Bill Johns - Performance Monitoring for Today's IT - What is Nirvana?
Performance monitoring has been around since the beginning of IT. Over time component level monitoring tools have been finely honed to provide technical experts with the measurements needed to keep elements of systems finely tuned.  However, as IT becomes more closely aligned with business deliverables, IT performance monitoring needs are shifting to a more business oriented view. The purpose of this discussion is to identify the gaps in monitoring created by the evolution of IT and business and define the new needs of performance monitoring.

Ned Diehl - DB2 CPU and Response Metrics
DB2 requests originate from a variety of diverse sources including batch, CICS, DDF, and SAP. Related DB2 CPU usage can be recorded in RMF, DB2, SMF 30, and other subsystem records. Proper selection and interpretation of these values will vary with transaction source, DB2 environment, product levels, and analysis objectives. Analysts must be careful to include all desired values and avoid multiple counting of the same logical utilization. This paper will discuss the sources and analysis of DB2 CPU metrics and corresponding response times. Examples will include CICS, DDF, and SAP.

Michael Sharp - IBM z9 Technical Hardware Update - Overview PDF
IBM z9 Technical hardware update IBM z9 Technical hardware update

Scott Chapman - Adding Value to Performance Management with Business Metrics
CMG members are well versed in measuring and reporting system performance and capacity.  A great deal of system and human effort is expended to collect detailed technical measurements. These measurements are usually stored in some form of a Performance Database, or PDB.

However, these data merely reflect the technical measures of our systems and do little to help us understand the larger purpose of those systems: supporting our business.  By simply examining the basic performance measures, we can tell very little about the systems’ business value.  To understand that business value we need to collect data about the work being performed in business terms.  That data could be stored, along with selected technical measurements, in a Business Metrics Database, or BMDB.

This paper will introduce the concept of the BMDB.  The potential benefits of the BMDB will be discussed. A simple methodology for getting a BMDB started will be proposed. A follow-on paper will discuss the more technical aspects of the BMDB design, reporting, and sources of data for the BMDB.

A Business Metrics Database, or BMDB, has the potential for adding significant value to an organization’s performance management and capacity planning processes.  The BMDB needs to be flexible, extensible, and efficient.  Reporting needs to be simple and easy to update as new metrics are added. This paper will present one possible BMDB design and discuss a simple web-based reporting architecture based on XML and JavaScript that could be extended to other applications as well.  Potential sources for both the technical measures and business metrics of mainframe applications will be discussed.

Dr. Boris Zibitsker - DB2 UDB ESE Performance Management Tradeoffs - OCMG.ppt Powerpoint
- Challenges of planning and managing DB2 UDB ESE applications during different phases of the application life cycle
- How to evaluate performance management tradeoffs
- Continuous process of setting and managing expectations

Gregory Hutchinson - IBM Eserver Zseries 890 Overview - z890-MASTER Powerpoint
- Introduction
- Book Structure
- Upgrades
- I/O
- Sysplex Considerations
- Statements of Direction
- Operating Systems
- Cryptography
- Hardware Management Console
- Physical Planning
- Reference Material

Rich Fronheiser - Too many servers, not enough eyes TooManyServers.ppt
Too ManyServers.doc

This paper is based on the Author’s experiences in formal Capacity Planning and Performance Management departments – starting with a large company that had few servers and many analysts and concluding with an even larger company that better reflected the title of this paper.  The paper outlines a methodology that allows analysts and planners to target their limited resources at systems (and more importantly, applications) that require the most attention as the number of servers grows and the number of analysts decrease.

Greg Caliri - Large Scale Processor Reference, and implications
Large Scale processor reference in Capacity Planning situations:
- A scalability refinement in system capacity in use through the years in OS/390, z/OS and predecessor operating systems
- It is still relevant today - past and current generations
- "LSPR benchmarks are laboratory controlled tests of representative workload environments, objectivley measured and analyzed. IBM views LSPR data as providing accuracy approaching that of a customized benchmark." (LSPR guide, IBM)  (Please note that file was removed at the request of BMC Corporation on 05/17/2007).

Joseph L Babcock - Care and feeding of SMF in the Large System Environment 2004.ppt
- Define the problem
- A model for SMF capture
- Processing the SMF data (Parsing)
- Summarization of SMF parsed data

Ivan Gelb - CICS
Ivan Gelb will unload many years of CICS performance tuning experience…

Jaqui Lynch - AIX I/O Performance Tuning
Jaqui will unload many years of UNIX tuning experience right before our very eyes…

Tom Aurand - ESCON to FICON
Planning and modeling ESCON to FICON conversions:
Mr. Aurand will explore qualitatively and semi-quantitatively the effects of FICON channel
implementation on channel and device performance. He will present a review of RMF device
response time components, the effect FICON has on each, and the background reasons for these effects. A semi-quantitative discussion then will center on an approach to designing an optimum FICON configuration, including:

• How many channel paths will I need from the processor to the director?
• How many paths must I have from the director to the control unit?
• What target channel utilization should I have?
• What can I expect the impact on device performance to be?

Tom Thompson - Optimizing Server Consolidations
Consolidation/Relocation of servers without over-spending and adversely impacting application
response times is a daunting task. In this session we will present best-practice approaches that address this challenge by modeling enterprise infrastructures with live data sources including server workloads, network configurations, and application traces. These approaches provide a framework to:

• Aggregate server resources to achieve better utilization
• Reduce costs of maintaining multiple data-centers
• Avoid under-provisioning, or over-provisioning (networks and servers) while meeting SLAs
• Evaluate many consolidation/re-location alternatives quickly without expensive lab setups
• Accommodate changes in traffic patterns due to re-location of servers 

Jerry Rosenberg, NT Performance Monitoring
NT systems (including Windows 2000) are emerging as production platforms in many enterprises. As production systems, they required the same level of care and nurturing as any other production environment. This tutorial will outline a process to monitor the available metrics regularly to proactively identify and avoid impending bottlenecks.

Ed Woods, DB2: A Critical Component In Websphere and e-Business
Websphere is rapidly gaining momentum in many shops as a platform for e-Business and application development. DB2 is an integral component of the Websphere infrastructure. This presentation will examine the role of DB2 in a typical Websphere implementation.

Tim Follen, How Do You Spell MIPS?
This paper will discuss issues around using MIPS as a reporting metric. A brief history and listing of issues will be presented. A technique for applying a MIPS rating for mainframe processors will be documented along with uses and reporting suggestions.

Monte Bauman, The Modern Mainframe
What does the modern mainframe hardware platform look and behave like?
The Modern Mainframe Software Platform:
    What software platforms does the modern mainframe support?
The Modern Mainframe Enterprise Application Portfolio:
    What applications are running on modern mainframes