Triple-Parity Vertical Array Codes with Optimal Update Bandwidth and Fast Encoding/Decoding Performance

It is well-known that erasure codes have been widely applied in the distributed storage systems (DSSs). This paper concentrates on the update bandwidth of erasure codes, which is defined as the system network IO consumption required when a node is updated. Based on the OUB-codes [1] and MDS array codes [2], we introduce the array-OUB-codes which are vertical MDS array codes with triple fault tolerant and minimal update bandwidth. In addition, according to our experiments implemented by C++ program, our array-OUB-codes achieve better encoding and decoding performance compared with OUB-codes. Moreover, through the update bandwidth IO test, our array-OUB-codes can increase the average throughput by 37.5% compared with the RS scheme in [3].

Authors

Institutions

Publication Details

Published
2024-12-15
DOI
https://doi.org/10.1109/bigdata62323.2024.10825320
Primary Topic
Advanced Data Storage Technologies
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Triple-Parity Vertical Array Codes with Optimal Update Bandwidth and Fast Encoding/Decoding Performance

Hanxu Hou, Haitao Wu, Jingjie Lv, Lian Xue
Advanced Data Storage Technologies
article

Triple-Parity Vertical Array Codes with Optimal Update Bandwidth and Fast Encoding/Decoding Performance

Hanxu Hou, Haitao Wu, Jingjie Lv, Lian Xue
article en

Abstract

It is well-known that erasure codes have been widely applied in the distributed storage systems (DSSs). This paper concentrates on the update bandwidth of erasure codes, which is defined as the system network IO consumption required when a node is updated. Based on the OUB-codes [1] and MDS array codes [2], we introduce the array-OUB-codes which are vertical MDS array codes with triple fault tolerant and minimal update bandwidth. In addition, according to our experiments implemented by C++ program, our array-OUB-codes achieve better encoding and decoding performance compared with OUB-codes. Moreover, through the update bandwidth IO test, our array-OUB-codes can increase the average throughput by 37.5% compared with the RS scheme in [3].

Intel (United States) (US), Dongguan University of Technology (CN)
National Natural Science Foundation of China, Research and Development
Affordable and clean energy
Openalex Percentile: Top 70%
Advanced Data Storage Technologies
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.