InfoQ Homepage Performance & Scalability Content on InfoQ
-
/articles/Wait-Based-Tuning-Steven-Haines/en/smallimage/geek.jpg)
A Formal Performance Tuning Methodology: Wait-Based Tuning
In this article, Steven Haines talks about web application performance tuning which used to be more of an art than science. He proposes a method called wait-based tuning, making the entire process more measurable and, consequently, more scientific.
-
/articles/fibers-neverblock-revactor/en/smallimage/image_textile_fibers.jpg)
Using Ruby Fibers for Async I/O: NeverBlock and Revactor
Rails 2.2 is schedule to be thread safe - but will blocking I/O libraries make it necessary to run multiple Ruby instances? We take a look at how non-blocking I/O and Ruby 1.9's Fibers help solve the problem. We talked to Mohammad A. Ali of the NeverBlock project and Tony Arcieri of the Revactor project.
-
/articles/scalability-worst-practices/en/smallimage/image_broken_chain.jpg)
Scalability Worst Practices
In this article, former Orbitz lead architect Brian Zimmer discusses scalability worst pratices. Topics covered include The Golden Hammer, Resource Abuse, Big Ball of Mud, Dependency Management, Timeouts, Hero Pattern, Not Automating, and Monitoring.
-
/articles/scalability-panel/en/smallimage/logo_table.jpg)
Building Scalability and Achieving Performance: A Virtual Panel
Join our industry-heavyweight (eBay, Betfair, FiveRuns and Twitter) panel as they explore the cost of making their sites as scalable as possible, whilst tuning to get the most performance they possibly can. They explore the pros-and-cons of making their apps as awesome as possible - all the while under the pressure of their business requirements.
-
/articles/java-threading-optimizations-p2/en/smallimage/images_java_racetrack.jpg)
Do Java 6 threading optimizations actually work? - Part II
Features like biased locking, lock coarsening, lock elision by escape analysis and adaptive spin locking are all designed to increase concurrency by allowing more effective sharing amongst application threads. But do they actually work? In this two part article, Jeroen Borgers explores these features and attempt to answer the performance question with the aid of a single threaded benchmark.
-
/articles/java-threading-optimizations-p1/en/smallimage/images_java_racetrack.jpg)
Do Java 6 threading optimizations actually work?
Features like biased locking, lock coarsening, lock elision by escape analysis and adaptive spin locking are all designed to increase concurrency by allowing more effective sharing amongst application threads. But do they actually work? In this two part article, Jeroen Borgers explores these features and attempt to answer the performance question with the aid of a single threaded benchmark.
-
/articles/ebay-scalability-best-practices/en/smallimage/logoEbay.gif)
Scalability Best Practices: Lessons from eBay
eBay Distinguished Architect at eBay Randy Shoup explains eBay key scalability practices of partitioning, horizontal scale, avoiding XA, asynchronicity, and virtualization. eBay has hundreds of millions of users, over a billion page views a day, and petabytes of data in their systems.
-
/articles/scalability-principles/en/smallimage/asynchronous.jpg)
Scalability Principles
At the simplest level, scalability is about doing more of something. This could be responding to more user requests, executing more work or handling more data. This article presents some principles and guidelines for building scalable software systems.
-
/articles/scale-with-service-contracts/en/smallimage/spectacular.jpg)
Spectacular Scalability with Smart Service Contracts
Scalability isn't the Boolean value stateless design tends to assume. Udi’s team averts a second failure using service contracts to address multiple dimensions of scale.
-
/articles/real-time-java/en/smallimage/small1.GIF)
Real-Time Java for the Enterprise
Simon Ritter explains the vision and capabilities of the Real-Time Java specification (RTSJ), if your Java app really, really must respond within a certain time regardless of what the garbage collector does, RTSJ is now a possibility rather than a probability.
-
/articles/master-worker-terracotta/en/smallimage/image_clouds_briefcase.jpg)
Implementing Master-Worker with Terracotta
A real world case study of a consultancy that distributed the load & increased scalability of its applications using Terracotta using the Master/Worker pattern.
-
/articles/actors-rubinius-interview/en/smallimage/imageruby.jpg)
Ruby Concurrency, Actors, and Rubinius - Interview with MenTaLguY
With Erlang popularizing Actors, Rubinius adding its Multi-VM, and Ruby 1.9 adding another concurrency primitive with Fibers (Coroutines), a lot of things are going on in the Ruby concurrency world. So we interviewed MenTaLguY, who works on Rubinius, JRuby and many aspects of concurrency in the Ruby world.