Rob's post on walltime efficiency was interesting. I did the same with HCC and found that we had much better efficiency than I expected. Especially with GlideinWMS's default behavior of sticking around for 20 minutes waiting for a job before exiting.
What's interesting is that we rarely run jobs at RENCI-Engagement, OSCER, or GPGRID. It's difficult to interpret this. Since we run so many workflows, it's not clear to me that this means much.