1072 - Application Performance Management
Using web analytics it’s possible to obtain useful performance metrics for an application in runtime. This information when fed into a regression model can provide accurate transaction resource demand which can be used to plan and predict capacity for future application enhancements and changes. The paper presents a novel approach to automate gathering of useful user interactions with the web application using web analytics and then have a dynamic performance model help understand application trends, capacity requiremetns and predict capacity thereby enabling continuous capacity planning.
The success in setting standards in the IT management following ITIL, among other challenges, depends on its adaptability to network management, ie, to traditional tools that use SNMP for fault and performance management. Integrating these two concepts, ITIL and network management, improves the use of best practices in a automated management. We present a case study, where incident, change, and configuration management are used in a open software tool.The results integrates governance, and operational environment, facilitating incident notification messages and processes definitions.
1070 - Performance Engineering and Testing
The layered queueing network model has been very useful for solving performance models of distributed systems with client-server interactions. Fast analytic solutions exist for a broad range of models. However, models which contain elements which cannot be solved using approximate mean value analysis (MVA) must instead be solved using simulation or another approach. In this work, a hybrid solution strategy is used where MVA is used for part of the solution, and another solver, in this case simulation, is used for the remainder.
1069 - Performance Engineering and Testing
Analysis of highly efficient air based datacenter coolingsystems versus new emerging technologies with liquid based datacenter coolingsystems. Review of ASHRAE TC 9.9 assessmentof liquid based cooling in datacenters. Data-center best practices with an assessmentof PUE (Power Usage Effectiveness) andcomparison in pump, fan systems energy use among systems.
1068 - Application Performance Management
IT is being challenged to free up resources, reduce consumption, and avoid unnecessary costs while maintaining a high level of service. IT-savvy people know that tuning is the WHAT which can achieve all three objectives; but it can be difficult to get changes implemented and much less clear is the HOW of measuring results. This paper will examine a standard process developed and used to create, track, test, implement, and finally measure tuning savings in an objective, consistent manner, across both mainframe and distributed, application and systems.
1067 - Performance Engineering and Testing
In this paper, I intend to show the comparison between the various flavors of Virtualization available in the market. I have taken VMware ESXi, KVM and Xen Virtualization for this evaluation. A Java based IO intensive application is deployed and load tested with the available resources and IO traces are measured.
1066 - Performance Engineering and Testing
This paper aims to provide the analysis of response time variations for an online application with different amount of workload. Common behavior is being observed that for a particular user workload in the system causes surprising performance results. During the analysis, an author explores various parameters which has a significant role in response time behaviour. Effect of these parameters on different load conditions has been presented.
As we see proliferation of disruptive technology like virtualization and cloud computing, existing infrastructure operation management are cumbersome, slow to response and most important prone to errors.The current process-find a problem, send alert to human,and then manual intervention to fix should now be - find a problem, automatically re-mediate,and send alert to humans.This paper will investigate and demonstrate how automation is leading to better up-time,lower cost of operation and fewer service disruption both for capacity and performance management of cloud infrastructure.
1064 - Performance Engineering and Testing
With the evolution of broad range of programming languages, programar have a wide range of options for their application based on maturity of language and the performance desired. In this paper, comparative study has been performed between the JAVA, C & JNI performance. To avail the best performance across these various options have been analyzed and compared. Evenif the study has been done for messaging application, then also presented analysis can be easily mapped to other kind of application. This study provides a platform to find the available language options for desired performance.
1063 - Performance Engineering and Testing
In this paper, we present a systematic evaluation of the most popular SPEC benchmark suites. Our goal is to show that SPEC component-level benchmarks need to be evaluated from the standpoint of redundancy and completeness, and that such procedures can be efficiently used for tuning of existing benchmark suites and reducing the cost of benchmarking.
Cloud Computing allows businesses to quickly scale so that IT departments can easily adapt to changing demands. However, during the adoption of this exciting approach to solve IT needs, a number of pitfalls are often not factored properly. Myths have existed since the time when limitations existed and new ones surface due to lack of understanding. This presentation attempts to address the top 10 performance-related myths experienced by the presenter during the implementation of a successful cloud computing approach.
IT organizations are constantly challenged to keep pace with changing technology trends like virtualization and cloud, while maintaining quality of service and SLA of their current and legacy infrastructure. The challenge is that different systems in the infrastructure parses, aggregates and process data very differently. This paper presents a real world use case to show how Delta Dental with BMC Capacity Optimization was able to define common baseline across their disparate infrastructure systems like x86 servers,virtualization technology from different vendors,Storage and other devices.
The ITIL® Capacity Management process is comprised of three key sub-processes: 1) Business Capacity Management 2) Service Capacity Management 3) Component Capacity Management. This paper explores forecasting and analytical techniques such as he Natural Forecasting Unit (NFU), Key Value Indicator (KVI), Natural Business Unit (NBU). It then examinex some of today’s advances relevant to the three sub-processes and analytical approaches to holistic, business-based capacity planning, including: BI, Business Analytics, Predictive Analytics, Workload Automation, Virtualization, Cloud Computing
Faced with the problem of large and continuing increases in SMF/RMF records, the requirement to have online web reports ready for early morning status calls, and increased demand for inclusion of more high volume data types (e.g. DB2, MQ), the author of this paper designed a “divide and conquer” approach to processing data into MXG databases, one that is very scalable and efficient. This approach has proved successful in being able to process over 500 million input records daily, with longest batch job running over 2.0 hours.
In the beginning, there was Green Bar… This paper will examine the evolution of performance monitoring and reporting, from printed static reports to hyperlinked, drill-down “Click to Know” reporting. Though most shops still employ “what happened?” reporting, useful monitoring and reporting is increasingly about proactively alerting “what’s going to happen?” so action can be taken to PREVENT user-impactful incidents. You might be surprised at what sophisticated reporting is possible using tools you may already have. Presentation will conclude with a real-time tour of our reporting website
Cloud services give us a lot of web hosting opportunities these days. We will discuss experiences with a number of alternative hosting approaches in the cloud. This includes measurements of their uptime, performance and scalability. We will also present some cost models for cloud based webhosting. If time permits we can have a look at how cloud providers work to make webhosting so affordable, allowing us to parafrase Dolly Parton’s famous line: "it takes a lot of money to make webhosting this cheap"
Capacity planners need to compare the processing power of different hardware systems and ensure that the enterprise capacity needs are fulfilled optimally. Multiple vendors and a huge mixture of hardwares present in an enterprise make this a challenging task. This paper defines the common consumption unit (CCU) in relation to hardware performance/processing power comparisons in an capacity management program, outlines the key techniques and usefulness. It also illustrates the approaches with several case studies from an Enterprise Capacity Management program implemented in a large telecom.
1055 - Performance Engineering and Testing
Amdahl’s Law predicts the program speed-up on multiple processors when serial and parallel proportion of the program is known. In practice, estimating these, is not easy. Hence one resorts to testing. Based on testing, the speed-up and the Serial / Parallel proportions can be found. Amdahl’s Law is applicable to activities that can be parallelized on multiple instances. Using this property, we show the Law can be applied to a state-space of a combination of 2 resources to get performance predictions. Performance can thus be projected for explosive number of test cases based on minimal testing.
1054 - Performance Engineering and Testing
Performance Testing(both unit and system) are useful to understand application performance characteristics. For HPC applications,system perf testing becomes complex as simulating very high throughput inputs might need custom load injectors and for applications with complex workflows,simulating proper transaction mix and maintaining stable backend database size can be complex.Unit performance testing/POC of components may involve detailed workload and throughput modeling. Monitoring various data points(latency,throughput) and debugging(log levels) is tricky because of the overheads those incur.
