Hello All : I am planning to propose a Ganglia-related project to the OSCAR toolkit as part of Google Summer of Code and hope I can get some input from this list. One of the possible enhancements to the OSCAR-Ganglia package is to derive and show some useful HPC metrics to the user from the output of Ganglia, for example, average CPU load over the past n timeperiods, average job queue lengths over past n timeperiods and such. Are there any other meaningful metrics that users often like to see and get implemented? Please let me know if you have any suggestions. Thank you.
Regards, Babu http://www.cs.uh.edu/~babu
