Using active data repair and migration technologies for RAID-based storage systems

Abstract

This paper proposes a new RAID-based system using Active data Repair and Migration technologies called RARM, which detects the status of sector, then allocates reserved space in every disk and arranges to redirect the data in the non-repairable sectors to the reserved space. If we ensure the reliability and utilization of disk, RARM will copy data of the low reliability disk or the number of the bad sectors in the disk exceeding threshold to a new one; it will also copy and redirect popularity data of the medium reliability and high utilization disk to the reserved space in high reliability disk or a new one, these process, as we called data migration can avoid lengthy data reconstruction. It can adjust migration speed to reduce the impact on the front end performance dynamically and prioritize user requests when the system I/O workload is bursting. The overall results indicate that the RARM can improve performance and reliability of the system with little influence.