Scheduling Data-Intensive Workflows onto Storage-Constrained Distributed Resources
Abstract
In this paper we examine the issue of optimizing disk usage and of scheduling large-scale scientific workflows onto distributed resources where the workflows are data- intensive, requiring large amounts of data storage, and where the resources have limited storage resources. Our approach is two-fold: we minimize the amount of space a workflow requires during execution by removing data files at runtime when they are no longer required and we schedule the workflows in a way that assures that the amount of data required and generated by the workflow fits onto the individual resources. For a workflow used by gravitational- wave physicists, we were able to improve the amount of storage required by the workflow by up to 57 %. We also designed an algorithm that can not only find feasible solutions for workflow task assignment to resources in disk- space constrained environments, but can also improve the overall workflow performance.
Additional Information
© 2007 IEEE. This work was supported by the National Science Foundation under the grant CNS 0615412. R. Sakellariou and H. Zhao would like to acknowledge partial support from the EU-funded CoreGrid Network of Excellence (grant FP6-004265) and the UK EPSRC grant GR/S67654/01. The authors thank Duncan Brown for his contributions to the LIGO workflow used to model simulated workflows. The authors also thank the Open Science Grid for resources used to motivate the work presented. The work of K. Blackburn, D. Meyers. and M. Samidi was supported by the National Science Foundation under awards PHY-0107417 and PHY-0326281. The LIGO Observatories were constructed by the California Institute of Technology and Massachusetts Institute of Technology with funding from the National Science Foundation under cooperative agreement PHY-9210038. The LIGO Laboratory operates under cooperative agreement PHY-0107417. This paper has been assigned LIGO Document Number LIGO-P070003-00-Z.Attached Files
Published - 04215405.pdf
Files
| Name | Size | Download all |
|---|---|---|
|
md5:3d8986fd96ecd4e806e0e21996442bce
|
548.7 kB | Preview Download |
Additional details
- Eprint ID
- 76722
- Resolver ID
- CaltechAUTHORS:20170419-154436528
- NSF
- CNS 0615412
- CoreGrid Network of Excellence
- FP6-004265
- Engineering and Physical Sciences Research Council (EPSRC)
- GR/S67654/01
- NSF
- PHY-0107417
- NSF
- PHY-0326281
- NSF
- PHY-9210038
- NSF
- PHY-0107417
- Created
-
2017-04-19Created from EPrint's datestamp field
- Updated
-
2023-10-25Created from EPrint's last_modified field
- Caltech groups
- LIGO
- Other Numbering System Name
- LIGO Document
- Other Numbering System Identifier
- LIGO-P070003-00-Z