http://www.cmg.org/cgi-bin/agenda_2008.pl Current agenda for CMG'08 en-us Thu, 20 Nov 2008 11:03:53 GMT Thu, 20 Nov 2008 11:03:53 GMT webmaster@cmg.org webmaster@cmg.org http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8610 Class OverviewThe standard outline for the class and the various sections it comprises is as follows:Day 1 * Introduction * ITIL® Capacity Management * Levels of Capacity Management * Iterative Activities * Exercises * Sample ExamDay 2 * Capacity Database * Demand Management * Application Sizing * Modelling * Capacity Plan * Benefits/Costs/Possible ProblemsDay 3 * Process Review/Reporting * Exercise and Review of Exercises * Process Planning & Implementation * Interfaces and Dependencies * Exercise and Review of Exercises * Mock Exam * ISEB Written Examination * ISEB Multiple Choice ExaminationDetailsThis 3-day course runs Saturday through Monday and must be taken along with CMG registration Option 2 for an additional cost of $1,850.00 above the CMG registration price. Thu, 20 Nov 2008 11:03:53 GMT Computer Performance Evaluation http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8610 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8715 Formal Service Level Agreements (SLA's) are increasingly used for ensuring Quality of Service. SLA's comprise one or more Service Level Objectives (SLO), with the objective of meeting a target value. This workshop presents both business and technical aspects of SLA's, including. - Terminology, conventions, and variations used in formulating SLA's, - SLA's as a component of overall QoS provisioning, Service Management, and Risk Management, - ITIL and other standards related to SLA's. - Deriving Objective Functions that yield future SLA values required to meet an SLA target, - Deriving a Challenge Index that quantifies the risk of missing an SLA target, - Using an SLA Projection Model for forecasting future SLO values for achieving the overall SLA target.An SLA Dashboard is used to illustrate the technology and its visualization. Illustrative examples are presented for the SLA's of System Availability and End-to-End Response Time. A drill-down framework is used, whereby top-level results contain links to more detailed results. The overall objective of the workshop is to enable attendees to answer the two questions: (1) Is an SLA on track to meet its target? and (2) What can be done to ensure compliance to target? Thu, 20 Nov 2008 11:03:53 GMT Hot Topics http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8715 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8712 Whether you’re new to z/OS or on an unfamiliar system you need to know where things are and how they are configured before you can be productive. Once you have access to a z/OS system there is a methodology you can follow to discover common z/OS objects, such as PARMLIB, PROCLIB, catalog structures and TSO/ISPF options. This workshop will describe commonly available z/OS tools, commands and utilities to allow you to quickly become effective on the z/OS system. A brief historyCommon z/OS assumptionsTSO/ISPF primerDataset names and typesEdit tools & tricksISRDDN capabilitiesCatalog structureSecurityPARMLIB settingsProceduresJobs, TSO and Started tasksExecutables Thu, 20 Nov 2008 11:03:53 GMT System z http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8712 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8710 Objective• During the workshop you will learn how to build and apply analytical models to predict the impact of workload and database size growth, new applications and hardware upgrade.• You will use our Excel spreadsheet with exercises • At the end of the workshop you will summarize results and prepare a report with capacity management recommendations. Outline1. Objectives 2. Description of exercises 3. Overview of the major factors affecting scalability, concurrency and parallelism of applications in a multi-tier environment with distributed Oracle RAC, DB2 and other DBMS4. How to collect OS, DBMS and JVM performance measurement data5. How to perform workload characterization 6. How to perform workload forecasting7. How to build analytical queueing network models8. How to predict the impact of workload growth, and evaluate the impact of hardware upgrades 9. How to set a realistic SLO and SLA and organize proactive SLM 10. How to predict the impact of database tuning11. How to predict the impact of new applications12. How to predict the impact of the server consolidation13. How to organize proactive performance management14. How to prepare and present a Strategic Performance Management Report15. Summary Thu, 20 Nov 2008 11:03:53 GMT Computer Performance Evaluation http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8710 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8708 All systems, whether physical or computational, have operational limits. An aircraft cannot exceed its flight parameters or it may stall. Exceeding the carrying capacity of a bridge can lead to its collapse. Physical systems exhibit a predictable critical point beyond which they collapse. The same can hold for computer systems but more commonly performance just degrades. Highly scalable applications are desirable for reasons other than performance, e.g., lower development cost, availability, simpler maintenance, flexibility and heterogeneity. How can we characterize these effects and incorporate them into predictable scalability before an application gets deployed? In this tutorial, we will identify and quantify the following critical determinants of good scalability: 1. Equal bang for the buck: ideal parallelism or concurrency 2. Diminishing returns: due to contention delays in the system 3. Negative dividends: loss of capacity due to coherency delays which leads to the *Universal Law Of Computational Scalability*. The course notes will contain new material which updates my book "Guerrilla Capacity Planning" and each attendee will have the option of obtaining a copy of the book at a substantial discount. Thu, 20 Nov 2008 11:03:53 GMT Computer Performance Evaluation http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8708 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8721 This workshop will discuss the challenges involved in managing Enterprise Disk Subsystems in a mainframe environment. How many RMF metrics may actually mislead us into believing that things are running just fine; and how the old rules of thumb simply don't apply anymore.Recent architectural changes have shifted the most likely bottlenecks from the host systems down to the Disk Subsystem components. We need to adapt our perspective from the standard RMF/LPAR view to that of the Disk Subsystem.A new methodology and complementary new metrics will be introduced and discussed.This workshop will provide students with the opportunity to better understand the performance and utilization of their storage environment. We are asking attendees to send in a sample of their RMF data and we will analyze the data during the workshop. Tables and graphs of the performance of your environment will be studied with recommendations for how things may be improved.By the time you leave the workshop you will understand: - if response time is poor; why? and what can be done about it - if response time is fine, are you overconfigured or how close are you to 'the edge' - how utilized are your Disk Subsystems and where are the opportunities for rebalancing?Please contact John at: John.Baker@intellimagic.net for data gathering instructions. Thu, 20 Nov 2008 11:03:53 GMT Storage http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8721 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8722 This workshop will provide a comprehensive overview of the tools available for performance measurement and management in Solaris OS environments. Discussion of the tools will be prefaced by some discussion of problem-solving strategies and some essential conceptual context for performance problem-solving in general.Our tool survey will include the native tools provided in Solaris, as well as Sun's developer tools and 3rd-party tools. Some focus will be drawn to DTrace and the ecosystem of tools that has evolved around DTrace. We'll demonstrate how anyone can benefit from DTrace without being a programming guru. Drill-down coverage will focus on the most important basic tools in Solaris. Flashy inspiring demos will be given of some of the fancier tools for which drill-down exploration will be prohibited by time constraints. Attendees will be provided with options for exploring the tools hands-on using their own notebook computers. A common lab system will also be configured for common use during the workshop.The content is designed to empower practitioners and enlighten newcomers to the Solaris environment. It should prove valuable for attendees with diverse skills and interests.NOTE: Companion to PM workshop More Performance Tools and Problem-Solving in Solaris"" Thu, 20 Nov 2008 11:03:53 GMT Linux and Unix http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8722 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8702 Attendees at this workshop will benefit from my many years of doing Java performance tuning, both in our lab where we run industry standard benchmarks, and in our application excellence centers where I have helped tuning our customer’s real-world applications. I will cover the following topics:* Understanding the garbage collector (GC), gathering and analyzing GC data, and using that to tune the Java heap.* Understanding various GC algorithms, how to configure them, and how to decide which one works best for you.* Working with the Java Management Extensions (JMX) to gather data about the performance of your application, including the use of VisualVM and other applications to monitor that data.* Taking a holistic approach to Java Enterprise Edition (Java EE) tuning, where I show you what to tune in the OS, network, JVM, application server and application.After attending this workshop you will have a concrete set of tools and ideas that you can apply to your Java application to improve its performance. Thu, 20 Nov 2008 11:03:53 GMT Computer Performance Evaluation http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8702 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8705 As we CMG members age, many of us are approaching retirement. We need to take actions for ourselves and our families to protect us when our financial resiliency is reduced and our needs have evolved. We need to do the necessary planning so that our financial capacity will make retirement possible.What should you do about health insurance and life insurance? How much money will you need, and how reasonable is it to get that much? What will be the effects of demographics (e.g., the baby boom, increased longevity) and probable government responses? If you sell your house, where should you live? Will taxes destroy you, and what reasonable plans should you make to cope with them? Should you just hand over your assets to that nice young financial planner and hope for the best?When we're between 25 and 40, we need to make plans and begin saving. By the time we're about 40 or 45 we need to implement plans, especially because demographic shifts promise to put real burdens on people who haven't retired by 2015.A real retiree (Dr. Thomas Bell) and a real Certified Financial Planner (Joe Delano) will describe the challenge and make specific suggestions. Thu, 20 Nov 2008 11:03:53 GMT Management http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8705 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8730 