gridengine.info : Tag unicluster, everything about unicluster

LSF to SGE Migration Workshop at SC08

dag@sonsorol.org (chris) — Wed, 12 Nov 2008 16:45:39 -0500

For people who will be attending the SuperComputing 2008 conference next week in Austin, TX there will be an interesting full-day workshop on Monday, November 17th entitled "How to migrate from LSF to Unicluster with SGE".

Sure this workshop talks about UniCluster but the foundation of that product is Sun Grid Engine. Much of what will be discussed here will be applicable to both Univa UD customers and the community at large.

Some of the technical information including an LSF to SGE quick reference guide is coming via the Open HPC Management Interoperability (OHMI) project.

Click below to download the invitation:
LSF-SGE-Migration-Invite.pdf

My flight lands in Austin at noon on the 18th so I'll be present for the 2nd half of the workshop.

Q&A on Univa UD Unicluster & Amazon EC2

dag@sonsorol.org (chris) — Wed, 10 Sep 2008 12:05:44 -0400

What does this have to do with Grid Engine? Well the UniCluster Express suite includes Grid Engine with integrated monitoring and reporting tools.

I did a project for Univa UD where I documented the steps required to get their product integrated into the Amazon EC2 elastic compute cloud. That is the whitepaper referred to in the marketing materials below.

I've agreed to participate in a webinar and answer questions about the project, click on through for the full event details.

Amazon Web Services, BioTeam and Univa UD invite you to attend a free, live webinar: "Cloud and Clusters: Running UniCluster in Amazon's EC2"

Date: Wednesday, September 17th

Time: 2:00 pm - 3:00 pm Central Standard Time

Presented by leaders in HPC and Web Services, this webinar will provide IT decision-makers and System Administrators a unique opportunity to access real world information and examples of deploying clusters in a cloud environment.

Attendees will:

-Learn about Amazon's EC2 web services, the UniCluster open sourcesoftware stack, and deployment of this software within EC2

-Gain insight into key data points from the people out in the field making it happen

-Be able to engage in a technical Q and A with the author of the technical white paper: "Deploying UniCluster in Amazon EC2"

Learn more about the webinar and register to attend at:

http://www.univaud.com/hpc/webinar20080917.php

Univa UD UniCluster Express (and Amazon EC2)

dag@sonsorol.org (chris) — Mon, 14 Jul 2008 19:55:25 -0400

Univa is a company that I became familiar with when Steve Tuecke gave a talk at the 2007 Grid Engine workshop in Regensberg, Germany. Steve's talk was called "Univa Open Source HPC Cluster and Grid Software" and you can download the PDF version here.

Steve's talk and his company were pretty interesting and he specifically hit on some areas I had mentioned in my talk on "LSF vs. SGE" where we discussed the lack of ISV and commercial entities capable of supporting the Grid Engine community with service, support, consulting, training and other "value added" activities. I came home from Germany thinking that Univa would be worth watching (also Steve had dropped some hints informally about 'some news may be happening soon...') -- and sure enough a short time later Univa became "Univa UD" as Univa and United Devices became a single company.

If you point a web browser over at http://grid.org or the corporate site at http://www.univaud.com you'll quickly see that they have a product out called "UniCluster Express".

Cluster stacks are normally not all that exciting to me but Univa is doing something different that makes it worth checking out ...

Click on through for the full article ...

The UniCluster Express stack is free, 100% open-source and contains the following core components: Grid Engine, Grid Engine Analysis & Reporting Console (ARCo), Ganglia, Globus and a custom Java based central monitoring console application.

But that is not the really interesting part. The eye catching bit is that Univa UD is offering free support for this integrated stack.

Yep.

Free support for an integrated stack including some really complex bits like SGE ARCo and the impossible-for-most-mortals Globus stack (heck, I attended a GGF meeting and actually sat through the Globus tutorial and still could barely get it functioning in my lab environment...)

Univa UD has taken already popular open-source compute farming technologies, added in a new Java based monitoring console and bundled everything up into a installable tarball. Free support comes through grid.org and I'm guessing that they plan to actually make money by offering customization, commercial support and other services to people willing to pay.

I recently took the software for a spin myself and got it integrated into the Amazon Web Services EC2 elastic compute cloud framework. My work was written up as a HOWTO whitepaper and was documented in a series of recorded screencasts.

One of the screencasts is linked to at the top of the article, all of the others are available by following this URL:
http://www.screencast.com/users/BioTeam/folders/UniCluster-in-Amazon-EC2

If you want the PDF Whitepaper you'll have to get it via a web form over at http://www.univaud.com/hpc/wp-unicluster-amazon-ec2.php.

Disclaimer/Disclosure: In my role as part-owner/employee of BioTeam, my company earned money on this project. Univa UD basically challenged us to get their stuff working in EC2 and offered to pay for a few days of consulting time. A more detailed disclaimer can be found within the whitepaper.