A flexible elastic control plane for private clouds

While public cloud computing platforms have become popular in recent years, private clouds---operated by enterprises for their internal use---have also begun gaining traction. The configuration and continuous tuning of a private cloud to meet user demands is a complex task. While private cloud management frameworks provide a number of flexible configuration options for this purpose, they leave it to the administrator to determine how to best configure and tune the cloud platform for local needs. In this paper, we argue for an adaptive control plane for private clouds that simplifies the tasks of configuring and operating a private cloud such that each control plane service is adaptive to the workload seen due to end-user requests. We present a logistic regression model to automate the provisioning and dynamic reconfiguration of control plane services in a private cloud. We implement our approach for two control plane services---monitoring and messaging---for OpenStack-based private clouds. Our experimental results on a laboratory private cloud testbed and using public cloud workloads demonstrates the ability of our approach to provision and adapt such services from very small to very large private cloud configurations.

[1]  May,et al.  [Wiley Series in Probability and Statistics] Applied Survival Analysis (Regression Modeling of Time-to-Event Data) || Extensions of the Proportional Hazards Model , 2008 .

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

[3]  David Josephsen,et al.  Building a Monitoring Infrastructure with Nagios , 2007 .

[4]  D. McDowall,et al.  Interrupted Time Series Analysis , 1980 .

[5]  Armando Fox,et al.  Ensembles of models for automated diagnosis of system performance problems , 2005, 2005 International Conference on Dependable Systems and Networks (DSN'05).

[6]  Steve Vinoski,et al.  Advanced Message Queuing Protocol , 2006, IEEE Internet Computing.

[7]  Manish Marwah,et al.  Probabilistic performance modeling of virtualized resource allocation , 2010, ICAC '10.

[8]  W. Marsden.  I and J , 2012 .

[9]  Prashant J. Shenoy,et al.  Agile dynamic provisioning of multi-tier Internet applications , 2008, TAAS.

[10]  学 赤沢,et al.  Interrupted Time-series Analysis , 2015 .

[11]  Raghunath Nambiar,et al.  Selected Topics in Performance Evaluation and Benchmarking , 2012, Lecture Notes in Computer Science.

[12]  Christopher Stewart,et al.  Performance modeling and system management for multi-component online services , 2005, NSDI.

[13]  Xiaoyun Zhu,et al.  1000 Islands: Integrated Capacity and Workload Management for the Next Generation Data Center , 2008, 2008 International Conference on Autonomic Computing.

[14]  Qi Zhang,et al.  A Regression-Based Analytic Model for Dynamic Resource Provisioning of Multi-Tier Applications , 2007, Fourth International Conference on Autonomic Computing (ICAC'07).

[15]  R. Yaffee.  Forecast evaluation with Stata United Kingdom Stata Users Group Conference London School of Hygiene and Tropical Medicine , 2010 .

[16]  Lieven Eeckhout,et al.  Performance Evaluation and Benchmarking , 2005 .

[17]  Maarten L. Buis.  Predict and Adjust with Logistic Regression , 2007 .

[18]  Adam Silberstein,et al.  Benchmarking cloud serving systems with YCSB , 2010, SoCC '10.

[19]  Guillaume Pierre,et al.  EC2 Performance Analysis for Resource Provisioning of Service-Oriented Applications , 2009, ICSOC/ServiceWave Workshops.