Hello,

Martin Fowler has published an article (
http://martinfowler.com/articles/lmax.html) on the LMAX architecture, in
case anyone is interested:

>From the article:
--
LMAX is a new retail financial trading platform. As a result it has to
process many trades with low latency. The system is built on the JVM
platform and centers on a Business Logic Processor that can handle 6 million
orders per second on a single thread. The Business Logic Processor runs
entirely in-memory using event sourcing. The Business Logic Processor is
surrounded by Disruptors - a concurrency component that implements a network
of queues that operate without needing locks. During the design process the
team concluded that recent directions in high-performance concurrency models
using queues are fundamentally at odds with modern CPU design.
--

Cordialement,

Matthew.


2011/6/24 Michael Barker <[email protected]>

> Hi,
>
> Given the recent discussion on concurrency and performance in the Scala
> Persistence thread, I thought some of the readers may be interested in an
> open source project that some colleagues and I launched recently:
> http://code.google.com/p/disruptor/.  It's a concurrent structure used at
> the heart of a high performance financial exchange that we've been building
> over the past 3 years (in Java of course).  I also chatted to a few people
> at the round-up about the work we were doing.
>
> It falls squarely into the exceptional case of Dick's "Don't Repeat
> Yourself or Others" rule, so we've thrown it out there in open source form.
>  In its simplest form it's an alternative to a queue, i.e. a structure to
> move data between threads.  We've also added a couple of classes that give
> it the feel of an actor framework (not truly actors, as it's 1 consumer per
> thread).  It's pretty fast, over 3 orders of magnitude lower latency when
> compared to ArrayBlockingQueue.  For those that are interested in the gory
> details, there's a technical paper on the Google code site that does a very
> deep dive into the implementation and describes the results of our
> performance tests.
>
> Mike.
>
> --
> You received this message because you are subscribed to the Google Groups
> "The Java Posse" group.
> To view this discussion on the web visit
> https://groups.google.com/d/msg/javaposse/-/DynCqAEpU0gJ.
> To post to this group, send email to [email protected].
> To unsubscribe from this group, send email to
> [email protected].
> For more options, visit this group at
> http://groups.google.com/group/javaposse?hl=en.
>

-- 
You received this message because you are subscribed to the Google Groups "The 
Java Posse" group.
To post to this group, send email to [email protected].
To unsubscribe from this group, send email to 
[email protected].
For more options, visit this group at 
http://groups.google.com/group/javaposse?hl=en.

Reply via email to