Re: [HTCondor-users] Machine allocation - unused machines

[Todd L Miller <tlmiller@xxxxxxxxxxx>]

> I see that the one single machine running all my jobs at the moment is 
> using swap memory, slowing down execution. I am wondering if I can solve 
> this by setting requestmemory in my submit file? Will this tell the 
> negotiator to spread the jobs around?

	It will cause HTCondor to assign a job to a machine only if 
there's enough memory left to fulfill the job's RequestMemory.  Note that 
HTCondor does not by default enforce the job's RequestMemory, so jobs may 
use more memory than requested.  If you want HTCondor to enforce the job's 
RequestMemory, consider configuring the startds with the policies
preempt_if_memory_exceeded or hold_if_memory_exceeded, documented on the 
following page:

https://htcondor.readthedocs.io/en/latest/admin-manual/configuration-templates.html

	Althought I think everything in it has been covered, also see the 
Wiki page about filling a pool breadth-first:

https://htcondor-wiki.cs.wisc.edu/index.cgi/wiki?p=HowToFillPoolBreadthFirst

- ToddM