[GE users] qdel

Lönroth Erik erik.lonroth at scania.com
Wed Sep 19 12:25:38 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. ]

Thanx Reuti!

I will try it out and get back with feedback.

/Erik

-----Original Message-----
From: Reuti [mailto:reuti at staff.uni-marburg.de] 
Sent: den 18 september 2007 16:59
To: users at gridengine.sunsource.net
Subject: Re: [GE users] qdel


Am 18.09.2007 um 16:13 schrieb Lönroth Erik:

> I'm using "HPMPI"

We are using HP-MPI with Turbomole and ADF - integration is easy. The  
actual release 2.2.5 also accepts a -hostfile <machinefile> in  
contrast to the former -f <appfile>.

export MPI_REMSH=rsh
export MPI_TMPDIR=$TMPDIR

mpirun -hostfile $TMPDIR/machines ...

with a slightly modified PeHostfile2MachineFile():

PeHostfile2MachineFile()
{
    cat $1 | while read line; do
       # echo $line
       host=`echo $line|cut -f1 -d" "|cut -f1 -d"."`
       nslots=`echo $line|cut -f2 -d" "`
       echo $host $nslots
    done
}


-- Reuti

PS: If you have a former version of HP-MPI it's also possible, just  
the appfile must be created which I also did before. Let me know, if  
this is the case in your program.


> Is there some guide as how to do this tightly intergrated?
>
> /Erik
>
>
>
> -----Original Message-----
> From: Reuti [mailto:reuti at staff.uni-marburg.de]
> Sent: den 18 september 2007 15:15
> To: users at gridengine.sunsource.net
> Subject: Re: [GE users] qdel
>
>
> Hi,
>
> Am 18.09.2007 um 14:36 schrieb Lönroth Erik:
>
>> I have an application that detects the presence of a file 
>> ".isstopping" to kill its paralell child processes on different 
>> hosts. I wan't this file to be created upon a "qdel" invocation for 
>> this specific application.
>
> so your parallel application isn't tightly integrated with SGE, as 
> otherwise the child processes would be killed by SGE automatically. 
> Which parallel library are you using?
>
> -- Reuti
>
>
>> My initial focus was the "PE" stop_procedure, but it's only executed 
>> AFTER the completion of the job-script, so that won't help me much.
>>
>> I need to catch the "qdel" and act on this by creating that file and 
>> wait for some time before killing the job to let the application 
>> finish up.
>>
>> My question is: How would I achieve this in a good way?
>>
>>  I've read something about trapping SIGKILL or SIGTERM, but I'd 
>> figure there are good ideas out there....
>>
>> I'm on SGE 6.0u8
>>
>> Regards
>> /Erik
>
> ---------------------------------------------------------------------
> To unsubscribe, e-mail: users-unsubscribe at gridengine.sunsource.net
> For additional commands, e-mail: users-help at gridengine.sunsource.net
>
> ---------------------------------------------------------------------
> To unsubscribe, e-mail: users-unsubscribe at gridengine.sunsource.net
> For additional commands, e-mail: users-help at gridengine.sunsource.net
>

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

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