Browse Prior Art Database

Method and System for Enabling Root Cause Data Analysis for Lab Performance Changes

IP.com Disclosure Number: IPCOM000198606D
Publication Date: 2010-Aug-10
Document File: 4 page(s) / 29K

Publishing Venue

The IP.com Prior Art Database

Abstract

A method and system is disclosed for enabling a user to perform root cause data analysis for lab performance changes.

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 28% of the total text.

Page 1 of 4

Method and System for Enabling Root Cause Data Analysis for Lab Performance Changes

Disclosed is a method and system for enabling a user to perform root cause data analysis for lab performance changes.

While performing root cause data analysis, it is necessary to ensure that a particular logical set of lab infrastructure such as specific hosts, ports, and subsystem volumes used for a specific purpose such as real-time video servers meets specific performance criteria.

The method and system disclosed herein provides a user with an ability to specify minimum performance thresholds for logical groups of storage resources. Further it also assists a user to manually analyze performance changes over time against configuration changes and/or events to determine reasons for a performance change. Additionally, it also enables a user to automatically identifying configuration changes and/or events which are likely to be related to a change in the performance of the logical groups.

A user is provided with an option of creating storage resource groups (SRGs). The SRGs includes physical and logical entities such as hosts, ports, subsystems, extent pools, volumes, and disks.

While creating/editing an SRG, the user is provided with an option to specify performance thresholds either manually or via a list of pre-determined generic settings. As not all performance thresholds are applicable to every component in the SRG, therefore, when the user selects a particular performance threshold in the SRG, applicable SRG elements are highlighted in User Interface Display. Accordingly, performance thresholds are set, by user, to be applicable to specific component types. In an embodiment, while the user is setting the performance thresholds, a validation check is performed to ensure that performance meets thresholds currently otherwise, notification are provided stating that monitoring can't be done till SRG performance is in a "good state".

Further, the user is also enabled to create/edit alerts appropriate for the performance thresholds. Subsequently, once the performance thresholds are set, current performance monitors are evaluated to see if any additional monitors are needed to be created and/or started. Further, currently available performance and configuration information are also evaluated to see if the SRG is currently meeting its performance thresholds. If there is not enough data available to analyze or if the performance threshold is not met, the user is notified.

Moving on, as new performance data is retrieved, the data is periodically analyzed against the SRG's performance thresholds. The performance data that is retrieved includes performance information for time X, configuration changes at time X and effective configuration changes at time X, where effective configuration changes

1

Page 2 of 4

represent the point in time where I/O begins to occur over a new configuration change. Accordingly, alerts are generated based on the analysis and re...