Master of Science (MS)
Cloud computing and cloud-based hosting has become embedded in our daily lives. It is imperative for cloud providers to make sure all services used by both enterprises and consumers have high availability and elasticity to prevent any downtime, which impacts negatively for any business. To ensure cloud infrastructures are working reliably, cloud monitoring becomes an essential need for both businesses, the provider and the consumer. This thesis project reports on the need of efficient scalable monitoring, enumerating the necessary types of metrics of interest to be collected. Current understanding of various architectures designed to collect, store and process monitoring data to provide useful insight is surveyed. The pros and cons of each architecture and when such architecture should be used, based on deployment style and strategy, is also reported in the survey. Finally, the essential characteristics of a cloud monitoring system, primarily the features they host to operationalize an efficient monitoring framework, are provided as part of this review. While its apparent that embedded and decentralized architectures are the current favorite in the industry, service-oriented architectures are gaining traction. This project aims to build a light-weight, scalable, embedded monitoring tool which collects metrics at different layers of the cloud stack and aims at achieving correlation in resource-consumption between layers. Future research can be conducted on efficient machine learning models used on the monitoring data to predict resource usage spikes pre-emptively.
Kundu, Shreya, "Hybrid Cloud Workload Monitoring as a Service" (2021). Master's Projects. 978.