Rerouting Strategies for Networks with Advance Reservations

Burchard, L.-O.; Linnert, Barry; Schneider, Joerg

doi:10.1109/e-science.2005.71

Cited by 17 publications

(9 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Previous work in the field of failure recovery in advance reservation scenarios dealt mainly with architectures that provide fault tolerance [4]. The strategies include remapping [5], rerouting [2], job migration and so on. Burchard [5] discusses the properties of advance reservations with respect to failure recovery and outline a number of strategies applicable in such cases in order to reduce the impact of resource failures and outages.…”

Section: Related Workmentioning

confidence: 99%

“…Underestimations lead to a significantly higher abnormal termination ratio than possible. So in [2], Burchard presents a novel loadbased approach for dealing with link failures in advance reservation environments. The approach does not rely on prediction of the downtime, but instead reroutes flows only based on available information about the network.…”

Section: Related Workmentioning

confidence: 99%

“…Fault recovery from link error has been discussed in [1,2]. Another kind of faults is not as obvious as link error or hardware failure.…”

Section: Introductionmentioning

confidence: 98%

See 2 more Smart Citations

An Overtime-Tolerance Strategy for Advance Reservation

Cui

et al. 2006

2006 Seventh International Conference on Parallel and Distributed Computing, Applications and Technologies (PDCAT'06)

View full text Add to dashboard Cite

In advance reservation environment, failure discovery strategy is very important to keep the normal running of whole system. One job's overtime (exceeding its booked time) may lead to a serious of jobs' abnormal termination in co-allocation environment. So there should be some strategies to solve this problem. In this paper, a novel overtimetolerance strategy is introduced. The strategy can tolerate active job exceeding its booking time and redirect transparently later inactive jobs to other resources. The architecture of implementing our strategy is described in this paper too. Simulation shows our overtime-tolerance strategy can decrease the abnormal termination ratio and improve the system throughput.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

An Overtime-Tolerance Strategy for Advance Reservation

Cui

et al. 2006

2006 Seventh International Conference on Parallel and Distributed Computing, Applications and Technologies (PDCAT'06)

View full text Add to dashboard Cite

show abstract

“…Thus an important challenge when using this platform is ensuring that a task submitted to the platform can finish in a given time. A number of papers present approaches to solving this problem: [5][6][7] present the methods through the prediction of available CPUs, [8][9][10] are through the prediction of available Network, [11][12][13] present through the framework to match the resource and task. Those solutions try to solve the problem from a resource-centric viewpoint.…”

Section: Introductionmentioning

confidence: 99%

Tm-Dg

Shang

Wang

Zhou

et al. 2007

Proceedings of the 2007 Symposium on Component and Framework Technology in High-Performance and Scientific Computing

View full text Add to dashboard Cite

Volatility is the key challenge of the desktop Grid platform and the character of volatility mainly depends on the daily behavior of computer user. In this paper, a trust model (TM-DG) based on Dempster-Shafer's (D-S) theory is presented to predict which node is more reliable according to users' daily behavior based on history information from a desktop Grid platform. In TM-DG, a trustworthy degree of a node is introduced to quantify the node's reliability. Using Dempster's rules of combination, it can be determined from two bodies of independent evidence: 1) percentage of completion of the allocated task, and 2) an active probe by a special test node. Simulations performed on a lightweight desktop Grid platform illustrate that TM-DG can make full use of the most reliable node for a given computation, leading to reductions in the communication overhead, and improvement in the computing power of the platform.

show abstract

“…Link Failure can be recovered by rerouting flows based on the actual load of the network. Once a failure on the network is notified, the affected flows are mapped onto alternative paths using downtime-independent strategy [9]. One job's overtime (exceeding its booked time) may lead to a serious of job's abnormal termination (Process Failure).…”

Section: Fault Tolerance In Advance Reservationsmentioning

confidence: 99%