Dear Jason,
I floated this questionon on ROLLOUT and nobody replied. Something wrong with it?
The daily acitivity report shows all lhcb jobs failed at our site on 09-jul-2008.
http://gridportal.hep.ph.ic.ac.uk/rtm/reports/report-CE--9-July-2008-CE.pakgrid.org.pk.pdf
Where as on scanning the accounting data in pbs, only two jobs are exited with non-zero status and even they are not from lhcb vo.
>>>>>>> 07/09/2008 01:32:23;E;131174.ce.pakgrid.org.pk;user=bio026 group=biomed jobname=STDIN queue=biomed ctime=1215543934 qtime=1215543934 etime=1215543934 start=1215543934 exec_host=PAKWN10.pakgrid.org.pk/0 Resource_List.cput=48:00:00 Resource_List.neednodes=1 Resource_List.nodect=1 Resource_List.nodes=1 Resource_List.walltime=72:00:00 session=23829 end=1215545543 Exit_status=271 resources_used.cput=00:00:00 resources_used.mem=21384kb resources_used.vmem=80864kb resources_used.walltime=00:26:50
>>>>>>> 07/09/2008 01:34:02;E;131177.ce.pakgrid.org.pk;user=bio026 group=biomed jobname=STDIN queue=biomed ctime=1215544184 qtime=1215544184 etime=1215544184 start=1215544189 exec_host=PAKWN13.pakgrid.org.pk/0 Resource_List.cput=48:00:00 Resource_List.neednodes=1 Resource_List.nodect=1 Resource_List.nodes=1 Resource_List.walltime=72:00:00 session=21067 end=1215545642 Exit_status=271 resources_used.cput=00:00:00 resources_used.mem=22444kb resources_used.vmem=85072kb resources_used.walltime=00:24:13
Then why report is showing all lhcb jobs as failed?
281 jobs are executed for biomed, 2 are executed for dteam and they are not listed in report.
How can I trace further?
Cheers,
Asif Osman
|