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

[Condor-users] Admin queue


I have an admin queue, and I want to run an admin job on each one of the nodes in my pool. For example, if I want to reinstall my cluster after the current set of jobs stop running, I want to send an admin job that: holds the node, waits for the job to finish, and then runs a shutdown script to reinstall the node. How do I guarantee every node gets this "admin" job and only one of them? Is it possible to guarantee that?



Joe Kaiser - Systems Administrator Fermi Lab CD/CMS-Tier1 Never laugh at live dragons.
jlkaiser@xxxxxxxx ===================================================================