*********************************
There is now a CONTENT FREEZE for Mercury while we switch to a new platform. It began on Friday, March 10 at 6pm and will end on Wednesday, March 15 at noon. No new content can be created during this time, but all material in the system as of the beginning of the freeze will be migrated to the new platform, including users and groups. Functionally the new site is identical to the old one. webteam@gatech.edu
*********************************
Monitoring-as-a-Service in the Cloud: Architecture and Algorithms
Shicong Meng
School of Computer Science
Georgia Institute of Technology
Committee:
Dr. Ling Liu (Advisor, School of Computer Science,
Georgia Tech)
Dr. Calton Pu (School of Computer Science, Georgia Tech)
Dr.
Karsten Schwan (School of Computer Science, Georgia Tech)
Dr. Leo Mark (School
of Computer Science, Georgia Tech)
Abstract:
System monitoring is an indispensable capability of cloud computing for both cloud service users and providers. With the massive scale of cloud systems and the complexity of cloud applications, providing efficient and scalable monitoring functionalities to cloud administrators and users remains a grand challenge.
This dissertation research is dedicated to the research and development of a monitoring as a service (MaaS) paradigm. Delivering monitoring as a service in the cloud not only makes monitoring functionalities easily accessible and reduces application maintenance cost, but also provides unique service and workload consolidation opportunities to further enhance the efficiency, scalability, reliability and customizability of state monitoring. We conduct our research by identifying the problems and opportunities in system and application state monitoring domains, developing practical and scalable solutions, and evaluating our solutions by providing experimental and analytical comparison with existing approaches.
Concretely, we present a suite of key functional requirements in MaaS, including instantaneous state monitoring and window-based monitoring, periodic and violation-likelihood based monitoring, single tenant and multi-tenant state monitoring. Furthermore, these monitoring functions should also meet quality-of-service demands on pursuing monitoring accuracy, enhancing monitoring scalability, and improving monitoring effectiveness through consolidation and isolation.
In this dissertation proposal, I will present the MaaS model and my research efforts to date. I will focus on window-based state monitoring protocol and algorithms. I will show that by encapsulating core monitoring functionalities into different service layers and consolidating monitoring workload, we can offer monitoring as a service with convenient customization, better monitoring efficiency and scalability, and higher monitoring reliability.
