International Business Machines Corporation

Eduardo Campos Peiro

Yang Liu

Jason Lee Peipelman

Bruce McNutt

Vernon Walter Miller

Joshua Douglas Martin

A computer-implemented method according to one embodiment includes identifying aggregated customer performance data for a system resource, creating a first system map for the system resource, utilizing the aggregated customer performance data, comparing the first system map to a second system map created for the system resource utilizing calibration data, and adjusting the second system map, based on the comparing.

Storage system performance models based on empirical component utilization

A method for intelligently gathering historical performance information for computing resources is disclosed. In one embodiment, such a method includes sampling, for a computing resource, first performance information at a first frequency. The method retains the first performance information for a first time period. The method further samples, for the computing resource, second performance information at a second frequency that is greater than the first frequency. The method retains the second performance information for a second time period that is shorter than the first time period. In certain embodiments, in response to detecting an event in association with the computing resource, the method takes a snapshot of the second performance information retained for the computing resource at the time of the event. A corresponding system and computer program product are also disclosed.

High-granularity historical performance snapshots

A method for intelligently gathering historical performance information for computing resources is disclosed. In one embodiment, such a method includes determining a set of computing resources for which to gather performance information. The method further designates criteria that is used to divide the computing resources into subsets. For a first subset of computing resources, the method gathers performance information for the first subset at a first frequency. For a second subset of computing resources, the method gathers performance information for the second subset at a second frequency that differs from the first frequency. Computing resources may move between the first and second subsets based on whether they satisfy or do not satisfy the criteria. A corresponding system and computer program product are also disclosed.

Growing community of inventors

Tucson, AZ, United States of America

Eduardo Campos Peiro