Openstack scheduler evaluation using design of experiment approach

Cloud computing is a computing model which is essentially characterized by an on-demand and dynamic provisioning of computing resources. In this model, a cloud is a large-scale distributed system which leverages internet and virtualization technologies to provide computing resources as a service. Efficient, flexible and dynamic resource management is among the most challenging research issues in this domain. In this context, we present a study focusing on the dynamic behavior of the scheduling functionality of an Infrastructure-as-a-Service (IaaS) cloud, namely OpenStack Scheduler. We aim, through this study at identifying the limitations of this scheduler and ultimately enabling its extension using enhanced metrics. Towards this end, we present a Design of Experiment (DOE) based approach for the evaluation of the OpenStack Scheduler behavior. In particular, we use the screening type of experiment to identify the factors with significant effects on the responses. In our context, these factors are the amount of memory and the number of CPU cores assigned to virtual machine (VM) and the amount of memory and the number of cores on physical nodes. More specifically, we present a two-level fractional factorial balanced with the resolution IV and four center points experimental design with no replication.

[1]  Jacky W. Keung,et al.  Evaluating Cloud Platform Architecture with the CARE Framework , 2010, 2010 Asia Pacific Software Engineering Conference.

[2]  Swann Perarnau,et al.  KRASH: Reproducible CPU load generation on many-core machines , 2010, 2010 IEEE International Symposium on Parallel & Distributed Processing (IPDPS).

[3]  Antonia Bertolino.  Approaches to testing service-oriented software systems , 2009, QUASOSS '09.

[4]  Nik Bessis,et al.  Towards Inter-cloud Schedulers: A Survey of Meta-scheduling Approaches , 2011, 2011 International Conference on P2P, Parallel, Grid, Cloud and Internet Computing.

[5]  R Core Team,et al.  R: A language and environment for statistical computing. , 2014 .

[6]  Marco Lovera,et al.  Black-box performance models for virtualized web service applications , 2010, WOSP/SIPEW '10.

[7]  Margaret J. Robertson,et al.  Design and Analysis of Experiments , 2006, Handbook of statistics.

[8]  G. Oehlert.  A first course in design and analysis of experiments , 2000 .

[9]  Insup Lee,et al.  An empirical analysis of scheduling techniques for real-time cloud-based data processing , 2011, 2011 IEEE International Conference on Service-Oriented Computing and Applications (SOCA).

[10]  Munyaradzi Felix Murove.  Ubuntu , 2012 .

[11]  El-Ghazali Talbi,et al.  A pareto-based GA for scheduling HPC applications on distributed cloud infrastructures , 2011, 2011 International Conference on High Performance Computing & Simulation.

[12]  Sape J. Mullender,et al.  Predictable cloud computing , 2012, Bell Labs Technical Journal.

[13]  Douglas Thain,et al.  A Comparison and Critique of Eucalyptus, OpenNebula and Nimbus , 2010, 2010 IEEE Second International Conference on Cloud Computing Technology and Science.

[14]  Carlos A. Varela,et al.  Impact of Cloud Computing Virtualization Strategies on Workloads' Performance , 2011, 2011 Fourth IEEE International Conference on Utility and Cloud Computing.

[15]  Chris Rose,et al.  A Break in the Clouds: Towards a Cloud Definition , 2011 .

[16]  James J. Filliben,et al.  Comparing VM-Placement Algorithms for On-Demand Clouds , 2011, CloudCom.

[17]  Mohamed Jmaiel,et al.  A Comparative Study of the Current Cloud Computing Technologies and Offers , 2011, 2011 First International Symposium on Network Cloud Computing and Applications.

[18]  Marin Litoiu,et al.  CloudOpt: Multi-goal optimization of application deployments across a cloud , 2011, 2011 7th International Conference on Network and Service Management.

[19]  Moustafa Ghanem,et al.  Improving Resource Utilisation in the Cloud Environment Using Multivariate Probabilistic Models , 2012, 2012 IEEE Fifth International Conference on Cloud Computing.

[20]  Yannis E. Ioannidis,et al.  Schedule optimization for data processing flows on the cloud , 2011, SIGMOD '11.

[21]  Dario Pompili,et al.  Energy-Aware Application-Centric VM Allocation for HPC Workloads , 2011, 2011 IEEE International Symposium on Parallel and Distributed Processing Workshops and Phd Forum.

[22]  Douglas C. Montgomery,et al.  Response Surface Methodology: Process and Product Optimization Using Designed Experiments , 1995 .

[23]  Fatos Xhafa,et al.  Cloud Virtual Machine Scheduling: Modelling the Cloud Virtual Machine Instantiation , 2012, 2012 Sixth International Conference on Complex, Intelligent, and Software Intensive Systems.

[24]  Eunmi Choi,et al.  A service-oriented taxonomical spectrum, cloudy challenges and opportunities of cloud computing , 2012, Int. J. Commun. Syst..

[25]  E. Michael Maximilien,et al.  Towards a Formal Definition of a Computing Cloud , 2010, 2010 6th World Congress on Services.

[26]  Xue-Jie Zhang,et al.  Comparison of open-source cloud management platforms: OpenStack and OpenNebula , 2012, 2012 9th International Conference on Fuzzy Systems and Knowledge Discovery.

[27]  Geoffrey C. Fox,et al.  Comparison of Multiple Cloud Frameworks , 2012, 2012 IEEE Fifth International Conference on Cloud Computing.

[28]  Waheed Iqbal,et al.  Black-box approach to capacity identification for multi-tier applications hosted on virtualized platforms , 2011, 2011 International Conference on Cloud and Service Computing.

[29]  Tommaso Cucinotta,et al.  The effects of scheduling, workload type and consolidation scenarios on virtual machine performance and their prediction through optimized artificial neural networks , 2011, J. Syst. Softw..

[30]  Christopher J. Nachtsheim,et al.  A Class of Three-Level Designs for Definitive Screening in the Presence of Second-Order Effects , 2011 .