一种新型瓦记录磁盘的高可靠数据存储方法

近年来，传统磁记录的存储密度增长已经达到极限，为了满足快速增长的数据容量需求，多种新型存储技术不断涌现，其中瓦记录（shingled magnetic recording，SMR）技术已实现商业化，在企业实际应用.由于瓦记录磁盘的叠瓦式结构，磁盘在随机写入时会引起写放大，造成磁盘性能下降.这一问题在部署传统的高可靠存储方案（如RAID5）时会变得更加严重，原因在于校验数据更新频率很高，磁盘内出现大量的随机写请求.研究发现瓦记录内部其实存在具有原位更新能力的“可覆盖写磁道（free track）”，基于“可覆盖写磁道”，提出了一种专门针对瓦记录盘的高可靠数据存储方法——FT-RAID，以替代经典的RAID5方法，实现一种廉价、大容量、高可靠的存储系统.FT-RAID包含两个部分：“可覆盖写磁道映射（FT-mapping）”和“可覆盖写磁道缓冲区（FT-buffer）”.FT-mapping实现了一种瓦记录友好的RAID映射方式，将频繁更新的校验块数据映射至“可覆盖写磁道”；FT-buffer实现了一种瓦记录友好的两层缓冲区结构，上层确保了热数据能够原位更新，下层提高了缓冲区的容量.基于真实企业I/O访问记录的实验结果表明，与传统RAID 5相比，FT-RAID能够减少80.4%的写放大率，显著提高存储系统整体性能.

Highly Reliable Data Storage Method Based on Novel Shingled Magnetic Disks

In recent years, traditional HDDs'' areal density is reaching its limit. To extend the capacity of disk drives, several new storage techniques were proposed, including shingled magnetic recording (SMR), which is the first one to reach market among those new technologies. However, the shingled track structure of SMR disks encounters serious write amplification and performance declining when processing random write requests. Furthermore, constructing RAID5 based on SMR drives worsens the write amplification (WA) because the parity updating of RAID5 is very frequent to produce many random writes. This study, for current SMR disks'' structure, finds that the first track of each band can be overwritten without impacting other tracks, because the wide write head can be moved a bit to cover both the first track and the guard region. In other words, the first track of each band can be called the free track, because it can be overwritten freely without causing any write amplification. Therefore, a new free-track-based RAID system (FT-RAID) is propose based on SMR drives, to fully develop the potentials of the overwriting-free region in SMR disk drives. FT-RAID is consisted of two key techniques, i.e., FT-Mapping and FT-Buffer. FT-Mapping is an SMR-friendly data mapping manner in RAID, which maps the frequently updated parity blocks to the free tracks; FT-Buffer adopts an SMR-friendly two-layer cache structures, in which the upper level can support in-place updating for hot blocks and the lower level can supply higher capacity for the write buffer. Both of them are designed to mitigate the degradation of performance by reducing SMR WA, leading to an 80.4% lower WA ratio than CMR-based RAID5 based on practical enterprise I/O workloads.