Full Queue

I’ve been running simulations over the holiday break, trying to get some data for a deadline, and I’ve had the queue on our cluster mostly to myself for two weeks.

As you can see here (if you look soon), there are now plenty of jobs in the queue, submitted by several users. My lovely vacation of nearly-unlimited CPU power is over. Unfortunately, I just discovered today that some old simulations of mine had a few incorrect parameters, and they need to be re-run. This could be done overnight on an empty cluster. Now I shall have to wait a little while.

The cluster includes some open-source, commodity status monitoring software called Ganglia, as well as some proprietary load monitoring software. I’m curious to see how the cluster and queue loads will look over time — how holidays, weekends, and the time of day affect the cluster load. In my experience using other clusters, Friday, Saturday, and morning on Sunday, as well as early morning on weekdays are the best times to run jobs on shared computing resources.