@misc{9632,
  author = {Wei Guay and Sven-Arne Reinemo},
  title = {A Scalable Method for Signalling Dynamic Reconfiguration Events With OpenSM},
  abstract = {Rerouting around faulty components, on-the-fly policy changes, and migration of jobs all require reconfiguration of data structures in the Queue Pairs residing in the hosts on an InfiniBand cluster. In addition to a proper implementation at the host, the subnet manager needs to implement a scalable method for signaling reconfiguration events to the hosts. In this paper we propose and evaluate three different implementations for signalling dynamic reconfiguration events with OpenSM. Through our evaluation we demonstrate a scalable solution for signalling host-side reconfiguration events in an InfiniBand network based on an example where dynamic network reconfiguration combined with a topology-agnostic routing function is used to avoid malfunctioning components. Through measurements on our test-cluster and an analytical study we show that our best proposal reduces reconfiguration latency by more than 90\% and in certain situations eliminates it completely. Furthermore, the processing overhead in the subnet manager is shown to be minimal.},
  year = {2011},
  journal = {11th IEEE/ACM International Symposium on Cluster, Cloud, and Grid Computing (CCGrid 2011)},
  pages = {332-341},
  publisher = {IEEE Computer Society Press},
  isbn = {978-1-4577-0129-0},
  editor = {Rajkumar Buyya},
}