With the advent of specialty engines such as zIIPs and zAAPs, and the new z10 processor, measuring CPU time and processor utilizaitons are not as simple or straightforward as they use to be. Now when analyzing CPU consumed at the address space level, workload level, or LPAR level we need to be concerned what work is running on what types of processors, the speed of the different processors, Hiper Dispatch, and a whole host of other factors. During this z/OS performance workshop, Peter Enrico will provide a real world practical understanding and insights into this key z/OS performance topic. Even if you’ve been working with SMF measurements for a long while, you are sure to learn something new. At a high level the topics to be discussed include:- Level set of zArchitecture specialty engines - CEC level and LPAR level measurements - Workload level processor measurements - Address space level processor measurements Extra Offer : Send SMF Data Prior To The Workshop! Peter will process any SMF data received at least 1 week prior to workshop. Peter will make available, to those attendees, tables and graphs of their own data. On an informal basis, Peter will be available during CMG week to those wishing to discuss their measurements. For data gathering instructions, email Peter at Peter.Enrico@EPStrategies.com. Thu, 20 Nov 2008 11:03:53 GMT System z http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8730 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8729 Diagnosing performance problems and system bottlenecks is a complex and time-consuming task. A successful diagnosis requires in-depth system knowledge, a robust data collection mechanism, and comprehensive analysis tools. Windows Vista provides new innovations that will make diagnosis experience much more pleasant. The new Event Tracing for Windows (ETW) and Performance counter infrastructure provide a powerful instrumentation solution. In addition, the new Reliability and Performance Monitor (RPM) (formerly Perfmon) provides built-in diagnosis knowledge and richer UI controls that help users quickly gain insight into performance issues. Likewise, the newly improved Task Manager becomes a more valuable tool with added details and services integration. Windows Vista also introduces a new programming model called Performance Logs & Alerts (PLA) for logging various types of performance data including performance counters, events, API traces, registry, and WMI data. Join us and see how easy it is to instrument and use tools to drill down performance tools. This workshop will focus on the best practices of diagnosis/monitoring solutions of the Windows Vista. In addition, we will demo the latest innovation in Windows 7 that leverages Windows Vista experience. The demo includes a new Powershell-based diagnosis solution and the new Resource Monitor. Thu, 20 Nov 2008 11:03:53 GMT Windows http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8729 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8718 Service Oriented Architecture (SOA) has now emerged as the architectural style of choice for developing enterprise applications that will result in the sought-after benefits of reusability of software components, flexibility, and business agility. Enterprise applications are not developed but rather composed of individual, service components, each of which encompasses a unit of business functionality. A service, which may encapsulate legacy functionality or a recent requirement, may be deployed anywhere across the enterprise and possibly at multiple locations.This session will present the challenges of managing the infrastructure that must be in place to support a scalable SOA implementation along with real-world solutions to some of these challenges. After an introduction to the characteristics and benefits of SOA-based enterprise, we will discuss the challenges that arise in managing the operation and performance of this environment which consists of services deployed across many heterogeneous platforms and where the dependencies between the services change constantly. We will then present approaches and solutions that an organization can utilize today to build the management layer that is needed in order to achieve a successful SOA implementation. Thu, 20 Nov 2008 11:03:53 GMT Hot Topics http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8718 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8706 This workshop includes new and revised content for 2008.Abstract:Computer system and Network performance data collection, analysis, modeling and capacity planning on any platform using bundled utilities and freely available tools such as Orca, BigBrother, OpenNMS, Nagios, Ganglia, SE Toolkit, R, Ethereal/Wireshark, Ntop, MySQL and PDQ.Overview:Capacity planning and performance management tools have been commercially available for many years. A new generation of freely available tools provides data collectors and analysis packages. As the underlying computer platforms and network devices have evolved, they have added improved data sources and have bundled free data collectors. Several open source and freeware projects have sprung up to collect and display cross-platform data, and with the advent of highly functional free statistics and modeling packages comprehensive analysis, modeling and archival storage can now be assembled. Free and bundled tools are of special interest to sites with very diverse mixes of systems, very large sites where licensing costs become prohibitive, and sites replacing a few large single systems with many more low cost horizontally scaled systems. Thu, 20 Nov 2008 11:03:53 GMT Computer Performance Evaluation http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8706 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8707 As performance specialists we are presented with a large amount of data, from various sources, which we have to analyze to determine the characteristics of a system. This requires that we read in the data, convert it to a representation that is easy to process (e.g., spreadsheets, matrices, vectors, etc.), perform various calculations (e.g., average throughput, regression analysis, response time by transaction, etc.), and present the data in various formats (reports, graphs, web pages, etc.) so that others can understand what it means.This workshop will introduce the student to the Open Source software called R. This is a statistical programming environment that allows the quick interactive development of a script and then the script can be run in a batch environment for repeated executions. This is very similar to the way that the UNIX “shell” is used; you can interactively try out commands and then store them in a script. The workshop will provide the basics of the language and will use some performance data (‘vmstat’ and ‘ps’ from UNIX/Windows) to illustrate the commands. Scripts will be provided so that the student can implement these operations on their systems. Thu, 20 Nov 2008 11:03:53 GMT Computer Performance Evaluation http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8707 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8610 See Part 1. Thu, 20 Nov 2008 11:03:53 GMT Computer Performance Evaluation http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8610 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8601 Energy efficiency is a global issue with significant impact today and will have an even greater impact in the future. IBM's Project Big Green is defining leadership in data center energy efficiency with five areas to improve your data center energy management - diagnosis, build, virtualize, cool and manage, and measure.Learn how other clients - and IBM - have implemented these areas to gain immediate business benefit to double their IT capacity, reduce operational costs by 50 percent annually, and have a positive impact on the environment. We'll also discuss the role of CIO, CFO, adn CEO in going green. Thu, 20 Nov 2008 11:03:53 GMT http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8601 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8089 Most DB2 monitors can load accounting and statistics data into DB2 tables. We can use spreadsheets as an adhoc reporting against this data. Statistics rows show usage of critical resources during peak times and accounting rows show which applications are consuming the critical resources.We will build an inventory of tables and column names and generate SELECT statements from a Rexx exec. Each of our spreadsheets will be focused on a related group of metrics over a meaningful time frame. We will then subtotal, summarize and graph the data. Thu, 20 Nov 2008 11:03:53 GMT Computer Performance Evaluation http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8089 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8030 Don’t have time to read through manuals and books, trying to ferret out best practices for capacity planning? Learn the KPRs (Denise Kalm Performance Rules) based on years of just doing the performance and capacity planning job, keeping my lines of business up and running well. By learning how this approach evolved, and what worked for me, you can craft your own “best practices” and work smarter, not harder. Thu, 20 Nov 2008 11:03:53 GMT Computer Performance Evaluation http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8030 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8191 The identification of business driver information is an early step in its use for capacity planning. The information may be in the form of business metrics and affected IT resources or a compilation of growth rates. The ideal capacity forecasting methodology creates predictions of future resource demand by combining business forecasts with resource trending. This session discusses forecast techniques and issues around the identification and use of business growth information, and outlines approaches to integrate business forecasting with capacity forecasting. Thu, 20 Nov 2008 11:03:53 GMT Management http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8191 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8511 This is a two part session which reviews some of the statistical techniques which can be useful in performance analysis and capacity planning.Part 1 reviews some of the statistical concepts and their psychology used in all of statistics. The process of seeing and describing reality in terms of numbers and graphs is foremost. This analysis is essential to grasping statistical concepts that follow. Emphasis in this part will provide the under pinning of more complex statistical ideas: average, distribution, standard deviation, coefficient of variation. Thu, 20 Nov 2008 11:03:53 GMT Computer Performance Evaluation http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8511 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8907 A case study report is presented on a "Converging Networks" technology demonstration trial held at the 2008 Coalition Warrior Interoperability Demonstration (CWID 2008). The trial demonstrated how multiple, parallel networks can be securely virtualized onto a single, common network infrastructure. Thu, 20 Nov 2008 11:03:53 GMT http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8907 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8801 Can’t see the forests for the trees in your IT platforms reporting? Today we are called upon to present our IT environments from an overall perspective versus the platform level. Requirements have changed to that we must be able to present our IT environments from an enterprise view and based on services supported, geographical locations, homogeneous groupings, business units and etc. In this session, you will discover, utilizing TeamQuest’s IT Service Analyzer and Reporter (ITSAR) tools, how to report on enterprise wide IT environments. Thu, 20 Nov 2008 11:03:53 GMT http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8801 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8071 FICON/FCP protocol intermix in a common storage network has been supported by IBM since early 2003, yet has not seen widespread adoption among end users for a variety of reasons. Recent developments such as the new System z10, Node Port Identifier Virtualization (NPIV), and advances in storage networking management make intermix a more compelling technological strategy. Thu, 20 Nov 2008 11:03:53 GMT Storage http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8071 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8140 This session is targeted at IT Leaders, Service Managers and ITSM process owners who intend to improve the quality of IT services in their organization and lower operational costs. The session introduces the meaning of quality in ITSM context and highlights the key quality goals for an ITSM Organization. Statistical inputs from various studies and experimental models have been included to provide quantitative indicators to the impact of contributing factors. A quality improvement approach has been suggested based on our findings, experience and experiments. Thu, 20 Nov 2008 11:03:53 GMT Management http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8140 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8075 The Universal Scalability Law (USL) is an analytic function used to quantify application scaling. It is universal because it subsumes Amdahl’s law (AL) and linear scaling (LS) as special cases. Using simulation, we show (1) that USL is equivalent to synchronous queueing in a load-dependent machine repairman model, and (2) how LS, AL and USL can be regarded as boundaries defining three performance zones. Typical throughput measurements lie in all three zones. Simulation scenarios provide insight into which application features should be tuned to get into the optimal performance zone. Thu, 20 Nov 2008 11:03:53 GMT Computer Performance Evaluation http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8075 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8511 This is a two part session which reviews some of the statistical techniques which can be useful in performance analysis and capacity planning.Part 2 reviews the basic techniques will be expanded to talk about the comparison of measurement results (T-test) and the use of techniques which can be useful in performance analysis and capacity planning, namely regression analysis (a.k.a. trending). Thu, 20 Nov 2008 11:03:53 GMT Computer Performance Evaluation http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8511 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8091 Growth patterns change frequently in z/OS computing systems. Capacity managers are often challenged as to perform future projections based on expected trends, or whether modeling studies should be undertaken to expand predictions to include performance implications. Workload categorizations, transactional volumes, analysts’ time, cost options, and overall benefits play into the decision to trend, model, or, to do both. Thu, 20 Nov 2008 11:03:53 GMT System z http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8091 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8802 Today's economic pressures are often at odds with the need for speed from mainframe storage. In this session, we will demonstrate technical solutions that improve storage hardware utilization levels while at the same time reducing the risk of service disruptions. We will also address the topic of overcoming the complexity of modern architectures despite the reduced staffing levels common today. Each session participant will receive a copy of the presentation on a 2GB USB memory stick. Thu, 20 Nov 2008 11:03:53 GMT http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8802 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8610 See Part 1. Thu, 20 Nov 2008 11:03:53 GMT Computer Performance Evaluation http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8610 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8046 Since the inception of OS/MVT in the mid-1960s, volumes have been the basis of storage management. Volumes are viewed in terms of units of capacity, work units for storage administration, and as potential units of serialization in the I/O subsystem.Building on the foundation of HyperPAVs, EAVs offer a new taxonomy for storage management. The combination of these two technologies offers the opportunity to recast the role of volumes from principal elements to artifacts and to significantly simply both storage administration and performance management. Thu, 20 Nov 2008 11:03:53 GMT Storage http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8046 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8603 TBD Thu, 20 Nov 2008 11:03:53 GMT System z http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8603 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8058 This session investigates the impact that failures may have on performance and capacity planning using a simulation model. The simulation model that is proposed is subject to varying frequency of failures to analyze the impact on survivability, utilization, workload throughput, and response time. The goal is to better plan capacity requirements in a computer center subject to unpredictable levels of accidental threats such as node/network failures, job aborts and job cancellations. Thu, 20 Nov 2008 11:03:53 GMT Computer Performance Evaluation http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8058 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8185 Successful enterprise capacity planning depends on swiftly (and ideally automatically) detecting and removing process pathologies (loops, ramps, shrieks, etc.) prior to analyzing real consumption needs. While detection algorithms are similar across all firms, your firm might also have specific needs that you are unlikely to be able to buy ''canned'' from a vendor. You need a way to apply these rules to all machines and processes. You need a rule engine. Join your author as he shares important techniques, shortcuts, problems encountered and labor saving ideas that he’s learned building his. Thu, 20 Nov 2008 11:03:53 GMT Computer Performance Evaluation http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8185 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8509 Part 1: Modeling and Forecasting BasicsThis is the first of two sessions. Computer performance modeling is mainly focused on understanding how business activity and the infrastructure can be analyzed to understand the impact on IT services. The key to this activity is to understand how requests for service queue for usage of resources. This first session provides basic definitions, the history of modeling queueing systems and some basic analytical queueing models. Thu, 20 Nov 2008 11:03:53 GMT Computer Performance Evaluation http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8509 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8902 TBD Thu, 20 Nov 2008 11:03:53 GMT http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8902 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8803 VMware is not a set it and forget solution. It requires expertise throughout its lifecycle from candidate selection to deployment and ongoing management and monitoring. Join PERFMAN as they show you how to use their solution to implement best practices for VMware. Topics include: the best CPU configurations for guests, dealing with unique memory issues such as page sharing and ballooning, sixing LUNS, and more. Thu, 20 Nov 2008 11:03:53 GMT http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8803 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8300 There are many frameworks, universal solutions, and quick fixes to application performance management competing for your attention. This session explains how the various parts all fit together in a comprehensive approach to managing performance. This approach is backed by data gathered from more than 600 companies that determined the key factors underlying successful APM. The session shows the critical points where Apdex can play a vital role in achieving success. Attendees will learn the four principles that deliver good performance and how to start applying them inside their enterprise. Thu, 20 Nov 2008 11:03:53 GMT http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8300 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8193 Green Capacity Planning is the holistic approach to effectively plan for today’s data centers. The approach builds on traditional computer and network capacity planning to include environmental considerations. This paper describes the terminology, theory, and practical application of the methodology using a case study. The case study evaluates the capacity, storage, and energy footprint of an existing e-Business system. It then quantifies the potential energy improvements to be gained through virtualization as the system is scaled up to meet demands of a growing business. Thu, 20 Nov 2008 11:03:53 GMT Hot Topics http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8193 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8223 If you have a DB2 question regarding performance tips, functionality, insights, or DB2 special features such as stored procedures, zIIPs,version 8 or 9 conversion or performance, then this is THE panel to ask. The members will be able to answer your questions and enlighten you with their valuable expertise. Come prepared with questions that affect your work life. Email them as soon as you can to db2_panel@cmg.org, or drop a written question into the Q&A box you will find at various ''System z'' track sessions, or hand your written questions to any ''System z'' session monitor. Panelists include: Bonnie Baker of Bonnie Baker Corporation, Akiko Hoshikawa of IBM, Tom Moulder of EMC Corporation, Mike Wingfield of Compuware Corporation Thu, 20 Nov 2008 11:03:53 GMT System z http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8223 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8612 Today you can't avoid the network and simple things can make performance go bad if the networking is not tuned. This session will go through the basics of TCP tuning and how to get the best performance out of your server and network. This session will concentrate on application level tuning and how it affects the system networking. One application can cause a server to perform poorly just through bad socket and network tuning. This session is for the novice and covers TCP/IP sockets and system resource allocations. Understanding the basics of socket tuning cam make an application go from sluggish to at the speed of the internet. Thu, 20 Nov 2008 11:03:53 GMT Network/Internet http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8612 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8406 TBD Thu, 20 Nov 2008 11:03:53 GMT http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8406 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8509 Part 2: Queueing Network ModelsThis is the second of two sessions. Building on session 1, the discussion turns to understanding the distribution of requests for service as well as the distribution for the service times for each request. It is