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

Re: [Condor-users] Jobs are Executed Only on the Central Manager



Erik,

:) I have logged in via ssh so that I can see what happened to every
machine. NOW, nobody are using or logged in via ssh on other machines, but
still the same errors appear. What I did is that I changed the UWCS to
TESTINGMODE in the condor_config file then it works...What's with the
TESTINGMODE? Does this force other machines to do jobs even if someone are
using them?

--BUT there is now new error when I fire condor_q -analyze, it says:

  2 machines match but rejects the jobs for unknown reasons
-What are the possible causes of this?

Thank you very much.

Leo


> It'd be more helpful to see the condor_status while you've got jobs
> submitted - but in all likelyhood the problem is the same.
>
> The only machine that is available to run jobs is your central manager,
> because Condor has detected keyboard or console activity on all of the
> other machines, and they're in "Owner" state and not willing to run
> jobs. Are people sitting at the machine, or are they logged in via ssh?
>
> Change your START expression to not reference the keyboard, or get
> people to leave the machines idle and your jobs will run on all the
> machines.
> -Erik

>>
>> ###########################################3
>> [condor@phys-ugradlab01 test]$ condor_status -l
>> MyType = "Machine"
>> TargetType = "Job"
>> Name = "nucleus.cluster.physics.msuiit.edu.ph"
>> Machine = "nucleus.cluster.physics.msuiit.edu.ph"
>> KeyboardIdle = 0
>> ConsoleIdle = 0
>> State = "Owner"
>> Activity = "Idle"
>> Start = ((KeyboardIdle > 15 * 60) && (((LoadAvg - CondorLoadAvg) <=
>> 0.300000) || (State != "Unclaimed" && State != "Owner")))
>> Requirements = (START) && (IsValidCheckpointPlatform)
>>
>> MyType = "Machine"
>> TargetType = "Job"
>> Name = "phys-ugradlab01.physics.msuiit.edu.ph"
>> Machine = "phys-ugradlab01.physics.msuiit.edu.ph"
>> KeyboardIdle = 600
>> ConsoleIdle = 600
>> State = "Unclaimed"
>> Activity = "Idle"
>> Start = TRUE
>> Requirements = (START) && (IsValidCheckpointPlatform)
>>
>> MyType = "Machine"
>> TargetType = "Job"
>> Name = "phys-ugradlab02.physics.msuiit.edu.ph"
>> Machine = "phys-ugradlab02.physics.msuiit.edu.ph"
>> KeyboardIdle = 0
>> ConsoleIdle = 0
>> State = "Owner"
>> Activity = "Idle"
>> Start = ((KeyboardIdle > 15 * 60) && (((LoadAvg - CondorLoadAvg) <=
>> 0.300000) || (State != "Unclaimed" && State != "Owner")))
>> Requirements = (START) && (IsValidCheckpointPlatform)
>>
>> MyType = "Machine"
>> TargetType = "Job"
>> Name = "phys-ugradlab03.physics.msuiit.edu.ph"
>> Machine = "phys-ugradlab03.physics.msuiit.edu.ph"
>> KeyboardIdle = 0
>> ConsoleIdle = 0
>> State = "Owner"
>> Activity = "Idle"
>> Start = ((KeyboardIdle > 15 * 60) && (((LoadAvg - CondorLoadAvg) <=
>> 0.300000) || (State != "Unclaimed" && State != "Owner")))
>> Requirements = (START) && (IsValidCheckpointPlatform)
> _______________________________________________
> Condor-users mailing list
> To unsubscribe, send a message to condor-users-request@xxxxxxxxxxx with a
> subject: Unsubscribe
> You can also unsubscribe by visiting
> https://lists.cs.wisc.edu/mailman/listinfo/condor-users
>
> The archives can be found at either
> https://lists.cs.wisc.edu/archive/condor-users/
> http://www.opencondor.org/spaces/viewmailarchive.action?key=CONDOR
>