Scheduling workilow applications in GrADS

Mandal, Anirban; Dasgupta, Anshuman; Kennedy, Ken; Mazina, M.; Koelbel, Charles; Marin, Gabriel; Cooper, Keith D.; Mellor-Crummey, John; Liu, B.; Johnsson, Lennart

doi:10.1109/ccgrid.2004.1336714

Cited by 4 publications

(2 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Duplication heuristic (Park et al, 1997) provides a method for an application to transmit data to succeeding applications creating duplicate applications on the destination compute node or processor. Level based method divides workflows into independent applications levels and then apply the map of applications to resources (Mandal et al, 2005).…”

Section: Related Workmentioning

confidence: 99%

A Data-Aware MultiWorkflow Cluster Scheduler

Acevedo¹,

Hernández²,

Espinosa³

et al. 2016

Proceedings of the 1st International Conference on Complex Information Systems

View full text Add to dashboard Cite

Previous scheduling research work is based on the analysis of the computational time of application workflows. Current use of clusters deals with the execution of multiworkflows that may share applications and input files. In order to reduce the makespan of such multiworkflows adequate data allocation policies should be applied to reduce input data latency. We propose a scheduling strategy for multiworkflows that considers the data location of shared input files in different locations of the storage system of the cluster. For that, we first merge all workflows in a study and evaluate the global design pattern obtained. Then, we apply a classic list scheduling heuristic considering the location of the input files in the storage system to reduce the communication overhead of the applications. We have evaluated our proposal with an initial set of experimental environments showing promising results of up to 20% makespan improvement.

show abstract

Section: Related Workmentioning

confidence: 99%

A Data-Aware MultiWorkflow Cluster Scheduler

Acevedo¹,

Hernández²,

Espinosa³

et al. 2016

Proceedings of the 1st International Conference on Complex Information Systems

View full text Add to dashboard Cite

show abstract

“…Section 3 pp ng ultpleDAG. Sctln 3presents two scheduling in the topic has increased in recent years, partly as a policies which aim to deliver fairness in the schedule result of the emergence of the so-called workflow applications as an important use case in the context of gnd Section 4 te themp Grid Computing; some of those workflow applications can be represented by a DAG [2,10,20]. Grid computing provides an initial motivation for this work too.…”

mentioning

confidence: 99%

Scheduling multiple DAGs onto heterogeneous systems

Zhao

Sakellariou

2006

Proceedings 20th IEEE International Parallel &Amp; Distributed Processing Symposium

View full text Add to dashboard Cite

of the first DAG in the set of multiple DAGs to finish time of the last task of the last DAG in the set of mul-The problem of scheduling a single DAG onto hetero-tiple DAGs), another objective could be to achieve a geneous systems has been studied extensively. In this certain level of Quality of Service for the given DAGs. paper, we focus on the problem of scheduling more than Such a level of Quality of Service could be based on one DAG at the same time onto a set of heterogeneous priorities (for instance, one requirement could be to resources. The aim is not only to optimize the overall complete the execution of one DAG as soon as possimakespan, but also to achieve fairness, defined on the ble) or other constraints. In this paper, we focus on basis of the slowdown that each DAG would experience fairness, which is defined on the basis of the slowdown as a result of competing for resources with other DA Gs.that each DAG would experience (as a result of sharing Two policies particularly focussing to deliver fairness the resources with other DAGs as opposed to having are presented and evaluated along with another four the resources on its own); to achieve fairness, the aim policies that can be used to schedule multiple DAGs.is to make this slowdown equal for all DAGs, yet without affecting the overall makespan of the multiple DAG schedule. The paper describes two policies to schedule

show abstract

A framwork for grid workflow scheduling with resource constraints

Yuan

Ping

2011

2011 International Conference on Consumer Electronics, Communications and Networks (CECNet)

View full text Add to dashboard Cite

Scheduling workilow applications in GrADS

Cited by 4 publications

References 14 publications

A Data-Aware MultiWorkflow Cluster Scheduler

A Data-Aware MultiWorkflow Cluster Scheduler

Scheduling multiple DAGs onto heterogeneous systems

A framwork for grid workflow scheduling with resource constraints

Contact Info

Product

Resources

About