Good work. One issue is hosts that dont run 24/7/365 or not at 100% load will appear to skew the results. Perhaps you could also include a total of recent results returned per CPU core, which would indicate if hosts have wildly varying duty cycles/% CPU usage?
You are viewing a single comment's thread from:
First of all great work @nexusprime.
Some other area which can cause variation in the output and make @scalextrix comments interesting to take into consideration: