CMG IMPACT 2019
Feb. 19 to Feb. 21, 2019
Hyatt at Olive 8, Seattle, Washington, USA
IMPACT Speaker Sessions
Performance and the software development life cycle | Mark B. Friedman
This talk presents best practices for integrating performance into each phase of software development, from specifying performance requirements to instrumenting applications during development to track progress against performance goals, to stress testing during the QA, and through DevOps.
How to mitigate slow run-time risk against in web applications | Mark B. Friedman
The importance of maintaining capacity planning in the next era of the mainframe | Chris Walker
As the cost of resources has declined, the discipline of capacity planning practices has relaxed. Ironically, workloads have become more complex and the expertise needed to measure and plan for them are dwindling. The mainframe is the lifeblood of the business. Come and see what best practices can be leveraged.
Building a representative, effective model to randomly generate valid sequences of web page visits for load testing | Andre B. Bondi
Co-written by Andre Bondi and Apeni Lotha: We used a compiler design technique to build an extensible, modifiable program and workload model to randomly generate valid sequences of web pages for load testing. We used mathematics to predict the relative counts of page visits before testing occurred. This method reduces perceived scripting efforts.
Using Excel VBA to tour useful BMC TrueSight Capacity Optimization (TSCO) internal public tables | Todd Voros
BMC TSCO (TrueSight Capacity Optimization) has a number of publicly available internal tables (PV_* tables) that can be useful to know. The presentation discusses what they contain and how they can be accessed using Excel VBA.
Java performance troubleshooting and optimization at scale | Kingsum Chow, Jonathan Lu, and Sanhong Li
On November 11, 2017, Alibaba smashed its own online transaction record once again: the peak number of transactions per second reached 325,000. This talk describes how it achieved comprehensive and efficient performance profiling for large-scale applications by building tools based on OpenJDK.
Addressing load generators and how to reduce incorrect system performance results metrics | Jim Brady
A load generator that launches web requests in bunches produces incorrect system performance results. Until now, there were no tools for load testers to identify the problem. In this talk, a free downloadable tool is used to evaluate request timing quality by comparing a test run stat with real user behavior.
How to analyze and plan for a mainframe upgrade | Scott Chapman
When considering upgrading the mainframe it is always best to conduct an analysis of the options instead of just relying on a business partner’s recommendation. But since it is an analysis that is only done every few years, most sites are unfamiliar with the process.
The fine art of combining capacity management with machine learning | Charles W. Johnson Jr.
Capacity management within the enterprise continues to evolve. In the past we focused on hardware, today we focus on services. The amount of data available has increased significantly. To be successful with this discipline going forward, we need the machines to do more of the heavy lifting.
From the move from monolith to microservices. An introduction to DevOps in SaaS tool sets | Yuri Ardulov
Moving from monolith to microservices, it is necessary to build a successful SRE organization that will help to obtain a high goal of 5 nines for the organization’s services. It is impossible to make this journey successful without taking extra steps and without building an additional set of tools.
A new foundation in understanding AI's impact on business and IT | Rick Lebsack
Artificial Intelligence (AI) has moved from the domain of universities to businesses. It is easy to get lost in the new terms, not to mention the deep math, that let machines assist humans—be it phone unlocking, password protection, or detecting criminals. This talk provides a foundation for understanding AI’s entry to general IT.
Avoiding Mistakes in Large Scale Performance Analysis | Kingsum Chow
When tackling many servers in the data center, saving a small percentage of servers would bring significant return. We will describe how we identify performance opportunities at scale, and how it is different from optimization on a single system.
Effectively using and managing container workloads | Per Bauer
Containers are becoming a popular way to manage workloads. When a new technology breaks into the market, many decide to adopt without a plan for managing performance and capacity. Just like other workloads, it is essential that container workloads are monitored and managed effectively.
Anomaly detection at scale for performance engineers | Tuli Nivas
Automated anomaly detection in production by using simple statistics can be beneficial not only to how long it takes to identify an issue, but also how quickly we can get customers out of an outage. This session demonstrates how simple methods can be used to resolve performance issues at scale.
An introduction to Chaos Engineering for enterprise cloud infrastructure | Gary Little
Wouldn’t you like to know what happens to systems performance when things start to fail? In public cloud environments this is known as “Chaos Engineering.” X-ray is a tool that enables the construction of “Chaos Experiments” that can be run (carefully) in an enterprise environment.
Leveraging HTTP Archive for better web comparatives and analytics | Paul Calvano
Have you ever wondered how your site’s performance and construction compares to the web as a whole? Or how different technologies are used on the web? This session explores how the HTTP Archive works, how people are using it, and how to leverage the data for analysis today.
An exploration of z/OS SYSTEM abnormalities | Mark Cohen Austrowiek
This presentation locates abnormalities in all z/OS areas and understands the correlation between them in seconds thanks to a simple methodology and enhanced view.
Empathy in modern business. How compassion cannot be containerized | Kevin Crawley
As businesses race to the finish line many may lose sight of what truly matters. The audience will walk away perhaps questioning how their interactions could negatively impact their peers and will be equipped with concrete examples of how to practice being more empathetic.
Embracing Blockchain. Best practices and recommendations for Blockchain implementation in the enterprise | Elisabeth Stahl
How are organizations using Blockchain to reduce time, cost, and risk? How can they create a successful first project? This session describes best practices and gives recommendations for Blockchain implementation for the enterprise.
