数据中心网络中,虚拟机在线迁移需要在网络核心链路上完成大量的数据传输,造成虚拟机承载的网络应用及其他应用性能下降。在继承现有相同内存页重传避免方法的基础上,引进带链表的计数型布隆过滤器查找结构,避免了内存页查找的假阳性问题。进一步提出了最大化剪枝算法,实现链表长度的最大化缩减,加速查找匹配过程,完成数据中心网络中机架级的虚拟机快速在线迁移。实验结果表明,该方法比现有方法的数据传输量更低,迁移时间更短,降低了迁移对网络应用性能造成的影响。
In data center networks, virtual machine live migration causes large volume of data transfer on core links of the network, which leads to performance degradation of the baring application and other background services. Based on inheriting the existing memory page de-duplication technique, a new search structure was presented com- posed of a counting Bloom filter with each bucket pointing to a link list, which overcame the problem of false posi- tive of memory page lookup. Furthermore, a pruned algorithm was proposed to reduce the length of each link list and accelerate the lookup as much as possible to accomplish live and fast virtual machine migration in rack level. Expe- riment results show that the proposed method transfers less data on core links, takes less time to finish migration, and decreases the degradation of network applications caused by migration.