Efficient techniques for replicated data management

Data replication in distributed systems is considered. Two approaches are developed to partially mitigate the costs associated with replicated data management. The first approach, termed the views protocol, is developed to address the concern of practitioners who reject the quorum protocol since it requires that a read operation be executed on more that one copy. The second approach organizes the copies of data into a logical structure such as a tree, a grid, etc. By using the additional information of the logical structure it is possible to relax the quorum intersection requirements. The two approaches are briefly described, and the possibility of combining them to manage replicated data more efficiently is considered