An Evaluation of the Cost and Performance of Scientific Workflows on Amazon EC2
Abstract
Workflows are used to orchestrate data-intensive applications in many different scientific domains. Workflow applications typically communicate data between processing steps using intermediate files. When tasks are distributed, these files are either transferred from one computational node to another, or accessed through a shared storage system. As a result, the efficient management of data is a key factor in achieving good performance for workflow applications in distributed environments. In this paper we investigate some of the ways in which data can be managed for workflows in the cloud. We ran experiments using three typical workflow applications on Amazon's EC2 cloud computing platform. We discuss the various storage and file systems we used, describe the issues and problems we encountered deploying them on EC2, and analyze the resulting performance and cost of the workflows.
Additional Information
© 2012 Springer Science+Business Media B.V. Received: 15 August 2011; Accepted: 1 March 2012; Published online: 18 March 2012. This work was supported by the National Science Foundation under the IntelData (IIS-0905032) and Pegasus (OCI-0722019) grants. This research made use of Montage, funded by the National Aeronautics and Space Administration's Earth Science Technology Office, Computation Technologies Project, under Cooperative Agreement Number NCC5-626 between NASA and the California Institute of Technology.Additional details
- Eprint ID
- 31438
- Resolver ID
- CaltechAUTHORS:20120511-131415294
- IIS-0905032
- NSF
- OCI-0722019
- NSF
- NCC5-626
- NASA
- Created
-
2012-05-14Created from EPrint's datestamp field
- Updated
-
2021-11-09Created from EPrint's last_modified field
- Caltech groups
- Infrared Processing and Analysis Center (IPAC)