Re: [HTCondor-users] using idle computers in computer labs for CFD jobs

[Todd L Miller <tlmiller@xxxxxxxxxxx>]

> Now, this type of checkpoint is distinct from the standard universe's 
> checkpoint, as it's managed internally by the application rather than 
> the standard universe wrapper applied by condor_compile. For Fluent and 
> similar applications which can't be relinked in this way, we need to 
> figure out how to signal Fluent itself to checkpoint periodically.

	We expect to be releasing a new developer version (8.5.3) of 
HTCondor soon, which will contain some experimental features to help 
simplify situations like this.  It sounds like you'd still need to write a 
wrapper script, but that may be easier than changing the configuration of 
your execute nodes.  At any rate, if you'd like to help test the new 
features (or are just curious about what they'll probably be), please 
contact me off-list.

> I think that the alternative would have to be having a wrapper script 
> around the Fluent executable which would be able to recognize the 
> eviction signals from HTCondor and create the exit-fluent flag file when 
> such a signal is received.

	IIRC, the 'KillSig' job attribute determines which signal is sent 
on an eviction, so if you'd rather not trap SIGTERM, you can choose 
something else.

- ToddM