Cross-layer multi-cloud real-time application QoS monitoring and benchmarking as-a-service framework

dc.contributor.advisor Rabhi, Prof. Fethi en_US
dc.contributor.advisor Ranjan, Prof. Rajiv en_US Alhamazani, Khalid en_US 2022-03-22T12:07:44Z 2022-03-22T12:07:44Z 2016 en_US
dc.description.abstract Cloud computing provides on-demand access to affordable hardware (e.g., multi-core CPUs, GPUs, disks, and networking equipment) and software (e.g., databases, application servers and data processing frameworks) platforms with features such as elasticity, pay-per-use, low upfront investment and low time to market. This has led to the proliferation of business criti-cal applications that leverage various cloud platforms. Such applications hosted on sin-gle/multiple cloud platforms have diverse characteristics requiring extensive monitoring and benchmarking mechanisms to ensure run-time Quality of Service (QoS) (e.g., latency and throughput). The process of monitoring and benchmarking cloud applications is as yet a criti-cal issue to be further studied and addressed. Current monitoring and benchmarking approaches do not provide a holistic view of per-formance QoS for distributed applications cross cloud layers on multi-cloud environments. Furthermore, current monitoring frameworks are limited to monitoring tasks and do not in-corporate benchmarking abilities. In other words, there is no unified framework that com-bines monitoring and benchmarking functionalities. To gain the ability of both monitoring and benchmarking all under one framework will empower the cloud user to gain more in-depth control and awareness of cloud services. The Thesis identifies and discusses the major research dimensions and design issues relat-ed to developing techniques that can monitor and benchmark an application’s components cross-layers on multi-clouds. Furthermore, the thesis discusses to what extent such research dimensions and design issues are handled by current academic research papers as well as by the existing commercial monitoring tools. Moreover, the Thesis addresses an important research challenge of how to undertake cross-layer cloud monitoring and benchmarking in multi-cloud environments to provide es-sential information for effective cloud applications QoS management. It proposes, develops, implements and validates CLAMBS: Cross-Layer Multi-Cloud Application Monitoring and Benchmarking, as-a-Service Framework. The core contributions made by this thesis are the development of the CLAMBS framework and underlying monitoring and benchmarking tech-niques which are capable of: i) performing QoS monitoring of application components (e.g. ii database, web server, application server, etc.) that may be deployed across multiple cloud platforms (e.g. Amazon EC2, and Microsoft Azure); and ii) giving visibility into the QoS of in-dividual application components, which is not supported by current monitoring and bench-marking frameworks. Experiments are conducted on real-world multi-cloud platforms to em-pirically evaluate the framework and the results validate that CLAMBS can effectively monitor and benchmark applications running cross-layers on multi-clouds. The thesis presents implementation and evaluation details of the proposed CLAMBS framework. It demonstrates the feasibility and scalability of the proposed framework in real-world environments by implementing a proof-of-concept prototype on multi-cloud platforms. Finally, it presents a model for analysing the communication overheads introduced by various components (e.g. agents and manager) of CLAMBS in multi cloud environments. en_US
dc.language English
dc.language.iso EN en_US
dc.publisher UNSW, Sydney en_US
dc.rights CC BY-NC-ND 3.0 en_US
dc.rights.uri en_US
dc.subject.other SLA en_US
dc.subject.other Cloud Computing en_US
dc.subject.other QoS en_US
dc.subject.other Application Monitoring en_US
dc.subject.other Application Benchmarking en_US
dc.title Cross-layer multi-cloud real-time application QoS monitoring and benchmarking as-a-service framework en_US
dc.type Thesis en_US
dcterms.accessRights open access
dcterms.rightsHolder Alhamazani, Khalid
dspace.entity.type Publication en_US
unsw.relation.faculty Engineering
unsw.relation.originalPublicationAffiliation Alhamazani, Khalid, Computer Science & Engineering, Faculty of Engineering, UNSW en_US
unsw.relation.originalPublicationAffiliation Rabhi, Prof. Fethi, School of Computer Science and Engineering, UNSW en_US
unsw.relation.originalPublicationAffiliation Ranjan, Prof. Rajiv, Reader (Associate Professor) in Computing Science, Newcastle University, UK en_US School of Computer Science and Engineering *
unsw.thesis.degreetype PhD Doctorate en_US
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
public version.pdf
7.76 MB
Resource type