Using Performance Forecasting to Accelerate Elasticity

Cloud computing facilitates dynamic resource provisioning. The automation of resource management, known as elasticity, has been subject to much research. In this context, monitoring of a running service plays a crucial role, and adjustments are made when certain thresholds are crossed. On such occasions, it is common practice to simply add or remove resources. In this paper we investigate how we can predict the performance of a service to dynamically adjust allocated resources based on predictions. In other words, instead of “repairing” because a threshold has been crossed, we attempt to stay ahead and allocate an optimized amount of resources in advance. To do so, we need to have accurate predictive models that are based on workloads. We present our approach, based on the Universal Scalability Law, and discuss initial experiments.

[1]  Jean-Marc Vincent,et al.  Performance characterization of black boxes with self-controlled load injection for simulation-based sizing , 2008 .

[2]  Ivan Porres,et al.  Towards Automatic Performance and Scalability Testing of Rich Internet Applications in the Cloud , 2011, 2011 37th EUROMICRO Conference on Software Engineering and Advanced Applications.

[3]  Du Wan Cheun,et al.  A Quality Model for Evaluating Software-as-a-Service in Cloud Computing , 2009, 2009 Seventh ACIS International Conference on Software Engineering Research, Management and Applications.

[4]  C. Murray Woodside,et al.  Evaluating the scalability of distributed systems , 1998, Proceedings of the Thirty-First Hawaii International Conference on System Sciences.

[5]  C Chapman,et al.  Elastic service definition in computational clouds , 2010, 2010 IEEE/IFIP Network Operations and Management Symposium Workshops.

[6]  Vipin Kumar,et al.  Isoefficiency: measuring the scalability of parallel algorithms and architectures , 1993, IEEE Parallel & Distributed Technology: Systems & Applications.

[7]  David Bermbach,et al.  A Runtime Quality Measurement Framework for Cloud Database Service Systems , 2012, 2012 Eighth International Conference on the Quality of Information and Communications Technology.

[8]  Fabio Kon,et al.  Patterns for testing distributed systems interaction , 2014 .

[9]  Wei-Tek Tsai,et al.  SaaS performance and scalability evaluation in clouds , 2011, Proceedings of 2011 IEEE 6th International Symposium on Service Oriented System (SOSE).

[10]  A. Galis,et al.  Elastic Service Management in Computational Clouds , 2010 .

[11]  Guillaume Pierre,et al.  Resource Provisioning of Web Applications in Heterogeneous Clouds , 2011, WebApps.

[12]  Zhenhuan Gong,et al.  PRESS: PRedictive Elastic ReSource Scaling for cloud systems , 2010, 2010 International Conference on Network and Service Management.

[13]  Jean-Marc Vincent,et al.  Self-scalable Benchmarking as a Service with Automatic Saturation Detection , 2013, Middleware.

[14]  Stephen A. Jarvis,et al.  An investigation into the application of different performance prediction techniques to e-Commerce applications , 2004, 18th International Parallel and Distributed Processing Symposium, 2004. Proceedings..

[15]  Virgílio A. F. Almeida,et al.  Capacity Planning: an Essential Tool for Managing Web Services , 2002 .

[16]  Xian-He Sun,et al.  STAS: A Scalability Testing and Analysis System , 2006, 2006 IEEE International Conference on Cluster Computing.

[17]  Asser N. Tantawi,et al.  An analytical model for multi-tier internet services and its applications , 2005, SIGMETRICS '05.

[18]  Fabio Kon,et al.  Automated scalability testing of software as a service , 2013, 2013 8th International Workshop on Automation of Software Test (AST).

[19]  Paola Inverardi,et al.  Model-based performance prediction in software development: a survey , 2004, IEEE Transactions on Software Engineering.

[20]  Neil J. Gunther,et al.  A General Theory of Computational Scalability Based on Rational Functions , 2008, ArXiv.

[21]  Irfan-Ullah Awan,et al.  Modeling and Performance Analysis of Scalable Web Servers Deployed on the Cloud , 2013, 2013 Eighth International Conference on Broadband and Wireless Computing, Communication and Applications.

[22]  Bruno Dillenseger,et al.  Introducing Queuing Network-Based Performance Awareness in Autonomic Systems , 2010, 2010 Sixth International Conference on Autonomic and Autonomous Systems.

[23]  Jean-Marc Vincent,et al.  Model-Based Performance Anticipation in Multi-tier Autonomic Systems: Methodology and Experiments , 2010 .

[24]  Ricardo Bianchini,et al.  DejaVu: accelerating resource allocation in virtualized environments , 2012, ASPLOS XVII.

[25]  Neil J. Gunther.  A Simple Capacity Model of Massively Parallel Transaction Systems , 1993, Int. CMG Conference.

[26]  Guillaume Pierre,et al.  Autonomous resource provisioning for multi-service web applications , 2010, WWW '10.

[27]  Jeffrey S. Chase,et al.  Automated control in cloud computing: challenges and opportunities , 2009, ACDC '09.

[28]  Jens Happe,et al.  Statistical Inference of Software Performance Models for Parametric Performance Completions , 2010, QoSA.

[29]  D. Janaki Ram,et al.  A model for characterizing the scalability of distributed systems , 2005, OPSR.

[30]  C. Murray Woodside,et al.  Using regression splines for software performance analysis , 2000, WOSP '00.

[31]  Xian-He Sun,et al.  Reevaluating Amdahl's law in the multicore era , 2010, J. Parallel Distributed Comput..