On Feb 8, 2012, at 12:02 PM, Jaromir Capik wrote: > I believe the problem is pretty existent, but regular users > are often happy with the current behaviour, because they just > need to know which processes are the most resource eaters. > They're not interested in long-term statistics and > resource reserves. Such needs come in case of monitoring platforms > for servers where the stats of free reserves become the most > important part of the graphs. Hi Jaromir, I just ran a little test on my 4-core laptop. Using top with some fprintf statements, taskset for cpu affinity, cpufreq-set to force a given frequency and cpufreq-info for verification, here's what I found. The kernel tics recorded for /proc/stat line one AND each individual cpu line are virtually identical when running at either 800MHz or 2.10GHz. Does this make your problem go away? Jim