Current status of the condor batch system implementation and testing

Mach 23:

• Infosystem seems to work.
• Job submission in successful trough the CERN WMS 3.1 (lxb7283.cern.ch) but there are still problems with the condor_submit.sh script.
• No accounting support yet

Mach 30:

• We set up an local 3.1 WMS at PIC (vwms01.pic.es)
• Job submission still fails at the blahd level. The blahd does not call the condor_submitt script:

     dteam003 13800  0.5  1.3  5596 3680 ?        S    12:05   0:01 globus-job-manager -conf /opt/glite/etc/globus-job-manager.conf -type fork -rdn jobmanager-fork -machine-type unknown -publish-jobs
     dteam003 13848  0.0  1.3  6068 3612 ?        S    12:05   0:00 /opt/condor-c/sbin/condor_master -f -r 713
     dteam003 13851  0.0  1.0  4296 2708 ?        S    12:05   0:00 perl /home/dteam003/.globus/.gass_cache/local/md5/a8/7d267aa1945065305a6e2e48008ba6/md5/ab/6267e8656c310ed1222d3936f723bf/data --dest-url=https://vwms01.pic.es:20001/tmp/condor_g_scratch.0x85befa8.6181/grid-monitor.vce02.pic.es:2119.1/grid-monitor-job-statu
     dteam003 13860  0.0  1.7  6408 4772 ?        S    12:05   0:00 perl /tmp/grid_manager_monitor_agent.dteam003.13851.1000 --delete-self --maxtime=3599s
     dteam003 13887  0.3  1.7  7588 4608 ?        S    12:06   0:00 condor_schedd -f -n d25df84a3366f3d507640be740e948cd@vce02.pic.es
     dteam003 14986  0.0  1.3  7288 3584 ?        S    12:07   0:00 condor_gridmanager -f -C (Owner=?="glite"&&JobUniverse==9) -S /tmp/condor_g_scratch.0x8519a88.13887
     dteam003 15049  0.0  0.4 12984 1136 ?        S    12:07   0:00 /opt/glite/bin/blahpd

April 12:

• First Job reached the condor lrms master node and returned some output.
• We siscovered a problem with the Job Wrapper script produced by the 3.1 WMS. We will investigate this with DI.

     [root@vce02 cluster30.proc0.subproc0]# cat StandardError 
     Unknown command 'quote

April 18:

• First Job submitted and output retrived correctly

    *************************************************************
    BOOKKEEPING INFORMATION:
    
    Status info for the Job : https://vwms01.pic.es:9000/MFvX7JOkCwlCwiAp3hxBkg
    Current Status:     Done (Success)
    Exit code:          0
    Status Reason:      Job terminated successfully
    Destination:        vce02.pic.es:2119/blah-condor-dteam
    Submitted:          Wed Apr 18 17:13:35 2007 CEST
    *************************************************************

July 6:

• After upgrading the WMS and the condor batch system 6.8.5 and taking the new blñahs scripts for CNAF integrated job submission to our gLite CE works again
• We updated the wiki pages for condor batch system support for both flavour ov CEs
  • LCG CE: https://twiki.cern.ch/twiki/bin/view/EGEE/InstallationInstructionsForCondorOnTheLcg-CE
  • GLite CE: https://twiki.cern.ch/twiki/bin/view/EGEE/InstallationInstructionsForCondorOnTheGLite-CE

-- Main.kneuffer - 23 Mar 2007