(1) The Internet of Things and It's Impact On Our Application Economy
The IoT wave is predicted to deliver almost 30 billion new connected devices. Thatís a lot of new data fighting for capacity with existing enterprise systems. How will you process IoT data points based on business needs? How will you ensure sufficient data center and compute capacity for the applications that depend on IoT data? Learn how a more forward-looking capacity planning strategy is needed now more than ever to guarantee that you will be able to ride the IoT wave.
(2) Performance Testing Mobile Apps - Tips and Tricks
Mohit will walk you through mobile performance testing and analysis approaches applicable to browsers and native apps. Using case study scenarios, Mohit will demonstrate specific tools and techniques to enhance your performance testing and diagnosis arsenal.
Mohit Verma has 15 years of experience in software testing during which time he has used a variety of tool suites and implemented solutions for numerous complex environments. Currently he is the Lead Software Performance Architect at Tufts Health Plan. His prior employment includes being a Performance Engineer at John Hancock Financial Services. He holds a master's degree from Brandeis University.
(3) Tradeoffs When Choosing An APM Solution
Having an APM solution is no longer an option for most enterprises given the growing SOA complexity, use of cloud services and hosting provides, and push for DevOps culture. Fortunately, the APM space has matured in depth and sophistication to monitor production environments. However like most IT efforts, APM solutions are also budget and time constrained so trade-offs must be made. This presentation will provide an overview of APM, trade-offs faced when deciding on which solution to pick, and examples of trade-offs made from several customer implementations.
Rob Jahn is a senior performance architect and Joe Sicree is a technical architect at Collaborative Consulting based in Burlington, MA. They have experience assessing, designing, building, and using a variety of APM tools on many enterprise applications.
(4) Implementing A Massive Benchmark Project
This presentation will demonstrate some of the challenges, lessons learned, and tools developed in the course of a major benchmark collaboration effort between a software startup and a customer/investor. Topics include: team organization, benchmark test case design, tools developed for automation, using a resource manager to run benchmarks in parallel, and using Google Sheets for collaboration.
Lance Hartford is a performance engineer with NuoDB, a distributed database software company in Cambridge, MA. Lance has extensive performance and software engineering experience in the insurance, software, and consulting industries. Ever since receiving an analog stopwatch at the age of 8, he has been obsessed with timing things, and enjoys applying his programming and systems knowledge to tackling the hardest benchmark projects. Lance has B.S. and M.S. degrees in Computer Science from University of New Hampshire and Boston University, and resides in New Hampshire with his wife and seven children.
(5) Flamegraphs and Profiling using a Mac
Flamegraphs are a new way of visualizing call-stacks. They allow the most frequent code-paths, both kernel and user level stacks, to be identified quickly and accurately. Flamegraphs can be generated from any profile data that contain stack traces including various profilers like VTune, Xperf, DTrace and Instruments. In this presentation Rohit will show how to generate flamegraphs using DTrace and Instruments on Macs for both CPU time and memory.
Rohith Bakkannagari is a Performance Engineer at The MathWorks, Inc. Rohit is currently working on automation involving flamegraphs, and is making them accessible to a wider community of engineers. Flamegraphs are a part of their performance toolkit, enabling them to quickly and reliably identify performance regressions and solve other performance puzzles. Rohit holds a masterís degree in Electrical Engineering from West Virginia University and is an avid cricket player.
(6) User Perspective On Detecting Memory Leaks
Continually increasing memory usage is not always a memory leak. It could be a poorly designed program or operating system memory manager at work or both. Is there a way for the program user without access to the source code or instrumentation tools to tell a memory leak versus a memory hog on UNIX?
(7) Peak Season Tuning