2010 · 10 citations · 22 references
ComputingComputer EngineeringComputer ScienceFault ToleranceFault-tolerant ComputingFault-tolerant SystemsCluster ArchitectureFault Tolerance DesignNetwork Fault ToleranceReconfigurable System ArchitectureReconfiguration StrategiesRoutingCluster ReconfigurationFault-tolerant NetworkingFault-tolerant NetworksFault-tolerant ReconfigurationInfinibandNetwork ReconfigurationTopology-adaptive RoutingTopology-aware Routing
Rerouting around faulty components and migration of jobs both require reconfiguration of data structures in the Queue Pairs residing in the hosts on an InfiniBand cluster. In this paper we report an implementation of dynamic reconfiguration of such host side data-structures. Our implementation preserves the Queue Pairs, and lets the application run without being interrupted. With this implementation, we demonstrate a complete solution to fault tolerance in an InfiniBand network, where dynamic network reconfiguration to a topology-agnostic routing function is used to avoid malfunctioning components. This solution is in principle able to let applications run uninterruptedly on the cluster, as long as the topology is physically connected. Through measurements on our test-cluster we show that the increased cost of our method in setup latency is negligible, and that there is only a minor reduction in throughput during reconfiguration.
22
Albert Greenberg, James R. Hamilton, Navendu Jain et al. · 2009 · 2.1K citations
Chuanxiong Guo, Guohan Lu, Dan Li et al. · 2009 · 1.4K citations · Full text
Radhika Niranjan Mysore, Andreas Pamboris, Nathan Farrington et al. · 2009 · 936 citations
Albert Greenberg, James R. Hamilton, Navendu Jain et al. · ACM SIGCOMM Computer Communication Review · 2009 · 695 citations
Chuanxiong Guo, Guohan Lu, Dan Li et al. · ACM SIGCOMM Computer Communication Review · 2009 · 519 citations