基于事务的分布式虚拟化环境下服务替换方法

Service Substitution Method in Distributed Virtualized Environment Based on Transaction

分布式虚拟化环境的动态性与异构性,随时会导致运行在其上的服务组合中出现失效等情况,从而导致整个业务流程中断,极大影响整个系统的可信性.作为应对服务失效最常用的方法,现有的服务替换方法由于缺少事务支持,会导致替换后的服务组合的一致性与正确性缺乏保障.对此,以服务组合事务级属性为核心,提出一种基于事务补偿的分布式虚拟化环境下服务替换方法.首先,提出了一个支持事务级属性的层次化服务组合模型,然后根据服务间数据依赖关系来识别服务事务粒度,最后基于事务粒度识别与服务补偿机制,提出了一种服务组合失效处理方法,促使服务组合的可信性增强演化.实验结果证明,该方法保证了替换过程中服务组合的事务原子性和数据一致性,具有良好的扩展性.

The dynamic and heterogeneous characteristics of distributed virtualized environment can lead to the failure or error of the service composition running in the distributed virtualized environment.It can result in the disruption of the entire business process,which greatly affects the dependability of the whole software system.As the most commonly used method to cope with the service failure,the existing service substitution methods can cause that the consistency and correctness of the service composition after the substitution is destroyed due to the lack of transaction support.In this paper,we propose a service substitution method in distributed virtualized environment based on transaction compensation.The method we proposed is based on the service composition transactional attributes.Firstly,a hierarchical service composition model which supports transaction attributes is proposed.Then the scope of the service transaction is identified according to the service data dependencies.Finally,based on transaction scope identification and service compensation mechanism,we propose a service failure processing method to promote the dependability of the service composition enhanced evolution.The experimental results show that the proposed method can ensure the atomic and data consistency of the transaction in service composition,and has good scalability that can achieve good service substitution.