Analyzing the impact of elasticity on the profit of cloud computing providers

Bag-of-tasks (BoT) is an important class of scientific applications. These applications are typically comprised of a very large number of tasks that can be executed in parallel in an independent way. Due to its cost associativity property, a public cloud computing environment is, theoretically, the ideal platform to execute BoT applications, since it could allow them to be executed as fast as possible, yet without implying any extra costs for the rapid turnaround achieved. Unfortunately, current public cloud computing providers impose strict limits on the amount of resources that a single user can simultaneously acquire, substantially increasing the response time of large BoT applications. In this paper we analyze the reasons why traditional providers need to impose such a limit. We show that increases in the limit imposed have a severe impact on the profit achieved by providers. This leads to the conclusion that new approaches to deploy cloud computing services are required to properly serve BoT applications.

► We propose a simplified model for the profit achieved by an IaaS provider.
► We analyze how the clients’ demand distribution impacts the provider’s profitability.
► Clients with eventual and intense demand increase the provider’s idleness, reducing profitability.
► Providers limit the amount of service offered per client to ease capacity planning.
► Narrowed elasticity prevents applications from fully exploiting cost associativity.