A transition-based fault-tolerant routing methodology for infiniband networks

Montañana, José Miguel; Flich, José; Robles, Antonio; López, Pedro; Duato, José

doi:10.1109/ipdps.2004.1303198

Cited by 7 publications

(6 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To this end, we will analyze its fault tolerance degree, the required resources and computation time, and the exhibited performance. Also, we will compare RFTR with other fault tolerant routing methodologies, such as TFTR and SPFTR [2,3], and with respect to the alternative of applying a reconfiguration process, such as the Simple Reconfiguration method [4]. TFTR and SPFTR are fault-tolerant mechanism that statistically provide a limited number of disjoint paths (they are previously computed) to cope with failures.…”

Section: Discussionmentioning

confidence: 99%

“…An alternative [2] proposed for PC clusters consists of providing a certain number of disjoint paths between every source-destination pair. The main drawback of this approach is that the number of possible disjoint paths is bounded by the switch degree and strongly depends on the routing flexibility exhibited by the applied routing scheme.…”

Section: Related Workmentioning

confidence: 99%

“…In this sense, let us assume the previous example but now with several virtual channels in the network. In this situation, an illegal transition (Y → X) could be permitted (it does not lead to deadlock) if a virtual channel transition at the switch where the illegal transition would take place were performed [2,12]. Indeed, a path performing a virtual channel transition can be viewed as two joined subpaths, each one on a different virtual channel or layer.…”

Section: Motivationmentioning

confidence: 99%

See 2 more Smart Citations

Reachability-based fault-tolerant routing

Montañana

Flich

Robles

et al. 2006

12th International Conference on Parallel and Distributed Systems - (ICPADS'06)

Self Cite

View full text Add to dashboard Cite

Currently, clusters of PCs are being used as a costeffective alternative to large parallel computers. In most of them it is critical to keep the system running even in the presence of faults. As the number of nodes increases in these systems, the interconnection network grows accordingly. Along with the increase in components the probability of faults increases dramatically, and thus, fault-tolerance in the system, in general, and in the interconnection network, in particular, plays a key role.An interesting approach to provide fault-tolerance consists of migrating on fly the paths affected by the failure to new fault-free paths.In this paper, we propose a simple and effective faulttolerant routing methodology, referred to as Reachability Based Fault Tolerant Routing (RFTR), that can be applied to any topology. RFTR builds new alternative paths by joining subpaths extracted from the set of already computed paths, thus being time-efficient. In order to avoid deadlocks, RFTR performs, if required, a virtual channel transition on the subpath union.As an example of applicability, in this paper we apply RFTR to InfiniBand. Evaluation results on tori show that RFTR exhibits a low computation cost and does not degrade performance significantly.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Motivationmentioning

confidence: 99%

See 1 more Smart Citation

Reachability-based fault-tolerant routing

Montañana

Flich

Robles

et al. 2006

12th International Conference on Parallel and Distributed Systems - (ICPADS'06)

Self Cite

View full text Add to dashboard Cite

show abstract

“…al [13] presents a faulttolerant routing algorithm for k-ary n-cube networks requiring only three virtual layers, but still the paths with faulty nodes are not optimal. Montañana et al [5] describe an endpoint dynamic fault tolerance algorithm for tori relying on the use of multiple disjoint paths between all node pairs, and show that using two virtual channels is sufficient to guarantee four disjoint paths between all pairs. These paths are, however, not necessarily the shortest paths.…”

Section: Introductionmentioning

confidence: 99%

Fault tolerance with shortest paths in regular and irregular networks

Sem-Jacobsen

Lysne

2008

2008 IEEE International Symposium on Parallel and Distributed Processing

View full text Add to dashboard Cite

Fault tolerance has become an important part of current supercomputers. Local dynamic fault tolerance is the most expedient way of tolerating faults by preconfiguring the network with multiple paths from every node/switch to every destination. In this paper we present a local shortest path dynamic fault-tolerance mechanism inspired by a solution developed for the Internet, that can be applied to any shortest path routing algorithm such as Dimension Ordered Routing, Fat Tree Routing, Layered Shortest Path, etc., and provide a solution for achieving deadlock freedom in the presence of faults. Simulation results show that 1) for fat trees this yields the to this day highest throughput and lowest requirements on virtual layers for dynamic one-fault tolerance, 2) we require in general few layers to achieve deadlock freedom, and 3) for irregular topologies it gives at most a 10 times performance increase compared to FRoots.

show abstract

“…We say that a routing algorithm is fault-tolerant if it is able to persist in delivering messages between all non-faulty nodes in the presence of failures. Many fault-tolerant routing algorithms have been proposed for networks [1,[6][7][8][9][10][11]. The SoftwareBased fault-tolerant routing algorithm [1] is a one of popular routings that widely used in literature for achieving fault-tolerance capability in the networks.…”

Section: Introductionmentioning

confidence: 99%