Title :
Back-Track Routing for Fat-Tree Based Data Center Networks
Author :
Jijun Cao ; Kefei Wang ; Xin Wang
Author_Institution :
Coll. of Comput., Nat. Univ. of Defense Technol., Changsha, China
Abstract :
Fat-tree topology is very popular for constructing interconnect network for data centers. Routing is one of the most important design issues of data center networks. Several routing algorithms have been proposed for fat-tree topology, but they all ignore the fault diagnosis problem. In order to facilitate the diagnosis of link-fault in fat-tree based networks, in this paper we propose the FT-BTR, a back-track routing algorithm for fat-tree which constrains both the routing path from the source processing node to the destination processing node and the routing path from destination processing node to source processing node use the same physical links set. Since the two and three stage fat-trees are the most common used, we further provide a detailed description of FT-BTR2 and FT-BTR3 routing algorithms, respectively. The theoretically analysis results show that the FT-BTR algorithm not only guarantee the back-track characteristic for routing between any two processing nodes, which can directly benefits the link fault diagnosis in interconnection networks, but also is load balanced and free of deadlock.
Keywords :
computer centres; fault diagnosis; resource allocation; telecommunication links; telecommunication network routing; telecommunication network topology; FT-BTR2 routing algorithm; FT-BTR3 routing algorithm; back-track routing; destination processing node; fat-tree based data center network; fat-tree topology; interconnect network; link-fault diagnosis; load balanced; physical links set; routing path; source processing node; Algorithm design and analysis; Classification algorithms; Fault diagnosis; Network topology; Routing; Switches; Topology; back track; deadlock freedom; fat-tree; load balance; routing algorithm;
Conference_Titel :
Cloud Computing Technology and Science (CloudCom), 2013 IEEE 5th International Conference on
Conference_Location :
Bristol
DOI :
10.1109/CloudCom.2013.125