[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Fwd: Re: [Condor-users] preempt and then hold?
- Date: Fri, 29 Jul 2005 20:42:14 -0500
- From: Scott Koranda <skoranda@xxxxxxxxxxxxxxxxxxxx>
- Subject: Fwd: Re: [Condor-users] preempt and then hold?
Any thoughts from the Condor team?
----- Forwarded message from Scott Koranda <skoranda@xxxxxxxxxxxxxxxxxxxx> -----
Date: Thu, 28 Jul 2005 14:12:50 -0500
From: Scott Koranda <skoranda@xxxxxxxxxxxxxxxxxxxx>
To: Condor-Users Mail List <condor-users@xxxxxxxxxxx>
Subject: Re: [Condor-users] preempt and then hold?
Cc: Stuart Anderson <anderson@xxxxxxxxxxxxxxxx>
> On Fri, Dec 03, 2004 at 11:42:16AM -0600, Scott Koranda wrote:
> > Hi,
> > For a long time we have set up our pool with
> > PREEMPT = False
> > so that the nodes in our cluster would not preempt a running
> > job for any reason (of course, the negotiator could still
> > cause jobs to preempt).
> > Lately, however, a few users have been running jobs that
> > malloc() a lot of memory and then eventually run the machine
> > in full swap, which eventually takes them into the weeds.
> > So we plan to change our configuration to
> > PREEMPT = (TARGET.ImageSize > ( 512 * 1024))
> > since each machine has 512 MB of physical memory (yes, the OS
> > uses some but we don't mind a little use of swap).
> > The idea is that when the job's memory usage grows, and Condor
> > notices, it will preempt the running job.
> > Two questions:
> > 1) Will this work?
> It should.
How often is the ImageSize computed for
a) standard universe jobs ?
b) vanilla universe jobs ?
If we do not do periodic checkpointing then will the ImageSize
still be updated for the standard universe jobs so that Condor
can act on the PREEMPT?
Condor-users mailing list
----- End forwarded message -----