Messages in this thread | | | Date | Fri, 2 Oct 1998 18:29:43 -0400 (EDT) | From | "Albert D. Cahalan" <> | Subject | Re: RT sceduler patch (testing...) |
| |
Kurt Garloff writes: > On Fri, Oct 02, 1998 at 10:07:09AM +0200, Hans Eric Sand
>> degradation, but the variance of the results are to big. > > Sure? ... > rt-patch (all lines but the first): 34 values used ... > Non-rt-patch: 41 values used ...
Don't do that. If you want to benchmark the patch, you need to make sure you don't end up benchmarking a random code alignment difference. You need to use many different kernels. Change the unrelated config options, move functions around, etc. You could put all the functions in alphabetical order, then backwards, then alphabetical order of backwards names...
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.tux.org/lkml/
| |