基于集群的轻量可扩展TCP容错方法

Cluster computing-based fault tolerance scheme of lightweight and scalable TCP connection

针对现有TCP容错方案在高可用性方面的不足,提出了一个新的容错方案———轻量拷贝的传输控制协议ER-TCP.该方案采用日志管理配合主动复制的方法,可降低通信转发结点的负载;采用高效的同步算法可以减轻多个备份服务器的同步对通信造成的性能损失.与其他TCP容错方案进行性能测试的结果比较表明,ER-TCP对通信造成的性能损失小,在多个备份服务器的情况下ER-TCP仍可保持较高的通信效率.

There being poorer high availability in existing transmission control protocol （TCP）, a novel TCP fault-tolerance scheme, ER-TCP, is proposed. The load of the primary server is alleviated by the combination of logging mechanism with active replication, and the performance penalty from multiple backup servers synchronized is reduced by using a high efficient algorithm. The experimental resuits show that ER-TCP scheme exhibits its better performance than that of other schemes, keeping high communication efficiency with multiple backup servers being used.