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

[Condor-users] Condor pool on globus

Hi all,

I am having a condor pool consisting of 3 machines sjcehp2.sjce.edu.in
, sjcehp3.sjce.edu.in and sjcehp5.sjce.edu.in of which sjcehp2 is the
central manager. Each host has a globus 2.4.3 installed on it. I
submit jobs to condor with the following rsl script

( &(resourceManagerContact="sjcehp2.sjce.edu.in/jobmanager-condor")
   (label="subjob 0")
   (environment=(GLOBUS_DUROC_SUBJOB_INDEX 0)
       (LD_LIBRARY_PATH /opt/globus-2.4.3/lib/))

now If I have run condor_master ONLY on sjcehp2 (central manager)
globusrun completes successfully. but If i've run condor_master on all
the three machines, globusrun hanges. Also i've checked out that no
problem with globus( no authentication errors etc).

here is the output of condor_q -analyze on the central manager

[root@sjcehp2 root]# condor_q -analyze
-- Submitter: sjcehp2.sjce.edu.in : <> : sjcehp2.sjce.edu.in
016.000:  Run analysis summary.  Of 3 machines,
      0 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
      3 match, 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: Fri May 13 23:18:01 2005
1 jobs; 1 idle, 0 running, 0 held

and I am 100% sure that I submitted only the above job to condor pool
using command

globusrun -w -f date.rsl

Can anyone point out what the problem is?

Raghavendra G
8th Semester Computer Science & Engg,
SJCE, Mysore 570006

Smile is a Curve that straightens up many things