Meryn: open, SLA-driven, cloud bursting PaaS

PaaS (Platform as a service) systems are revolutionizing the way modern applications are developed and hosted. Current PaaS offerings provide limited support for managing SLAs (Service Level Agreements) that constrain application quality properties, such as response times. To overcome this limitation, PaaS systems should be capable of dynamically adjusting resource allocations to meet provider objectives. At the same time, PaaS systems should retain their extensibility to host diverse application types. In this paper we propose Meryn, an open, SLA-driven, PaaS system that aims at maximizing the provider profit and providing SLA guarantees to diverse application types. Meryn provides support for cloud bursting and applies a decentralized protocol for selecting resources to run applications. This protocol tries to minimize the cost of running applications without affecting their agreed quality properties. We implemented a prototype of the Meryn system and performed a preliminary evaluation. The results show that the effectiveness of Meryn in optimizing the provider profit is very promising.

[1]  Randy H. Katz,et al.  Mesos: A Platform for Fine-Grained Resource Sharing in the Data Center , 2011, NSDI.

[2]  Dick H. J. Epema,et al.  Cost-driven scheduling of grid workflows using Partial Critical Paths , 2010, 2010 11th IEEE/ACM International Conference on Grid Computing.

[3]  Christine Morin,et al.  Snooze: A Scalable and Autonomic Virtual Machine Management Framework for Private Clouds , 2012, 2012 12th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (ccgrid 2012).

[4]  Calvin J. Ribbens,et al.  Hybrid Computing - Where HPC meets grid and Cloud Computing , 2011, Future Gener. Comput. Syst..

[5]  Guillaume Pierre,et al.  ConPaaS: A Platform for Hosting Elastic Cloud Applications , 2012, IEEE Internet Computing.

[6]  Marija Mikic-Rakic,et al.  A Decentralized Redeployment Algorithm for Improving the Availability of Distributed Systems , 2005, Component Deployment.

[7]  Massoud Pedram,et al.  Multi-dimensional SLA-Based Resource Allocation for Multi-tier Cloud Computing Systems , 2011, 2011 IEEE 4th International Conference on Cloud Computing.

[8]  Rajkumar Buyya,et al.  SLA-Based Resource Allocation for Software as a Service Provider (SaaS) in Cloud Computing Environments , 2011, 2011 11th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing.

[9]  Dejan S. Milojicic,et al.  OpenNebula: A Cloud Management Tool , 2011, IEEE Internet Computing.

[10]  Stefania Costache,et al.  Themis: Economy-based Automatic Resource Scaling for Cloud Systems , 2012, 2012 IEEE 14th International Conference on High Performance Computing and Communication & 2012 IEEE 9th International Conference on Embedded Software and Systems.

[11]  Paul Marshall,et al.  Elastic Site: Using Clouds to Elastically Extend Site Resources , 2010, 2010 10th IEEE/ACM International Conference on Cluster, Cloud and Grid Computing.

[12]  Nikos Parlavantzas,et al.  An Integrated Approach for Specifying and Enforcing SLAs for Cloud Services , 2012, 2012 IEEE Fifth International Conference on Cloud Computing.