Design and Implementation of a Performance Monitoring Tool for Clustered Streaming Media Server Systems

As Video-on-Demand (VoD) services become popular and clusters are widely-used for delivering streaming media data, it is critical and important to monitor, control and manage servers and various resources. To address this issue, we present a performance monitoring tool used for such cluster-based VoD service systems, which can monitor resources such as CPU utilization, memory usage, disk usage and network bandwidth from time to time on demand. The design of the monitoring tool enables certain flexibility and extensibility to scale up. Monitoring data are encapsulated and stored in different databases for future use. Information will be displayed in the format of charts generated from the graph database, and will be refreshed within specified interval. Experiments based on a prototype system demonstrate that the tool we developed can measure and collect necessary data as needed and then visualize them by certain charts, exhibiting feasibility and good usability.