Dismiss
InnovationQ will be updated on Sunday, Oct. 22, from 10am ET - noon. You may experience brief service interruptions during that time.
Browse Prior Art Database

Modularized Data Mining Method

IP.com Disclosure Number: IPCOM000149785D
Original Publication Date: 2007-Apr-05
Included in the Prior Art Database: 2007-Apr-05
Document File: 1 page(s) / 21K

Publishing Venue

IBM

Abstract

An apparatus is described that permits collection from a running system of the necessary state data to perform Performance Analysis Capacity Planning Problem Detection Problem Diagnosis Workload Characterization

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 100% of the total text.

Page 1 of 1

Modularized Data Mining Method

Described is a program that enables the user to collect state data from the system memory with no dependence on support in data-owning components, no instrumentation inserted into data-owning components, and minimal performance impact on data-owning components.

The program has been implemented for the z/OS operating system.

The program structure consists of a main program, data collection descriptors, and control statements.

Operation is as follows:

Read control statements
1.

Load requested descriptor(s)
2.

Interpret the descriptor(s), that is, collect the desired data
3.

Store output data
4.

Repeat at interval(s) specified in the control statements
5.

 Control Statements

Object Data of Application or System

Job

Data Collection Main Program

Extracted Data File

  Data Collection Descriptors

1