Large Scale Monitoring and Online Analysis in a Distributed Virtualized Environment

摘要

Due to increase in number and complexity of the large scale systems, performance monitoring and multidimensional quality of service (QoS) management has become a difficult and error prone task for system administrators. Recently, the trend has been to use virtualization technology, which facilitates hosting of multiple distributed systems with minimum infrastructure cost via sharing of computational and memory resources among multiple instances, and allows dynamic creation of even bigger clusters. An effective monitoring technique should not only be fine grained with respect to the measured variables, but also should be able to provide a high level overview of the distributed systems to the administrator of all variables that can affect the QoS requirements. At the same time, the technique should not add performance burden to the system. Finally, it should be integrated with a control methodology that manages performance of the enterprise system. In this paper, a systematic distributed event based (DEB) performance monitoring approach is presented for distributed systems by measuring system variables (physical/virtual CPU utilization and memory utilization), application variables (application queue size, queue waiting time, and service time), and performance variables (response time, throughput, and power consumption) accurately with minimum latency at a specified rate. Furthermore, we have shown that proposed monitoring approach can be utilized to provide input to an application monitoring utility to understand the underlying performance model of the system for a successful on-line control of the distributed systems for achieving predefined QoS parameters.