磁盘数量和条带单元大小)对存储系统耐久性的影响。写循环次数是衡量存储系统耐久性的一个指标。我们评估了四种不同的众所周知的擦除码,即Reed-Solomon, EVENODD, RDP和X-Code,在基于ssd的RAID系统中使用的持久性。在评估中,使用跟踪驱动的模拟,根据磁盘数量、条带单位大小和请求大小来测量写周期的数量。仿真结果表明,由于编码过程中数据和对偶之间的最佳依赖关系,Reed-Solomon提供了最少的写周期数。结果还表明,当使用大量条带单元大小较大的磁盘时,EVENODD和RDP施加的写周期数量最多。这些结果建议在数据和奇偶之间设计最小依赖关系的擦除代码,因为这种最小依赖关系提供了最佳的写周期数量。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
On endurance of erasure codes in SSD-based storage systems
The wear-out of flash-based Solid-State Drives (SSDs) is a main concern that significantly affects their reliability. One major parameter that accelerates SSD wear-out is the number of write-cycles committed to flash chips. The number of write-cycles in SSD-based disk subsystem is highly dependent on the erasure code implemented in Redundant Array of Independent Disks (RAIDs). In this paper, we investigate the impact of erasure codes and the configuration of storage subsystems (i.e., the number of disks participated in the RAID array and stripe unit size) on the endurance of storage systems. The number of write-cycles is considered as a metric to evaluate the endurance of storage system. We evaluate the endurance of four different well-known erasure codes, i.e., Reed-Solomon, EVENODD, RDP, and X-Code, employed in SSD-based RAID systems. In the evaluation, the number of write-cycles is measured with respect to the number of disks, stripe unit size, and request size using trace-driven simulation. The simulation results show that Reed-Solomon provides the lowest number of write-cycles due to the optimal dependency between data and parities in its coding. The results also demonstrate that EVENODD and RDP impose the highest number of write-cycles when using the high number of disks with large stripe unit size. These results recommend designing erasure codes with minimum dependency between data and parities as this minimum dependency provides optimal number of write-cycles.
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
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