| In this work, I have shown that current parity-based RAID levels are nearing the end of their usefulness. Further, the widely used parity-based hierarchical RAID levels are not capable of significantly improving reliability over their component parity-based levels without requiring massively increased hardware investment. In response, I have proposed k + m RAID, a family of RAID levels that allow m, the number of parity blocks per stripe, to vary based on the desired reliability of the volume. I have compared its failure rates to those of RAIDs 5 and 6, and RAIDs 1+0, 5+0, and 6+0 with varying numbers of sets.;I have described how GPUs are architecturally well-suited to RAID computations, and have demonstrated the Gibraltar RAID library, a prototype library that performs RAID computations on GPUs. I have provided analyses of the library that show how evolutionary changes to GPU architecture, including the merge of GPUs and CPUs, can change the efficiency of coding operations. I have introduced a new memory layout and dispersal matrix arrangement, improving the efficiency of decoding to match that of encoding.;I have applied the Gibraltar library to Gibraltar RAID, a user space RAID infrastructure that is a proof of concept for GPU-based storage arrays. I have integrated it with the user space component of the Linux iSCSI Target Framework, which provides a block device for benchmarking. I have compared the streaming workload performance of Gibraltar RAID to that of Linux md, demonstrating that Gibraltar RAID has superior RAID 6 performance. Gibraltar RAID's performance through k+5 RAID remains highly competitive to that of Linux md RAID 6. Gibraltar RAID operates at the same speed whether in degraded or normal modes, demonstrating a further advantage over Linux md. |
