Re: [PATCH 1/2] sched/fair: Filter out locally-unsolvable misfit imbalances

2021-04-19 Thread Valentin Schneider
On 16/04/21 15:29, Vincent Guittot wrote: > On Thu, 15 Apr 2021 at 19:58, Valentin Schneider > wrote: >> @@ -9441,8 +9465,8 @@ static struct rq *find_busiest_queue(struct lb_env >> *env, >> * average load. >> */ >> if (env->sd->flags &

Re: [PATCH 1/2] sched/fair: Filter out locally-unsolvable misfit imbalances

2021-04-16 Thread Vincent Guittot
On Thu, 15 Apr 2021 at 19:58, Valentin Schneider wrote: > > Consider the following (hypothetical) asymmetric CPU capacity topology, > with some amount of capacity pressure (RT | DL | IRQ | thermal): > > DIE [ ] > MC [][] >0 1 2 3 > > | CPU | capacity_orig |

Re: [PATCH 1/2] sched/fair: Filter out locally-unsolvable misfit imbalances

2021-04-15 Thread Rik van Riel
On Thu, 2021-04-15 at 18:58 +0100, Valentin Schneider wrote: > ... > Further tweak find_busiest_queue() to ensure this doesn't happen. > Also note > find_busiest_queue() can now iterate over CPUs with a higher capacity > than > the local CPU's, so add a capacity check there. > > Signed-off-by:

[PATCH 1/2] sched/fair: Filter out locally-unsolvable misfit imbalances

2021-04-15 Thread Valentin Schneider
Consider the following (hypothetical) asymmetric CPU capacity topology, with some amount of capacity pressure (RT | DL | IRQ | thermal): DIE [ ] MC [][] 0 1 2 3 | CPU | capacity_orig | capacity | |-+---+--| | 0 | 870 |