 |
Search |
 |
|||
|
Blogs by Community: Sun GridSun Grid
After JavaOne you feel like the Buridan's Donkey
Unfortunately in these days I don't have much time for blogging. Work is going on and we're optimizing the code for the Sun Grid in order to take advantage of the shared file system and to avoid serializing all the images through the network.
If you happen to be at JavaPolis next week, we will be talking about the project in a BoF Wednesday evening.
Unfortunately in these days I'm pretty busy and I don't have the time for extensively blogging - but I'm happy to say that Mistral, the imaging engine designed for extreme scalability from the multi-core up to the Grid, has been run successfully for the first time on the Sun Grid. :-) It was really exciting to look at the logs and see that the application was scheduled on 102 CPUs 8-). The...
I've been flying under the radar on Java.net for a while. I wanted to let everyone know where I am and about my new gig working for CollabNet on the Sun Grid community site.
I'm sitting here watching Van and his ComputeCycles.org team describe the benefits of Java and Jini in the construction of grid technologies that bridge heterogeneous networks (including firewalls), systems / operating environments and deal with Deutsch's Fallacies of Networking to assist in massively parallel processing (master-worker pattern) - and cannot help but say, pretty cool...
In a...
Along with a number of enhancements, the latest release of Compute Server includes a source code release licensed under the Apache License, v2.0.
If you're using Compute Server and you're not already a test driven developer, then this blog is for you! Time to roll up your sleeves and test the Compute Server project that you've created.
I thought it might be helpful to give a 50,000 foot overview of the recently created Compute Server project.
Today, reliable distributed computing on a grid just got a whole lot easier for Java developers.
As a software quality engineer for a number of advanced technologies for distributed systems, I can't think of a better test bed for qualifying my distributed applications than a pre-installed, pre-networked, pay-as-you-go compute grid.
Sun Grid's resource management semantics basically dictate that jobs be self-contained, and terminate all processes in order to exit. The problem with terminating processes in a grid context is that it's not quite as simple as doing a PID trap on a single host, instead, you need to use the qsub, qstat and qdel commands to better manage your distributed jobs.
The example pattern that I'd like...
There is really a fantastic set of resources available in the Sun Developer Network (SDN). The Sun Grid Community makes active use of both the Java.NET and SDN forums to try and maintain a balance of church and state. I've been told that as part of a Beta program, access to SDN Developer Assistance is free, as in Beer (for a limited time), so please do sign-up and take advantage of this...
Sun Grid looks like a traditional IT stack, exposing common interfaces to enable developers and ISV's to target different abstraction layers:
The core environment is made up of a "Resource Factory" (RF), a production plant that is optimized to produce power at appropriately consumable chunks (balancing the economics of operations/distribution against typically demanded performance units)....
|
|||
|
||||
|
