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

Re: [Condor-users] Scheduler/local universe



Drop the requirements statement from your submit file
and see if the jobs will run.
In the scheduler universe there is no way for any daemon
to evaluate those requirements anyway as far as I know
because there is no matchmaking that goes on.  I've
never seen a scheduler universe job  (or local universe job)
with requirements other than TRUE.

Steve


On Tue, 1 Feb 2011, MAO, WANCHENG  (WANCHENG) wrote:

Steve,

SchedLog says the following:
02/01 11:59:48 (pid:13708) The Requirements attribute for job 93.0 evaluated to false. Unable to start job
02/01 11:59:48 (pid:13708) The Requirements attribute for job 105.0 evaluated to false. Unable to start job
02/01 11:59:48 (pid:13708) The Requirements attribute for job 99.0 evaluated to false. Unable to start job
02/01 11:59:48 (pid:13708) The Requirements attribute for job 95.0 evaluated to false. Unable to start job
02/01 11:59:48 (pid:13708) The Requirements attribute for job 101.0 evaluated to false. Unable to start job
02/01 11:59:48 (pid:13708) The Requirements attribute for job 98.0 evaluated to false. Unable to start job

Thanks,
Wancheng

-----Original Message-----
From: condor-users-bounces@xxxxxxxxxxx [mailto:condor-users-bounces@xxxxxxxxxxx] On Behalf Of MAO, WANCHENG (WANCHENG)
Sent: Tuesday, February 01, 2011 11:57 AM
To: Condor-Users Mail List
Subject: Re: [Condor-users] Scheduler/local universe

Steve,

Thanks for your help.


root[!]->condor_config_val -v START_SCHEDULER_UNIVERSE
START_SCHEDULER_UNIVERSE: TotalSchedulerJobsRunning < 200
 Defined in '/etc/condor/condor_config', line 721.

root[!]->condor_config_val -v START_LOCAL_UNIVERSE
START_LOCAL_UNIVERSE: TotalLocalJobsRunning < 200
 Defined in '/etc/condor/condor_config', line 718.


Thanks,
Wancheng


-----Original Message-----
From: condor-users-bounces@xxxxxxxxxxx [mailto:condor-users-bounces@xxxxxxxxxxx] On Behalf Of Steven Timm
Sent: Monday, January 31, 2011 10:42 PM
To: Condor-Users Mail List
Subject: Re: [Condor-users] Scheduler/local universe

What's the value of START_SCHEDULER_UNIVERSE in your condor_config?
What does SchedLog say?  As condor_q -analyze says, it won't tell
you anything, scheduler universe jobs should start immediately regardless
of requirements.

Steve


On Mon, 31 Jan 2011, MAO, WANCHENG  (WANCHENG) wrote:

Hi,

I have problem to run scheduler universe jobs.

Job description:
Executable = /usr/bin/uname
Arguments = -a
Universe = scheduler
Requirements = Memory > 1 && Disk > 1
Error = err/err.sch
output = out/out.sch
Log = log/sch.log
Queue

scylla05<wmao>condor_submit job.sch
Submitting job(s).
Logging submit event(s).
1 job(s) submitted to cluster 105.

scylla05>condor_q -better-analyze  105

-- Submitter: scylla05 : <135.207.178.168:46953> : scylla05
---
105.000:  Run analysis summary.  Of 128 machines,
     2 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
   126 match but reject the job for unknown reasons
     0 match but will not currently preempt their existing job
     0 match but are currently offline
     0 are available to run your job

The Requirements expression for your job is:

( target.Memory > 1 && target.Disk > 1 ) && ( target.Arch == "INTEL" ) &&
( target.OpSys == "SOLARIS210" ) && ( ( RequestMemory * 1024 ) >= ImageSize )

   Condition                         Machines Matched    Suggestion
   ---------                         ----------------    ----------
1   ( ( 1024 * ceiling(ifThenElse(JobVMMemory isnt undefined,JobVMMemory,9.765625000000000E-03)) ) >= 10 )
                                     0                   REMOVE
2   target.Disk > 1                   126
3   target.Memory > 1                 128
4   ( target.Arch == "INTEL" )        128
5   ( target.OpSys == "SOLARIS210" )  128

WARNING: Analysis is meaningless for Scheduler universe jobs.

Please help.

Thanks a lot,
Wancheng


_______________________________________________
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:
https://lists.cs.wisc.edu/archive/condor-users/




--
------------------------------------------------------------------
Steven C. Timm, Ph.D  (630) 840-8525
timm@xxxxxxxx  http://home.fnal.gov/~timm/
Fermilab Computing Division, Scientific Computing Facilities,
Grid Facilities Department, FermiGrid Services Group, Group Leader.
Lead of FermiCloud project.