When you said "total VM time" I thought you meant for 1 virtual machine, since there are 2 fields with CPU time: All CPU time (sometimes called the total time) and Virtual time. But you are adding up all of the "total time" values to create an overall total.
But, what you are adding up is the time for one virtual CPU (such as virtual CPU 0) for all machines. Virtual CPU 0 is not always run on Real CPU 0; it could be run on any real CPU, and the virtual CPU 0 from many machines can be run in parallel on your real CPUs. So, the total of all of these could add up to more than the connect time. It should be true, however, that the total of all of the consumed CPU time divided by the number of real CPUs should be less than the connect time. On Fri, Feb 18, 2011 at 2:55 PM, Ackerman, Derek <derek.acker...@infocrossing.com> wrote: > I am simply summing the total CPU times for each CP, for my report I > keep them separate, here is one example for one CP and one interval. > > <snip> -- Bruce Hayden z/VM and Linux on System z ATS IBM, Endicott, NY