[GE users] sge_shepherd problems perhaps connected to nfs problems

Fred Youhanaie fly at anydata.co.uk
Thu Jun 28 17:18:48 BST 2007


    [ The following text is in the "ISO-8859-1" character set. ]
    [ Your display is set for the "ISO-8859-10" character set.  ]
    [ Some special characters may be displayed incorrectly. ]



Margaret Doll wrote:
> I have a job that I started last night.
> 
> It is no longer running on top, but it shows up in qstat -f
> 
> ps -ef --forest | more^M
> UID        PID  PPID  C STIME TTY          TIME CMD^M
> sge       4228     1  0 Jun27 ?        00:02:53 
> /opt/gridengine/bin/lx26-amd64/sge_execd^M
> sge       5094  4228  0 Jun27 ?        00:00:00  \_ sge_shepherd-549 -bg^M
> mad       5095  5094  0 Jun27 ?        00:00:00      \_ -csh /opt/gridengine/default/spool/compute-0-1/job_scripts/549^M
> mad       5168  5095 84 Jun27 ?        13:30:53          \_ /home/mad/user1/mad^M


It looks like the script has been running and so far it has used 13.5 
hours of cpu time. Is the TIME column still increasing?

qdel 549 should delete the job and the 3 processes should disappear.

I think it is also worthwhile following John's advice and investigate 
the hanging df problems. Are there any NFS issues?


Cheers
f.

---------------------------------------------------------------------
To unsubscribe, e-mail: users-unsubscribe at gridengine.sunsource.net
For additional commands, e-mail: users-help at gridengine.sunsource.net




More information about the gridengine-users mailing list