Best Practice to Measuring the Performance in a Cloud
Estimating right hardware capacity is beneficial and sometimes essential for IT organizations.Capacity planning techniques are used towards this and the goal is to decide the right amount of hardware required to achieve acceptable service demands conformance,now and in future.For very large scale applications,it is especially beneficial to have understanding of the hardware capacity requirements and its dependency on workload/various application and technology changes/enhancements/upgrades.Hardware capacity models of different nature and complexities are built towards fulfilling this goal.
1051 - Application Performance Management
Optimization of application memory footprint has always been a fascinating proposition. Despite rapid strides in technology resulting in drastic reduction in the memory costs, it continues to be a limited resource especially in mainframe environment. While good software programming skills can’t be substituted, there are a number of techniques that can be deployed to optimize the memory footprint. The paper presents the case of a C++ application on mainframe where a 25% reduction in memory footprint was achieved leading to significant performance improvements.
Amdahl’s law and the universal scalability model are functions of the number of machine processors p, therefore only modeling a single machine with varying quantities of homogeneous processors. These models cannot directly predict software capacity for: heterogeneous machines (varying in their threads and clock speed); virtual machines (on the same server, migrating across servers or scaling-up). We addresses these shortcomings by: (1) generalizing and extending these models to cover heterogeneous machines and virtualization, (2) proposing model building methods for QA and production systems.
Regular forms of Amdahl’s law and the universal scalability model are functions of the number of processors p alone, therefore modeling only data sets with a single machine varying in its processor count. This paper demonstrates how these performance models can be expressed in terms of intrinsic machine characteristics such as: processor clock c; external resource access speed es; total threads t; etc. Our new models broaden all previous applications including: sensitivity analysis, forecasting, scaling; while providing new ones such as evaluations for: migration, purchase, upgrading, etc.
Modern business’ high reliance on IT has led to rapid growth in IT estate. With rising energy cost and global regulations, it’s important for IT organizations to reduce their environmental impact. Measurements & Improvements have to be carried out in the following areas: Data Center, End user computing, People, IT Service & IT Asset Management. The speakers would share their experience of designing & implementing a Green IT based optimization exercise based on this approach, which has been used to reduce the carbon footprint by upto 80% including best practices, detailed checklists & how-tos.
In the search for dramatic transformation, IT organizations world-wide are virtualizing and consolidating their datacenters. While this exercise receives good attention, there is little change in the day-to-day delivery of services, resulting in continued poor experience for users. During this presentation, the speakers will share best practices or “mantras” for driving a Service Catalog Driven Engagement (CDE) Model that has helped organizations achieve upto 30% productivity improvement. The speakers will also share checklists, how-tos and guides on setting up and achieving this.
Applications and organizations are regularly being confronted with security attacks at record levels. This presentation discusses techniques to test for and prevent security breaches, pass audits from outside vendors while keeping your external facing websites running at optimal performance levels.
Description A temporarily reduction of the buffer pool pages from a specific TDB2 database being performance tested, prevents the data from being cached in memory and will produce actual non-cached response times throughout the when the test and during the peak perioud of several hundred user sessions.
1044 - Performance Engineering and Testing
Large companies are complex to run, and the Enterprise Resource Planning (ERP) software packages they implement can entail running several thousand batch programs in a single day. Analysis and optimization of these batch windows presents a significant performance analysis challenge. This paper presents a case study in which a batch window of over 3000 individual jobs is analyzed for its critical path using some very simple techniques to build Gantt Bars which allow a dynamic, visual analysis of the window. A custom application is presented which automates the building the Gantt Bars.
1043 - Performance Engineering and Testing
Many times load testing is dismissed as a waste of time and money because past results didn’t conform to real world experience when the application went live. Sometimes it’s because the test suite is too narrow but often it is due to the approach used to produce traffic and the way results are interpreted. This discussion focuses on the later situation because a lack of testing scope is an obvious limitation but poor quality traffic and improper analysis techniques are subtle shortcomings that impact test credibility in ways that aren’t always clear until the live application reveals them.
