An optimal and dynamic monitoring interval for grid resource information system

Grid technology uses geographically distributed resources from multiple domains. For that reason, resource monitoring services or tools will run on various kinds of systems to find static resource information and dynamic resource information, such as architecture vendor, OS name and version, MIPS rate, memory size, CPU capacity, disk size, NIC information, CPU usage, network usage (bandwidth, latency), and memory usage, etes. Thus monitoring itself may cause the system overhead. This paper proposes the optimal monitoring interval to reduce the cost of monitoring services and the dynamic monitoring interval to measure the monitoring events accurately. By simulating and implementing those two factors, we find out that unnecessary system overhead is significantly reduced and accuracy of events is satisfied.