@misc{9774,
  author = {Ernst Gran and Sven-Arne Reinemo and Olav Lysne and Tor Skeie and Eitan Zahavi and Gilad Shainer},
  title = {Exploring the Scope of the InfiniBand Congestion Control Mechanism},
  abstract = {In a lossless interconnection network, network congestion needs to be detected and resolved to ensure high performance and good utilization of network resources at high network load. If no countermeasure is taken, congestion at a node in the network will stimulate the growth of a congestion tree that not only affects contributors to congestion, but also other traffic flows in the network. Left untouched, the congestion tree will block traffic flows, lead to underutilization of network resources and result in a severe drop in network performance. The InfiniBand standard specifies a congestion control (CC) mechanism to detect and resolve congestion before a congestion tree is able to grow and, by that, hamper the network performance. The InfiniBand CC mechanism includes a rich set of parameters that can be tuned in order to achieve effective CC. Even though it has been shown that the CC mechanism, properly tuned, is able to improve both throughput and fairness in an interconnection network, it has been questioned whether the mechanism is fast enough to keep up with dynamic network traffic, and if a given set of parameter values for a topology is robust when it comes to different traffic patterns, or if the parameters need to be tuned depending on the applications in use. In this paper we address both these questions. Using the three-stage fat-tree topology from the Sun Datacenter InfiniBand Switch 648 as a basis, and a simulator tuned against CC capable InfiniBand hardware, we conduct a systematic study of the efficiency of the InfiniBand CC mechanism as the network traffic becomes increasingly more dynamic. Our studies show that the InfiniBand CC, even when using a single set of parameter values, performs very well as the traffic patterns becomes increasingly more dynamic, outperforming a network without CC in all cases. Our results show throughput increases varying from a few percent, to a seventeen-fold increase.},
  year = {2012},
  journal = {2012 IEEE International Symposium on Parallel \& Distributed Processing (IPDPS)},
  pages = {1131-1143},
  publisher = {IEEE Computer Society},
  doi = {10.1109/IPDPS.2012.104},
  editor = {Bob Werner},
}