Evaluating caching and storage options on the Amazon Web Services Cloud
Authors:
- 1 October 2010
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21521085,p. 17-24
Abstract
With the promise on-demand compute/storage resources, many users are deploying data-intensive scientific applications onto Clouds. To accelerate these applications, the prospect of caching intermediate data using the elastic compute and storage framework has proved promising. To this end, we believe that an in-depth study of cache placement decisions over various Cloud storage options would be highly beneficial to a large class of users. While tangential analyses have been proposed, ours in contrast focuses on cost-performance tradeoffs of maintaining a data cache with various parameters of any Cloud application. We have compared several Amazon Web Service (AWS Cloud) resources as possible cache placements and found that application dependent attributes like unit-data size, total cache size, and persistence, have far reaching implications on the cost of cache sustenance. Moreover, while instance-based caches expectedly yield higher cost, the performance that they afford may outweigh lower cost options.Keywords
This publication has 11 references indexed in Scilit:
- A cost-effective strategy for intermediate data storage in scientific cloud workflow systems2010
- eScience in the cloud: A MODIS satellite data reprojection and reduction pipeline in the Windows Azure platform2010
- Building the Trident Scientific Workflow Workbench for Data Management in the Cloud2009
- Cost-benefit analysis of Cloud Computing versus desktop grids2009
- High-Performance Cloud Computing: A View of Scientific Applications2009
- Hierarchical Caches for Grid Workflows2009
- On the Use of Cloud Computing for Scientific Workflows2008
- Amazon S3 for science grids2008
- BOINC: A System for Public-Resource Computing and Storage2005
- Chord2001