Comparison and Performance Analysis of EVENODD and RDP Fault-Tolerant Coding Methods
DOI:
https://doi.org/10.54097/4yvmrv71Keywords:
RDP; EVENODD; fault-tolerant coding.Abstract
Fault-tolerant coding schemes are techniques designed to protect original data from errors and data loss by introducing redundant data. This study compares the performance of two commonly used fault-tolerant coding methods, EVENODD and RDP. These methods are widely employed in data storage to ensure data integrity and fault tolerance. The objective of this research is to determine which method is better suited for specific application scenarios. Through experiments and performance evaluations, this research found that RDP outperforms EVENODD in terms of encoding and decoding, requiring fewer computational resources, especially excelling in encoding and decoding times. EVENODD exhibits better storage and I/O efficiency, typically requiring fewer data disks but demanding more computational resources for encoding and decoding. The choice between EVENODD and RDP should be based on specific application requirements and the balance of performance, storage, and computational resources. Furthermore, this research discusses their respective advantages and disadvantages and proposes future research directions, including hybrid fault-tolerant coding schemes, integration with cryptography, and combining them with artificial intelligence and deep learning technologies. These studies will contribute to enhancing the security, integrity, and reliability of data storage.
Downloads
References
A. Thomasian, G. Fu, and C. Han, “Performance of Two-Disk Failure-Tolerant Disk Arrays,” IEEE Transactions on Computers, vol. 56, no. 6, pp. 799–814, Jun. 2007, doi: 10.1109/TC.2007.1041.
J. Li, P. Li, R. J. Stones, G. Wang, Z. Li, and X. Liu, “Reliability Equations for Cloud Storage Systems with Proactive Fault Tolerance,” IEEE Transactions on Dependable and Secure Computing, vol. 17, no. 4, pp. 782–794, Jul. 2020, doi: 10.1109/TDSC.2018.2882512.
G. Duchrau and M. Gössel, “A New Decoding Method for Double Error Correcting Cross Parity Codes,” in 2022 IEEE 28th International Symposium on On-Line Testing and Robust System Design (IOLTS), Sep. 2022, pp. 1–5. doi: 10.1109/IOLTS56730.2022.9897284.
S. Huang, H. Hou, and X. Yu, “A Lower Bound on Disk Reads for Single Information Disk Failure Recovery and One Recovery Scheme for EVENODD(p, 3),” in 2019 Ninth International Workshop on Signal Design and its Applications in Communications (IWSDA), Oct. 2019, pp. 1–5. doi: 10.1109/IWSDA46143.2019.8966126.
H. Hou and P. P. C. Lee, “A New Construction of EVENODD Codes With Lower Computational Complexity,” IEEE Communications Letters, vol. 22, no. 6, pp. 1120–1123, Jun. 2018, doi: 10.1109/LCOMM.2018.2820007.
H. Hou, Y. S. Han, K. W. Shum, and H. Li, “A Unified Form of EVENODD and RDP Codes and Their Efficient Decoding,” IEEE Transactions on Communications, vol. 66, no. 11, pp. 5053–5066, Nov. 2018, doi: 10.1109/TCOMM.2018.2859956.
“Row-diagonal parity for double disk failure correction | Proceedings of the 3rd USENIX conference on File and storage technologies.” Accessed: Oct. 13, 2023. [Online]. Available: https://dl.acm.org/doi/10.5555/1973374.1973375
M. Blaum, J. Brady, J. Bruck, and J. Menon, “EVENODD: an efficient scheme for tolerating double disk failures in RAID architectures,” IEEE Transactions on Computers, vol. 44, no. 2, pp. 192–202, Feb. 1995, doi: 10.1109/12.364531.
G. Zhang, K. Li, J. Wang, and W. Zheng, “Accelerate RDP RAID-6 Scaling by Reducing Disk I/Os and XOR Operations,” IEEE Transactions on Computers, vol. 64, no. 1, pp. 32–44, Jan. 2015, doi: 10.1109/TC.2013.210.
“Optimal recovery of single disk failure in RDP code storage systems | Proceedings of the ACM SIGMETRICS international conference on Measurement and modeling of computer systems.” Accessed: Oct. 02, 2023. [Online]. Available: http://dl-acm-org-s.libziyuan.bjut.edu.cn:8118/doi/10.1145/1811039.1811054
Downloads
Published
Issue
Section
License
Copyright (c) 2024 Highlights in Science, Engineering and Technology

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.







