Estimating service response time for elastic cloud applications

Khaled Salah, Raouf Boutaba

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

37 Scopus citations

Abstract

This paper presents a Markovian analytical model to estimate service response time for elastic cloud applications. Given the expected application workload, the number of virtual machine (VM) instances, and the capacity of each VM instance, the model can approximate the mean service time. The mean service time is a critical metric to estimate, and contributes to the SLA end-to-end response time experienced by application users. The end-to-end response time is an aggregated delay of the service time in addition to delays incurred at the network nodes and links. Our analytical model focuses on estimating the mean service time; however, the model is sufficiently general and can be extremely useful in studying cloud performance. Equations for key performance measures are derived. These measures include mean response time, throughput, request loss, queueing probability, and CPU utilization. The correctness of the model has been verified using discrete-event simulation.

Original languageBritish English
Title of host publication2012 1st IEEE International Conference on Cloud Networking, CLOUDNET 2012 - Proceedings
Pages12-16
Number of pages5
DOIs
StatePublished - 2012
Event2012 1st IEEE International Conference on Cloud Networking, CLOUDNET 2012 - Paris, France
Duration: 28 Nov 201230 Nov 2012

Publication series

Name2012 1st IEEE International Conference on Cloud Networking, CLOUDNET 2012 - Proceedings

Conference

Conference2012 1st IEEE International Conference on Cloud Networking, CLOUDNET 2012
Country/TerritoryFrance
CityParis
Period28/11/1230/11/12

Keywords

  • Cloud Computing
  • Elastic Applications
  • Performance Modeling and Analysis
  • Queueing Theory
  • Service and Network Delays
  • SLA

Fingerprint

Dive into the research topics of 'Estimating service response time for elastic cloud applications'. Together they form a unique fingerprint.

Cite this