RAID: Redundant Array of Inexpensive Disks

962 Words2 Pages

The term RAID was coined in 1987 as an acronym for Redundant Array of Inexpensive Disks; a computer storage technology that was first described by researchers David Patterson, Garth Gibson and Randy Katz at the University of California, Berkley. The concept proposed that an increase in I/O performance and storage reliability could be obtained by arranging several low-cost disk drives into arrays. Several different schemes of organizing the data across the array emerged and were described by the word RAID followed by a single number. Each of these RAID levels has associated advantages and disadvantages however they all share the same primary characteristic in which the data is distributed across multiple disks and seen by the host computer as a single disk. There are three key concepts in RAID technology; mirroring, which writes the same data to more than one disk; stripping, which splits the data across more than one disk; and error correction, where redundant or ‘parity’ data is stored to allow errors in the array to be detected and fixed. Each of the individual RAID levels implements one or more of these concepts to increased I/O performance and improved data reliability. However, it is difficult for researches to design a RAID level that will meet all three and therefore there are tradeoffs when selecting a level for your RAID array. Each of the standard RAID schemes can have positive and negative affects on the reliability and performance of the array; mirroring, can speed up the reading of data but will be slow to write data since the data must be written to the entire mirrored disks. RAID 0 stripes the data across multiple disks without parity or mirroring; resulting in improved read/write performance and space efficiency... ... middle of paper ... ...tripe units can be read simultaneously; however, the write performance takes a hit as the parity stripe has to be recalculated when new data is written. RAID 5 is mainly used for applications requiring decent data redundancy and very good read performance such as the data drives of highly available server systems. RAID 6 expands on the strengths of RAID 5 by striping the data across multiple disks with dual distributed parity; resulting in excellent fault tolerance and data availability. Traditionally a single parity RAID array is vulnerable to data loss until the failed drive is replaced and the array is rebuilt. By making use of dual distributed parity stripe units RAID 6 is able to survive dual drive failures. Due to its similarity to RAID 5, RAID 6 is used in similar applications but where an extra level of data redundancy and fault tolerance is required.

More about RAID: Redundant Array of Inexpensive Disks

Open Document