Exploiting locality in distributed SDN control
Exploiting locality in distributed SDN control
复制标题
DOI：
10.1145/2491185.2491198
复制
发表时间：
2013-08
期刊：
影响因子：
--
通讯作者：
S. Schmid;J. Suomela
中科院分区：
文献类型：
--
作者：
S. Schmid;J. Suomela
大型SDN网络将被划分为多个控制器域；每个控制器负责一个域，相邻域的控制器可能需要进行通信以执行全局策略。本文研究了控制器本地网络视图的含义。特别是，我们建立了与本地算法和分布式计算领域的联系，并讨论了分布式控制平面设计的经验教训。我们表明，现有的本地算法可用于开发有效的协调协议，其中每个控制器只需要响应在其本地邻居中发生的事件。然而，虽然可以使用现有算法，但 SDN 网络还提出了一种研究分布式计算局部性的新方法。我们引入所谓的分布式计算的支持局部性模型。新模型比分布式算法设计和分析中常用的经典模型更具表现力，并且更符合SDN网络的特点。
Large SDN networks will be partitioned in multiple controller domains; each controller is responsible for one domain, and the controllers of adjacent domains may need to communicate to enforce global policies. This paper studies the implications of the local network view of the controllers. In particular, we establish a connection to the field of local algorithms and distributed computing, and discuss lessons for the design of a distributed control plane. We show that existing local algorithms can be used to develop efficient coordination protocols in which each controller only needs to respond to events that take place in its local neighborhood. However, while existing algorithms can be used, SDN networks also suggest a new approach to the study of locality in distributed computing. We introduce the so-called supported locality model of distributed computing. The new model is more expressive than the classical models that are commonly used in the design and analysis of distributed algorithms, and it is a better match with the features of SDN networks.