This page contains a series of graphs that use data from the PDSF batch scheduler (SGE) to show the utilization of the cluster over the past 24 hours. The graphs were generated with RRDTool and are updated approximately every 15 minutes.
This graph shows the aggregate cluster CPU availability and usage according to sgeload:
This graph shows the number of jobs being run by each group:
This is the same graph as above weighted by the clockspeed (GHz) of the node used for the job:
This graph show the number of pending jobs by group:
This is the same graph as above but array jobs are expanded: