Chapter 8: Performance Tools for Stand-Alone Systems and Clusters

Chapter 8: Performance Tools for Stand-Alone Systems and Clusters

The Monitor Utility

Monitor, a free utility, is an excellent source for system-wide performance information. It has been part of OpenVMS for many years; if used properly, it should be able to assist you greatly in your efforts to tune performance.

You should develop a Monitor database by setting up regular and continuous monitoring, recording the data to a file. The system-defined logical SYS$EXAMPLES contains three Digital Command Language (DCL) procedures for doing so:


	?	SUBCOM.COM


	?	MONITOR.COM


	?	MONSUM.COM.

The use of these three procedures is clearly described in the Monitor manual, but some editing may be required. In particular, you may wish to add or delete Monitor summary reports in the MONSUM.COM procedure.

If you continuously record Monitor data, you can easily produce summary reports for any given time period on a regular basis. Collecting, reading, and comparing these reports over several weeks or months will give you a very good feel for the normal behavior of your system. As you begin to understand the figures reported, you will be able to detect quickly any anomalies that indicate performance problems, such as a gradually increasing page fault rate or excessive Kernel Mode time. In discussing performance figures in this section, I have assumed that you are looking at summary reports that span entire prime time shifts, for example, instead of an interactive display covering only a matter of minutes.

You can obtain cluster-wide performance information by...

< Previous Excerpt Next Excerpt >

Purchase This Book

High Performance Cluster Configuration System Management

TABLE OF CONTENTS

Chapter 8: Performance Tools for Stand-Alone Systems and Clusters

Contact Preferences

This is embarrasing...

Customize Your GlobalSpec Experience

Select Your Free Newsletters

Industry Newsletters

Select Your Free Product Alerts

This is embarrasing...