Measuring Software Systems Scalability for Proactive Data Center Management

Abstract

Abstract. The current trend of increasingly larger Web-based applications makes scalability the key challenge when developing, deploying, and maintaining data centers. At the same time, the migration to the cloud computing paradigm means that each data center hosts an increasingly complex mix of applications, from multiple owners and in constant evolution. Unfortunately, managing such data centers in a cost-effective manner requires that the scalability properties of the hosted workloads to be accurately known, namely, to proactively provision adequate resources and to plan the most economical placement of applications. Obviously, stopping each of them and running a custom benchmark to asses its scalability properties is not an option. In this paper we address this challenge with a tool to measure the software scalability regarding CPU availability, to predict system behavior in face of varying resources and an increasing workload. This tool does not depend on a particular application and relies only on Linux's SystemTap probing infrastructure. We validate the approach first using simulation and then in an actual system. The resulting better prediction of scalability properties should allow improved (self-)management practices.

Systematic scalability assessment for feature oriented multi-tenant services

“…Dayarathna and Suzumura (2013) document their results of comparing the performance of three complex event processing engines via benchmarking. Carvalho and Pereira (2010) document a method to analyze scalability of running systems from the data center viewpoint, by only measuring CPU utilization.…”

Scalability Analysis of the OpenAM Access Control System with the Universal Scalability Law

“…Dayarathna et al [11] document their results of comparing the performance of three complex event processing engines via benchmarking. Carvalho et al [12] document a method to analyze scalability of running systems from the data center viewpoint, by only measuring CPU utilization.…”

AIT: A method for operating system kernel function call graph generation with a virtualization technique

“…The more recent and familiar methods of dynamic function call graph generation focus on the generation of graphs for application programs such as JavaScript programs [10,13], and rely on the use of source code [11], symbol tables [14], a specified compiler, kernel architecture [15][16], etc. However, when applied to the OS kernel, these conditions may not be met.…”