[condor-users] Worrying Run_Time Queue Values

["Charles Kubicek" <Charles.Kubicek@xxxxxxxxxxxxxxx>]

Hi,

 To test an application I am using with Condor I have submitted lots of java jobs to a condor pool with 13 resources, each jobs simply sleeps for 1 minute. I have noticed 2 things that have concerned me.

 

1. Sometimes when I start the pool and begin submitting jobs, 13 jobs are in the “R” (running) state and but the run_time for half of the jobs remains at 0 for quite some time. It is as if there is a limit on how many jobs are actually allowed to run. This problem does disappear after a while though.

 

2. Although the 1 minute long job only sleeps for a minute, the run_time goes over one minute, and some times over 2. Why is this? Are there any config settings I can adjust to change this? There are 2 condor_q outputs showing this, each queue had approximately 100 entries in and I have a slight feeling the run_time values could be rising as the queue length rises.

 

2.5 while Im posting a message I might as well ask; why has the size of one of my jobs suddenly gone from 0.0 to 9300.0?

 

Thanks, for any help, Charles

 

 

-- Submitter: xx : <xx> : xx

 ID      OWNER            SUBMITTED     RUN_TIME ST PRI SIZE CMD              

2447.0   nck8            4/28 14:16   0+00:01:42 R  0   0.0  SimpleWait.class S

2448.0   nck8            4/28 14:16   0+00:01:41 R  0   0.0  SimpleWait.class S

2449.0   nck8            4/28 14:16   0+00:01:39 R  0   9300.0 SimpleWait.class S

2450.0   nck8            4/28 14:16   0+00:01:37 R  0   0.0  SimpleWait.class S

2451.0   nck8            4/28 14:16   0+00:01:35 R  0   0.0  SimpleWait.class S

2452.0   nck8            4/28 14:16   0+00:01:33 R  0   0.0  SimpleWait.class S

2453.0   nck8            4/28 14:16   0+00:01:28 R  0   0.0  SimpleWait.class S

2454.0   nck8            4/28 14:16   0+00:01:21 R  0   0.0  SimpleWait.class S

2455.0   nck8            4/28 14:16   0+00:00:47 R  0   0.0  SimpleWait.class S

2456.0   nck8            4/28 14:16   0+00:00:45 R  0   0.0  SimpleWait.class S

2457.0   nck8            4/28 14:16   0+00:00:44 R  0   0.0  SimpleWait.class S

2458.0   nck8            4/28 14:16   0+00:00:42 R  0   0.0  SimpleWait.class S

2459.0   nck8            4/28 14:16   0+00:00:40 R  0   0.0  SimpleWait.class S

2460.0   nck8            4/28 14:16   0+00:00:00 I  0   0.0  SimpleWait.class S

2461.0   nck8            4/28 14:16   0+00:00:00 I  0   0.0  SimpleWait.class S

2462.0   nck8            4/28 14:16   0+00:00:00 I  0   0.0  SimpleWait.class S

…

 

-- Submitter: xx : <xx> : xx

 ID      OWNER            SUBMITTED     RUN_TIME ST PRI SIZE CMD              

2402.0   nck8            4/28 14:13   0+00:02:13 R  0   0.0  SimpleWait.class S

2404.0   nck8            4/28 14:13   0+00:01:24 R  0   0.0  SimpleWait.class S

2405.0   nck8            4/28 14:13   0+00:01:22 R  0   0.0  SimpleWait.class S

2406.0   nck8            4/28 14:13   0+00:01:20 R  0   0.0  SimpleWait.class S

2407.0   nck8            4/28 14:13   0+00:00:59 R  0   0.0  SimpleWait.class S

2408.0   nck8            4/28 14:13   0+00:00:40 R  0   0.0  SimpleWait.class S

2409.0   nck8            4/28 14:13   0+00:00:37 R  0   0.0  SimpleWait.class S

2410.0   nck8            4/28 14:13   0+00:00:27 R  0   0.0  SimpleWait.class S

2411.0   nck8            4/28 14:13   0+00:00:32 R  0   0.0  SimpleWait.class S

2412.0   nck8            4/28 14:13   0+00:00:30 R  0   0.0  SimpleWait.class S

2413.0   nck8            4/28 14:13   0+00:00:27 R  0   0.0  SimpleWait.class S

2414.0   nck8            4/28 14:13   0+00:00:25 R  0   0.0  SimpleWait.class S

2415.0   nck8            4/28 14:14   0+00:00:00 I  0   0.0  SimpleWait.class S

2416.0   nck8            4/28 14:14   0+00:00:00 I  0   0.0  SimpleWait.class S

2417.0   nck8            4/28 14:14   0+00:00:00 I  0   0.0  SimpleWait.class S

…