Concurrency control algorithms for deduplicated cloud storage

Deduplication of data is essential to effectively use cloud storage. As the metadata in deduplicated cloud storage are shared across multiple users, concurrent updates may result in inconsistencies. A coarse-grained locking strategy that has been proposed earlier to overcome this difficulty is not suited for inline deduplication owing to poor performance. In the present work, a fine-grained locking strategy that overcomes this shortcoming is proposed. A metadata structure along with a set of concurrent control mechanisms to accomplish this is presented. This strategy is shown to improve the throughput by as much as 60% with only marginal lock overhead.