Browse Prior Art Database

Resource Measurement Facility Data Interface to Resource Management Facility Data

IP.com Disclosure Number: IPCOM000115563D
Original Publication Date: 1995-May-01
Included in the Prior Art Database: 2005-Mar-30
Document File: 4 page(s) / 124K

Publishing Venue

IBM

Related People

Koenig, D: AUTHOR [+2]

Abstract

Cross-system access to Resource Management Facility (RMF) measurement data residing on different systems in an MVS sysplex (systems complex) is required to provide a single point of control by RMF performance reporters from any point in the sysplex.

This text was extracted from an ASCII text file.
This is the abbreviated version, containing approximately 52% of the total text.

Resource Measurement Facility Data Interface to Resource Management
Facility Data

      Cross-system access to Resource Management Facility (RMF)
measurement data residing on different systems in an MVS sysplex
(systems complex) is required to provide a single point of control by
RMF performance reporters from any point in the sysplex.

      Fast access to RMF measurement data, residing in the remote
system"s RMF Monitor III address space, is required in order to allow
cross-system and/or multi-system reporting within an acceptable
response time.

      Furthermore, the amount of raw RMF measurement data for
real-time reporting does not allow the transmission and storage of a
whole set of measurement data, collected on a larger number of
systems, at the same time.

      RMF measurement data is currently used and intended for future
use by a number of application programs, for example, automation or
workstation reporting applications.  A service is needed that allows
the retrieval of RMF measurement data for the whole MVS sysplex
without the necessity for the application to communicate to each
individual MVS system.

      All the different potential application programs have different
views of the RMF data, i.e. they may want to construct different data
objects from the raw measurement data.  New application programs may
want to construct their own new views of the data without changing
existing interfaces.

      Application programs may want to use the advantage of
distributed, parallel processing when constructing their view of the
data, before the so-created objects are sent to the calling
application.

      Another requirement for the data reduction is that it can be
parameterized by the calling application, that is, dynamically
created parameters are passed to the distributed routine that
performs the data reduction, again, in or...