Implementing Replica Placements: Feasibility and Cost Minimization

Given two replication schemes X^old and X^new, the replica transfer scheduling problem (RTSP) aims at reaching X^new, starting from X^old, with minimal implementation cost. In this paper we generalize the problem description to include special cases, where deadlocks can occur while in the process of implementing X^new. We address this impediment by introducing artificial (dummy) transfers. We then prove that RTSP-decision is NP-complete and propose two kinds of heuristics. The first attempts to replace dummy transfers with valid ones, while the second minimizes the implementation cost. Experimental evaluation of the algorithms illustrates the merits of our approach.