BTW, Marco, if you're having strange behavior with different
job servers, I'll be happy to help.
Make sure you've got 'sched fifo' in ALL the rush.conf files,
and are running the same version of rush that supports FIFO
(102.42a9 or higher) on all the machines, since the older
releases won't understand FIFO scheduling.
There are some easy tests you can do from the command line
to submit a couple of jobs and watch them compete.
For instance, from a Unix machine (linux or OSX), you can
submit two 100 frame jobs as a test:
(echo title AAA; echo frames 1-100; echo cpus +any=500@10; echo command
rush -sleep 10) | rush -submit
(echo title BBB; echo frames 1-100; echo cpus +any=500@10; echo command
rush -sleep 10) | rush -submit
Each line will submit a job that does nothing but sleep 10 seconds
per frame.
Those should be two separate lines; make sure your newsreader
is wide enough to show those as complete lines before copy/pasting.
Run the lines one at a time, with at least 1 or 2 seconds between
each submit, so the FIFO system can tell which job was first.
When running, the AAA job should get all the cpus, and the BBB
job should wait around until the AAA job starts finishing.
You should also be able to run similar command lines on other job
servers, or tack a hostname on the end, after the 'rush -submit',
to tell it to use some other machine as the job server, eg. to use
'tahoe' as the job server:
(echo title CCC; echo frames 1-100; echo cpus +any=500@10; echo command
rush -sleep 10) | rush -submit tahoe