Why specialized disks for composite operations may be unnecessary
ACM SIGARCH Computer Architecture News
Survey and analysis of disk scheduling methods
ACM SIGARCH Computer Architecture News
Hierarchical RAID: Design, performance, reliability, and recovery
Journal of Parallel and Distributed Computing
| Hi-index | 14.98 |
Large-scale erasure-coded storage systems have a serious performance problem due to I/O congestion and disk media access congestion caused by read-modify-write operations involved in small-write operations. All the existing technologies based on the conventional disk can provide very limited performance improvement. This paper presents a new Disk Architecture with Composite Operation (DACO), whose disk media access interface consists of three kinds of operations: READ, WRITE, and Composite Operation (CO). The CO adopts a sector-based pipeline technology to implement block-level data modify operations, and thus, can replace the read-modify-write operations involved in small-write operations. When the DACO is adopted in a large-scale erasure-coded storage system with t fault tolerance, t I/Os and t disk media access operations can be reduced in each small-write operation, respectively. This alleviates both I/O congestion and disk media access congestion in nature, and thus, can remarkably improve the performance of large-scale erasure-coded storage systems. A simulation study shows that the DACO can provide significant performance improvement: reducing the average I/O response time by up to 31.16 percent even in the worst case where t=1. This paper also discusses the important implementation issues of the DACO and investigates the additional cost involved in the DACO.