[GE users] qsub/qstat/qacct information sequencing

Daniel Templeton Dan.Templeton at Sun.COM
Fri Nov 11 18:39:08 GMT 2005


    [ 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. ]

David,

Once qsub reports the job number, qstat should see the job.  For the
problem with qstat and qacct, see here:

http://blogs.sun.com/roller/page/templedf?entry=immediate_accounting_data_flushing

Daniel

David Pinsky 288-3739 wrote On 11/11/05 19:24,:

>Is it guaranteed that, once qsub reports the job number for a submitted job
>request, that qstat can report that job info?  (Is there ever a case where
>qsub can report a submitted job number, but the information that qstat reads
>and reports is not yet available, causing qstat to report "Following jobs do
>not exist: XXX")
>
>Can I count on the accounting information for a completed
>job having been written by the time that the job information
>is no longer available to qstat?
>
>Note that I am not asking about NFS latency or other elements outside the
>scope of SGE itself, just the flow sequence in how SGE provides info.
>
>The (pseudo-code) sequence I am trying to work with is:
>
>jobno = qsub cmd
>qstat -j $jobno
>when [qstat reports "Following jobs do not exist: $jobno"]
>  qacct -j $jobno
>
>Again, ignoring latency in the updating of the .../common/accounting file
>on disk, is this sequence legitimate based on the order in which
>sge handles the actions between submit, status report, accounting.
>
>I am only now getting familiar with the drmaa api, which seems like
>it might be a more robust approach to this problem.  However,
>my above approach worked fine in 5.3, but sporadically reports
>incorrectly in 6.0u3, qacct reports 'job id XXX not found' *after*
>qstat reports 'Following jobs do not exist...', but a second
>qacct does find and report on jobno.
>
>David
>
>David Pinsky                                    david_pinsky at agilent.com
>Agilent Technologies, ISD                       970-288-3739
>4380 Ziegler Road                               970-288-6580 (fax)
>Fort Collins, CO  80525-9790                    Mailstop 72
>
>
>
>
>---------------------------------------------------------------------
>To unsubscribe, e-mail: users-unsubscribe at gridengine.sunsource.net
>For additional commands, e-mail: users-help at gridengine.sunsource.net
>
>  
>

-- 
***************************************************
*        Daniel Templeton   ERGB01 x60220         *
*       Staff Engineer, Sun N1 Grid Engine        *
***************************************************
* "So let the sunshine in.  Face it with a grin.  *
*  Smilers never lose, and frowners never win."   *
*      -Let the Sunshine In, Pebbles Flintstone   *
***************************************************



---------------------------------------------------------------------
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