Re: [Condor-users] Reseting the ImageSize

[Alan Malta <alanmalta@xxxxxxxxx>]

Dan,

in fact I'm not the job submitter, I'm just one of the cluster administrators, so I can't check the memory footprint. Anyway, I guess it's more secure to get in touch with the submitter and not run those jobs.

Thank you for your time,
Alan.

On Wed, Jun 1, 2011 at 3:22 PM, Dan O'Donovan <odonovan@xxxxxxxxxxxxxxxxxxx> wrote:

Hi Alan,

> I changed the ImageSize, in fact I tried, but the command didn't ended with code 0. Also, I messed up the whole system, so it was necessary restart the services to be able to see again the status of the schedd and jobs.

Ooh - that's not good. I imagine that adjusting ImageSize could lead to *bad things*.
I think I understand a little more now. You say that

> the job ImageSize still will be greater than 2GB available per job (ImageSize = 2500000, in this case).

is that ImageSize correct (have you checked the memory footprint on a non-condor machine) ? There seems to be an issue with some multi-threaded binaries reporting the wrong memory size:

https://www-auth.cs.wisc.edu/lists/condor-users/2011-May/msg00152.shtml

However, if you have actually got a real memory footprint of 2.5 GB then it is inadvisable to run this on a machine with only 2GB of RAM available! If there really is more than 2GB available then you could change the limits for those nodes.

Hope that helps, Dan

Dan O'Donovan Ph.D
SBGrid Consortium
Harvard Medical School

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

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