Health Data Availability Protection:Delta-XOR-Relay Data Update in Erasure-Coded Cloud Storage Systems  

作　　者：Yifei Xiao Shijie Zhou 

机构地区：[1]School of Information and Software Engineering,University of Electronic Science and Technology of China,Chengdu,610054,China

出　　处：《Computer Modeling in Engineering & Sciences》2023年第4期169-185,共17页工程与科学中的计算机建模（英文）

基　　金：supported by Major Special Project of Sichuan Science and Technology Department(2020YFG0460);Central University Project of China(ZYGX2020ZB020,ZYGX2020ZB019).

摘　　要：To achieve the high availability of health data in erasure-coded cloud storage systems,the data update performance in erasure coding should be continuously optimized.However,the data update performance is often bottlenecked by the constrained cross-rack bandwidth.Various techniques have been proposed in the literature to improve network bandwidth efficiency,including delta transmission,relay,and batch update.These techniques were largely proposed individually previously,and in this work,we seek to use them jointly.To mitigate the cross-rack update traffic,we propose DXR-DU which builds on four valuable techniques:(i)delta transmission,(ii)XOR-based data update,(iii)relay,and(iv)batch update.Meanwhile,we offer two selective update approaches:1)data-deltabased update,and 2)parity-delta-based update.The proposed DXR-DU is evaluated via trace-driven local testbed experiments.Comprehensive experiments show that DXR-DU can significantly improve data update throughput while mitigating the cross-rack update traffic.

关 键 词：Data availability health data data update cloud storage IoT 

分 类 号：TP333[自动化与计算机技术—计算机系统结构]