Method and program of collecting performance data for storage network

Abstract

In a storage network including at least a computer system, at least an external storage and at least a network system for communication of input / output data between the computer system and the external storage, a method of collecting the performance data on the network system and the software operated on the network system, in which the range or degree of data collection is automatically adjusted as required based on the performance data collected.

Description

CROSS-REFERENCES [0001] This is a continuation application of U.S. Ser. No. 10 / 789,472, filed Feb. 24, 2004.BACKGROUND OF THE INVENTION [0002] The present invention relates to a method and a system for collecting the performance data of hardware devices constituting a storage network and the software operated in the hardware devices, or in particular a method and a system for collecting the storage network performance data suitable to a case in which the network is increased in scale to such an extent that the component elements for which the performance data are to be collected are vast in number. [0003] A storage network so configured that a centralized storage is accessed from a plurality of host servers through the network is extending widely as an architecture for a data center to improve the utilization rate and reduce the management cost of the storage ever on the increase in scale. [0004] The performance management software meets this situation by being configured of an agen...

AI Technical Summary

Problems solved by technology

With the extension of the centralized storage based on a storage network, the component elements of the network increased in scale has become vast in number and the correlation between the component elements tends to be complicated more and more.

With a further increase expected in the scale of the network, however, automatic comprehensive collection of the performance data for all the component elements of the network may become considerably difficult in terms of the processing capacity including the storage capacity, computation performance and the communication performance.

This is by reason of the fact that unlike in the conventional architecture in which each application system is independently associated with a corresponding server with a computer processing system and an external storage connected directly to each other, the storage network environment is liable to develop an interference in performance between application systems at a portion shared by the network devices and the storage systems.

The use of this function could limit the amount of the performance data to be collected.

This is a considerably tough job for a storage network environment in which various applications having different tendencies of the performance load are unified and a vast number of component elements affect each other in complicated way.

Also, the manual operation of the user may cause the timing of acquiring crucial information to be lost or a problem, if any, to be detected too late.

Images