shown how the understanding of these distributions contributes to developing accurate models that predict IT service end-to-end times. During this session, both analytic queueing and simulation queueing models will be discussed. Thu, 20 Nov 2008 11:03:53 GMT Computer Performance Evaluation http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8509 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8082 This presentation will show how one analyst uses the pivot table feature of Microsoft EXCEL to arrive at a quick performance analysis for DB2 and BATCH mainframe applications. At our enterprise, we use pivot tables and charts as monitoring tools, performance analysis, and management communication. An explanation of the basic concepts to create and manipulate pivot tables will be combined with a real-time demonstration of the tables and charts. At times in your career you find a tool that is truly worth learning about. This is one of those times and one of those tools! Thu, 20 Nov 2008 11:03:53 GMT Computer Performance Evaluation http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8082 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8804 CPU architectures for systems have become move complex over the pass five years. Chips, Cores, and threads on are now common place in the Data Center. Trying to plan effectively for these differing vendor implementations of this cpu architecture can be a difficult task. In this training session, TeamQuest Model will be used to show how to predict capacity utilization and workload performance based on this new cpu architecture. We also use TeamQuest Model to move application workloads from one platform type to a different platform type. Thu, 20 Nov 2008 11:03:53 GMT http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8804 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8301 Apdex is simple to understand but requires process to implement. This session will provide an introduction to Apdex and describe a step-by-step process to help implement the methodology within your enterprise. It will show how to gather information from various parts of your organization, organize a planning workshop meeting, achieve buy-in from management, and write an Apdex project plan. A critical step in the process is benchmarking your organization's effectiveness relative to the industry so you can make management aware of current conditions and how the Apdex process will improve them. Thu, 20 Nov 2008 11:03:53 GMT http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8301 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8600 eBay is the world's largest virtual economy, enabling its 240+ million registered users to trade a vast array of goods, with something like 110 million individual items available on the site at any one time. While extreme in terms of actual size, eBay's infrastructure is a view into the future for many more typical data centers. It offers incredible scale and resiliency, yet is built out of essentially commodity components.This presentation will provide a brief overview of eBay, its infrastructure, how it has evolved, and what this tells us about future data center infrastructure and the challenges ahead. Thu, 20 Nov 2008 11:03:53 GMT http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8600 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8099 Storage energy efficiency is becoming more important in our data centers, not only because energy efficient storage is environmentally friendly, but also because it takes less space and provides relief for data centers that are maxing out on their power and cooling ability. This paper provides a comprehensive overview of techniques that can be used to save power without sacrificing performance. The potential of FATA drives, the impact of the RAID technology, the use of multiple drive types, and the influence of mirroring will all be discussed in the context of potential power savings. Thu, 20 Nov 2008 11:03:53 GMT Storage http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8099 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8005 Our common tool for determining availability is statistics. Statistics provide us with an analysis of what we think is pertinent to continue the use of the application or set of applications. But are statistics always the best tool to really determine a user-centric environment? What this session will explore is the somewhat tentative nature of statistics and establishing a more hands-on approach to determining user satisfaction and the consequent rise in quality for application development as a result of determining this user satisfaction. Thu, 20 Nov 2008 11:03:53 GMT Management http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8005 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8407 To guarantee the VWLC expected savings IBM introduced the possibility of setting both a defined capacity limit at the LPAR level and a group capacity limit (since z/OS 1.8) at the CPC level. Aggressive use of these parameters could allow to a further reduction in software costs. A technique is presented to:- analyze the 4-hour rolling average by WLM workload importance,- evaluate optimal "defined" and "group" capacity limits penalizing lowest important workloads.- estimate possible MSU savings.Additional savings could be obtained through a full exploitation of AAP and IIP technology; a similar technique is presented to analyzing the eligible workload running on standard CPUs and decide if buying AAP and/or IIP engines will enable you to save money. Thu, 20 Nov 2008 11:03:53 GMT System z http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8407 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8119 Network workload models rely to some degree on certain invariant properties of internet traffic. In this session we investigate some implications that such invariants introduce in the accuracy of network performance models. We also investigate factors that impact the validity of invariance property assumptions and the range of scales in which such invariants apply. The aim is to establish sensitivity of ensuing performance models on these assumptions. Finally, some practical problems are discussed. Thu, 20 Nov 2008 11:03:53 GMT Computer Performance Evaluation http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8119 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8505 If you are new to the idea of zAAPs, zIIPs and specialty engines, or are confused with all the details, then this session is for you. The speaker will begin by looking at what makes work zAAP eligible, including JVMs and XML System Services. Then a look at enclave SRBs, their use by DB2, IPSec, XML System Services and z/OS Global Mirror, and what makes work zIIP eligible. Other topics will look at the basics of how the z/OS dispatcher gets involved, the controls in PARMLIB, and how to predict how much zAAP and zIIP eligible work you have on z/OS. This is a basic session, and will prepare you to understand more advanced information. Thu, 20 Nov 2008 11:03:53 GMT System z http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8505 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8007 Oracle’s applications feature complex architecture with server farms on different layers. A constant growth of users, increase inthe data volume, as well as complexity of business transactions require Oracle customers proactively estimate capacity of their installations. This session discusses an application sizing methodology employed by Oracle’s Hyperion performance engineering group. The methodology used, in concert, load testing and queuing network modeling tools. After calibration model generated estimates of transaction response times and server utilizations for different what-if sizing scenarios. Thu, 20 Nov 2008 11:03:53 GMT Computer Performance Evaluation http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8007 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8805 Virtualization and VMware are hot topics today but both come with challenges. In this presentation, we will focus on performance in Virtual environments and especially on VMware. - How to manage the hosts from a performance perspective? - Why we cannot forget the guest machines. - What to manage and how?During this presentation we will answer these questions along with the ultimate question; how to keep users happy while saving money in our optimized VMware world? Thu, 20 Nov 2008 11:03:53 GMT http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8805 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8302 In this session, we will hear about interesting applications of Apdex in the field. Several organizations are using Apdex in creative ways and achieving good results. The session will show how organizations create Apdex reports using innovative measurement approaches and report generation. The speakers will show some sample reports and how they are used in their company. Thu, 20 Nov 2008 11:03:53 GMT http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8302 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8044 HiperDispatch was introduced with IBM’s z10 server. HiperDispatch was designed to (1) minimize the z10 hardware performance degradation caused by processor cache misses, and (2) maximize the amount of CPU processing power associated with any single logical processor. This paper provides an overview of the z10 hardware implications that require HiperDispatch, explains the algorithms that existed before HiperDispatch, presents an introduction to HiperDispatach concepts, and describes performance considerations when implementing HiperDispatch. Thu, 20 Nov 2008 11:03:53 GMT Hot Topics http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8044 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8210 Today's culture of rapid technology refreshes benefit the technology vendor provider far more often than it does the customer. In a financial climate where technology must pass ever increasing justification tollgates it is imperative architects/engineers/support managers understand when and how to avoid unnecessary refreshes and how to structure necessary refreshes to their benefit. This session will identify the significant driving forces behind technology refreshes and provide a frame of reference for end user’s to identify when and how to leverage technology for cost savings. Thu, 20 Nov 2008 11:03:53 GMT Management http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8210 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8217 This presentation-only session will discuss some of the basic system tuneables in AIX for an Oracle environment and will then go into some of the resources you can request from your DBA to help with tuning. We will also look at an AWR report to determine what other areas that should be examined when tuning a system. This is written from the perspective of an AIX administrator, not a DBA Thu, 20 Nov 2008 11:03:53 GMT Linux and Unix http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8217 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8084 How often does the need arise for modeling and forecasting? Should it be done manually by ad-hoc,by project requests or automatically? What tools and techniques are best for that? When is trending forecast enough and when is a correlation with business drivers required? The answers to these questions are presented in this session. The capacity management system should automatically provide a small list of resources that needs to be modeled or forecasted;a simple spreadsheet tool can be used for that. This