1042 - Performance Engineering and Testing
Competition is increasing, available resources are stretched, and budgets are limited. The general economy is in large part still in severe crisis. In these challenging conditions, what are the opportunities for implementing and rolling-out valuable System Performance Engineering (SPE) initiatives, be professionally successful and prevent the risk to be considered “redundant”? This paper presents the author direct experiences, defining and practically implementing a flexible SPE approach, in multiple and actual Web Portals and IPTV projects.
The role of the capacity planner is changing - they are required to apply analytical skills and provide timely deliverables that can be easily consumed by other teams to ensure that IT is aligned to business. This presentation discusses the benefit of solutions that automate all the phases of the capacity mgmt. process, including data collection, sophisticated analyses, forecast models, by-exception reports and visualization in near-real-time dashboards. In particular, we describe how major financial companies have successfully leveraged a solution that meets these requirements.
Organizations world-wide are struggling to justify their IT spend. This presentation illustrates a case study where the speakers implemented an ITIL based Business Change Methodology to enable Portfolio Management Transformation and Value Realization of Business Change. This presentation describes an approach to rollout a Business Change in an Enterprise from 0 i.e. the time when a business change is conceptualized to 100 i.e. the time when value is realized, in 3 simple steps. The speakers will share their best practices, detailed approach, checklists and how-tos.
The paper will give full technical overview of data and information structure, where information is defined through unique information global key. It will examine new initiatives such as "NoSQL" and "Big Data”, giving the answer why their methods do not provide permanent solution, but just accommodate current exponential information growth applying scalable technology. It will explain data recycle process, through example of technical implementation. Final result of the paper will be full presentation of a new paradigm where information growth is insignificant.
1038 - Application Performance Management
The conventional software performance engineering process is limited to certifying, tuning and benchmarking the product according to client requirements. Critical performance problems are identified at later stage of development. Today, the fundamental challenges faced by performance engineers are identifying the performance bottlenecks at root, predicting the performance parameters and planning the perfect hardware capacity requirements at early stage of development. The paper presents our approach to overcome challenges and enhances the performance engineering process management of product.
A methodology to estimate the constant parameters of Universal Scalability Law (USL) has been proposed by Dr.Gunther. Certain theoretical inadequacies of the subject methodology is found when applied to some typical example data sets. An improved methodology is proposed that circumvents the problems. USL is compared against Super-serial Scalability Law (SSL) for accuracy. SSL is found to be more robust than USL in case of noisy input data.
A methodology to estimate the parameters of Super-serial Scalability Law (SSL) was initially proposed by Dr.Gunther. SSL was substituted by Universal Scalability Law (USL) later. SSL is reported to be able to handle performance issues better at times when USL fails. Some theoretical drawbacks of the initial methodology and a new methodology circumventing the problems were reported by the authors before. More improvements to the methodology to better deal with noisy performance measurements are reported here and effectively applied to noisy performance data.
As performance analysis and capacity planners, we collect data to share with co-workers and management in order to explain and justify our technical capacity and performance recommendations. To display this data, we often create the easiest graphs and don’t consider how it is perceived. This paper discusses ways to visualize your data and describes scenarios in which these visualizations should be used to transform data into useful information. We discuss common ‘mistakes’ and ways to improve your charts to better get your point across and better represent your intended message.
The paper shares some challenges the Online Banking Capacity Management team had and overcame during the Solaris to AIX migration. The raw capacity estimation model was build to estimate AIX frames capacity needs. The Capacity planning process was adjusted to virtualized environment. The essential system, middleware and database metrics to monitor capacity were identified; business driver correlated forecast reports were built to proactively tune entitlements; IT-Control Charts were created to establish dynamic thresholds for Ph. Processors and IOs usage. Capacity Council was established.
1033 - Performance Engineering and Testing
A corporation is planning on ramping up their use of Web Report Studio (WRS) by adding several users in waves. Two questions emerge: 1) what happens to WRS response time when several users are added, 2) At what point is a hardware upgrade inevitable in order to maintain performance. This paper examines a scalable WRS load generator and ‘grows’ the workload and examines results as each ‘wave’ of new users is simulated. A second Capacity Planning technique is also introduced for a non-BI SAS workload that relies on SAS/CONNECT to simulate and measure a SAS workload.
