Avoiding performance fluctuation in cloud storage

Cloud computing is an elastic computing model whereby users can lease computing and storage resources on demand from a remote infrastructure. Cloud computing is gaining popularity due to its low cost, high reliability and wide availability. However, a serious impediment to its wider deployment is the relative lack of effective data management services. The relatively slow access to persistent data and large variability in cloud storage I/O performance, can significantly degrade the performance of data-intensive applications. This paper addresses the problem of I/O performance fluctuation and proposes an automatic optimization schema for cloud storage called AOSC, which utilizes data chunking, placement, and replication to achieve more stable and predictable performance. Our experimental results based on Amazon Elastic Cloud Computing (EC2) data center show that AOSC can improve the stability and help provide better performance guarantees for cloud computing.