<GREETING>

Below are <CASE> that ran on <CLUSTER> (<PARTITIONS>) in the past <DAYS> days:

<TABLE>

It appears that you are requesting too much time for your jobs since you are
only using on average <AVERAGE>% of the allocated time (for the <NUM-JOBS> jobs). This has
resulted in <UNUSED-HOURS> <MODE-UPPER>-hours that you scheduled but did not use (it was made
available to other jobs, however).

Please request less time by modifying the --time Slurm directive. This will
lower your queue times and allow the Slurm job scheduler to work more
effectively for all users. For instance, if your job requires 8 hours then use:

    #SBATCH --time=10:00:00

The value above includes an extra 20% for safety. This is important because jobs
that exceed the run time limit are automatically canceled. A good target for
Percent-Used is 80%.

Note that jobs with a run time limit of less than one hour will land in the test
queue where only a small number of jobs can run simultaneously. In this case
one should use a run time limit of sixty-one minutes.

Time-Used is the time (wallclock) that the job needed. The total time allocated
for the job is Time-Allocated. The format is DD-HH:MM:SS where DD is days,
HH is hours, MM is minutes and SS is seconds. Percent-Used is Time-Used
divided by Time-Allocated.

For more information on allocating time via Slurm:

    https://researchcomputing.princeton.edu/KB/slurm

Consider attending an in-person Research Computing help session for assistance:

    https://your-institution.edu/support/help-sessions

Replying to this automated email will open a support ticket with Research
Computing.
