ULE vs. 4BSD in RELENG_7
Josh Carroll
josh.carroll at gmail.com
Sat Nov 10 12:18:31 PST 2007
> 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
More information about the freebsd-performance
mailing list