Balancing the use of remote I/O versus staging in distributed environments

Data staging and remote I/O are two most widely used data access methods for distributed applications. Application developers generally chose one over the other intuitively without making any scientific comparison specific to their applications since there is no generic model available that they can use. Our goal is to develop a model and set guidelines for the application developers which will help them to choose the most appropriate data access method for their application. We define the parameters that potentially affect the end-to-end performance of the distributed applications which need to access remote data. We aim to study several widely used and well known applications as well some local projects based on the parameters we define, and will develop performance models for these applications based on our findings. Our ultimate goal is to develop a generic model which can be applied to most data intensive distributed applications to decide the best data access model for those applications.