SRCMap: energy proportional storage using dynamic consolidation
FAST'10 Proceedings of the 8th USENIX conference on File and storage technologies
Data prefetching to reduce energy use by heterogeneous disk arrays in video servers
Proceeding of the 23rd ACM Workshop on Network and Operating Systems Support for Digital Audio and Video
Saving disk energy in video servers by combining caching and prefetching
ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP) - Special issue of best papers of ACM MMSys 2013 and ACM NOSSDAV 2013
Hi-index | 14.98 |
Today's storage system places an imperative demand on energy efficiency. Storage system often places disks into standby mode by stopping them from spinning to conserve energy when load is not high. The major obstacle of this method is by introducing a high spin-up cost introduced by passively waking up the standby disk to service the request. In this paper, we propose a redundancy-based, hierarchical I/O cache architecture called RIMAC to solve the problem. The idea of RIMAC is to enable data on the standby disk(s) to be recovered by accessing two-level I/O cache and/or active disks if needed. In parity-based redundant disk arrays, RIMAC exploits parity redundancy to dynamically XOR-reconstruct data being accessed toward standby disk(s) at both cache and disk levels. By avoiding passive spin-ups, RIMAC can significantly improve both energy efficiency and performance. We evaluated RIMAC by augmenting a validated storage system simulator disksim and tested four real-life server traces including HP's cello99, TPC-D, OLTP and SPC's search engine. Comprehensive results indicate RIMAC is able to reduce energy consumption by up to 18% and simultaneously improve the average response time by up to 34% in a small-scale RAID-5 system compared with threshold-based power management schemes.