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

Re: [HTCondor-users] HTCondor - stop queue



On 1/14/2020 10:46 AM, Daniel Rodrigues de Silos Moraes wrote:
> 
> Dear all,
> 
> The CBPF's grid migrate from PBS/Torque to HTCondor recently. In PBS, 
> when I needed to stop the queue, I used the qdisable command. Are there 
> any similar command on htcondor? How can I stop queuing on HTCondor, ie 
> avoid receiving jobs?
> 
> 

Hi Daniel,

One solution: I think you could set the config knob 
MAX_JOBS_SUBMITTED=0, and then do a condor_reconfig to your submit 
machine(s)  (or kill -HUP <pid of condor_schedd>).

Some similar config settings of interest appear below (cut-n-pasted from 
the manual at 
https://htcondor.readthedocs.io/en/v8_9_5/admin-manual/configuration-macros.html#condor-schedd-configuration-file-entries)

Hope this helps,
Todd

MAX_JOBS_SUBMITTED
     This integer value limits the number of jobs permitted in a 
condor_schedd daemonâs queue. Submission of a new cluster of jobs fails, 
if the total number of jobs would exceed this limit. The default value 
for this variable is the largest positive integer value.


MAX_JOBS_PER_OWNER
     This integer value limits the number of jobs any given owner (user) 
is permitted to have within a condor_schedd daemonâs queue. A job 
submission fails if it would cause this limit on the number of jobs to 
be exceeded. The default value is 100000.
     This configuration variable may be most useful in conjunction with 
MAX_JOBS_SUBMITTED, to ensure that no one user can dominate the queue.


MAX_RUNNING_SCHEDULER_JOBS_PER_OWNER
     This integer value limits the number of scheduler universe jobs 
that any given owner (user) can have running at one time. This limit 
will affect the number of running Dagman jobs, but not the number of 
nodes within a DAG. The default value is 200


MAX_JOBS_PER_SUBMISSION
     This integer value limits the number of jobs any single submission 
is permitted to add to a condor_schedd daemonâs queue. The whole 
submission fails if the number of jobs would exceed this limit. The 
default value is 20000.
     This configuration variable may be useful for catching user error, 
and for protecting a busy condor_schedd daemon from the excessively 
lengthy interruption required to accept a very large number of jobs at 
one time.






-- 
Todd Tannenbaum <tannenba@xxxxxxxxxxx> University of Wisconsin-Madison
Center for High Throughput Computing   Department of Computer Sciences
HTCondor Technical Lead                1210 W. Dayton St. Rm #4257
Phone: (608) 263-7132                  Madison, WI 53706-1685