[torqueusers] Question about prologue scripts and sending jobs
back to queue.
griznog at gmail.com
Wed Jan 23 14:30:59 MST 2008
I found DEFERTIME and I think that'll solve my deferred issue. I'll
have to read more about resources, I just assumed adding
'fakeresource' to my test nodes in my nodes file would be sufficient
but it makes sense that I'd have to tell moab about it. Just need to
figure out how.
On Jan 23, 2008 12:34 PM, Garrick Staples <garrick at usc.edu> wrote:
> On Tue, Jan 22, 2008 at 11:10:47PM -0700, John Hanks alleged:
> > And it gets rejected correctly and sent back to the queue, but is now
> > deferred. When I release the hold on it, it runs again but this time
> > ignores my fakeresource request and runs on the next available node.
> > How do I get this to return a job to the queue without a hold on it
> > and get my resource request to stick?
> Torque doesn't know anything about features, those are handled by the
> scheduler. Which scheduler are you using?
> torqueusers mailing list
> torqueusers at supercluster.org
More information about the torqueusers