An Advanced Data Redistribution Approach to Accelerate the Scale-Down Process of RAID-6

摘要

Nowadays RAID is widely used with the increasing requirements of the reliability in storage systems and the fast development of cloud computing. Among various levels and implementations of RAID systems, RAID-6 is one of the most significant category with the ability to tolerate concurrent failures of any two disks. However, the scalability of RAID-6 is a big challenge. Although many approaches are proposed to accelerate the scaling process and reduce the overhead, how to efficiently remove disks (refers to scale-down process) from existing array is still an open problem.To address the scalability problem, we propose an Advanced Data Redistribution (ADR) approach. The basic idea of ADR is to reorganize previous stripes in RAID-6 systems to achieve higher scalability. ADR is a stripe-level scheme and can be combined with other approaches as SDM and MDS-Frame. It can minimize the overhead of data migration and parity modification. We have conducted mathematical analysis by comparing ADR to various popular RAID-6 codes. The results show that, compared to typical approach (Round-Robin), ADR decreases more than 52.1% migration I/O operations, saves the migration time by up to 63.5%, and speeds up of the scaling process by up to 1.91.