my file .sub is the
following:
universe = vanilla
executable =
sim_rebounding_DT.exe
requirements = Memory >= 128
rank =
kflops
should_transfer_files = YES
when_to_transfer_output
= ON_EXIT
transfer_input_files = meas.txt
error = FIR_SRA.err
log = FIR_SRA.log
output = FIR_SRA_cmeans_432.txt
arguments = 0
0
queue
output = FIR_SRA_cmeans_422.txt
arguments = 0
1
queue
when i submit this file to condor pool the command condor_status
show it:
C:\thesis\simulation>condor_status
Name
OpSys Arch
State Activity LoadAv Mem
ActvtyTime
vm1@dtc-mvill WINNT51
INTEL Unclaimed Idle
0.000 251 0+02:08:28
vm2@dtc-mvill
WINNT51 INTEL Unclaimed
Idle 0.000 251
0+02:08:29
dtc-snaranjo. WINNT51 INTEL
Unclaimed Idle 0.030
478 0+02:03:27
dtc-vhinojosa WINNT51
INTEL Claimed Busy
0.000 1015 0+00:02:21
id-vhinojosa.
WINNT51 INTEL Unclaimed
Idle 0.840 254
0+02:05:22
Machines Owner Claimed Unclaimed Matched Preempting
INTEL/WINNT51
5 0
1
4
0 0
Total 5
0
1
4
0 0
The the dtc-vhinojosa is running with the job, but due to my
constraint the next machine is dtc-snaranjo, but i don't know because it doesn't
run the job.
i use the command -analyze and the result is
the next:
Victor,
The first step is to use the -analayze switch to
condor_q. Try using
this command on the submit
node:
condor_q -analyze 26.0
and also this one (if it
works in Windows):
condor_q -better-analzye
26.0
Those commands should give you some indication of why job 26.0 is
not
starting.
If you get nothing useful from those commands, compare
long listings of
the jobs and the machines:
condor_q -l
26.0
condor_status -l dtc-mvill
to see if you can spot
incompatibilities between the job's requirements
and the machine's
requirements.
- dave
Víctor Hinojosa wrote:
> i have a
condor pool. the summary is the following:
>
>
Name
OpSys Arch
State Activity LoadAv Mem
ActvtyTime
> vm1@dtc-mvill <mailto:vm1@dtc-mvill>
WINNT51 INTEL Unclaimed
Idle 0.000 508
0+02:08:29
> vm2@dtc-mvill <mailto:vm2@dtc-mvill>
WINNT51 INTEL Unclaimed
Idle 0.330 508
0+02:08:30
> dtc-vhinojosa WINNT51 INTEL
Unclaimed Idle 0.000 1015
0+00:08:06
> id-vhinojosa. WINNT51 INTEL
Unclaimed Idle 0.010
254
0+02:08:09
>
Machines Owner Claimed Unclaimed Matched
Preempting
>
INTEL/WINNT51
4 0
0
4
0
0
>
Total 4
0
0
4
0 0
>
>
i submit a task with condor_submit. i check the status of my job with condor_q
command.
>
> -- Submitter: dtc-vhinojosa :
<10.0.1.171:2934> : dtc-vhinojosa
>
ID
OWNER
SUBMITTED RUN_TIME ST PRI SIZE CMD
>
26.0 Victor
6/1 13:02 0+00:00:00 I 0 0.3
sim_rebounding_DT
> 26.1
Victor 6/1
13:02 0+00:00:00 I 0 0.3
sim_rebounding_DT
> 26.2
Victor 6/1
13:02 0+00:00:00 I 0 0.3
sim_rebounding_DT
> 26.3
Victor 6/1
13:02 0+00:00:00 I 0 0.3
sim_rebounding_DT
> 26.4
Victor 6/1
13:02 0+00:00:00 I 0 0.3
sim_rebounding_DT
> 26.5
Victor 6/1
13:02 0+00:00:00 I 0 0.3
sim_rebounding_DT
> 26.6
Victor 6/1
13:02 0+00:00:00 I 0 0.3
sim_rebounding_DT
> 26.7
Victor 6/1
13:02 0+00:00:00 I 0 0.3
sim_rebounding_DT
> 26.8
Victor 6/1
13:02 0+00:00:00 I 0 0.3
sim_rebounding_DT
> 26.9
Victor 6/1
13:02 0+00:00:00 I 0 0.3
sim_rebounding_DT
> 10 jobs; 10 idle, 0 running, 0
held
>
> when i install the condor pool i set up all machines
with the option "always run Condor jobs".so i don't know what happen. somebody
can help me or where i can search the mistake?
>
>
regards,
>
>
> victor
hinojosa
>
>
>
------------------------------------------------------------------------
>
>
_______________________________________________
> Condor-users mailing
list
> Condor-users@xxxxxxxxxxx
> https://lists.cs.wisc.edu/mailman/listinfo/condor-users
_______________________________________________
Condor-users
mailing list
Condor-users@xxxxxxxxxxx
https://lists.cs.wisc.edu/mailman/listinfo/condor-users
![[Computer Systems Lab]](https://www-auth.cs.wisc.edu/pics/csl_logo.gif){kind=logo}