I found the answer to my previous parallel job problem, and felt I should post here because the defaults for PBS are not very good. One, is that in a PBS script, you should specify the number of nodes you need like: #PBS -l nodes=1 to run a job on a single machine (in my case)
The other is that PBS queues and servers have an option called MAX_RUNNING which determines the maximum number of simultaneous jobs that the queue or server should push out to the cluster. In my starting setup, this variable wasn't set, and I'm not sure what the default is if not present, but setting it to the number of Nodes in my configuration worked great. start the qmgr then: set queue workq max_running = 20 set server max_running = 20 Hope this helps for the next version of Oscar. mix Brian E. Williams Software Developer and Systems Administrator Quantum Leap Innovations (302)894-8036 [EMAIL PROTECTED] http://copland.udel.edu/~brianw ------------------------------------------------------- This SF.NET email is sponsored by: SourceForge Enterprise Edition + IBM + LinuxWorld = Something 2 See! http://www.vasoftware.com _______________________________________________ Oscar-users mailing list [EMAIL PROTECTED] https://lists.sourceforge.net/lists/listinfo/oscar-users
