Anzeige
Erschienen in:
2017 | OriginalPaper | Buchkapitel
The Design and Evaluation of a Heaviness Metric for Cloud Fairness and Correct Virtual Machine Configurations
verfasst von : Patrick Poullie, Burkhard Stiller
Erschienen in: Economics of Grids, Clouds, Systems, and Services
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
Abstract
Fairness problems in data centers have been pointed out frequently over the last years. To enforce fairness in data centers, the application of job/Virtual Machine (VM) scheduling impels the traditional solution. Scheduling determines the order in which VMs/jobs are started. However, it is insufficient to enforce fairness, when jobs/VMs run over long periods and/or their PR utilization is highly fluctuant. Clouds form a special case of data centers in which this can be observed.
To overcome this shortcoming, previous work suggested to enforce fairness by handicapping VMs of heavy users and prioritizing VMs of light users during runtime. The Greediness Metric (GM) was developed and shown to be a well suited heaviness measure for that purpose. This work here defines an allocation to be GM Fair (GMF) if all users have the same greediness and resources are allocated efficiently. GM is refined such that enforcing GMF provides incentives to users to configure virtual resources of their VMs in-line with the VMs’ subsequent resource PR utilization allowing cloud providers to schedule these VMs more efficiently. Finally, this work here proves that GMF provides for the same desirable characteristics as Dominant Resource Fairness, including especially sharing incentive, strategy proofness, envy-freeness, and Pareto-efficiency.