Workstation/PC server farms have become a cost-effective solution for high performance computing. Server farm or server cluster is a collection of computer servers usually maintained by an enterprise to accomplish server needs far beyond the capability of one machine. Server farms often have backup servers, which can take over the function of primary servers in the event of a primary server failure. It is critical and important to monitor, control, and manage servers and various resources. To address this issue, it needs present a performance monitoring tool used for such cluster-based on client server systems, which can monitor resources such as CPU utilization, memory usage, disk utilization and network bandwidth from time to time. The design of the monitoring tool enables certain flexibility and extensibility to scale up. Information of server resource and performance will be displayed in the format of charts, and will be refreshed within specified interval. Experiments based on a prototype system demonstrate that the tool can measure and collect necessary data as needed and then visualize them by certain charts, exhibiting feasibility and good usability.
展开▼
