摘要:The replication of the non-structure data from one data center to another is an urgent task in HBase. The paper studies the priority growth probability of the priority replication queue and proposed a dynamic priority replication task queue algorithm based on the earliest deadline first algorithm (EDF). The experiment results show that the proposed algorithm can balance the replication overhead between the high and low priority tasks and avoid the low priority task starving to death as well as ensure the high priority task’s interests.
关键词:non-structure data;HBsase;replication queue;earliest deadline first algorithm (EDF)