Cost-efficient negotiation over multiple resources with reinforcement learning

Cloud applications can achieve similar performance with diverse multi-resource configurations, allowing cloud service providers to benefit from optimal resource allocation for reducing their operation cost. This paper aims to solve the problem of multi-resource negotiation with considerations of both the service-level agreement (SLA) and the cost efficiency. The performance and resource demand are usually application-dependent, making the optimization problem complicated, especially when the dimension of multi-resource configuration is large. To this end, we use reinforcement learning to solve the optimization problem of multi-resource configuration with simultaneous optimization of the learning efficiency and performance guarantee. The developed prototype named SmartYARN is extended Apache YARN equipped with our learning algorithm which can enable cloud applications to negotiate multiple resources cost-effectively. The extensive evaluations show that SmartYARN performs well in reducing the cost of resource usage while maintaining compliance with the SLA constraints of cloud service simultaneously.

[1]  David M. Brooks,et al.  Accurate and efficient regression modeling for microarchitectural performance and power prediction , 2006, ASPLOS XII.

[2]  Henry Hoffmann,et al.  Minimizing energy under performance constraints on embedded platforms: resource allocation heuristics for homogeneous and single-ISA heterogeneous multi-cores , 2015, SIGBED.

[3]  Sanjay Ghemawat,et al.  MapReduce: Simplified Data Processing on Large Clusters , 2004, OSDI.

[4]  Gürhan Küçük,et al.  Reducing power requirements of instruction scheduling through dynamic allocation of multiple datapath resources , 2001, MICRO.

[5]  Samuel Kounev,et al.  Model-based self-adaptive resource allocation in virtualized environments , 2011, SEAMS '11.

[6]  Le Yi Wang,et al.  VCONF: a reinforcement learning approach to virtual machines auto-configuration , 2009, ICAC '09.

[7]  Srikanth Kandula,et al.  Multi-resource packing for cluster schedulers , 2014, SIGCOMM.

[8]  Mahesan Niranjan,et al.  On-line Q-learning using connectionist systems , 1994 .

[9]  Ulrich Lampe,et al.  Pricing in Infrastructure Clouds - An Analytical and Empirical Examination , 2014, AMCIS.

[10]  Kapil Vaswani,et al.  Construction and use of linear regression models for processor performance analysis , 2006, The Twelfth International Symposium on High-Performance Computer Architecture, 2006..

[11]  Klara Nahrstedt,et al.  A control-based middleware framework for quality-of-service adaptations , 1999, IEEE J. Sel. Areas Commun..

[12]  Sujata Banerjee,et al.  Application-driven bandwidth guarantees in datacenters , 2015, SIGCOMM.

[13]  Imtiaz Ahmad,et al.  Cloud Computing Pricing Models: A Survey , 2013 .

[14]  Jie Huang,et al.  The HiBench benchmark suite: Characterization of the MapReduce-based data analysis , 2010, 2010 IEEE 26th International Conference on Data Engineering Workshops (ICDEW 2010).