Evaluation of Applied Intra-disk Redundancy Schemes to Improve Single Disk Reliability

Exponentially growing capacities of disk drives have increased the problem that not only a complete disk can fail, but also individual, small groups of sectors can be erroneous. These sector errors are especially critical during RAID rebuilds because they can only be detected when the corresponding sectors are read. Mechanisms to cope with sector errors, therefore, have become an important way to improve disk reliability. One approach to deal with sector errors is the introduction of intra-disk redundancy, where additional redundancy blocks are calculated and stored for each set of disk sectors. Previous studies have introduced intra-disk redundancy schemes and have evaluated their impact on disk reliability. None of these studies has evaluated the influence on disk drive performance or the underlying energy consumption. The study presented in this paper benchmarks existing schemes concerning these metrics. It shows the surprising result that weaker codes combined with newly introduced scrambling techniques can produce faster layouts with similar reliability properties than previously proposed strong codes.