Cost-Effective Spot Instances Provisioning Using Features of Cloud Markets

Cost-Effective Spot Instances Provisioning Using Features of Cloud Markets

Abdullah Alourani, Ajay D. Kshemkalyani
Copyright: © 2022 |Pages: 27
DOI: 10.4018/IJCAC.308276
OnDemand:
(Individual Articles)
Available
$37.50
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

Cloud computing offers a variable-cost payment scheme that allows cloud customers to specify the price they are willing to pay for renting spot instances at much lower costs than fixed payment schemes, and depending on the varying demand from cloud customers, cloud platforms could revoke spot instances at any time. To alleviate the effect of spot instance revocations, applications often employ different fault-tolerance mechanisms to minimize or even eliminate the lost work for each spot instance revocation. However, these fault-tolerance mechanisms incur additional overhead related to application completion time and deployment cost. This article proposes a novel cloud market-based approach for provisioning spot instances using features of cloud markets to reduce the deployment cost and completion time of applications. The simulation results show that the approach reduces the deployment cost and completion time compared to approaches based on fault-tolerance mechanisms.
Article Preview
Top

Introduction

In this section, the authors describe cloud spot markets, discuss different types of fault-tolerance mechanisms, and present our major contributions.

Cloud Spot Markets

Cloud computing offers a variable-cost payment scheme that allows cloud customers to specify the price they are willing to pay for renting spot instances to run their applications at much lower costs than fixed payment schemes, and depending on the varying demand from cloud customers, cloud platforms could revoke spot instances at any time. The price of a spot instance can increase if the demand increases and the number of available instances that can be supported by a finite number of physical resources in a data center of cloud providers decreases. Conversely, the price of this spot instance can decrease if the demand decreases and the number of available instances increases. Therefore, if the customer’s price is greater than the cloud provider’s price that depends on the demand, a spot instance will be provisioned to cloud customers’ applications at the customer’s price. However, when spot instances are already provisioned to cloud customer applications and the cloud provider’s price goes above the customer’s price, the cloud providers will terminate those spot instances within two minutes by sending termination notification signals. As a result, even though cloud customers sometimes rent spot instances at 90% lower prices than on-demand prices (Amazon, 2022), their applications that run on spot instances can be terminated based on price fluctuations that happen frequently; thus, those applications may incur additional overhead related to application completion time and deployment cost from re-executing lost work for each spot instance revocation.

Figure 1.

An overview of a migration mechanism

IJCAC.308276.f01

Complete Article List

Search this Journal:
Reset
Volume 14: 1 Issue (2024)
Volume 13: 1 Issue (2023)
Volume 12: 4 Issues (2022): 2 Released, 2 Forthcoming
Volume 11: 4 Issues (2021)
Volume 10: 4 Issues (2020)
Volume 9: 4 Issues (2019)
Volume 8: 4 Issues (2018)
Volume 7: 4 Issues (2017)
Volume 6: 4 Issues (2016)
Volume 5: 4 Issues (2015)
Volume 4: 4 Issues (2014)
Volume 3: 4 Issues (2013)
Volume 2: 4 Issues (2012)
Volume 1: 4 Issues (2011)
View Complete Journal Contents Listing