Virtualization of Data Centers: Case Study on Server Virtualizationn
2018 (English)Independent thesis Advanced level (degree of Master (One Year)), 20 credits / 30 HE credits
Student thesis
Abstract [en]
Nowadays, Data Centers use Virtualization, as a technique to make use of the opportunity for extension of independent virtual resources from the available physical hardware. Virtualization technique is implemented in the Data Centers to maximize the utilization of physical hardware (which significantly reduces the energy consumption and operating costs) without affecting the “Quality of Service (QoS)”. The main objective of this thesis is to study, the different network topologies used in the Data Center architecture, and to compare the QoS parameters of the virtual server over the physical server and also to abstract the better technology exists for virtualization. The research methodology used in this thesis is “qualitative”. To measure the QoS, we take the Latency, Packet loss, Throughput aspects of virtual servers under different virtualization technologies (KVM, ESXi, Hyper-V, Fusion, and Virtualbox) and compare their performance over the physical server. The work also investigates the CPU, RAM Utilizations and compare the physical and virtual server's behavior under different load conditions. The Results shows us that the virtual servers have performed better in terms of resource utilization, Latency and response times when compared to the physical servers. But there are some factors like backup and recovery, VM Sprawl, capacity planning, building a private cloud, which should be addressed for the growth of virtual data centers. Parameters that affect the performance of the virtual servers are addressed and the trade-off between the virtual and physical servers is established in terms of QoS aspects. The overall performance of virtual servers is effective when compared to the performance of physical servers.
Place, publisher, year, edition, pages
2018. , p. 44
Keywords [en]
Internet, Servers, System Performance, Throughput, Virtualization
National Category
Telecommunications
Identifiers
URN: urn:nbn:se:bth-16010OAI: oai:DiVA.org:bth-16010DiVA, id: diva2:1192518
Subject / course
ET2580 Master's Thesis (120 credits) in Electrical Engineering with emphasis on Telecommunication Systems
Educational program
ETATX Master of Science Programme in Electrical Engineering with emphasis on Telecommunication Systems
Presentation
2018-01-24, J1620, Blekinge Institute of Technology, Campus Grasvik, Karlskrona, 11:15 (English)
Supervisors
Examiners
2018-04-162018-03-222018-04-16Bibliographically approved