Cost-Optimal Cloud Service Placement under Dynamic Pricing Schemes

Li, Wubin; Svärd, Petter; Tordsson, Johan; Elmroth, Erik

doi:10.1109/ucc.2013.42

Cited by 37 publications

(26 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Previous research on automatically finding optimal deployments of distributed applications on multi-clouds has explored mathematical optimization techniques with main objectives being performance and cost [41][42][43]. QoS-aware deployment and management of applications on cloud infrastructures using workload characterization and system modeling techniques offer another approach to this problem [44].…”

Section: Configuration Management and Deploymentmentioning

confidence: 99%

Design and implementation of a social networking platform for cloud deployment specialists

Magoutis

Papoulas

Papaioannou

et al. 2015

J Internet Serv Appl

View full text Add to dashboard Cite

A new discipline at the intersection of the development and operation of software systems known as DevOps has seen significant growth recently. Among the wide range of tasks of DevOps professionals, we focus on that of selecting appropriate cloud deployments for distributed applications. Despite the advent of automated software deployment and management frameworks, reasoning about good deployments still requires interaction with experts, often through discussions on online technical forums and social networks. Current social networking technologies offer basic ways to communicate. Within the DevOps community, communication on application structure and cloud deployment tradeoffs could become more effective by using knowledge present in global community-sourced information repositories. In this paper we argue for the benefits of tapping into such knowledge and for seamlessly feeding it back into the social networking platform. The social networking platform presented in this paper integrates social networking with automated deployment of applications on multi-clouds and with knowledge drawn from community-sourced information repositories. The implementation leverages two such repositories, the PaaSage repository and Chef Supermarket. Our user evaluation experiments demonstrate the value created for DevOps professionals.

show abstract

Section: Configuration Management and Deploymentmentioning

confidence: 99%

Design and implementation of a social networking platform for cloud deployment specialists

Magoutis

Papoulas

Papaioannou

et al. 2015

J Internet Serv Appl

View full text Add to dashboard Cite

show abstract

“…With respect to existing solutions such as [9,17,29], we want to increase the level of accuracy by using fluid-approximated models based on differential equations to evaluate the system response time. These systems have been shown in [22] to be able to scale well with respect to the system size and to provide information about the distribution of the response times of the overall system in addition to the average.…”

Section: Motivating Examplementioning

confidence: 99%

“…Finally, research on service placement and load allocation has been specialized to take into account spot pricing models and the possibility to lose resources unexpectedly [4,5,9,12,16,17,19,33,34]. With respect to these works we also solve the allocation problem in such a way to minimize the costs while maintaining the desired service level.…”

Section: Related Workmentioning

confidence: 99%

“…This makes the decision of choosing a bid price both difficult and important. While a number of works have considered this problem in recent years [9,17,29,31], the problem of deciding bid prices in light of performance requirements or constraints on the application architecture is more complex and still poorly understood. This paper, which extends [11], aims at helping cloud users to take maximum advantage from spot instances by supporting the following decisions:…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

OptiSpot: minimizing application deployment cost using spot cloud resources

Dubois

Casale

2016

Cluster Comput

View full text Add to dashboard Cite

The spot instance model is a virtual machine pricing scheme in which some resources of cloud providers are offered to the highest bidder. This leads to the formation of a spot price, whose fluctuations can determine customers to be overbid by other users and lose the virtual machine they rented. In this paper we propose OptiSpot, a heuristic to automate application deployment decisions on cloud providers that offer the spot pricing model. In particular, with our approach it is possible to determine: (i) which and how many resources to rent in order to run a cloud application, (ii) how to map the application components to the rented resources, and (iii) what spot price bids to use to minimize the total cost while maintaining an acceptable level of performance. To drive the decision making, our algorithm combines a multi-class queueing network model of the application with a Markov model that describes the stochastic evolution of the spot price and its influence on virtual machine reliability. We show, using a model developed for a real enterprise application and historical traces of the Amazon EC2 spot instance prices, that our heuristic finds low cost solutions that indeed guarantee the required levels of performance. The performance of our heuristic method is compared to that of nonlinear programming and shown to markedly accelerate the finding of low-cost optimal solutions.

show abstract

“…In this scaling model, each microservice can be scaled out by creating new instances which are placed separately according to the associated load, in contrast to monolithic applications. Another strength is the design for failure by strict separation of stateful and stateless services in which the stateless ones can be respawned at any time without having to consider violations of data characteristics such as availability or consistency [5,7]. State is either kept in carefully designed and implemented stateful microservices or in centralized services outside of the application scope which are dynamically bound through service brokers [1].…”

Section: Introductionmentioning

confidence: 99%

Companion Proceedings of the10th International Conference on Utility and Cloud Computing

Anjum

Sill

Fox

et al. 2017

View full text Add to dashboard Cite

One of the most useful features of a microservices architecture is its versatility to scale horizontally. However, not all services scale in or out uniformly. The performance of an application composed of microservices depends largely on a suitable combination of replica count and resource capacity. In practice, this implies limitations to the efficiency of autoscalers which often overscale based on an isolated consideration of single service metrics. Consequently, application providers pay more than necessary despite zero gain in overall performance. Solving this issue requires an application-specific determination of scaling limits due to the general infeasibility of an application-agnostic solution. In this paper, we study microservices scalability, the auto-scaling of containers as microservice implementations and the relation between the number of replicas and the resulting application task performance. We contribute a replica count determination solution with a mathematical approach. Furthermore, we offer a calibration software tool which places scalability boundaries into declarative composition descriptions of applications ready to be consumed by cloud platforms.

show abstract

Cost-Optimal Cloud Service Placement under Dynamic Pricing Schemes

Cited by 37 publications

References 16 publications

Design and implementation of a social networking platform for cloud deployment specialists

Design and implementation of a social networking platform for cloud deployment specialists

OptiSpot: minimizing application deployment cost using spot cloud resources

Companion Proceedings of the10th International Conference on Utility and Cloud Computing

Contact Info

Product

Resources

About