State monitoring is a fundamental building block for Cloud services.
The demand for providing state monitoring as services (MaaS) continues to grow and is evidenced by CloudWatch from Amazon EC2, which allows cloud consumers to pay for monitoring a selection of performance metrics with coarse-grained periodical sampling of runtime states. One of the key challenges for wide deployment of MaaS is to provide better balance among a set of critical quality and performance parameters, such as accuracy, cost, scalability and customizability.
This dissertation research is dedicated to innovative research and
development of an elastic framework for providing state monitoring as
a service (MaaS). We analyze limitations of existing techniques, systematically identify the need and the challenges at different layers of a Cloud monitoring service platform, and develop a suite of
distributed monitoring techniques to support for flexible monitoring
infrastructure, cost-effective state monitoring and monitoring-enhanced Cloud management. At the monitoring infrastructure layer, we develop techniques to support multi-tenancy of monitoring services by exploring cost sharing between monitoring tasks and safeguarding monitoring resource usage. To provide elasticity in monitoring, we propose techniques to allow the monitoring infrastructure to self-scale with monitoring demand. At the cost-effective state monitoring layer, we devise several new state monitoring functionalities to meet unique functional requirements in Cloud monitoring. Violation likelihood state monitoring explores the benefits of consolidating monitoring workloads by allowing utility-driven monitoring intensity tuning on individual monitoring tasks and identifying correlations between monitoring tasks. Window based state monitoring leverages distributed windows for the best monitoring accuracy and communication efficiency. Reliable state monitoring is robust to both transient and long-lasting communication issues caused by component failures or cross-VM performance interferences. At the monitoring-enhanced Cloud management layer, we devise a novel technique to learn about the performance characteristics of both Cloud infrastructure and Cloud applications from cumulative performance monitoring data to increase the cloud deployment efficiency.
Identifer | oai:union.ndltd.org:GATECH/oai:smartech.gatech.edu:1853/43634 |
Date | 03 April 2012 |
Creators | Meng, Shicong |
Publisher | Georgia Institute of Technology |
Source Sets | Georgia Tech Electronic Thesis and Dissertation Archive |
Detected Language | English |
Type | Dissertation |
Page generated in 0.0013 seconds