* Ingo Molnar <mi...@kernel.org> wrote:
> - Do you have enough RAM that there's essentially no IO
> in the system worth speaking of? Do you have enough RAM
> to copy a whole kernel tree to /tmp/linux/ and do the
> measurement there, on ramfs?
Doing that will also pin down the page cache: kernel build
times are very sensitive to the page cache layout, and once
a page cache layout is established on systems with lots of
RAM it does not tend to be flushed out. But the next bootup
will generate another random page cache layout - which
makes inter-kernel kernel build times comparisons much
noiser than the run-to-run numbers suggest.
So to get more precise measurements a 'pinned' page cache
layout and the dynamic debug switch you implemented is very
helpful and --repeat stddev will be pretty representative
of the true noise of the measurement.
Thanks,
Ingo
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
