[GE users] checking job return status in epilog script

pollinger harald.pollinger at sun.com
Fri Jun 12 13:44:54 BST 2009

madpower wrote:
> Hi,
>> So the job (the process) still runs on the execution host,
> No. It sleeps on the execution host...

Sorry, I don't get it. You wrote:

"Maybe I was a little unprecise on this
topic. In my case the "S" output is from the unix command "top" (or ps
faux) on the console of the execution host. So the jobs are regularily
listes as "running" in qstat but actually they are not running on the
execution host."

"S" in the "ps" output means "Sleeping: process is waiting for an event 
to complete". This what every running process does that e.g. waits for 
user input or for some data to arrive on a socket or...

So the process is running, but it's currently waiting in a blocking 
system call.

>> but SGE 
>> doesn't list it as a running job any more? 
> ...and SGE believes it is still running. (Which is from SGE view correct.)

Which is absolutely correct. Even if the process would be in "suspended" 
state ("T" in "ps" output), from the SGE point of view it would be 
running, because it wasn't suspended by SGE.

>> What and how exactly did you submit, and what does the "pstree" output 
>> of your job and of the sge_execd look like?
> Well, submitted was simply by using the qsub command with some arguments
>  only necessary for the program itself, i.e., no special parameters
> given to SGE. Everything else looks quite normal.
> So, as written in my previous post, we are currently doing an upgrade to
> the new linux kernel. Maybe this will solve all of our problems.

I still didn't get what the problem is. Maybe it's just a 
misinterpretation of states?


> Thanks
> to everyone trying to help, but I think, since we are changing our
> system now, it won't be worth the energy put into solving this problem,
> since they might be gone.
> Nevertheless, if there are still problems left, I will let you know.
> Best regards,
> Matthias
> ------------------------------------------------------
> http://gridengine.sunsource.net/ds/viewMessage.do?dsForumId=38&dsMessageId=201648
> To unsubscribe from this discussion, e-mail: [users-unsubscribe at gridengine.sunsource.net].

Sun Microsystems GmbH         Harald Pollinger
Dr.-Leo-Ritter-Str. 7         Sun Grid Engine Engineering
D-93049 Regensburg            Phone: +49 (0)941 3075-209  (x60209)
Germany                       Fax: +49 (0)941 3075-222  (x60222)
mailto:harald.pollinger at sun.com
Sitz der Gesellschaft:
Sun Microsystems GmbH, Sonnenallee 1, D-85551 Kirchheim-Heimstetten
Amtsgericht Muenchen: HRB 161028
Geschaeftsfuehrer: Thomas Schroeder, Wolfgang Engels, Wolf Frenkel
Vorsitzender des Aufsichtsrates: Martin Haering


To unsubscribe from this discussion, e-mail: [users-unsubscribe at gridengine.sunsource.net].

More information about the gridengine-users mailing list