Automated analysis of performance and energy consumption for cloud applications

Abstract

In cloud environments, IT solutions are delivered to users via shared infrastructure. One consequence of this model is that large cloud data centres consume large amounts of energy and produce significant carbon footprints. A key objective of cloud providers is thus to develop resource provisioning and management solutions at minimum energy consumption while still guaranteeing Service Level Agreements (SLAs). However, a thorough understanding of both system performance and energy consumption patterns in complex cloud systems is imperative to achieve a balance of energy efficiency and acceptable performance. In this paper, we present StressCloud, a performance and energy consumption analysis tool for cloud systems. StressCloud can automatically generate load tests and profile system performance and energy consumption data. Using StressCloud, we have conducted extensive experiments to profile and analyse system performance and energy consumption with different types and mixes of runtime tasks. We collected finegrained energy consumption and performance data with different resource allocation strategies, system configurations and workloads. The experimental results show the correlation coefficients of energy consumption, system resource allocation strategies and workload, as well as the performance of the cloud applications. Our results can be used to guide the design and deployment of cloud applications to balance energy and performance requirements.

Joint‐analysis of performance and energy consumption when enabling cloud elasticity for synchronous HPC applications

“…Feifei et al developed StressCloud, a performance and energy consumption profiling and analysis tool for cloud systems. Using StressCloud, they have conducted extensive experiments to analyze empirically the performance and energy consumption of cloud systems.…”

Scrutiny of Energy Efficiency for Green Cloud Computing

“…Chen et al [14], present StressCloud which can automatically generate load tests and profile system performance and energy consumption data. The demonstration consists of the impact of system resource allocation strategies on system performance and energy consumption by creating heterogeneous VMs in the cloud system.…”

Software engineering for multi-tenancy computing challenges and implications

“…StressCloud [10] is a new performance profiling and energy consumption analysis tool for cloud applications. It supports users to generate cloud application services comprised of data, computing and communication tasks to realize load test and automatically deploy these load test services.…”

“…StressCloud allows these services to take the user requests in order to execute tasks defined in the workload model and send the corresponding responses. For each task, a stochastic form chart is built to describe the detailed user requests and required response from the cloud services [10]. The tasks can be classified as computation-intensive tasks, data-intensive tasks, and communication-intensive tasks and StressCloud can model all of these and mix different task types according to different services: [10] (1) Computation-intensive tasks: It mainly cost CPU and RAM resources, so it can be divided into CPU-intensive tasks and memory-intensive tasks.…”

“…For each task, a stochastic form chart is built to describe the detailed user requests and required response from the cloud services [10]. The tasks can be classified as computation-intensive tasks, data-intensive tasks, and communication-intensive tasks and StressCloud can model all of these and mix different task types according to different services: [10] (1) Computation-intensive tasks: It mainly cost CPU and RAM resources, so it can be divided into CPU-intensive tasks and memory-intensive tasks. (2) Dataintensive tasks: It is local and global I/O bound in common, requires to process large volumes of data, and spend most time on moving and manipulating data in databases and files.…”