Re: [HTCondor-users] Process not running - out of memory

[Tim Theisen <tim@xxxxxxxxxxx>]

Hello Peter,

HTCondor can do memory enforcement. The default memory request is the size of your executable (or script). Have you set request memory value?

...Tim

On 5/3/23 07:41, Peter Ellevseth wrote:

Hello all

 

I am trying a third party application in our cluster. I have prepared a bash script to run the program, and I make a submit-file to tell condor to start that script with some arguments.

 

However, it does not behave as I would like it to.

 

The condor-job starts and moves input-files as I expect it to. The process starts, and runs for about 8-10 minutes and then is killed by the kernel (oom-kill). The strange thing is that when I observe the running jobs on the startd-machine (via ssh) it does not seem to use almost any resources at all (top says MEM% less than 0.5).

 

I have tried starting the job manually (via ssh) on the startd-machine and it runs just fine. When I start it this was it also consumes a lot more resources. Top says %CPU of about 200 and %MEM of about 4. The programs clearly demands some resources, but I find it strange that the kernel kills it when run through condor and I canât see that it uses hardly any resources at all.

 

Thoughts?

 

P

 

 

 

Peter Ellevseth
Principal Advisor / Principal Advisor
	+47 93 43 56 01 / +47 73 90 05 00
	peter.ellevseth@xxxxxxxxxx
	safetec.no

 

 

_______________________________________________
HTCondor-users mailing list
To unsubscribe, send a message to htcondor-users-request@xxxxxxxxxxx with a
subject: Unsubscribe
You can also unsubscribe by visiting
https://lists.cs.wisc.edu/mailman/listinfo/htcondor-users

The archives can be found at:
https://lists.cs.wisc.edu/archive/htcondor-users/

-- 
Tim Theisen (he, him, his)
Release Manager
HTCondor & Open Science Grid
Center for High Throughput Computing
Department of Computer Sciences
University of Wisconsin - Madison
4261 Computer Sciences and Statistics
1210 W Dayton St
Madison, WI 53706-1685
+1 608 265 5736