Loading...
Data placement in heterogeneous storage of short videos
Author(s)
Jaipahkdee, W.
Date Issued
December 1, 2009
Type
Article
Abstract
The overall service performance of I/O intensive system depends mainly on workload on its storage system. In heterogeneous storage environment where storage elements from different vendors with different capacity and performance are put together, workload should be distributed according to storage capability. This paper addresses data placement issue in short video sharing website. Workload contributed by a video is estimated by the number of views and life time span of existing videos in same category. Experiment was conducted on 42,000 video titles in six weeks. Result showed that the proposed algorithm distributed workload and maintained balance better than round robin and random algorithms.
Citation
World Academy of Science Engineering and Technology, 36, 775-779, 2009