technique method is already implemented on the author’s environment with thousands of servers. Thu, 20 Nov 2008 11:03:53 GMT Computer Performance Evaluation http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8084 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8505 Looking for a basic understanding of the z/OS Workload Manager (WLM)? This session will introduce setting performance goals for z/OS workloads. Techniques for understanding and choosing between response time and velocity goals as well as setting importance levels will be presented. How to qualify into service classes the different z/OS workload types that WLM manages using classification will also be covered. Finally, how all this data looks in several basic RMF reports will also be introduced. Thu, 20 Nov 2008 11:03:53 GMT System z http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8505 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8081 Workload analysis on the mainframe can be complicated if your business runs operations 7/24 with hundreds of applications. At our enterprise, we have a success story where the Z-series MIPS capacity has been held flat for more than two years. Each month every application is measured for current activity and compared to a baseline. Those applications that exceed a variance threshold are detected as “out of standard” or OOS for short. The OOS applications receive scrutiny to determine a named cause of the variance. This session provides basic instruction and lessons learned. Thu, 20 Nov 2008 11:03:53 GMT Computer Performance Evaluation http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8081 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8806 A stir through the current Virtual technologies and how to plan Capacity Management activities for success. The meat and potato technologies we will be looking are VMware, Windows 2008 & Hyper-V, and various UNIX technologies. Learn the key metrics that you need to be aware of to make your Capacity Management activities thick and meaty. Thu, 20 Nov 2008 11:03:53 GMT http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8806 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8303 You can't manage what you can't measure. This session will showcase the best tools as identified in an industry tools survey. Measuring performance is a fundamental foundation for any performance management strategy. However good tools also need to find true problems, help diagnose issues, report performance in a business meaningful way, and improve the productivity of the IT staff. Apdex is best utilized when it is part of a comprehensive solution. Thu, 20 Nov 2008 11:03:53 GMT http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8303 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8176 Data centers are becoming more environmentally constrained and it’s time for the capacity manager to step up to the forefront and help out. This case study analyzes one such data center. It describes a five step approach to mitigating data center constraints, delaying a costly data center upgrade and data center relocation. Best practices will be described, including data center level metrics in the industry, and recent governmental work in the data center metrics. Thu, 20 Nov 2008 11:03:53 GMT Hot Topics http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8176 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8122 One of the challenges in analyzing performance data is discovering inter-relationships between different attributes. We present a visualization technique that compares multiple software releases by displaying performance attributes gathered on running different workloads on a storage server. We construct salient visualizations that help analysts, experts and engineers to explore, analyze, see trends, patterns, and identify performance bottlenecks. We use simple geometric objects that vary their spatial position, color and texture appearance to encode different performance workload attributes. Thu, 20 Nov 2008 11:03:53 GMT Storage http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8122 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8166 With all the tools for capacity and performance management available from SAP which ones do you use and how? This session discusses Intel’s Capacity and Performance Management Procedural Practices. It details Intel’s use of QuickSizer, Early Watch Reports, Service Level Reports, Wily Introscope, Central Performance History dashboard and reporting, and the development of SAP capacity plans in the day-to-day workings of SAP capacity and performance management. Thu, 20 Nov 2008 11:03:53 GMT Management http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8166 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8200 Probabilistic models have been used to analyze the performance of computer systems and communication networks for more than four decades. They have been used in other branches of science and engineering even longer. In many cases, such models provide accurate results despite the fact that their underlying mathematical assumptions are unlikely to be met. The key to this puzzle lies in understanding the distinction between distributional and trans-distributional properties. This distinction leads to new insights into the surprising accuracy of stochastic models in many real world settings. Thu, 20 Nov 2008 11:03:53 GMT Computer Performance Evaluation http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8200 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8505 Today your z/OS system is filled with transactions and server address spaces of all types. Remote DB2 queries, Stored Procedures , WebSphere App Server, CICS, IMS, WebSphere MQ, Unix Daemons, etc., etc. How does the Workload Manager (WLM) deal with all these different kinds of work? It uses a number of WLM services - enclaves, application environments, execution delay monitoring services along with a combination of response time and velocity goals. This session will cover these advanced WLM services along with proper use of classification rules and RMF reporting, all wrapped together in one quick hour of useful WLM information! Thu, 20 Nov 2008 11:03:53 GMT System z http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8505 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8083 At times the analysis of a performance problem will identify a particular DB2 application as the culprit. You may even have the problematic SQL. But do you have any idea what to do next? Changes to application software are costly and time-consuming. Here is a documented set of steps to apply DB2 tuning from the most passive levels to the most invasive. A rehash of wisdom from the experts, this basic triage process shows how to perform effective performance tuning for the least cost and effort. This process has been applied to legacy applications, in-house development and purchased products. Thu, 20 Nov 2008 11:03:53 GMT Computer Performance Evaluation http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8083 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8807 Join us to learn how to automate your MIPS Management efforts. You will also see how AutoStrobe, a feature of Compuware's Strobe product, enables you to focus Application Performance Management efforts on those application performance issues of high priority. In addition see how AutoStrobe is able to interface with the Vantage Service Manager and Fault Manager tools to alert people to performance issues on the Mainframe. Thu, 20 Nov 2008 11:03:53 GMT http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8807 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8304 Several members of the Apdex community have noticed ways in which Apdex can be improved. This panel session will describe the various changes being proposed along with the new issues generated by keeping Apdex a unified standard. Attendees will be encouraged to join in the discussion. The goal of this session is to make Apdex better for as many enterprises as possible so your participation is critical. Thu, 20 Nov 2008 11:03:53 GMT http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8304 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8004 Internally built applications can do damage to the enterprise if the performance or capacity of the system is unacceptable soon after implementation. At the same time SOA, virtualization, and other technologies are clouding how to accomplish performance testing. Over a couple years a standard approach has been developed for defining and analyzing performance test plans. The guidelines ensure that the plans are put together so as to ensure useful results without being unrealistic in their hardware expectations. This ''auditing'' approach will be defined and illustrated using real-world examples. Thu, 20 Nov 2008 11:03:53 GMT Computer Performance Evaluation http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8004 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8098 Performance baselining of applications is increasingly becoming essential before deployment. It requires extensive and detailed planning and simulation of Production scenario. This paper covers my experiences and recommendations that can be adopted when planning of production workload simulation and performance baselining of applications is being done. These experiences might help in eliminating rework and achieving best results from the exercise thus reducing the overall cost of the application development. Thu, 20 Nov 2008 11:03:53 GMT Computer Performance Evaluation http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8098 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8108 This article will describe methods of extracting SMF data on a daily basis for specialized monthly reporting. A practical method of collecting data, storing and saving for processes like MSU reporting, security audits, software auditing and sub capacity reporting. This will show examples of data extraction and selection based only on the data needed for a given time period. Most examples will use JCL, the IFASMFDP program and programming examples as a method of automating SMF utility control parameter creation. Thu, 20 Nov 2008 11:03:53 GMT Computer Performance Evaluation http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8108 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8138 Software development organizations are increasingly becoming more focused on performance evaluation and improvement. An initial process for performance evaluation is proposed and has been studied on a software application under various configurations and workloads. This method, using a combination of threshold analysis and correlation cluster analysis on collected performance measurements, identifies key relationships among different computer performance measurements, as well as existing bottlenecks without detailed knowledge of internal system information. Thu, 20 Nov 2008 11:03:53 GMT Computer Performance Evaluation http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8138 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8189 Aligning IT with Business, including End User Experience, is accomplished in a business climate with the following three items: 1) Business value - determined by the End User 2) Performance = the End User Experience. 