Attila Szegedi shares lessons learned tuning the JVM at Twitter, spending most of his talk discussing memory tuning, CPU usage tuning, and lock contention tuning.
Attila Szegedi discusses performance problems encountered at Twitter running Java and Scala applications, presenting how they solve them through JVM tuning.
Gil Tene explains the workings of a garbage collector: terminology, metrics, fundamentals, key mechanisms, classification of current GCs, the “Application Memory Wall” problem, and details Azul C4 GC.
Burt Beckwith discusses potential performance problems using mapped collections and Hibernate 2nd-level cache in GORM, along with strategies for avoiding such performance penalties.
Alois Reitbauer shows how to do performance testing of complex software systems during development, testing, and production by starting early in the development phase, breaking the test into pieces, and testing continuously. He also shows how to perform scalability tests on limited hardware or by using the cloud.
Examining the role of monitoring and testing techniques in solving DevOps problems.
Stefan Norberg presents Unibet.com’s architecture, the challenges faced and the solutions adopted in order to sustain live and offline betting over an entire continent. They started with a monolithic database and moved towards a finely tuned front-end architecture - XHTML 1.0, CSS 2.1, YUI, caching, compression, image spriting, CDN striping – plus using multiple replicas for scaling out.
Neal Ford shows what ThoughtWorks learned from scaling Rails development: infrastructure, testing, messaging, optimization, performance.
Mark Thomas, a member of the Apache Tomcat PMC, explains the tuning process for Tomcat, JVM and the applications running on them considering different usage patterns, hardware and network configurations.
Martin Fowler talks about ThoughtWorks's experience with using Ruby on client projects for the past three years, and the creation of a Ruby-based product 'Mingle'.