Messages in this thread | | | Date | Tue, 5 Apr 2016 10:56:07 +0200 | From | Jiri Olsa <> | Subject | Re: [RFC] sched: unused cpu in affine workload |
| |
On Mon, Apr 04, 2016 at 11:34:50PM +0200, Peter Zijlstra wrote: > On Mon, Apr 04, 2016 at 03:45:16PM -0400, Rik van Riel wrote: > > An optimal solution is NP hard. > > > > Heuristics that "move tasks with pressure" may be > > much more doable, and lead to perfectly satisfactory > > results, especially if most migrations happen within > > a socket (and the same shared L3 cache). > > Right; trick will be finding something that mostly works without making > the regular balance paths increase in complexity. > > As per the argument in kernel/sched/fair.c:5694 the current > load-balancing averages out to O(n), and I would very much like to keep > it that way.
guys, thanks a lot for all the thoughts and suggestions, I'll try to come up with something
jirka
| |