3) Business and IT Views - graphically displayable from each perspective. With these items, IT can identify and monitor its business services quality and able, on a real time basis, to adjust their quality level. Conversely, business is able to manage their end user services by alleviating the IT issues which negatively impact the bottom line. Let’s see how this is done. Thu, 20 Nov 2008 11:03:53 GMT Management http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8189 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8298 When you enable a cluster for DRS (Dynamic Resource Scheduling), VirtualCenter continuously monitors the distribution of CPU and memory resources for all hosts and virtual machines in theCluster. When a cluster enabled for DRS becomes unbalanced, DRS makes recommendations ormigrates virtual machines, depending on the automation level, or policy that has been defined. DRS must be implemented in order to provide High Availability for the VMs on a host and there are many configuration requirements for the processor, network and storage to facilitate the migration of VMs between hosts. Capacity planners need to understand the implementation considerations as well as automation level that best suits the applications in the environment. Reserve capacity for the server and storage are also required for a successful implementation. This presentation reviews the options available as well as alternative solutions to create a high availability implementation. Considerations for Disaster Recovery will also be presented with Consolidated Back-up as well as third-party tools for replication of data. Thu, 20 Nov 2008 11:03:53 GMT Hot Topics http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8298 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8405 TBD Thu, 20 Nov 2008 11:03:53 GMT Hot Topics http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8405 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8031 The Storage Performance Council (SPC) is a cross-vendor team of storage performance experts that has built the industry’s first benchmarks for storage. These benchmarks are the standard for decision making in many organizations. The SPC has used real-world workloads as the basis of the benchmarks that are vendor-neutral and platform independent. Many SPC-1 and SPC-2 results have been published to date. This panel session will discuss the status of the SPC and the Storage Industry standard performance benchmarks available and under development including Component Benchmarks and SPC-3. Thu, 20 Nov 2008 11:03:53 GMT Storage http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8031 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8218 This session will describe the new AIX tuning parameters along with the changes to performance/tuning methodologies for AIX V6. The new algorithms for memory management will be discussed as well as the defaults that AIX V6 now deploys. We will have a discussion on workload tuning vs. system tuning and have an open forum/panel on tuning and Power 6 experiences at the end of the session. Thu, 20 Nov 2008 11:03:53 GMT Linux and Unix http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8218 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8074 Performance analysts and capacity planners should have at least a rudimentary understanding of HTML coding. While poorly coded HTML can lead to performance problems, you are probably more likely to be interested in using HTML to present your own data. While there are many reporting tools that produce HTML output, sometimes it is preferable to modify the HTML from these tools or create your own HTML so you can present the data in the exact manner you chose. Fortunately, the basics of HTML are not hard to learn and this paper is designed to start you on that journey. Thu, 20 Nov 2008 11:03:53 GMT Computer Performance Evaluation http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8074 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8508 What is capacity planning? How does it differ from performance tuning? How do I get started? If you've been asking yourself these questions, then this is the CMG-T course for you. As the name implies, capacity planning for computer systems is about predicting the future. Financial planners do that all the time so, not surprisingly, many of the tools and techniques are similar. The difference lies in the data to be analyzed and the metrics used to express computer system performance rather than financial performance. And just like today's fast-paced business climate, IT decisions are made and revised so rapidly that merely providing your management with a sense of planning direction is often more important than calculating the compass bearing. Elsewhere, I have called this kind of tactical planning, *Guerrilla Capacity Planning*. This boot camp course will get you in shape in three sessions:Part 1. How to Get Started- Definitions vs buzzwords- Myths and magic- Other data sources: rumor, trade-rags, TPC.org, SPEC.org, slashdot, arstechnica- Developing Rules of Thumb- Three Steps to Success Thu, 20 Nov 2008 11:03:53 GMT Computer Performance Evaluation http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8508 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8901 Previous versions of Windows Server have enabled increasing levels of power optimizations and controls, and Windows Server 2008 R2 will continue that trend. This talk will discuss the various power management optimizations in past and future Windows releases, as well as provide power measurement data from multiple workloads and servers. Thu, 20 Nov 2008 11:03:53 GMT http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8901 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8808 The days of having one computer and one application are few and far between. In today’s world of IT computing it is more common to find an application that spans across multiple servers and multiple platforms. How does a capacity planner deal with this type of situation? This session will show how to use the TeamQuest tools to be able to model a multi-tiered environment. Thu, 20 Nov 2008 11:03:53 GMT http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8808 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8900 Although most organisations run regular batch suites that are business critical to the enterprise it is relatively unusual to hear of concerted attempts to model these applications. This paper describes the possible reasons behind this and proposes an approach to modeling that can result in an easy to use model that can predict accurately the batch run times using readily available tools and very simple techniques. Thu, 20 Nov 2008 11:03:53 GMT http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8900 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8613 With recent advances in networking technology networks are running faster and are larger that in the past. The speed of the network has been increasing faster than the speed of the processors and memory so it is more important, and harder to get the tuning right. This presents challenges in tuning high speed networks. This session covers the TCP/IP performance of high speed network adapters like 10 GigE and Infiniband adapters. Most of the tuning is of TCP/IP through tuning from within an application, adapter interface tuning and system global tuning. Finally, the session will discuss some of the issues related to tuning for high bandwidth adapters. It will include scaling and clustered systems where there may be a mixed environments of low speed and high speed adapters in the same server. Thu, 20 Nov 2008 11:03:53 GMT Network/Internet http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8613 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8906 The price of solid state disks (SSD) are beginning to compete with traditional spinning disks in the enterprose storage market. By avoiding seeks and rotational delays, SSD has the potential to dramatically improve the performance of disk storage. This article shares some early experiences using SSD to improve the performance of DB2® for z/OS® in a laboratory setting, and the lessons learned from this study. Thu, 20 Nov 2008 11:03:53 GMT http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8906 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8409 TBD Thu, 20 Nov 2008 11:03:53 GMT http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8409 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8142 When an analytic model or sizing tool predicts CPU Performance, it uses (1) queuing theory calculations and (2) a representation of relative performance for each CPU configuration. This session focuses on (2) using a sample CPU rating system from www.spec.org. Our research results include an algorithm for finding functions to describe relative performance, as well as specific properties of general and vendor-specific functions. These results can be directly applied to any case where the CPU vendor supplies limited benchmark data compared to the number of CPU configurations actually available. Thu, 20 Nov 2008 11:03:53 GMT Computer Performance Evaluation http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8142 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8508 What is capacity planning? How does it differ from performance tuning? How do I get started? If you've been asking yourself these questions, then this is the CMG-T course for you. As the name implies, capacity planning for computer systems is about predicting the future. Financial planners do that all the time so, not surprisingly, many of the tools and techniques are similar. The difference lies in the data to be analyzed and the metrics used to express computer system performance rather than financial performance. And just like today's fast-paced business climate, IT decisions are made and revised so rapidly that merely providing your management with a sense of planning direction is often more important than calculating the compass bearing. Elsewhere, I have called this kind of tactical planning, *Guerrilla Capacity Planning*. This boot camp course will get you in shape in three sessions:Part 2. Metrics and Management- Metric relationships- Errors, accuracy and precision- Little's law- Times and rates- ITIL connecting computer processes to business processes- Setting service delivery targets- Tools and techniques- Dashboards vs. windscreens Thu, 20 Nov 2008 11:03:53 GMT Computer Performance Evaluation http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8508 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8104 Considering taking an advantage of pureXML applications on DB2 9 for z/OS? This session will discuss what you can expect on performance and general practices on capacity planning for XML applications. These best practices are based on the laboratory performance measurement results. They include the expectation and consideration of applying zAAP and zIIP redirection for XML System Service. The session should bring you up to speed on understanding the performance impact of XML applications and basic performance tuning points that need your attention. Thu, 20 Nov 2008 11:03:53 GMT System z http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8104 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8809 The introduction of the Virtual Environments in the open systems arena has introduced a complexity in reporting. Being able to report on virtual and host layers has become an essential part of the IT environment. In this training session, TeamQuest Analyzer will be used to show utilizations at the guest and host/frame. We will show what data is important in the virtual environment and what statistics may not be as reliable. We will focus on the virtual environments of Solaris, AIX and VMWare. Thu, 20 Nov 2008 11:03:53 