Under cloudy skies. Capacity planning in changing times | Brian L Wong
Much of the world is moving to cloud, and many significant parts of IT are changing at the same time. Capacity planning is far from obsolete, but practicing it in a rapidly changing environment will be very different from practicing it in the past. This session shows where the field is going.
An introduction to the world of AI and Machine Learning | Odysseas Pentakalos and Alex Gilgur
Machine Learning is a branch of Artificial Intelligence (AI) that is providing the fuel for enormous productivity growth all around the world with new applications across every industry. Join this introductory session to learn how it works through a discussion of its key algorithms and some of its applications.
How to build a productive cloud-native organization with OpenTracing | Kevin Crawley
Building a cloud-native organization without having a robust understanding of what your applications are doing in production is near impossible. Exposure to these tools will give engineers making this transformation in their organization a greater understanding behind the need for observability.
The power of personal networking. How to build effective networks, mentors and sponsors | Center for Creative Leadership
The ability to learn from and influence people informally rather than solely based on one’s position in the organization is critically important in today’s workplace. And the ability to influence without authority is directly tied to the networks you build in your professional life. In fact, research shows that strong professional networks are one of the most important factors in promotability. Yet engineers and technologists are notoriously poor at networking and are dismissive of the proven value of networks. In this hands-on workshop, experts from the Center for Creative Leadership (CCL) will discuss the research, tools, and methodologies to understand and leverage professional networks, mentors and sponsors.
Driving innovation in the modern digital enterprise | Majdi Haroun
How EAs, SAs need to evolve towards evolutionary architecture to drive innovation in the modern digital enterprise. This session delivers five case studies with five lessons to learn: Intersection of Modern Architecture and DevOps, operations, deployment, Continuous Delivery Security, both internal and external
Achieving continuous availability | Silvio Orsini, Pietro Tiberi, and Marco Capotosto
This session presents a concept of an automated NFT running on a H24/7D application and focuses on a couple of implemented cases —Disaster Recovery, Chaos Monkey—with the aim of building a predictive and repeatable model for operating conditions under disturbances.
Integrating risk assessment in performance monitoring and capacity management | Chris Greco
Risk is one of the elements that is overlooked when discussing performance monitoring or capacity management. Risk is best understood by the concept of vulnerability versus convenience. This presentation demonstrates how performance monitoring and capacity planning deals with this correlation.
Context-driven performance testing | Alexander Podelko
The recent revolution in the industry opened new opportunities for performance testing; for example, to make it early or continuous. However, performance testing should be considered in full context. The question is not what technique is better, the question is what to use in a particular case.
Demystifying z/OS CPU measurements | Scott Chapman
z/OS CPU measurements seem to confuse many people, especially when trying to understand how all the different CPU metrics relate to each other. The truth is, it is all just CPU time and simple math.
The motivations and benefits of building a home-grown capacity management system | Len Wyatt
Why would anyone build their own capacity management system? We had both technical and organizational reasons, and there have been some surprising benefits. This talk surveys the motivations, the architecture, the tradeoffs and the benefits of creating our own capacity management system.
The new dimensions of cloud. IT infrastructure resource planning, optimization and cost | Karen Hughes
Capacity managers have been helping organizations plan and optimize the use of on-premises infrastructure resources for years. Cloud is adding a new dimension and new challenges to IT infrastructure resource planning, optimization and cost.
A quick-start guide to web performance analysis | Paul Calvano
You need to optimize your site’s performance, but where do you start? Do you focus on the backend or frontend? Which tools should you use? And what can you really expect out of 30 minutes? During this talk you will learn some techniques that will get your performance audit off to a productive start.
Compression and the web experience. Best practices and techniques to reduce website page weight and increase speed | Paul Calvano
How you configure compression matters to your customers’ experience and to your bottom line. With web pages growing >3MB, GZIP is no longer enough. This session dives deep into best practices and techniques that can be applied to reduce page weight.
The past, present, and future of AI | Bryan Knouse
Artificial Intelligence (AI): Where we came from, where we are, and where we are going with a particular focus on natural language technology. This talk is for everyone: non-technical individuals will appreciate the conceptual breadth and CTOs will enjoy the dips into present theory powering the space.
Sushi, beer, and 24-hour work days. An inside view of startup best practices and recommendations | Elisabeth Stahl
Interested in the culture of a startup? Need to work with or market to a startup? Want to learn more about what makes startups successful? Attend this session for the inside view of startups, best practices and recommendations.
Queueing laws and understanding weird performance test results | Andre B. Bondi
Strange features of performance test results can usually be diagnosed by examining how and why the performance measures deviate from standard queueing and performance laws. The structure of the test may also be informative. This is illustrated with some examples during this session.
Capacity management for the digital and the agile world | Jamie Baker
Is capacity management in a DevOps, cloud and agile dominated world still relevant? With Artificial Intelligence (AI) and Machine Learning becoming ever more present and with speed to market being a necessity, do we still need it? And if we still do, how can we ensure that it delivers governance without slowing things down
Managing VMware virtual machines and CPUs | Debbie Sheetz
A holistic approach is defined, identifying metrics from each layer of the virtualization, that is ESX cluster, host, VM, the VM’s operating system (Linux or Windows), and the application in order to determine if the guest needs to be resized or the ESX environment requires changes. CPU is the focus of the presentation.
Machine Learning the demise of static thresholds | Tom Quinn
Machine Learning can relieve you of the time-consuming and resource-intense activity of setting static thresholds, letting you focus on actually tuning the workloads, not just fighting fires. In this session we will look at how current techniques can be enhanced or replaced by Machine Learning.