[Condor-users] bad requirements for job

["Sophie Prieur" <s.prieur@xxxxxxxxxxxxxx>]

Hi everybody,

 

I have submitted 3 jobs from a machine with Solaris 8.

the first is a program in c, the second a java job, and the third a shell script, there are all simple programs which normally takes a few seconds. The problem is that jobs are running often, there status are often idle even if I see some available machines with condor_status -available.

 

 

bash-2.03$ condor_status -available

 

Name          OpSys       Arch   State      Activity   LoadAv Mem   ActvtyTime

 

vm1@balsa     SOLARIS28   SUN4u  Unclaimed  Idle       0.000  3072  0+00:00:04
vm1@birch     SOLARIS28   SUN4u  Unclaimed  Idle       0.000  3072  0+00:00:04
vm2@birch     SOLARIS28   SUN4u  Unclaimed  Idle       0.530  3072  0+01:10:05
vm1@cedar     SOLARIS29   SUN4u  Unclaimed  Idle       0.000  3072  0+05:02:33
vm2@cedar     SOLARIS29   SUN4u  Unclaimed  Idle       0.020  3072  0+01:40:47

 

                     Total Owner Claimed Unclaimed Matched Preempting Backfill

 

     SUN4u/SOLARIS28     3     0       0         3       0          0        0
     SUN4u/SOLARIS29     2     0       0         2       0          0        0

 

               Total     5     0       0         5       0          0        0

 

 ID      OWNER            SUBMITTED     RUN_TIME ST PRI SIZE CMD              
---
023.000:  Run analysis summary.  Of 8 machines,
      6 are rejected by your job's requirements
      1 reject your job because of their own requirements
      0 match but are serving users with a better priority in the pool
      1 match but reject the job for unknown reasons
      0 match but will not currently preempt their existing job
      0 are available to run your job
        Last successful match: Wed Jun 20 16:08:26 2007
---
024.000:  Run analysis summary.  Of 8 machines,
      4 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
      4 match but reject the job for unknown reasons
      0 match but will not currently preempt their existing job
      0 are available to run your job
        Last successful match: Wed Jun 20 16:08:26 2007
---
025.000:  Run analysis summary.  Of 8 machines,
      6 are rejected by your job's requirements
      1 reject your job because of their own requirements
      0 match but are serving users with a better priority in the pool
      1 match but reject the job for unknown reasons
      0 match but will not currently preempt their existing job
      0 are available to run your job
        Last successful match: Wed Jun 20 16:03:26 2007
        Last failed match: Wed Jun 20 16:08:26 2007
        Reason for last match failure: no match found

 

Here is one of submit file :

Universe = Vanilla
Executable = ./script
Log = script.log
Output = script.output
Error = script.error
Queue

Here is the condor_config.local file for all machines, the master have some things in addition:

NUM_CPUS=2
BackgroundLoad=5
HighLoad=7
JAVA=/software/jdk-5/jdk/instances/jdk1.5.0/bin/java
FILESSYSTEM_DOMAIN=macaulay.ac.uk
START=$(CPUIdle)
SUSPEND=((CpuBusyTime > 2 * $(MINUTE)) && $(ActivationTimer) > 90)
CONTINUE=($(CPUIdle) && ($(ActivityTimer) > 10))

 

Thank you in advance

Sophie

--
Please note that the views expressed in this e-mail are those of the
sender and do not necessarily represent the views of the Macaulay
Institute. This email and any attachments are confidential and are
intended solely for the use of the recipient(s) to whom they are
addressed. If you are not the intended recipient, you should not read,
copy, disclose or rely on any information contained in this e-mail, and
we would ask you to contact the sender immediately and delete the email
from your system. Thank you.
Macaulay Institute and Associated Companies, Macaulay Drive,
Craigiebuckler, Aberdeen, AB15 8QH.