GMT http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8809 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8187 ITIL has huge momentum and is well summarized as being “documented ITSM common sense.” Its main objective is to help newcomers find a sensible path towards 'Good Practice'. This paper describes what Bad Practice can achieve.ITIL is a bit like motherhood and apple pie – you can’t knock it. But you can observe some of the misconceptions and spurious detail that has emerged around it over the years.This session starts with comments about ITIL and its history and then submits piercing reviews from two perspectives, that of application development and that of the ITIL process practitioner. Thu, 20 Nov 2008 11:03:53 GMT Computer Performance Evaluation http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8187 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8602 CMG was founded in part on the notion that “If you can’t measurement it, you can’t manage it." But what should be done with measurements once they have been collected? Equations and spreadsheets are only part of the answer. If measurements are transformed into carefully crafted visual images, management can be more effective and it becomes significantly easier to discover and understand factors that govern the performance of complex systems. This panel of A.A. Michelson winners will share their favorite examples of especially interesting visualization techniques from a variety of areas. Thu, 20 Nov 2008 11:03:53 GMT Hot Topics http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8602 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8029 The Cheap Revolution has become a buzzword for the large-scale adoption of low-cost components and/or free software in the data center. The Cheap Revolutionaries have begun to argue that their compelling cost advantages should motivate the wholesale adoption of SATA disks for data center storage. This session develops a broad-brush but quantitative analysis of wholesale SATA adoption as a disk strategy. We find that, compared with standard fibre channel drives, current SATA technology does offer a very different, but viable way to bring disk performance, capacity, and cost into balance. Thu, 20 Nov 2008 11:03:53 GMT Storage http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8029 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8149 Business organizations face a daunting task of maintaining the peak performance of their applications, on failing which they have to incur heavy revenue loss in terms of increased IT investments and abated reputation. To alleviate this problem, performance engineers often turn to various performance testing solutions, which, on the other side, introduce their own hefty expenditure in organization’s overall IT investment. This paper proposes an approach that allows organizations to leverage open source technologies for economical and effective performance testing of applications. Thu, 20 Nov 2008 11:03:53 GMT Computer Performance Evaluation http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8149 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8105 The number of guests that an ESX host can optimally sustain is an important capacity measurement for a virtual infrastructure. This paper explores the relationship of various host attributes and performance metrics to aggregated Ready-Time (RT) performance. Using guest RT as a host capacity indicator other host capacity indicators, such as CPU utilization, I/O, and distribution of guest types, i.e. single, dual, or quad virtual CPU, are quantified. This paper provides insight into how the quantification of host attributes and performance capacity relate to an optimum guest capacity. Thu, 20 Nov 2008 11:03:53 GMT Hot Topics http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8105 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8508 What is capacity planning? How does it differ from performance tuning? How do I get started? If you've been asking yourself these questions, then this is the CMG-T course for you. As the name implies, capacity planning for computer systems is about predicting the future. Financial planners do that all the time so, not surprisingly, many of the tools and techniques are similar. The difference lies in the data to be analyzed and the metrics used to express computer system performance rather than financial performance. And just like today's fast-paced business climate, IT decisions are made and revised so rapidly that merely providing your management with a sense of planning direction is often more important than calculating the compass bearing. Elsewhere, I have called this kind of tactical planning, *Guerrilla Capacity Planning*. This boot camp course will get you in shape in three sessions:Part 3. Going Guerrilla:- Case study: Sizing a mainframe- Case study: Data warehouse optimization- Case study: Forecasting service demand- Case study: Virtualization prats and pitfalls Thu, 20 Nov 2008 11:03:53 GMT Computer Performance Evaluation http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8508 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8159 Enterprise Flash Drives were recently introduced into the high-end storage array market. These drives have unique characteristics that influence their deployment. This session will present some preliminary performance numbers on EFDs and discuss best practices discovered so far. Thu, 20 Nov 2008 11:03:53 GMT Storage http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8159 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8810 Thu, 20 Nov 2008 11:03:53 GMT http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8810 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8187 ITIL has huge momentum and is well summarized as being “documented ITSM common sense.” Its main objective is to help newcomers find a sensible path towards 'Good Practice'. This paper describes what Bad Practice can achieve.ITIL is a bit like motherhood and apple pie – you can’t knock it. But you can observe some of the misconceptions and spurious detail that has emerged around it over the years.This session starts with comments about ITIL and its history and then submits piercing reviews from two perspectives, that of application development and that of the ITIL process practitioner. Thu, 20 Nov 2008 11:03:53 GMT Computer Performance Evaluation http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8187 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8604 IBM has introduced new specialty engines such as the zAAP and the zIIP. The performance analyst and the capacity planner need to understand these technologies and how to integrate them into their current environments to ensure they are getting the most from the technology. This session will describe the latest planning information for zIIPs/zAAPs and will discuss their impacts on processor capacity and performance. Thu, 20 Nov 2008 11:03:53 GMT System z http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8604 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8227 This panel is intended to explore best practices around capacity planning on Linux and Unix platforms. We will also discuss ways in which our panelists hone their skills and update the models which they utilize for capacity planning on their platform.Panelists include: Jaqui Lynch of Mainline Information Systems, Susan Schreitmueller of IBM, Adrian Cockcroft of Netflix. Thu, 20 Nov 2008 11:03:53 GMT Linux and Unix http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8227 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8063 Service Level Agreements (SLA’s) comprise one or more Service Level Objectives (SLO’s) for meeting an overall SLA interval target value. This session will describe techniques for tracking interim SLA compliance and modeling the end-of-interval SLA value. Several predictive strategies are discussed and illustrated. The model can driven by achieved daily values of SLO’s within the current SLA interval or by historical values from a baseline period. A new projection strategy of Fit to Target is also described, in which future SLO values are derived, such that the SLA target value will be met exactly. Thu, 20 Nov 2008 11:03:53 GMT Management http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8063 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8215 Analytic modeling and sizing techniques for performance analysis and capacity planning have existed for over three decades. How do the latest UNIX and Windows virtualization strategies get represented? This presentation demonstrates a selection of modeling and sizing techniques specific to the architecture of the virtualization’s measurement data as well as to the architecture of the virtualization itself. Examples include IBM AIX partitions, HP nPar and vPars, Solaris containers, and VMware virtual machines. Similarities and dissimilarities of sizing techniques are cataloged. Thu, 20 Nov 2008 11:03:53 GMT Computer Performance Evaluation http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8215 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8507 Do you want to know how to get end-to-end response time for your TCP applications? Wouldn't it be nice to break it out into application vs. network time? In the first part of this session, we will show how you can get response time for various TCP applications such as Telnet, CICS, FTP, and web server. Then, we will discuss how to think about response time monitoring for Enterprise Extender. How do we define, match and break out a transaction into its components when so many headers are involved? We will again see if we can break out the time into application and network time, this time for packets flowing over HPR over UDP. Thu, 20 Nov 2008 11:03:53 GMT Network/Internet http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8507 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8179 It’s no secret that performance metrics are key to performance management. Having immediate access to those metrics will simplify your life as a performance analyst. There are numerous advantages to automating the collection of performance metrics and building a Performance Database. We’ll show you how to reduce hours of research time into seconds with easy preparation and planning. Real world examples will be used to demonstrate the impact you can have on your company’s bottom line with automated charts and reports generated from your PDB. Thu, 20 Nov 2008 11:03:53 GMT System z http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8179 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8811 Virtualization and VMware are hot topics today but both come with challenges. In this presentation, we will focus on performance in Virtual environments and especially on VMware. How to manage the hosts from a performance perspective ? Why we cannot forget the guest machines. What to manage and how? During this presentation we will answer these questions along with the ultimate question; how to keep users happy while saving money in our optimized VMware world? Thu, 20 Nov 2008 11:03:53 GMT http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8811 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8188 IBM’s PowerVM on System p provides a powerful virtualization layer to the Power platform. This paper covers information learned while spelunking through the documentation along with experimentation in AIX environments running in various configurations of PowerVM partitioning. Specifics include how to interpret data values provided by performance tools like: