High Throughput Computing using Condor

Monitoring Jobs

You can monitor your jobs with the following command when logged in to submitter:

[m65432ab@submitter ~]$ condor_q


-- Schedd: submitter.itservices.manchester.ac.uk : <130.88.203.22:9618?... @ 06/26/19 11:59:14
OWNER    BATCH_NAME    SUBMITTED   DONE   RUN    IDLE   HOLD  TOTAL JOB_IDS
m65432ab ID: 149627   6/26 15:48      1      4      _      _      5 149627.0-4
m65432ab ID: 150018   6/26 15:38      _      1      _      _      1 150018.0

Total for query: 6 jobs; 1 completed, 0 removed, 0 idle, 5 running, 1 held, 0 suspended 
Total for m65432ab: 6 jobs; 1 completed, 0 removed, 0 idle, 5 running, 1 held, 0 suspended 
Total for all users: 8043 jobs; 0 completed, 0 removed, 7052 idle, 978 running, 13 held, 0 suspended

In the above example…

  • OWNER should show your university username.
  • BATCH_NAME will show ‘ID:’ where the ID is the ‘Cluster_ID’.
  • SUBMITTED shows the submitted date and time.
  • DONE / RUN / IDLE / HOLD shows the status of each of the jobs in the batch cluster submission.
  • TOTAL shows the total number of jobs in the cluster submission
  • JOB_IDS shows the combined Cluster_ID and Job_ID numbers in total.

 

Last modified on June 27, 2019 at 1:13 pm by Chris Heeley