System and method for monitoring grid resources based on agents

Abstract

The invention provides a system and a method for monitoring grid resources based on agents. The method comprises the steps that first, sensors collect system resource information of hosts at respective node terminals, and pack and send the collected system resource information to sensor managers based on a predetermined protocol; after receiving the system resource information sent by the sensors in areas under respective jurisdiction, the sensor managers of all the domain agent layers carry out meta-information extraction and classification for the system resource information based on meta-data standards so as to save the information, and at the same time, send the state information of respective areas to an information center server; and finally, the information center server collects the information in all areas, and writes the information into a central database, thereby creating a multi-level monitoring environment based on the agents, and realizing the functions of collection, summarizing, arranging, storing and display for state information of the resource nodes in a 'virtual supermarket' environment.

Description

technical field [0001] The invention relates to the technical field of resource monitoring in grid resource management, in particular to an agent-based grid resource monitoring system and monitoring method. Background technique [0002] Grid computing is to connect and integrate geographically distributed and heterogeneous resources through high-speed Internet to form a virtual high-performance computing environment that is relatively transparent to users. The characteristics of grid resources are: distributed, heterogeneous, dynamic and autonomous. Resource management is the core of grid computing. Its purpose is to shield the heterogeneity and complexity of underlying resources, manage various grid resources scattered in the grid, effectively manage resources, and improve resource utilization. Grid jobs allocate reasonable grid resources to achieve load balancing. [0003] The grid resource monitoring system is responsible for managing the static and dynamic information ...

AI Technical Summary

Problems solved by technology

[0008] However, the above-mentioned monitoring tools have the following disadvantages: (1) Based on the "virtual supermarket" resource sharing and collaborative service platform, all computing tasks are described using XML

The above monitoring tools cannot parse XML documents in the platform

(2) On the "virtual supermarket" platform, the above monitoring tools are difficult to combine with the system's scheduling module and information management model, and thus cannot use the task management function and grid resource information provided by the platform

(3) The resource description protocol adopted by the "virtual supermarket" is incompatible with the one adopted by the above-mentioned monitoring tools

Images