iostat, lparstat and topas. Thu, 20 Nov 2008 11:03:53 GMT Linux and Unix http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8188 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8092 The key challenges the industry faces today in the adoption of SOA revolve around Performance management and Service Governance. Traditional approaches to performance management have been highly technology oriented. Given that SOA is mostly an enterprise-wide business-led IT initiative, tuning SOA applications for performance needs an enterprise outlook to provide tangible benefits. In addition to optimizing the applications for performance, the key to performance management lies in understanding the ecosystem - that involves optimizing the business-processes & information flow across the enterprise Thu, 20 Nov 2008 11:03:53 GMT Hot Topics http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8092 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8147 This session will cover the capacity planning process and considerations in a multi-generation node Teradata DataWarehouse environment. It will include workload characterization based on data loads, transforms, and reporting. Also covered will be customer interactions with application owners, job scheduling, and the use of advanced analytics in planning and forecasting capacity requirements. Thu, 20 Nov 2008 11:03:53 GMT Computer Performance Evaluation http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8147 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8026 The intense dependence on technology has also introduced new risks that have large financial consequences. The only rational reason for spending money to manage operational risk in the IT environment is the expectation that the benefits outweigh the costs. Subjective measures can lead to serious errors of fact. Traditional methods as those used in a BIA, are fatally flawed and provide no investment guidance. This session will describe a comprehensive process for economically measuring operational risk which will provide the cause-effect link missing from the dysfunctional BIA method. Thu, 20 Nov 2008 11:03:53 GMT Management http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8026 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8096 Although management consultancies offer audit services based on ranking sites’ IT processes against their peers, many companies prefer to identify any gaps in their adoption of good practice for capacity management. This is more objective, reveals “unknown unknowns” and relies less on attitude surveys. This session reviews a number of such gap analyses. Irrespective of the enterprise culture (performance “just adequate”, or “mission critical”) the same approach is applied. Good capacity management measures workloads and performance to ensure that business needs are met now and in the future. Thu, 20 Nov 2008 11:03:53 GMT Computer Performance Evaluation http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8096 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8507 Many companies are not optimizing their TCP/IP networks. This is a critical task and can save hard dollars in both CPU time taken by the stack and in the bytes transferred over the network. In our work, we have seen from 20% - 80% overhead at many companies which can be eliminated fairly easily.In this session, the speaker will discuss:- Unneeded traffic - where is it generated?- Unnecessary TCP sessions - why?- TCP errors which can be eliminatedWe will conclude by looking at productivity on Enterprise Extender networks. Thu, 20 Nov 2008 11:03:53 GMT Network/Internet http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8507 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8120 IBM introduced Parallel Access Volumes (PAVs) in 1999 to facilitate mainframe customers moving to larger logical volume sizes. This presentation will review the history of PAVs and describe some test results that compare the performance benefits of Static PAVs, Dynamic PAVs, and HyperPAVs. Thu, 20 Nov 2008 11:03:53 GMT Storage http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8120 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8812 Well, maybe not EIEIO (Old McDonald is presenting on that one) . Join Metron-Athene for an educational seminar covering an overview of the Capacity Management process and how it fits into ITIL v3. Then, get a brief overview on how ITIL and the Capacity Management process fit into the ISO20000 requirements and audit. Thu, 20 Nov 2008 11:03:53 GMT http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8812 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8065 Many enterprises are looking to server consolidation and virtualization to reduce operational cost while others are offloading work from mainframe and UNIX severs onto "blades" and "rack optimized" servers, to save on the price of acquisition. When do these activities make sense? While there are many other considerations, the comparison of the capacity of disparate platforms for the various workloads in the infrastructure inevitably comes into play. This paper will explore the basic ideas about relative capacity and how to use them to match work to platforms which are "fit for purpose". Thu, 20 Nov 2008 11:03:53 GMT Hot Topics http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8065 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8904 TBD Thu, 20 Nov 2008 11:03:53 GMT http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8904 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8222 If you have a System z performance question, this is the panel for you. Some of the many performance related questions this panel of experts can answer include: System z processors, processor configurations, general Sysplex considerations, z/OS system performance, WLM anything, variable Workload License Charges, WebSphere, etc... Come prepared with questions, email them as soon as you can to zos_panel@cmg.org, or drop a written question into the Q&A box you will find at various ''System z'' track sessions, or hand your written questions to any ''System z'' session monitor. Panelists include: Ivan Gelb of Gelb Information Systems, Kathy Walsh of IBM, Peter Enrico of Enterprise Performance Strategies, Clark Hunter of Compuware Corporation, Norman Hollander of CA, Inc.. Thu, 20 Nov 2008 11:03:53 GMT System z http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8222 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8111 Precise measurement of task execution time is central to resource management and performance characterization of systems. Tasks are often repetitive with short execution times depending on workload characteristics. CMPs facilitate these tasks to execute concurrently. In contrast to sequential case, precise and repeatable execution time measurement of concurrent, symmetric, and short duration tasks is a challenge. We review known time measurement methodologies, used in benchmarks, and introduce a precise and repeatable methodology for measuring concurrent symmetric tasks on CMPs. Thu, 20 Nov 2008 11:03:53 GMT Computer Performance Evaluation http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8111 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8042 As Yogi Berra said, ''You can see a lot just by observing.'' This paper presents some observations on Linux I/O at the intersection of exploratory data analysis and analytical modeling. Examples include a comparison of the performance characteristics of the four Linux I/O schedulers on a disk-intensive benchmark, visualizing the inverse correlation between seek activity and throughput, and determining the capacity function of an I/O subsystem using scatterplot matrices and other graphical tools. Thu, 20 Nov 2008 11:03:53 GMT Hot Topics http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8042 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8507 What should be monitored in real time to find if connections or applications are headed for trouble? The performance metrics to monitor are the following: - Congestion window- Round trip time- Round trip variance- Retransmissions- Duplicate acknowledgments- Bad status- Hung connectionsIn this session, we will discuss baselining for TCP/IP. Setting appropriate thresholds may be the most critical portion of this whole task. You may have 'Red letter days' in your industry. These are very high volume days. On such days, the thresholds should be different. In this session, we will discuss all the complexities of baselining and how to do this automatically.We will end by discussing an interesting security requirement from the U.S. Federal Government's Office of Management and Budget. The memo OMB 06-16 states that mobile and remote access devices should be reauthenticated after 30 minutes of inactivity. We will discuss how this may be accomplished and some of the pitfalls. Thu, 20 Nov 2008 11:03:53 GMT Network/Internet http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8507 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8903 This presentation will provide a reasonably detailed overview of the HiperDispatch function of the IBM z10 processors. The motivation for and the constructs of HiperDispatch will be explained. User feedback of experiences is still limited, partially because the analysis necessary to determine the value is challenging and has little reward for the work. There are very few opportunities to tune the function. Nevertheless, some user experiences have value to prospective users and said experiences will be discussed. Thu, 20 Nov 2008 11:03:53 GMT http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8903 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8813 This session will reveal methodologies and several case studies which demonstrate the use of passive agent less technology to measure and analyze multi tier transactional applications. Examples of enterprise applications such as billing and customer service as well as financial trading Applications will be discussed.In addition, this session will review the various challenges and solutions available to measure latency of both one way and round trip response time for these multi- tier applications. Certain application monitoring tools relying on synthetic transaction generation and agents are not viable solutions - only passive agentless measurement is the preferred option - this session will explain why it is necessary to reconstruct through semantic recognition, the full logical business transaction by passively capturing each and every packet on the network. Thu, 20 Nov 2008 11:03:53 GMT http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8813 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8038 Computer engineers rely on system-driven metrics to assess performance. Likewise, business analysts look to revenue-relevant metrics to gauge the health of a business. How system metrics relate to business metrics is one of the most difficult questions facing many companies today: Will this investment in hardware upgrade result in user satisfaction? What is the business impact in implementing the slower user interface? Drawing from psychological and retail research, this paper presents key user experience concepts that connect the numbers and the dollars. Thu, 20 Nov 2008 11:03:53 GMT Hot Topics http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8038 http://www.cmg.org/cgi-bin/agenda_2008.pl?action=more&token=8206 Managing the performance of software that is outsourced can be a minefield. As the client you might assume that your contractor is using good software performa