MK-MacPorts at techno.ms
Wed Dec 22 15:52:23 PST 2010
I noticed a strange thing concerning the execution time of a simple filter program of mine which I ran on Mac OSX natively as well as in a Linux VM via Parallels on one and the same iMac.
Here are typical values I measured using time:
MacOS X host system with MacPorts
OpenSUSE 11.2 VM on Parallels
Firstly one sees that the "real"ly spent time is 20% shorter on the VIRTUAL Linux on my Parallels 5.0.
On the other hand I see that "user"+"sys" time is usually equal to "real" on Linux, whereas "user"+"sys"<"real" on Mac OS X itself, which makes me believe that "user"+"sys" is the more actual than "real". :-)
Assuming "user"+"sys" being the really consumed time by the system to run my little filter tool would proove then the Mac OS X host system to be slightly faster than the virtual Linux guest system, which I would have expected in the first place.
Nevertheless I am a little taken aback, confused, dazed due to these unexpected numbers here.
Any ideas as to what causes this?
Anyway, there is more to come… But I would like to hear your opinion on this topic first, before I dive into other results which are even more shocking. ;-)
More information about the macports-dev