Blackboard & Throughput RA Webcast Archive
The Sun-Blackboard Reference Architecture for Throughput Computing Webcast is now on-line for viewing for those that missed the live event. Click here.
kevin roebuck's blog: My Almost Daily News
Skip to content, navigation.
What's this? Feeds let you keep up to date with the latest information on a blog or website. Right-click on a feed link and copy the link's URL, then paste it into your feed reader. Some browsers also allow you to click a feed link and subscribe directly.
Excellent, thanks for this; I was unable to attend the live event and I was very pleased to see that it's almost exactly what I've implemented over the summer (with the proviso that I have yet to move to multiple application servers, this having been my next plan).
Also, I'm a little unclear on whether the 600 hits/sec mentioned was using four JVMs on a single T1000 or on four separate machines. On a single T2000 we're currently able to process a sustained 342000 hits per hour which is just about our peak usage. Any pointers to documentation on that application clustering, as it's not easy to find on behind.blackboard.com?
Posted by Ceri Davies on October 12, 2007 at 08:11 AM PDT #
Excellent, thanks for this; I was unable to attend the live event and I was very pleased to see that it's almost exactly what I've implemented over the summer (with the proviso that I have yet to move to multiple application servers, this having been my next plan).
Also, I'm a little unclear on whether the 600 hits/sec mentioned was using four JVMs on a single T1000 or on four separate machines. On a single T2000 we're currently able to process a sustained 342000 hits per hour which is just about our peak usage. Any pointers to documentation on that application clustering, as it's not easy to find on behind.blackboard.com?
Posted by Ceri Davies on October 12, 2007 at 08:11 AM PDT #
Excellent, thanks for this; I was unable to attend the live event and I was very pleased to see that it's almost exactly what I've implemented over the summer (with the proviso that I have yet to move to multiple application servers, this having been my next plan).
Also, I'm a little unclear on whether the 600 hits/sec mentioned was using four JVMs on a single T1000 or on four separate machines. On a single T2000 we're currently able to process a sustained 342000 hits per hour which is just about our peak usage. Any pointers to documentation on that application clustering, as it's not easy to find on behind.blackboard.com?
Posted by Ceri Davies on October 12, 2007 at 08:11 AM PDT #