Horizontal Partition for Scalable Control in Software-Defined Data Center Networks

Shaojun ZHANG  Julong LAN  Chao QI  Penghao SUN  

Publication
IEICE TRANSACTIONS on Information and Systems   Vol.E101-D   No.6   pp.1691-1693
Publication Date: 2018/06/01
Online ISSN: 1745-1361
DOI: 10.1587/transinf.2017EDL8273
Type of Manuscript: LETTER
Category: Information Network
Keyword: 
software-defined networking,  control plane,  scalability,  load partition,  load balancing,  

Full Text: PDF(1.2MB)
>>Buy this Article


Summary: 
Distributed control plane architecture has been employed in software-defined data center networks to improve the scalability of control plane. However, since the flow space is partitioned by assigning switches to different controllers, the network topology is also partitioned and the rule setup process has to invoke multiple controllers. Besides, the control load balancing based on switch migration is heavyweight. In this paper, we propose a lightweight load partition method which decouples the flow space from the network topology. The flow space is partitioned with hosts rather than switches as carriers, which supports fine-grained and lightweight load balancing. Moreover, the switches are no longer needed to be assigned to different controllers and we keep all of them controlled by each controller, thus each flow request can be processed by exactly one controller in a centralized style. Evaluations show that our scheme reduces rule setup costs and achieves lightweight load balancing.