@inproceedings{fe3334299f5747b899a663cadca6368b,
title = "Data sharing options for scientific workflows on Amazon EC2",
abstract = "Efficient data management is a key component in achieving good performance for scientific workflows in distributed environments. Workflow applications typically communicate data between tasks using files. When tasks are distributed, these files are either transferred from one computational node to another, or accessed through a shared storage system. In grids and clusters, workflow data is often stored on network and parallel file systems. 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. 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.",
keywords = "Cloud computing, Cost evaluation, Performance evaluation, Scientific workflows",
author = "Gideon Juve and Ewa Deelman and Karan Vahi and Gaurang Mehta and Bruce Berriman and Berman, {Benjamin P.} and Phil Maechling",
year = "2010",
doi = "10.1109/SC.2010.17",
language = "American English",
isbn = "9781424475575",
series = "2010 ACM/IEEE International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2010",
booktitle = "2010 ACM/IEEE International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2010",
note = "2010 ACM/IEEE International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2010 ; Conference date: 13-11-2010 Through 19-11-2010",
}