Abstract:
Over the last few years, a major change in the IT world has been the consolidation of distributed computing into centralized data centers. As corporations struggle to cut costs in all departments, consolidation and sharing of servers is the key strategy for driving down IT costs. This session will examine how to demonstrate the value of consolidation to the user community. We will discuss how chargeback can drive efficient use of IT resources and provide critical executive information to both IT and organization business units. Consolidation, combined with chargeback, gives IT management the potential for huge payback.

Bio:
Sid Finehirsh is a nationally recognized authority on management applications of IT measurement. He has conducted seminars and spoken on chargeback, capacity planning and IT strategy at major industry conferences, seminars and live webcasts. In addition, Sid is the chairperson of the Management Track for CMG. His published articles and columns have appeared in various journals and conference proceedings including: CMG, SHARE, CFO Executive Conference, IT Financial Management Association, IQPC's Cost Allocation and Chargeback for IT Conference, and SUGI. Sid is the Founder and CEO of the CMX Group, a professional services firm of specialists who bring to each client a unique blend of experience and knowledge in leveraging technology to create business opportunity. Since 1983, CMX has assisted hundreds of Fortune 1000 clients in the areas of IT Accounting and Chargeback, Capacity and Performance Management, and IT Strategy.

The Stork Correlation: Use & Abuse Of Statistics In Performance & Capacity Planning
Denise P. Kalm, BMC Software

Abstract:
Serms like "mean," "standard deviation" and "correlation" are used frequently in our industry, but how many really understand them? And how often are statistics misused, creating confusion and misunderstandings, when their main purpose is to communicate your results more accurately? This paper will include a review of pertinent statistics, how they are derived, and where and when to use them in performance and capacity planning.

Statistics can be fun and increase your decision-making confidence. Now, if we can just get past the terminology and the math...and remember, it is often more art than science. "Statistics is a systematic method for getting the wrong conclusion with 95% confidence."

The Impact of Growth on Virtual Tape Subsystems
William T. Gray, Storage Technology Corporation

Abstract:
Growth impacts all equipment on the data center floor. Virtual tape systems are no exception. In order to properly plan for the future, we must understand the impact of growth and we must know what to measure. In this paper, I look at the three most important elements of virtual tape systems and evaluate the impact of growth on each:
A) Buffer Size: growth effectively reduces the buffer size of virtual tape subsystems. This is manifest in increasing recall rates, lower read-hit-ratios, and smaller residency times.
B) Bandwidth: each VTSS has a finite bandwidth in terms of MB/sec of data transferred.
C) Concurrent real tape drives use. I consider what metrics are important to measure and track and which not.

The Dimensions of Service - Exploring WLM.s Solution Space
Rich Olcott, Schering-Plough Corporation

Abstract:
The behavior of a WLM-managed MVS system is sometimes best understood by looking at the goals rather than the workloads. A WLM goal occupies a space of many dimensions. The system administrator is free to burden the goal with an assortment of workloads, assign it a high or low importance, and set it a target that is somewhere between lenient and stringent. In execution, the goal may be met well or poorly, at a cost that may be cheap or dear. In this paper, we consider WLM.s metrics and present several maps to facilitate navigation through its multi-dimensional space.

Oracle Performance Management on major Operating Systems: WULZ
Tim Foxon, Metron Technology Limited
(author: Adam Grummitt)

Abstract:
Windows, UNIX, Linux and z/OS (WULZ) are established as the leading operating systems (OS). Oracle is established as a leading relational database management system (RDBMS). The issue is how to exercise effective performance management (PM) of Oracle in each environment.

This paper outlines a PM approach used in a variety of case studies. Software factors reviewed include the OS architecture and RDBMS administration tools. PM functions reviewed include interpretation of metrics, tuning, workload trend analysis and modeling of Service Levels.

Seizing the New Opportunities in z/OS Software Licensing
Daniel A Kaberon, Hewitt Associates, Manager, Computer Resource Mgmt

Abstract:
Workload License Charge (WLC) is a program offering major software discounts for z900 z/OS environments with strong capacity management programs. z/OS capacity planners can guide the enterprise to substantial savings in IBM Software Monthly License Charges. The speaker will share his firm's successful and practical approach to a broad implementation of z/OS Workload License Charge (WLC).

If you don't do it, someone else will take the credit!

Bio:
Dan Kaberon is director of Computer Resource Management for Hewitt Associates. He is a member of two IBM customer councils. Dan has frequently presented at SHARE and CMG. This will be his third presentation to RMCMG.

Strategic Performance Management for DB2 UDB EEE, Oracle and Teradata
Dr. Boris Zibitsker, Chairman & Chief Technology Officer, BEZ Systems

Abstract:
With data volumes exploding, and the number of applications and users accessing data growing exponentially become more and more difficult to provide consistent level of performance and scalability for critical business applications. In this presentation, we will discuss strategic performance management approach to planning, managing, and controlling the usage of resources and data by applications based on DB2 UDB EEE, ORACLE and Teradata DBMS, incorporating the parallel processing. Several case studies will illustrate the process of the platform justification, performance management, database performance optimization and capacity planning.

Bio:
Dr. Zibitsker is the chairman and founder of BEZ Systems, Inc. Dr. Zibitsker has been working within the performance management arena for over 25 years. Dr. Zibitsker is a well known expert in performance management and performance prediction and is the author of many papers, articles and white papers about these topics. He is also a frequent presenter for various user groups throughout the United States and Europe.

The Effect of Workload Groupings on Distributed Transaction Capacity Models
Dr. Tim R. Norton, Simalytic Solutions, LLC

Abstract:
Modeling transaction workload behavior with a queuing network model becomes much more difficult when the application consists of multiple workloads. One of the goals of this type of model is to predict how the application will behave when moved to a distributed environment. Add to the situation the goal of predicting the necessary capacity to support the application in the distributed environment and the model quickly becomes very complex. One way to reduce the complexity is to reduce the number of workloads being modeled, but the question then becomes how to combine the transactions into workloads. This pa-per is a case study of a hypothetical modeling situation where the transactions are grouped differently to determine if such workload groupings have a significant effect on the outcome of a capacity model and whether the effect is the same in a distributed environment. These hypothetical transactions were grouped into several different groups of workloads and each of the groups was studied to see how the groupings effected the response times after the transaction arrival rates were increased. This analysis was done on both a single system scenario and a networked systems scenario.

Bio:
Tim R. Norton is a consultant with his own company, Simalytic Solutions, and a co-founder and the Chief Scientist of DevelopNET Corporation, providing web based capacity planning services for web applications. Dr. Norton also teaches Computer Science courses at the University of Colorado at Colorado Springs, DeVry University, Colorado Technical University. His research is focused on hybrid modeling techniques for client/server systems. He has worked with a variety of computer systems and has almost 30 years MVS, PC and Distributed Systems experience, including applications design, support, and systems programming. He provided Technology Planning and Capacity Planning and modeling for over 15 years at a variety of companies, including MCI/WorldCom, Covia/United Airlines, ARCO Oil and Gas, Colorado Interstate Gas, and Texas Instruments. He holds a Masters Degree in Computer Science and a Doctor of Computer Science Degree. He is a member of the Association for Computing Machinery, the IEEE Computer Society, and the Computer Measurement Group. CMG2003 will be his third National CMG Conference as the Subject Area Chair for Modeling Track. He is also on the Academic Advisory Board for Computer Science at DeVry University.

Rocky Mountain Computer Measurement Group