Application-Centric Resource Provisioning for Amazon EC2 Spot Instances

Khatua, Sunirmal; Mukherjee, Nandini

doi:10.1007/978-3-642-40047-6_29

Cited by 24 publications

(12 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Khatua and Mukherjee [13] proposed a checkpointing scheme on top of an application-centric resource provisioning framework that increases the execution reliability while reducing the monetary cost significantly. Di et al [22], designed an adaptive algorithm to optimise the impact of checkpointing regarding various costs like checkpointing/restart overhead in the context of cloud computing.…”

Section: Related Workmentioning

confidence: 99%

“…On the other hand, quality of service can be compromised on these instances because the provider can shutdown them when the instance price goes above the user's bid, preempting the applications. Many work present how to handle preemption by using fault tolerant techniques based on VM migration [13]- [15], based on redundancy [16], as well as how to estimate the bid value of spot VMs [17]- [21].…”

mentioning

confidence: 99%

See 1 more Smart Citation

Reducing Costs in Cloud Application Execution Using Redundancy-Based Scheduling

Vieira

Bittencourt

Madeira

2014

2014 IEEE/ACM 7th International Conference on Utility and Cloud Computing

View full text Add to dashboard Cite

Public providers around the world offer computing, storage, and communication services as virtual machines in a pay-per-use model. From the user perspective, it is important to choose providers and charging models to run distributed applications with quality of service at lower costs. In this work, we introduce an innovative strategy to decrease the cost of VM requests scheduling on different public cloud providers. The mechanism is based on redundancy with a mixed utilization of reserved and spot virtual machine (VM) instances, and it allows the balancing between cost and availability. We implemented a QoS-aware architecture that allows the scheduling of applications considering different VM charging models. Then, we propose an integer linear program (ILP) and a heuristic algorithm to compute the QoS-aware scheduling. Experimental results show that the proposed approach computes schedules with smaller costs than alternative approaches.

show abstract

Section: Related Workmentioning

confidence: 99%

mentioning

confidence: 99%

Reducing Costs in Cloud Application Execution Using Redundancy-Based Scheduling

Vieira

Bittencourt

Madeira

2014

2014 IEEE/ACM 7th International Conference on Utility and Cloud Computing

View full text Add to dashboard Cite

show abstract

“…Virtualization Mechanisms. Prior work handles the sudden revocation of spot servers either by checkpointing application state at coarse intervals [22,34,38] or eliminating the use of local storage [15,25]. In some cases, application modifications are necessary to eliminate the use of local storage for storing intermediate state, e.g., MapReduce [15,25].…”

Section: Related Workmentioning

confidence: 99%

SpotCheck

Sharma

Lee

Guo

et al. 2015

Proceedings of the Tenth European Conference on Computer Systems

View full text Add to dashboard Cite

Infrastructure-as-a-Service (IaaS) cloud platforms rent resources, in the form of virtual machines (VMs), under a variety of contract terms that offer different levels of risk and cost. For example, users may acquire VMs in the spot market that are often cheap but entail significant risk, since their price varies over time based on market supply and demand and they may terminate at any time if the price rises too high. Currently, users must manage all the risks associated with using spot servers. As a result, conventional wisdom holds that spot servers are only appropriate for delay-tolerant batch applications. In this paper, we propose a derivative cloud platform, called SpotCheck, that transparently manages the risks associated with using spot servers for users.SpotCheck provides the illusion of an IaaS platform that offers always-available VMs on demand for a cost near that of spot servers, and supports all types of applications, including interactive ones. SpotCheck's design combines the use of nested VMs with live bounded-time migration and novel server pool management policies to maximize availability, while balancing risk and cost. We implement SpotCheck on Amazon's EC2 and show that it i) provides nested VMs to users that are 99.9989% available, ii) achieves nearly 5× cost savings compared to using equivalent types of ondemand VMs, and iii) eliminates any risk of losing VM state.

show abstract

“…In fact in our evaluation we simply assume that bid prices observed so far tend to repeat in the future; however, in situations when our assumption on the future bid prices is not true, we can seamlessly benefit from the alternative methods cited above without the need to change our heuristic. Some different works such as [8,15,27] give tools that encourage the use of spot resources by increasing their reliability in case of outbid using recovery techniques based on checkpointing or replication. In our work we are aware of the system reliability thanks to the use of random environment for representing the possibility to lose spot resources; however, the possibility to use reliability-increasing techniques is also orthogonal to our approach and a combined one may result in additional savings in the total price for renting resources.…”

Section: Related Workmentioning

confidence: 99%

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

Application-Centric Resource Provisioning for Amazon EC2 Spot Instances

Cited by 24 publications

References 16 publications

Reducing Costs in Cloud Application Execution Using Redundancy-Based Scheduling

Reducing Costs in Cloud Application Execution Using Redundancy-Based Scheduling

SpotCheck

OptiSpot: minimizing application deployment cost using spot cloud resources

Contact Info

Product

Resources

About