Guaranteed Bang for the Buck: Modeling VDI Applications to Identify Storage Requirements
Autor: | Doug Voigt, Milan Shetti, Hao Wen, David H. C. Du, Shanshan Li |
---|---|
Rok vydání: | 2021 |
Předmět: |
020203 distributed computing
Computer Networks and Communications business.industry Computer science Distributed computing 020206 networking & telecommunications Cloud computing 02 engineering and technology computer.software_genre Virtualization Computer Science Applications Rule of thumb Hardware and Architecture Virtual machine 0202 electrical engineering electronic engineering information engineering Virtual machining business computer Virtual desktop Software Information Systems |
Zdroj: | IEEE Transactions on Cloud Computing. 9:627-640 |
ISSN: | 2372-0018 |
Popis: | In the cloud environment, most services are provided by virtual machines (VMs). Identifying storage requirements of VMs is challenging, but it is essential for good user experiences while optimizing use of storage resources. Determining the storage configuration necessary to support and satisfy VMs first requires an accurate description of the VM configurations, and the problem is further exacerbated by the diversity and special characteristics of the VMs. In this paper, we study Virtual Desktop Infrastructure (VDI), a prevalent and complicated VM application, to identify and characterize storage requirements of VMs and determine how to meet such requirements with minimal storage resources and cost. We first create a model to describe the behavior of VDI, and we collect real VDI traces to populate this model. The model allows us to identify the storage requirements of VDI and determine the potential bottlenecks of a given storage configuration. Based on this information, we can tell what capacity and minimum capability a storage configuration needs in order to support and satisfy given VDI configurations. We show that our model can describe more fine-grained VM behavior varying with time and virtual disk types compared with the rules of thumb currently used in industry. |
Databáze: | OpenAIRE |
Externí odkaz: |