Hi David,
The -better-analyze -reverse on an idle job MGHT tell you why that machine did not match that job. Hopefully itâll be something obvious. Itâs about. The machine not the ob.
Just my 2Â from the peanut gallery.
Best, Joe On Jul 8, 2025, at 07:59, David Cohen <cdavid@xxxxxxxxxxxxxxxxxxxxxx> wrote:
Hi, The problem isn't with a specific job not running on these machines but the machines not getting any jobs. Today some of them started running jobs, after a long time. So now I\m more confused. I'll try to see if they still get jobs when the load is lower, to understand if for some reason those machines are considered kast for jobs.
Thanks, David
Hi,
try a 'not running job' using:
condor_q <jobid> -better-analyze -reverse -machine <FQDN of the machine in question>
This should give you an idea :)
Best christoph
-- Christoph Beyer DESY Hamburg IT-Department Notkestr. 85 Building 02b, Room 009 22607 Hamburg phone:+49-(0)40-8998-2317 mail: christoph.beyer@xxxxxxx
Hi, A new machine, installed with the same version and configuration as all the other execute nodes, is not getting matched for running jobs, although there are queued jobs. Specifically requesting that machine as a requirement gets the job running. Any ideas? David
_______________________________________________ HTCondor-users mailing list To unsubscribe, send a message to htcondor-users-request@xxxxxxxxxxx with a subject: Unsubscribe The archives can be found at: https://www-auth.cs.wisc.edu/lists/htcondor-users/ _______________________________________________
HTCondor-users mailing list
To unsubscribe, send a message to htcondor-users-request@xxxxxxxxxxx with a
subject: Unsubscribe
The archives can be found at: https://www-auth.cs.wisc.edu/lists/htcondor-users/
_______________________________________________ HTCondor-users mailing list To unsubscribe, send a message to htcondor-users-request@xxxxxxxxxxx with a subject: Unsubscribe The archives can be found at: https://www-auth.cs.wisc.edu/lists/htcondor-users/
|