As new technologies emerge, how well positioned is your IT Asset Management system or process? What are some of the common practices used today to ensure your IT Asset Management system is delivering value to your Forecast and Budget? What items are needed to be tracked in your Asset Management system for use in your IT Chargeback rates, Cost Allocation model, or Showback model? How do you make necessary changes to your Budget and Forecast when budget changes are requested or when the business dynamically improves?
Remember when you only had a handful of servers or a single mainframe to manage? Back in those days, we also had teams of experts working on capacity and performance management. Now, one person is managing 1000’s of servers. It isn’t possible to manage as you have in the past – you need to change the game, eliminating manual processes wherever possible. Learn how to work smarter and have more fun on the job by letting go of the past and venturing boldly into the future of capacity planning. Build a vision and the management skills to create it.
1030 - Performance Engineering and Testing
There are a lot of technical measurements for measuring the performance of a website but they are not very good at expressing the actual user experience. This session will introduce a visual measurement technique that we have been using at Google that better represents the user experience as well as several use cases and real-world examples.
The paper talks about the following five ways to have a positive impact on business Integrate Mobile with other channels Connect with your customers Focus on Usability Track and Improve Keep a pulse on the continuously evolving technology
Six Sigma methods and techniques are applied in Business & Information Technology (IT) projects for product (Goods and Services) & process design (Define,Measure, Analyze, Design and Verify or DMADV) and improvements (Define, Measure, Analyze, Improve and Control or DMAIC). Six sigma methodologies have been applied within the IT Service Management disciplines primarily for Service and Process Improvement & Optimization. As the service industries look forward to the advent of service products, there is an attempt to minimize variations in service quality via service design and improvement.
1027 - Performance Engineering and Testing
Benchmarking is critical when evaluating performance of modern network attached systems. With the growing popularity of network attached system, the file system is becoming a critical part of a system. Measuring file system performance is complicated operation. The problem is that existing file system benchmarks are insufficient, suffering from difficulties ranging from not scaling with evolving technology to not evaluating modern NAS systems. The aim of this study is to identify some of the major issues involved with file system benchmarking in modern network attached storage systems.
As of SAS 9.3, SAS has moved ODS Graphics and the Statistical Graphics procedures from SAS/GRAPH® to Base SAS®. This provides an opportunity to eliminate SAS/GRAPH by converting SAS/GRAPH procedures to ODS Graphics procedures if we choose to do so. This is an overview of some ways to convert basic graphs from SAS/GRAPH to ODS Graphics. It provides a brief introduction to ODS Graphics and the SAS statements required to run the ODS Graphics procedures. It then compares some basic SAS/GRAPH and ODS Graphics output along with the statements required to produce each graph.
Statistical Exception Detection (SEDS) is one of the variations of learning behavior based performance analysis methodology developed, implemented and published by Author. This paper took main SEDS tools – IT-Control Chart and Exceptions (Anomalies) Detector - and showed how that could be built by Open Source type of BI tools, such as R, BIRT and MySQL or just by spreadsheet. The paper includes source codes, tool screen-shots and report input/output examples to allow reader building/developing a light version of SEDS.
Confused with all the new functionality in recent z/OS releases and zEnterprise processors? Let one of your favorite IBM instructors walk you step by step through a number of cool new capabilities that are now part of your z/OS performance management world. Let’s slow down and spend some time on line items you have heard about, but not taken the time to really understand. Topics will include the DS8000 I/O Priority Manager, WLM transaction management and LDAP management, workload promotion and what’s reported in RMF, hiperdispatch, etc. Fun and fast and extremely useful!
