TY - JOUR
T1 - An erasure-coded storage system for edge computing
AU - Liang, Lixin
AU - He, Huan
AU - Zhao, Jian
AU - Liu, Chengjian
AU - Luo, Qiuming
AU - CHU, Xiaowen
N1 - Funding Information:
This work was supported in part by Natural Science Foundation of Top Talent of SZTU under Grant 2018010801008, in part by Foundation of School-Enterprise Cooperation for Graduate Students of SZTU under Grant XQHZ201907, and in part by Guangdong Province Key Laboratory of Popular High Performance Computers 2017B030314073 under Grant SZU-GDPHPCL201902.
PY - 2020/5/20
Y1 - 2020/5/20
N2 - Emerging computing paradigm edge computing expects to store and process data at the network edge with reduced latency and improved network bandwidth. To the best of our knowledge, key performance issues such as coding performance of erasure-coded storage systems haven't been investigated for edge computing. In this paper, we present an erasure-coded storage system for edge computing. Unlike the data center and cloud storage systems, it employs edge devices to perform encoding and decoding operations, which can be a performance bottleneck of the whole storage system due to limited computing power. Hence, we present a comprehensive study of the performance of erasure coding to see if it can match the network performance of 5G and Wi-Fi 6 at the network edge. We use the popular edge device Jetson Nano and two state-of-the-art coding libraries: Jerasure and G-CRS. Our evaluation results reveal unsatisfied performance for Jerasure and high variance for G-CRS. To obtain better and stable performance, we accelerate erasure code with OpenMP on a multi-core CPU. Our work demonstrates our acceleration can bring stable performance and match the network bandwidth of 5G and Wi-Fi 6 for some commonly used cases. Besides, our work offers a better understanding of erasure-coded storage systems for edge computing and can be served as a reference to any further optimization for such kind of systems at the network edge.
AB - Emerging computing paradigm edge computing expects to store and process data at the network edge with reduced latency and improved network bandwidth. To the best of our knowledge, key performance issues such as coding performance of erasure-coded storage systems haven't been investigated for edge computing. In this paper, we present an erasure-coded storage system for edge computing. Unlike the data center and cloud storage systems, it employs edge devices to perform encoding and decoding operations, which can be a performance bottleneck of the whole storage system due to limited computing power. Hence, we present a comprehensive study of the performance of erasure coding to see if it can match the network performance of 5G and Wi-Fi 6 at the network edge. We use the popular edge device Jetson Nano and two state-of-the-art coding libraries: Jerasure and G-CRS. Our evaluation results reveal unsatisfied performance for Jerasure and high variance for G-CRS. To obtain better and stable performance, we accelerate erasure code with OpenMP on a multi-core CPU. Our work demonstrates our acceleration can bring stable performance and match the network bandwidth of 5G and Wi-Fi 6 for some commonly used cases. Besides, our work offers a better understanding of erasure-coded storage systems for edge computing and can be served as a reference to any further optimization for such kind of systems at the network edge.
KW - edge computing
KW - erasure coding
KW - Erasure-coded storage system
KW - jetson nano
UR - http://www.scopus.com/inward/record.url?scp=85086064844&partnerID=8YFLogxK
U2 - 10.1109/ACCESS.2020.2995973
DO - 10.1109/ACCESS.2020.2995973
M3 - Journal article
AN - SCOPUS:85086064844
SN - 2169-3536
VL - 8
SP - 96271
EP - 96283
JO - IEEE Access
JF - IEEE Access
M1 - 9097196
ER -