Skip to main content.

UW-Madison CS Dept. HTCondor Pool Policies

The policies in effect for our HTCondor pool are described below. Contact htcondor-admin@cs.wisc.edu to request a customized policy for your workstation or to comment on these policies.

Start

HTCondor will start running a job on a desktop workstation when:

Preempt

HTCondor will preempt (that is, stop running) a job when: HTCondor may use three different mechanisms to preempt the job. HTCondor will suspend the job by sending a SIGSTOP to all job processes if: HTCondor will unsuspend a suspended job by sending a SIGCONT to all job processes if:

A standard universe job that is preempted is given time to write a checkpoint and then exit. HTCondor will kill the job by sending a SIGKILL to all job processes if:

Periodic Checkpointing

HTCondor jobs run under the standard universe will take periodic checkpoints every 3 hours for fault tolerance.

Priorities

There are three tiers of user priorities in our pool. Local users have the highest priority, followed by users from outside the university, followed by "nice users" (i.e., with "nice-user" in their name). The HTCondor Manual describes the HTCondor priority mechanisms in more detail.

Job Submission

Job submission is currently disabled on the instructional workstations. We encourage users to submit HTCondor jobs from their desktop workstations. If that is not possible, contact htcondor-admin@cs.wisc.edu and we will make alternate arrangements for you.


htcondor-admin@cs.wisc.edu