Concerning the problem that the data in distributed system usually has many replicas among several datacenters and a robust mechanism was required to maintain data consistency, an algorithm of geographically distributed replication management was proposed after further research on the replication theory of distributed systems. Microsoft Research used Service Level Agreements (SLA) to divide the consistency requirements of users into several levels, each of which was associated with tolerable delay. The system ensured that users could have higher service levels within tolerable delay. Tuba system extends Pileus, it can dynamically change the location of primary and secondary replicas according to statistics sent by all users, so as to raise the average performance of the system. But the replication of Tuba system was carried out based on a single target unit. Improving the method in Tuba system, a set of algorithms independently to change the location of primary and secondary replicas was proposed. The mechanism was implemented in the replication among the HBase distributed systems. After the system is completed, the results show that taking the correlation between two regions into consideration when changing the location of primary and secondary replicas can improve the overall utility of the system.