As a mainframe sysprog in 2012, what is your reaction to the term “cloud computing?” For many of us, it is simply confusion. What do vendors, or your boss, or the IT industry mean today when they say “cloud computing.” Is the term even relevant any more? Don’t let all the hype cloud your thinking. Let Glenn clear the current fog for you in this enlightening session that will net out just what you need to understand about the current state of cloud computing.
The Platform Performance Mgmt component of IBM zEnterprise Unified Resource Manager extends a goal oriented performance management capability to both traditional System z and BladeCenter applications. This session introduces the intersection of WLM, RMF, and Platform Performance Mgmt, and helps you understand the leading-edge performance management capabilities of zEnterprise for hybrid applications. Recent announcements, including load balancing and API’s for data access will be covered. The session will also examine techniques to manage and improve z/OS capacity planning for the zEnterprise.
1021 - Application Performance Management
This paper shows how to use free browser tools to perform initial performance investigations and analysis. It shows how the client workstation browser requests and receives web page objects & information, that can be modeled/viewed in a “Project Management” strategy. As a result; prioritizing the object performance investigation (and betterment) along the “Critical Path”, maximizes the effort/benefit of such investigations. (Provides clarity on which objects to focus attention, in order to benefit web page performance.) By the way….. Did I mention the tools are FREE ???
To analyze the performance implications of hardware/software platform changes, elaborate performance testing methodologies are used. Alternatively economic scientific techniques involving standard benchmarks and performance modeling are applied. Using Industry benchmarks, which provide comparative hardware performance ratings, model can predict performance for hardware changes but not for software platform changes. Here we present our experience of using performance modeling with hardware/software benchmarks to predict system performance on varying platform combinations for a web application.
This is a test. This is only a test. Were this a real submission you would be reading something far more interesting than a test.
In this paper I will present a technique to identify trends and anomalies in Performance data using wavelets. I will answer the following questions: Why use Wavelets? What are Wavelets? How do I use them?
Lets stop gambling that everything will be okay and start planning to make sure it is. Organisations talk about how effective their incident and problem processes are. These areas become the focus for resourcing and there is a pride in how well the fires are fought. If we could prevent the fires, how much easy would things be and we can if we refocus our resources on the foundations the so called dull proactive processes of capacity, performance and availability management. Get these implemented effectively and the fires will reduce allowing us to focus on improving service
Social Media for the Performance Professional - or why blog and tweet and how not to get in trouble doing it. This session will highlight social media types, producers and consumers, tips for getting started, and social media rules of thumb.
Severs, Networking, storage, virtualization, and software for IT infrastructure management, automation, and orchestration optimized as a solution in a box ready for rapid deployment. Some of the benefits are lower cost, increased IT agility, and performance. With the most popular benefits are enabling rapid deployment for private and public cloud computing services including Infrastructure as a Service (IaaS), Platform as a Services (PaaS), Landscape as a Service (LaaS) and Software as a Service (SaaS).
1014 - Application Performance Management
Performance—responsiveness and scalability—is a make-or-break quality for applications. Many projects consider performance objectives as an afterthought. As a consequence, the application may fail to respond rapidly enough to end user actions or may be unable to handle the number of business operations required. This is the APM challenge and how an IT organization responds to it will have a profound impact on its position within the corporation. Meeting this challenge will reduce overall project costs by minimizing production break fix which is costly, let alone risky and stressful.
1013 - Performance Engineering and Testing
Agile Methodology brings in new complexity and challenges to traditional waterfall driven performance engineering approaches. We will discuss a Agile Performance Testing Lifecycle of a mission critical Web 2.0 app. We will discuss when as performance engineers to get involved in the project lifecycle, understanding the technical architecture, what are the NFRs,what tools to use, what value pairing with Developers and Test leads provides, how the rapid changing environment effects your test scripts, make tuning suggestions and how to communicate efficiently to the project teams.
We live in a technology driven world. IT is deeply embedded in the operating fabric of the modern organization and is now highly dependent on IT. Simultaneously, and quite unintentionally, IT introduced exposures that have seeped into every layer of the organization. Organizations are more likelihood to experience a large loss from IT interruption than from any disaster or ‘black swan’ event. Risk economics provides the cause-and-effect linkage that is deficient in the traditional approaches and improves business decisions relative to investments that reduce the risk of an IT interruption.
