From ec5884cbbfd34ef7e4f380e5a56d32f73e7e762e Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Tue, 8 Feb 2022 09:43:33 +0000 Subject: sched/fair: Improve consistency of allowed NUMA balance calculations [ Upstream commit 2cfb7a1b031b0e816af7a6ee0c6ab83b0acdf05a ] There are inconsistencies when determining if a NUMA imbalance is allowed that should be corrected. o allow_numa_imbalance changes types and is not always examining the destination group so both the type should be corrected as well as the naming. o find_idlest_group uses the sched_domain's weight instead of the group weight which is different to find_busiest_group o find_busiest_group uses the source group instead of the destination which is different to task_numa_find_cpu o Both find_idlest_group and find_busiest_group should account for the number of running tasks if a move was allowed to be consistent with task_numa_find_cpu Fixes: 7d2b5dd0bcc4 ("sched/numa: Allow a floating imbalance between NUMA nodes") Signed-off-by: Mel Gorman Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Gautham R. Shenoy Link: https://lore.kernel.org/r/20220208094334.16379-2-mgorman@techsingularity.net Signed-off-by: Sasha Levin --- kernel/sched/fair.c | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-) (limited to 'kernel') diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 6420580f2730..02766f3fe206 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -9005,9 +9005,10 @@ static bool update_pick_idlest(struct sched_group *idlest, * This is an approximation as the number of running tasks may not be * related to the number of busy CPUs due to sched_setaffinity. */ -static inline bool allow_numa_imbalance(int dst_running, int dst_weight) +static inline bool +allow_numa_imbalance(unsigned int running, unsigned int weight) { - return (dst_running < (dst_weight >> 2)); + return (running < (weight >> 2)); } /* @@ -9141,12 +9142,13 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, int this_cpu) return idlest; #endif /* - * Otherwise, keep the task on this node to stay close - * its wakeup source and improve locality. If there is - * a real need of migration, periodic load balance will - * take care of it. + * Otherwise, keep the task close to the wakeup source + * and improve locality if the number of running tasks + * would remain below threshold where an imbalance is + * allowed. If there is a real need of migration, + * periodic load balance will take care of it. */ - if (allow_numa_imbalance(local_sgs.sum_nr_running, sd->span_weight)) + if (allow_numa_imbalance(local_sgs.sum_nr_running + 1, local_sgs.group_weight)) return NULL; } @@ -9352,7 +9354,7 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s /* Consider allowing a small imbalance between NUMA groups */ if (env->sd->flags & SD_NUMA) { env->imbalance = adjust_numa_imbalance(env->imbalance, - busiest->sum_nr_running, busiest->group_weight); + local->sum_nr_running + 1, local->group_weight); } return; -- cgit v1.2.3