Hi, Here is my usual choices and i did not found reasons to change then yet. Under 300 hosts, Rush does the job, it easy to install easy to conifgure and there is some room for customization.
After 300 hosts things becomes serious and you need to be sure that the system will scale gracefully, which means an efficient load balancing scheme and in general you need more ressources management features in addition to the process management ones. And of course tones of logs to be sure that the thing is really efficient. That's really were things like Arsenal and equivalent reach their limits. So if you are building a big cluster, have a look at Condor or SunGridEngine. My preference goes to Condor but i am sure it is possible to do the same things with SGE. In any case both tools are used for years on giant computing clusters and you can be sure that it is efficient and scale really well. On the down side, it more work to configure them, but there is actually vendors that are used to do that and train your people at the same time. So it might be a solution. Cheers, Ash
_______________________________________________ Nuke-python mailing list [email protected], http://forums.thefoundry.co.uk/ http://support.thefoundry.co.uk/cgi-bin/mailman/listinfo/nuke-python
