Protected Data Objects Replication in Data Grid

Secret distribution and erasure convention based approaches have been used in distributed storage systems to provide the confidentiality, integrity, and availability of critical information. To achieve performance goals in data accesses, these data fragmentation approaches can be combined with dynamic replication. In this paper, we consider data partitioning (both secret distribution and erasure convention) and dynamic replication in data grids, in which security and data access performance are critical issues. More specifically, we investigate the problem of optimal allocation of sensitive data objects that are divided by using secret distribution scheme or erasure convention scheme and/or replicated. The grid topology we consider consists of two layers. In the upper layer, multiple clusters form a network topology that can be represented by a general graph. The topology within each cluster is represented by a tree graph. We decompose the share replica allocation problem into two sub problems: the Optimal Inter cluster Resident Set Problem (OIRSP) that determines which clusters share replicas and the Optimal Intra need cluster Share Allocation Problem (OISAP) that determines the number of share replicas needed in a cluster and their placements. We develop two heuristic algorithms for the two sub problems.