Live Instance Migration with Data Consistency in Composite Service Evolution

Composite service evolution is one of the most important challenges to deal with in the field of service composition. And how to migrate live instances to the evolved definition is a critical issue for correct service evolution. However, most of current instance migration approaches only consider control flow problem while ignoring data flow correctness during migration. In particular, this paper presents a data consistent approach to instance migration. We first propose a data dependence graph model to represent the data flow information in a composite service. Then, we propose a set of compliance criteria which relax the traditional compliance notion in instance migration through analyzing the data flow of the composite service. In this way, the number of migratable instances is increased, reducing the cost of redoing the case or service compensation. Finally, we design the DCIM algorithm to implement the data consistent instance migration, and an extensive set of simulations are performed to evaluate the algorithm.