[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [Condor-users] jobs wait in idle mode unecessarily

I think this is a very common newbie question but I've found very few answers addressing it. I can tell you about my own experiences.

First, by default if you're using non-windows operating system the condor installation assumes that all the computers in the pool share both a common file system and a common way to allow login to machines. If your machines are not like this, I found it impossible to run jobs. To "fix" the problem, look for FILESYSTEM_DOMAIN and UID_DOMAIN in both the condor.config file *and* the condor.config.local file. Make sure the value is $(FULL_HOSTNAME). Doing this tells condor that the computers do not share a file system or login accounts.

At 05:07 AM 6/21/2004, you wrote:

When I submit a Condor job it seems to wait in the idle
state and take ages to start despite a host being free
for it to run on. Using condor_q -analyze I get

174.000:  Run analysis summary.  Of 2 machines,
     1 are rejected by your job's requirements
     0 reject your job because of their own requirements
     0 match, but are serving users with a better priority in the pool
     1 match, but prefer another specific job despite its worse user-priority
     0 match, but will not currently preempt their existing job
     0 are available to run your job
       Last successful match: Mon Jun 21 10:54:27 2004

What does the "1 match, but prefer another specific job
despite its worse user-priority" mean ? Is there anyway around this ?

thanks in advance,


Dr Ian C. Smith,
e-Science team,
University of Liverpool
Computing Services Department

Condor-users mailing list