Messages in this thread | | | Subject | Re: [PATCH] sched: Wholesale removal of sd_idle logic | From | Peter Zijlstra <> | Date | Wed, 16 Feb 2011 12:43:55 +0100 |
| |
On Mon, 2011-02-14 at 14:38 -0800, Venkatesh Pallipadi wrote: > > The initial patch here - https://patchwork.kernel.org/patch/532501/ > applies cleanly over the below change and provides a micro-optimization > for a specific case, where an idle core can pull tasks instead of a > core with one thread being idle and other thread being busy. > It will be good to get some data on whether this micro-optimization > matters or not.
I would much rather see a solution that solves that problem for the more generic situation where we lower capacity to 1.
The whole double-balance thing is fairly inherent in the whole design, and making an exception for just one special case doesn't look right.
| |