InfoQ Homepage Performance & Scalability Content on InfoQ
-
GigaSpaces XAP 6.0：スペースベースアーキテクチャ向けの簡易化SpringベースAPI
GigaSpaces recently released version 6.0 of it's eXtreme Application Platform (XAP), which is an infrastructure software platform that provides scaling out of applications in distributed environments. InfoQ spoke with Geva Perry and Nati Shalom of GigaSpaces to learn more about this release and the changes that have occurred in this version.
-
Rubinius roundup
Rubinius development is rapidly gathering speed, and performance is shaping up well, as seen in recent benchmark results. With even members of the JRuby team contributing and praising its merits, it's time to look at the current state of Rubinius again.
-
Article: The Box: A Shortcut to finding Performance Bottlenecks
Quite often performance problems will be reported with some very antidotal comments that do nothing to help you understand where to start looking. Faced with this dilemma, it is not uncommon for teams to start guessing at the root cause. Now enter "the box", a little diagram that is an abstraction of a complete system. The box is a reminder of the true cases of performance bottlenecks.
-
Presentation: Operational Manageability lessons learned from eBay
You're confident that your software will handle horizontal scale to thousands of servers. But how about your operational team? Have you also architected for managing that large collection of servers? Dan Pritchett will present lessons learned at eBay and lead a discussion on how to ensure your transactional scalability doesn't ignore your architecture's manageability.
-
More on Parallel LINQ
MSDN Magazine has spilled the beans on Parallel LINQ. Parallel LINQ, also known as PLINQ, is a set of LINQ extensions that hide the dirty work of distributing LINQ queries across multiple cores.
-
Presentation: Transaction Management Strategies in Mission Critical Applications
A core part of Spring's middle tier support is the transaction management support. This session presents several interesting "mission critical" cases and shows you how to properly handle them using transactions driven by Spring 2. You'll learn the ins-and-out of the "dark art" that is transaction management within a high-volume mission-critical JEE application.
-
Visual Studio to Finally Address Performance Issues
Visual Studio has been plagued with performance issues that have been getting worse with each version. In a Channel 9 video, Cameron McColl apologized for the past performance issues and talks about improvements for VS 2008.
-
High Performance Ruby MVC: Merb
By some accounts, Ruby on Rails request-processing has slowed 10-20% with each recent release, so Ezra Zygmuntowicz built his own Ruby-based MVC framework using some of the best parts of Rails. Recently, at the Ruby Hoedown event, Ezra demonstrated how Merb keeps the agility of ActiveRecord while focusing on high-load performance and concurrency.
-
Interview: Dan Pritchett on Architecture at eBay
Dan Pritchett gives us an inside look into the decisions behind one of the largest scale architectures in the world: eBay. In explaining how the scale of eBay turns simple requirements a complex engineering problem, he walks us through the technical and organizational challenges of managing eBay's architecture.
-
Ruby 1.9 adds Fibers for lightweight concurrency
Fibers were recently in the Ruby 1.9 branch. The Coroutine-like concept has many uses, such as implementing lightweight concurrency and others. We look at the concept and influences of Fibers in Ruby 1.9, as well as code samples.
-
Ruby Hoedown Presentations available online
Videos of the sessions from the Ruby Hoedown conference are now available online. Topics such as Merb, Ruby tuning, VoIP with Ruby are covered, as well as Smalltalk and Ruby history and much more.
-
Erlang's Mnesia - a distributed DBMS for highly scalable apps
Not every application has the scalability requirements of Google, Flickr or Amazon, however the ideas behind the Mnesia DBMS are compelling: a fast, in-process DBMS that takes advantage of concurrency, with the ability to replicate tables across distributed nodes for high scalability and fault tolerance.
-
New patterns and middleware architecture needed for true linear scalability?
Nati Shalom says existing tier-based middleware cannot for true linear scalablility. Instead he proposes a new middleware stack based on self-sufficient processing units that supports a partitioned/scale-out model. Pat Helland at Microsoft some years ago proposed some new transactional patterns and formalizations to be used in what he calls almost-infinite scalable systems.
-
WSO2 publishes new round of performance metrics for their ESB
WSO2 has recently published a second set of performance metrics for their ESB. It shows that WSO2 ESB outperforms Mule and Apache ServiceMix.
-
Microsoft Research's Accelerator: A Data-Parallel Library for .NET that Targets GPUs
Microsoft Research's Accelerator Project exposes a .NET library for performing parallel data processing using a computer's GPU.