In order to determine availability of certain applications, it is essential that trending data be established to associate different times and other indicators. Statistical software provides the ability to formulate trending analysis, but some of the software is prohibitively expensive. This paper describes several kinds of statistical software that can not only determine trending of data, but can do so at no cost to the user.
1010 - Performance Engineering and Testing
Containing cost while distributing, accessing and collecting data across the Internet for a company with a worldwide presence can be a daunting task. In this paper, the author presents his research for new algorithms that position nodes in the topology of the Internet. The algorithms are based on a compact model of the Internet delay space. With this new approach, peers are selected with a bias for those nodes in the same neighborhood. For verification purposes, the new system is benchmarked against a conventional P2P system using simulation techniques.
Confused about SMS? Do your Storage Administrators intimidate you when discussing how to best use SMS for DB2? Not sure if your company is conforming to best practises for SMS and DB2? Come and understand what SMS means and how to relate what your DB2 needs to the Storage Administrators.
Maybe you are concerned about your DB2 environment or maybe just want to validate your environment, so you are thinking about an IBM ATS DB2 Health Check. You are thinking, what really happens in a DB2 Health Check? What will I walk away with? Why does ATS really need this detailed information and what will they do with it? Find out the answers to these questions and more by attending this presentation. You will leave understanding why the ATS DB2 Health Check is truly one of the best in the industry and how it will benefit you and your company.
Choosing the correct DB2 table (Space) type is very confusing. Should I go with a segmented table space, a UTS (if so, a PBG or PBR), HASH, or maybe good old classic partitioned? How about the page size? I now have a choice of 4K, 8K, 16K, or 32K for my table space and/or index. Should I choose a multi or single table option? Should I compress the object? Choosing the data’s correct type and size the first time is essential to avoid costly outages. Come learn about best practices in choosing the correct types and settings for your data.
Modern disk and tape does not resemble older technology. What is the real picture regarding modern disk and tape? How does the newer technology change the management of your DB2 environment? How does performance change? The real question is, why do I care about this new technology? Come and find the answers regarding the new technology, and how to best leverage it for your DB2 environment.
Remember when you only had a handful of servers or a single mainframe to manage? Now, one person is managing 1000’s of servers, at least one private cloud, virtualization and more with changes being applied to the system every day, if not every hour. It isn’t possible to manage as you have in the past – you need to change the game, eliminating manual processes wherever possible. Learn how to work smarter and have more fun on the job by letting go of the past and venturing boldly into the future of capacity planning.
Take a storm chasing expedition in the cloud, and experience the often unappreciated complexities of moving from Kansas to Oz , while circumventing the dangers lurking along the Yellow Brick Road to success. This user story, from a cloud provider’s perspective, will take the reader on a journey of discovery through the design and implementation of a newly hosted application, as well as, a perilous race to find an elusive and dangerous creature hidden in the cloud. Always pay attention to the man behind the curtain!
Uncertainty tends to grow (Second Law of Thermodynamics). We discuss a new method to staunch this growth when we have a model correlating a dependent variable with independent variable(s) and a forecast of the latter. Use cases go from sizing the capacity of a web site to a database; a host SPEC number to its memory; any entity whose performance can be linked with the business metric. A real-world example is worked through that demonstrates how this technique works to improve the performance metric prediction and highlight trends that would have been overlooked otherwise.
Little’s Law is well known: number of concurrent users of a resource equals the product of arrival rate and the holding time of one user. Somewhat less known is the fact that Little’s Law is based on the assumption of stationarity of the underlying processes. But at The Knee, all assumptions break down because this is where the system is not stationary anymore. Without going into an existential discussion of The Knee, this paper proposes a solution that allows an estimation of concurrency that is “not too low, not too high; just right” for non-stationary conditions.