[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [HTCondor-users] peaceful node drain and shutdown

Ah. I had seen the docs for START but didn't realize it would affect new job startup too. It seemed to imply that its for eviction.

But, the following seems to work to drain the node gracefully, as you suggested:
echo START=FALSE > /etc/condor/config.d/00shutdown

and to reverse it
rm -f /etc/condor/config.d/00shutdown

Thanks for the help. :)


From: HTCondor-users [htcondor-users-bounces@xxxxxxxxxxx] on behalf of Michael V Pelletier [Michael.V.Pelletier@xxxxxxxxxxxx]
Sent: Wednesday, July 13, 2016 11:10 AM
To: HTCondor-Users Mail List
Subject: Re: [HTCondor-users] peaceful node drain and shutdown

From: "Fox, Kevin M" <Kevin.Fox@xxxxxxxx>
Date: 07/13/2016 12:19 PM
> I'm trying to setup condor such that you can peacefully shutdown a startd
> from the node running it without killing existing jobs but without
> allowing user jobs running on the node from doing so, or allowing one node
> from shutting down another. Anyone know a good way to do that?

The "condor_off -peaceful" command is what you're looking for, I think.

A more labor-intensive alternative is to reconfigure the START _expression_
for the node to be false so that no new jobs will be accepted, and then just
wait for the jobs to finish off.

        -Michael Pelletier.