A case for redundant arrays of inexpensive disks (RAID)
SIGMOD '88 Proceedings of the 1988 ACM SIGMOD international conference on Management of data
EVENODD: An Efficient Scheme for Tolerating Double Disk Failures in RAID Architectures
IEEE Transactions on Computers - Special issue on fault-tolerant computing
MDS array codes with independent parity symbols
IEEE Transactions on Information Theory
IEEE Transactions on Information Theory
X-code: MDS array codes with optimal encoding
IEEE Transactions on Information Theory
Low-density MDS codes and factors of complete graphs
IEEE Transactions on Information Theory
FAST'08 Proceedings of the 6th USENIX Conference on File and Storage Technologies
GRID codes: Strip-based erasure codes with high fault tolerance for storage systems
ACM Transactions on Storage (TOS)
A performance evaluation and examination of open-source erasure coding libraries for storage
FAST '09 Proccedings of the 7th conference on File and storage technologies
P-Code: a new RAID-6 code with optimal properties
Proceedings of the 23rd international conference on Supercomputing
Higher reliability redundant disk arrays: Organization, operation, and coding
ACM Transactions on Storage (TOS)
Rotary-code: Efficient MDS array codes for RAID-6 disk arrays
WSEAS Transactions on Computers
FAST'14 Proceedings of the 12th USENIX conference on File and Storage Technologies
| Hi-index | 14.98 |
This paper presents a class of binary Maximum Distance Separable (MDS) array codes for tolerating disk failures in Redundant Arrays of Inexpensive Disks (RAID) architecture based on circular permutation matrices. The size of the information part is m \times n, the size of the parity-check part is m \times 3, and the minimum distance is 4, where n is the number of information disks, the number of parity-check disks is 3, and (m+1) is a prime integer. In practical applications, m can be very large and n is from 20 to 50. The code rate is R = {\frac{n}{n+3}}. These codes can be used for tolerating three disk failures. The encoding and decoding of the Reed-Solomon-like codes are very fast. There need to be 3mn XOR operations for encoding and (3mn+9(m+1)) XOR operations for decoding.