On Mon, 4 Aug 2003 07:19, Voluspa wrote:
> I can hardly spot any difference between 2.6.0-test2, A3 and A3-O12.2
> while running the test as outlined in:
Thanks for testing. The difference should only be noticable as X and other
interactive tasks remaining responsive under heavy load. Audio skips are far
less relevant any more.
> numbers. Just one oddity - and now I'm uncertain of its validity - as
> can be seen on the screencaps below. In A3 wine had a PRI of 25,
> wineserver had 15. In A3-O12.2 the numbers were reversed. I can redo the
> test if necessary.
No this is what I need to understand what went wrong. These hacks work on
changing the value of PRI basically. The wine/wineserver issue is an unusual
one as you've described it, and at O11 the test I put in to determine a task
is interactive by credits seems to select out the wrong one and keep that one
elevated.
Anyway most of this discussion is now moot as I've discussed with Ingo at
length a lot of the little things I've found that help and I suspect he will
develop his own, better solutions for them.
Con
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
This archive was generated by hypermail 2b29 : Thu Aug 07 2003 - 22:00:22 EST