Opened 14 years ago

Last modified 9 years ago

#311 new enhancement

IZ1938: qstat should display jobs on hung/halted machines as unknown istead of runnning

Reported by: ernst Owned by:
Priority: low Milestone:
Component: sge Version: 5.3p4
Severity: Keywords: Sun qmaster
Cc:

Description

[Imported from gridengine issuezilla http://gridengine.sunsource.net/issues/show_bug.cgi?id=1938]

        Issue #:      1938             Platform:     Sun           Reporter: ernst (ernst)
       Component:     gridengine          OS:        All
     Subcomponent:    qmaster          Version:      5.3p4            CC:    None defined
        Status:       NEW              Priority:     P4
      Resolution:                     Issue type:    ENHANCEMENT
                                   Target milestone: ---
      Assigned to:    ernst (ernst)
      QA Contact:     ernst
          URL:
       * Summary:     qstat should display jobs on hung/halted machines as unknown istead of runnning
   Status whiteboard:
      Attachments:

     Issue 1938 blocks:
   Votes for issue 1938:


   Opened: Tue Dec 13 02:31:00 -0700 2005 
------------------------


If a gridengine node unexpectedly halts or hangs, gridengine report the jobs in
the failed node as running.  This information is misleading, because gridengine
lost contact with execd and actually does not know the status of the job and
therefore, a "unknown" status is more appropriate.  Moreover, the "running"
status gives an impression to the user that everything is fine when this is not
the case.

   ------- Additional comments from joga Tue Jun 16 05:32:05 -0700 2009 -------
Major change in behaviour.
Cannot be delivered in a patch, only as enhancement in a major release.

Change History (0)

Note: See TracTickets for help on using tickets.