Job and data clustering for aggregate use of multiple production cyberinfrastructures

Maheshwari, Ketan; Espinosa, Allan; Wilde, Michael; Zhang, Zhao; Foster, Ian; Callaghan, S.; Maechling, P. J.

doi:10.1145/2286996.2287000

Cited by 6 publications

(1 citation statement)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Swift will then analyze the script and execute tasks based on their dataflow; a task is executed only after any of its dependent tasks finish. Applications encoded as Swift scripts have been shown to execute on multiple computational sites (clusters, clouds, supercomputers) via Swift coasters [13,12,14] mechanism which implements the pilot jobs paradigm. The pilot job paradigm dispatches a pilot task to each of the sites and measures the task completion rate.…”

Section: Swift: Parallel Workflow Scriptingmentioning

confidence: 99%

Workflow performance improvement using model-based scheduling over multiple clusters and clouds

Maheshwari

Jung

Meng

et al. 2016

Future Generation Computer Systems

Self Cite

View full text Add to dashboard Cite

Please cite this article as: K. Maheshwari, E.-S. Jung, J. Meng, V. Morozov, V. Vishwanath, R. Kettimuthu, Workflow performance improvement using model-based scheduling over multiple clusters and clouds, Future Generation Computer Systems (2015), http://dx. AbstractIn recent years, a variety of computational sites and resources have emerged, and users often have access to multiple resources that are distributed. These sites are heterogeneous in nature and performance of different tasks in a workflow varies from one site to another. Additionally, users typically have a limited resource allocation at each site capped by administrative policies. In such cases, judicious scheduling strategy is required in order to map tasks in the workflow to resources so that the workload is balanced among sites and the overhead is minimized in data transfer. Most existing systems either run the entire workflow in a single site or use naïve approaches to distribute the tasks across sites or leave it to the user to optimize the allocation of tasks to distributed resources. This results in a significant loss in productivity. We propose a multi-site workflow scheduling technique that uses performance models to predict the execution time on resources and dynamic probes to identify the achievable network throughput between sites. We evaluate our approach using real world applications using the Swift parallel and distributed execution framework. We use two distinct computational environments-geographically distributed multiple clusters and multiple clouds. We show that our approach improves the resource utilization and reduces execution time when compared to the default schedule.

show abstract

Section: Swift: Parallel Workflow Scriptingmentioning

confidence: 99%