> BTW, it doesn't make much sense to be measuring to millisecond precision > a quantity which has variation that is unknown but probably much larger > :) When trying to make comparisons to identify performance changes, a > careful statistical approach is necessary. > > Try the /usr/src/tools/tools/ministat utility for a simple and effective > way to compare these kinds of noisy measurements and extract reliable > comparisons.
Thanks Kris! I have been taking an average of 3 values, but this looks extremely useful. I'll go ahead and build the necessary input files for ministat for stock 4BSD and stock ULE from RELENG_7, so I can generate something like the ministat README for future benchmark runs. I'll also increase my number of runs to 5 to provide a better statistical set of data. Appreciate the pointer, I wasn't aware of ministat. :) Thanks! Josh _______________________________________________ freebsd-performance@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-performance To unsubscribe, send any mail to "[EMAIL PROTECTED]"