摘要
Efficient data management is a key issue for environments distributed on a large scale such as the data cloud. This can be taken into account by replicating the data. The replication of data reduces the time of service and the delay in availability, increases the availability, and optimizes the distribution of load in the system. It is worth mentioning, however, that with the replication of data, the use of resources and energy increases due to the storing of copies of the data. We suggest a replication manager that decreases the cost of using resources, energy, and the delay in the system, and also increases the availability of the system. To reach this aim, the suggested replication manager, called the locality replication manager （LRM）, works by using two important algorithms that use the physical adjacency feature of blocks. In addition, a set of simulations are reported to show that LRM can be a suitable option for distributed systems as it uses less energy and resources, optimizes the distribution of load, and has more availability and less delay.
有效的数据处理是大规模分布式环境(如云数据)中的一个关键性问题,其中需要考虑到数据的复制。数据复制可以减少服务时间和获取数据所需的时间,增加可用性并优化系统负载分布。然而值得一提的是,数据的同样会增加储存数据所需的资源和能源。我们提出了一种可减少资源、能源消耗,减少系统延迟,并增加系统可用性的复制管理器,称为位置复制管理器(Locality replication manager,LRM)。这一管理器采用的两种重要算法利用了数据块之间的物理邻接特性。对LRM进行的一系列模拟结果显示,LRM消耗了较少的资源和能源,优化了系统负载分布,并增加了系统可用性,减少了系统延迟,因此适用对于分布式系统。
